From 6940f11b15027d8afe802df6eddae47b34549277 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Thu, 11 Jul 2019 17:56:34 +0200
Subject: [PATCH 001/113] fix buffer overflow in build_plain()
---
src/hashes.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/src/hashes.c b/src/hashes.c
index 1b8f4591a..e9e0a3e7e 100644
--- a/src/hashes.c
+++ b/src/hashes.c
@@ -330,18 +330,22 @@ void check_hash (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param, pl
// plain
- u32 plain_buf[64] = { 0 };
+ u8 plain_buf[256+1];
- u8 *plain_ptr = (u8 *) plain_buf;
+ memset (plain_buf, 0, sizeof (plain_buf));
+
+ u8 *plain_ptr = plain_buf;
int plain_len = 0;
- build_plain (hashcat_ctx, device_param, plain, plain_buf, &plain_len);
+ build_plain (hashcat_ctx, device_param, plain, (u32 *)plain_buf, &plain_len);
if (module_ctx->module_build_plain_postprocess != MODULE_DEFAULT)
{
- u32 temp_buf[64] = { 0 };
+ u8 temp_buf[256+1] = { 0 };
- const int temp_len = module_ctx->module_build_plain_postprocess (hashcat_ctx->hashconfig, hashcat_ctx->hashes, tmps, plain_buf, sizeof (plain_buf), plain_len, temp_buf, sizeof (temp_buf));
+ memset (temp_buf, 0, sizeof (temp_buf));
+
+ const int temp_len = module_ctx->module_build_plain_postprocess (hashcat_ctx->hashconfig, hashcat_ctx->hashes, tmps, (u32 *)plain_buf, sizeof (plain_buf), plain_len, (u32 *)temp_buf, sizeof (temp_buf));
if (temp_len < (int) sizeof (plain_buf))
{
From c85cdd6cc88ef4f27649783fe96c61683e215ab3 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Thu, 11 Jul 2019 18:01:54 +0200
Subject: [PATCH 002/113] fix kernel 20600 build error, issue #2094
---
OpenCL/m20600-pure.cl | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/OpenCL/m20600-pure.cl b/OpenCL/m20600-pure.cl
index 355a21c45..bbcfe5002 100644
--- a/OpenCL/m20600-pure.cl
+++ b/OpenCL/m20600-pure.cl
@@ -150,10 +150,10 @@ KERNEL_FQ void m20600_comp (KERN_ATTR_TMPS (omt_sha256_tmp_t))
* digest
*/
- const u32x r0 = hc_swap32_S (tmps[gid].digest_buf[DGST_R0]);
- const u32x r1 = hc_swap32_S (tmps[gid].digest_buf[DGST_R1]);
- const u32x r2 = hc_swap32_S (tmps[gid].digest_buf[DGST_R2]);
- const u32x r3 = hc_swap32_S (tmps[gid].digest_buf[DGST_R3]);
+ const u32 r0 = hc_swap32_S (tmps[gid].digest_buf[DGST_R0]);
+ const u32 r1 = hc_swap32_S (tmps[gid].digest_buf[DGST_R1]);
+ const u32 r2 = hc_swap32_S (tmps[gid].digest_buf[DGST_R2]);
+ const u32 r3 = hc_swap32_S (tmps[gid].digest_buf[DGST_R3]);
#define il_pos 0
From 5d4fd047ee6396fb17761d3438219521aa71e289 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Fri, 12 Jul 2019 20:20:05 +0200
Subject: [PATCH 003/113] fix bug in mpsp
---
src/mpsp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/mpsp.c b/src/mpsp.c
index 0fce4d5fb..89a1b41e4 100644
--- a/src/mpsp.c
+++ b/src/mpsp.c
@@ -1232,7 +1232,7 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
sp_tbl_to_css (mask_ctx->root_table_buf, mask_ctx->markov_table_buf, mask_ctx->root_css_buf, mask_ctx->markov_css_buf, user_options->markov_threshold, uniq_tbls);
- if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1) return -1;
+ if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1)
{
event_log_error (hashcat_ctx, "Integer overflow detected in keyspace of mask: %s", mask_ctx->mask);
From 686e722db0ff24f49d0cbb046e60d46a9a664173 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Fri, 12 Jul 2019 23:55:53 +0200
Subject: [PATCH 004/113] fix bug with -S -O arguments set together
---
src/interface.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/interface.c b/src/interface.c
index 442076317..c908d9c0c 100644
--- a/src/interface.c
+++ b/src/interface.c
@@ -353,7 +353,7 @@ int hashconfig_init (hashcat_ctx_t *hashcat_ctx)
{
if (user_options->quiet == false) event_log_warning (hashcat_ctx, "%s: Optimized OpenCL kernel requested but not needed - falling back to pure OpenCL kernel", source_file);
}
- else
+ else if (user_options->slow_candidates == false)
{
hashconfig->opti_type |= OPTI_TYPE_OPTIMIZED_KERNEL;
}
From d0ec5c7b77182b4e28b0133893bdb4ef76df2f76 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 13 Jul 2019 00:20:41 +0200
Subject: [PATCH 005/113] move hc_* file functions from shared.c/.h to
filehandling.c/.h
---
include/filehandling.h | 25 ++-
include/shared.h | 23 +--
src/filehandling.c | 440 +++++++++++++++++++++++++++++++++++++----
src/shared.c | 366 ----------------------------------
4 files changed, 427 insertions(+), 427 deletions(-)
diff --git a/include/filehandling.h b/include/filehandling.h
index ac1a48ea0..32f3044b0 100644
--- a/include/filehandling.h
+++ b/include/filehandling.h
@@ -10,12 +10,31 @@
#include <string.h>
#include <errno.h>
-u64 count_lines (HCFILE *fp);
+#if defined (__CYGWIN__)
+int _wopen (const char *path, int oflag, ...);
+#endif
-size_t fgetl (HCFILE *fp, char *line_buf);
+bool hc_fopen (HCFILE *fp, const char *path, char *mode);
+int hc_fscanf (HCFILE *fp, const char *format, void *ptr);
+int hc_fprintf (HCFILE *fp, const char *format, ...);
+int hc_vfprintf (HCFILE *fp, const char *format, va_list ap);
+int hc_fseek (HCFILE *fp, off_t offset, int whence);
+void hc_rewind (HCFILE *fp);
+off_t hc_ftell (HCFILE *fp);
+int hc_fgetc (HCFILE *fp);
+int hc_fileno (HCFILE *fp);
+int hc_feof (HCFILE *fp);
+void hc_fflush (HCFILE *fp);
+void hc_fclose (HCFILE *fp);
+int hc_fputc (int c, HCFILE *fp);
+char *hc_fgets (char *buf, int len, HCFILE *fp);
+size_t hc_fwrite (void *ptr, size_t size, size_t nmemb, HCFILE *fp);
+size_t hc_fread (void *ptr, size_t size, size_t nmemb, HCFILE *fp);
+size_t fgetl (HCFILE *fp, char *line_buf);
+u64 count_lines (HCFILE *fp);
+size_t in_superchop (char *buf);
size_t superchop_with_length (char *buf, const size_t len);
-size_t in_superchop (char *buf);
#endif // _FILEHANDLING_H
diff --git a/include/shared.h b/include/shared.h
index e9cfd95ca..787a241c6 100644
--- a/include/shared.h
+++ b/include/shared.h
@@ -14,7 +14,9 @@
#include <fcntl.h>
#include <ctype.h>
#include <math.h>
+
#include "zlib.h"
+#include "filehandling.h"
#if defined (_WIN)
#include <winsock2.h> // needed for select()
@@ -62,27 +64,6 @@ bool hc_string_is_digit (const char *s);
void hc_string_trim_trailing (char *s);
void hc_string_trim_leading (char *s);
-#if defined (__CYGWIN__)
-int _wopen(const char *path, int oflag, ...);
-#endif
-
-bool hc_fopen (HCFILE *fp, const char *path, char *mode);
-int hc_fscanf (HCFILE *fp, const char *format, void *ptr);
-int hc_fprintf (HCFILE *fp, const char *format, ...);
-int hc_vfprintf (HCFILE *fp, const char *format, va_list ap);
-int hc_fseek (HCFILE *fp, off_t offset, int whence);
-void hc_rewind (HCFILE *fp);
-off_t hc_ftell (HCFILE *fp);
-int hc_fgetc (HCFILE *fp);
-int hc_fileno (HCFILE *fp);
-int hc_feof (HCFILE *fp);
-void hc_fflush (HCFILE *fp);
-void hc_fclose (HCFILE *fp);
-int hc_fputc (int c, HCFILE *fp);
-char *hc_fgets (char *buf, int len, HCFILE *fp);
-size_t hc_fwrite (void *ptr, size_t size, size_t nmemb, HCFILE *fp);
-size_t hc_fread (void *ptr, size_t size, size_t nmemb, HCFILE *fp);
-
bool hc_same_files (char *file1, char *file2);
u32 hc_strtoul (const char *nptr, char **endptr, int base);
diff --git a/src/filehandling.c b/src/filehandling.c
index ae39c1a06..22d3deda4 100644
--- a/src/filehandling.c
+++ b/src/filehandling.c
@@ -9,33 +9,370 @@
#include "shared.h"
#include "filehandling.h"
-u64 count_lines (HCFILE *fp)
+#if defined (__CYGWIN__)
+// workaround for zlib with cygwin build
+int _wopen(const char *path, int oflag, ...)
{
- u64 cnt = 0;
+ va_list ap;
+ va_start (ap, oflag);
+ int r = open (path, oflag, ap);
+ va_end (ap);
+ return r;
+}
+#endif
- char *buf = (char *) hcmalloc (HCBUFSIZ_LARGE + 1);
+bool hc_fopen (HCFILE *fp, const char *path, char *mode)
+{
+ if (path == NULL || mode == NULL) return false;
- char prev = '\n';
+ int oflag = -1;
- while (!hc_feof (fp))
+ int fmode = S_IRUSR|S_IWUSR;
+
+ if (strncmp (mode, "a", 1) == 0 || strncmp (mode, "ab", 2) == 0)
{
- size_t nread = hc_fread (buf, sizeof (char), HCBUFSIZ_LARGE, fp);
+ oflag = O_WRONLY | O_CREAT | O_APPEND;
- if (nread < 1) continue;
-
- size_t i;
-
- for (i = 0; i < nread; i++)
- {
- if (prev == '\n') cnt++;
-
- prev = buf[i];
- }
+ #if defined(MSDOS) || defined(OS2) || defined(WIN32) || defined(_WIN32) || defined(__CYGWIN__)
+ if (strncmp (mode, "ab", 2) == 0) oflag |= O_BINARY;
+ #endif
}
+ else if (strncmp (mode, "r", 1) == 0 || strncmp (mode, "rb", 2) == 0)
+ {
+ oflag = O_RDONLY;
+ fmode = -1;
+
+ #if defined(MSDOS) || defined(OS2) || defined(WIN32) || defined(_WIN32) || defined(__CYGWIN__)
+ if (strncmp (mode, "rb", 2) == 0) oflag |= O_BINARY;
+ #endif
+ }
+ else if (strncmp (mode, "w", 1) == 0 || strncmp (mode, "wb", 2) == 0)
+ {
+ oflag = O_WRONLY | O_CREAT | O_TRUNC;
+
+ #if defined(MSDOS) || defined(OS2) || defined(WIN32) || defined(_WIN32) || defined(__CYGWIN__)
+ if (strncmp (mode, "wb", 2) == 0) oflag |= O_BINARY;
+ #endif
+ }
+ else
+ {
+ // ADD more strncmp to handle more "mode"
+ return false;
+ }
+
+ fp->pfp = NULL;
+ fp->is_gzip = false;
+
+ unsigned char check[3] = { 0 };
+
+ int fd_tmp = open (path, O_RDONLY);
+
+ if (fd_tmp != -1)
+ {
+ lseek (fd_tmp, 0, SEEK_SET);
+
+ if (read (fd_tmp, check, sizeof(check)) > 0)
+ {
+ if (check[0] == 0x1f && check[1] == 0x8b && check[2] == 0x08) fp->is_gzip = true;
+ }
+
+ close (fd_tmp);
+ }
+
+ if (fmode == -1)
+ {
+ fp->fd = open (path, oflag);
+ }
+ else
+ {
+ fp->fd = open (path, oflag, fmode);
+ }
+
+ if (fp->fd == -1) return false;
+
+ if (fp->is_gzip)
+ {
+ if ((fp->gfp = gzdopen (fp->fd, mode)) == NULL) return false;
+ }
+ else
+ {
+ if ((fp->pfp = fdopen (fp->fd, mode)) == NULL) return false;
+ }
+
+ fp->path = path;
+ fp->mode = mode;
+
+ return true;
+}
+
+size_t hc_fread (void *ptr, size_t size, size_t nmemb, HCFILE *fp)
+{
+ size_t n = -1;
+
+ if (fp == NULL) return n;
+
+ if (fp->is_gzip)
+ {
+ n = gzfread (ptr, size, nmemb, fp->gfp);
+ }
+ else
+ {
+ n = fread (ptr, size, nmemb, fp->pfp);
+ }
+
+ return n;
+}
+
+size_t hc_fwrite (void *ptr, size_t size, size_t nmemb, HCFILE *fp)
+{
+ size_t n = -1;
+
+ if (fp == NULL) return n;
+
+ if (fp->is_gzip)
+ {
+ n = gzfwrite (ptr, size, nmemb, fp->gfp);
+ }
+ else
+ {
+ n = fwrite (ptr, size, nmemb, fp->pfp);
+ }
+
+ if (n != nmemb) return -1;
+
+ return n;
+}
+
+int hc_fseek (HCFILE *fp, off_t offset, int whence)
+{
+ int r = -1;
+
+ if (fp == NULL) return r;
+
+ if (fp->is_gzip)
+ {
+ r = gzseek (fp->gfp, (z_off_t) offset, whence);
+ }
+ else
+ {
+ r = fseeko (fp->pfp, offset, whence);
+ }
+
+ return r;
+}
+
+void hc_rewind (HCFILE *fp)
+{
+ if (fp == NULL) return;
+
+ if (fp->is_gzip)
+ {
+ gzrewind (fp->gfp);
+ }
+ else
+ {
+ rewind (fp->pfp);
+ }
+}
+
+off_t hc_ftell (HCFILE *fp)
+{
+ off_t n = 0;
+
+ if (fp == NULL) return -1;
+
+ if (fp->is_gzip)
+ {
+ n = (off_t) gztell (fp->gfp);
+ }
+ else
+ {
+ n = ftello (fp->pfp);
+ }
+
+ return n;
+}
+
+int hc_fputc (int c, HCFILE *fp)
+{
+ int r = -1;
+
+ if (fp == NULL) return r;
+
+ if (fp->is_gzip)
+ {
+ r = gzputc (fp->gfp, c);
+ }
+ else
+ {
+ r = fputc (c, fp->pfp);
+ }
+
+ return r;
+}
+
+int hc_fgetc (HCFILE *fp)
+{
+ int r = -1;
+
+ if (fp == NULL) return r;
+
+ if (fp->is_gzip)
+ {
+ r = gzgetc (fp->gfp);
+ }
+ else
+ {
+ r = fgetc (fp->pfp);
+ }
+
+ return r;
+}
+
+char *hc_fgets (char *buf, int len, HCFILE *fp)
+{
+ char *r = NULL;
+
+ if (fp == NULL) return r;
+
+ if (fp->is_gzip)
+ {
+ r = gzgets (fp->gfp, buf, len);
+ }
+ else
+ {
+ r = fgets (buf, len, fp->pfp);
+ }
+
+ return r;
+}
+
+int hc_vfprintf (HCFILE *fp, const char *format, va_list ap)
+{
+ int r = -1;
+
+ if (fp == NULL) return r;
+
+ if (fp->is_gzip)
+ {
+ r = gzvprintf (fp->gfp, format, ap);
+ }
+ else
+ {
+ r = vfprintf (fp->pfp, format, ap);
+ }
+
+ return r;
+}
+
+int hc_fprintf (HCFILE *fp, const char *format, ...)
+{
+ int r = -1;
+
+ if (fp == NULL) return r;
+
+ va_list ap;
+
+ va_start (ap, format);
+
+ if (fp->is_gzip)
+ {
+ r = gzvprintf (fp->gfp, format, ap);
+ }
+ else
+ {
+ r = vfprintf (fp->pfp, format, ap);
+ }
+
+ va_end (ap);
+
+ return r;
+}
+
+int hc_fscanf (HCFILE *fp, const char *format, void *ptr)
+{
+ if (fp == NULL) return -1;
+
+ char *buf = (char *) hcmalloc (HCBUFSIZ_TINY);
+
+ if (buf == NULL) return -1;
+
+ char *b = hc_fgets (buf, HCBUFSIZ_TINY - 1, fp);
+
+ if (b == NULL)
+ {
+ hcfree (buf);
+
+ return -1;
+ }
+
+ sscanf (b, format, (void *) ptr);
hcfree (buf);
- return cnt;
+ return 1;
+}
+
+int hc_fileno (HCFILE *fp)
+{
+ if (fp == NULL) return 1;
+
+ return fp->fd;
+}
+
+int hc_feof (HCFILE *fp)
+{
+ int r = -1;
+
+ if (fp == NULL) return r;
+
+ if (fp->is_gzip)
+ {
+ r = gzeof (fp->gfp);
+ }
+ else
+ {
+ r = feof (fp->pfp);
+ }
+
+ return r;
+}
+
+void hc_fflush (HCFILE *fp)
+{
+ if (fp == NULL) return;
+
+ if (fp->is_gzip)
+ {
+ gzflush (fp->gfp, Z_SYNC_FLUSH);
+ }
+ else
+ {
+ fflush (fp->pfp);
+ }
+}
+
+void hc_fclose (HCFILE *fp)
+{
+ if (fp == NULL) return;
+
+ if (fp->is_gzip)
+ {
+ gzclose (fp->gfp);
+ }
+ else
+ {
+ fclose (fp->pfp);
+ }
+
+ close (fp->fd);
+
+ fp->fd = -1;
+ fp->pfp = NULL;
+ fp->is_gzip = false;
+
+ fp->path = NULL;
+ fp->mode = NULL;
}
size_t fgetl (HCFILE *fp, char *line_buf)
@@ -83,34 +420,33 @@ size_t fgetl (HCFILE *fp, char *line_buf)
return (line_len);
}
-size_t superchop_with_length (char *buf, const size_t len)
+u64 count_lines (HCFILE *fp)
{
- size_t new_len = len;
+ u64 cnt = 0;
- while (new_len)
+ char *buf = (char *) hcmalloc (HCBUFSIZ_LARGE + 1);
+
+ char prev = '\n';
+
+ while (!hc_feof (fp))
{
- if (buf[new_len - 1] == '\n')
+ size_t nread = hc_fread (buf, sizeof (char), HCBUFSIZ_LARGE, fp);
+
+ if (nread < 1) continue;
+
+ size_t i;
+
+ for (i = 0; i < nread; i++)
{
- new_len--;
+ if (prev == '\n') cnt++;
- buf[new_len] = 0;
-
- continue;
+ prev = buf[i];
}
-
- if (buf[new_len - 1] == '\r')
- {
- new_len--;
-
- buf[new_len] = 0;
-
- continue;
- }
-
- break;
}
- return new_len;
+ hcfree (buf);
+
+ return cnt;
}
size_t in_superchop (char *buf)
@@ -142,3 +478,33 @@ size_t in_superchop (char *buf)
return len;
}
+
+size_t superchop_with_length (char *buf, const size_t len)
+{
+ size_t new_len = len;
+
+ while (new_len)
+ {
+ if (buf[new_len - 1] == '\n')
+ {
+ new_len--;
+
+ buf[new_len] = 0;
+
+ continue;
+ }
+
+ if (buf[new_len - 1] == '\r')
+ {
+ new_len--;
+
+ buf[new_len] = 0;
+
+ continue;
+ }
+
+ break;
+ }
+
+ return new_len;
+}
diff --git a/src/shared.c b/src/shared.c
index c6becae26..fff7192b6 100644
--- a/src/shared.c
+++ b/src/shared.c
@@ -603,372 +603,6 @@ void hc_string_trim_trailing (char *s)
s[new_len] = 0;
}
-#if defined (__CYGWIN__)
-// workaround for zlib with cygwin build
-int _wopen(const char *path, int oflag, ...)
-{
- va_list ap;
- va_start (ap, oflag);
- int r = open (path, oflag, ap);
- va_end (ap);
- return r;
-}
-#endif
-
-bool hc_fopen (HCFILE *fp, const char *path, char *mode)
-{
- if (path == NULL || mode == NULL) return false;
-
- int oflag = -1;
-
- int fmode = S_IRUSR|S_IWUSR;
-
- if (strncmp (mode, "a", 1) == 0 || strncmp (mode, "ab", 2) == 0)
- {
- oflag = O_WRONLY | O_CREAT | O_APPEND;
-
- #if defined(MSDOS) || defined(OS2) || defined(WIN32) || defined(_WIN32) || defined(__CYGWIN__)
- if (strncmp (mode, "ab", 2) == 0) oflag |= O_BINARY;
- #endif
- }
- else if (strncmp (mode, "r", 1) == 0 || strncmp (mode, "rb", 2) == 0)
- {
- oflag = O_RDONLY;
- fmode = -1;
-
- #if defined(MSDOS) || defined(OS2) || defined(WIN32) || defined(_WIN32) || defined(__CYGWIN__)
- if (strncmp (mode, "rb", 2) == 0) oflag |= O_BINARY;
- #endif
- }
- else if (strncmp (mode, "w", 1) == 0 || strncmp (mode, "wb", 2) == 0)
- {
- oflag = O_WRONLY | O_CREAT | O_TRUNC;
-
- #if defined(MSDOS) || defined(OS2) || defined(WIN32) || defined(_WIN32) || defined(__CYGWIN__)
- if (strncmp (mode, "wb", 2) == 0) oflag |= O_BINARY;
- #endif
- }
- else
- {
- // ADD more strncmp to handle more "mode"
- return false;
- }
-
- fp->pfp = NULL;
- fp->is_gzip = false;
-
- unsigned char check[3] = { 0 };
-
- int fd_tmp = open (path, O_RDONLY);
-
- if (fd_tmp != -1)
- {
- lseek (fd_tmp, 0, SEEK_SET);
-
- if (read (fd_tmp, check, sizeof(check)) > 0)
- {
- if (check[0] == 0x1f && check[1] == 0x8b && check[2] == 0x08) fp->is_gzip = true;
- }
-
- close (fd_tmp);
- }
-
- if (fmode == -1)
- {
- fp->fd = open (path, oflag);
- }
- else
- {
- fp->fd = open (path, oflag, fmode);
- }
-
- if (fp->fd == -1) return false;
-
- if (fp->is_gzip)
- {
- if ((fp->gfp = gzdopen (fp->fd, mode)) == NULL) return false;
- }
- else
- {
- if ((fp->pfp = fdopen (fp->fd, mode)) == NULL) return false;
- }
-
- fp->path = path;
- fp->mode = mode;
-
- return true;
-}
-
-size_t hc_fread (void *ptr, size_t size, size_t nmemb, HCFILE *fp)
-{
- size_t n = -1;
-
- if (fp == NULL) return n;
-
- if (fp->is_gzip)
- {
- n = gzfread (ptr, size, nmemb, fp->gfp);
- }
- else
- {
- n = fread (ptr, size, nmemb, fp->pfp);
- }
-
- return n;
-}
-
-size_t hc_fwrite (void *ptr, size_t size, size_t nmemb, HCFILE *fp)
-{
- size_t n = -1;
-
- if (fp == NULL) return n;
-
- if (fp->is_gzip)
- {
- n = gzfwrite (ptr, size, nmemb, fp->gfp);
- }
- else
- {
- n = fwrite (ptr, size, nmemb, fp->pfp);
- }
-
- if (n != nmemb) return -1;
-
- return n;
-}
-
-int hc_fseek (HCFILE *fp, off_t offset, int whence)
-{
- int r = -1;
-
- if (fp == NULL) return r;
-
- if (fp->is_gzip)
- {
- r = gzseek (fp->gfp, (z_off_t) offset, whence);
- }
- else
- {
- r = fseeko (fp->pfp, offset, whence);
- }
-
- return r;
-}
-
-void hc_rewind (HCFILE *fp)
-{
- if (fp == NULL) return;
-
- if (fp->is_gzip)
- {
- gzrewind (fp->gfp);
- }
- else
- {
- rewind (fp->pfp);
- }
-}
-
-off_t hc_ftell (HCFILE *fp)
-{
- off_t n = 0;
-
- if (fp == NULL) return -1;
-
- if (fp->is_gzip)
- {
- n = (off_t) gztell (fp->gfp);
- }
- else
- {
- n = ftello (fp->pfp);
- }
-
- return n;
-}
-
-int hc_fputc (int c, HCFILE *fp)
-{
- int r = -1;
-
- if (fp == NULL) return r;
-
- if (fp->is_gzip)
- {
- r = gzputc (fp->gfp, c);
- }
- else
- {
- r = fputc (c, fp->pfp);
- }
-
- return r;
-}
-
-int hc_fgetc (HCFILE *fp)
-{
- int r = -1;
-
- if (fp == NULL) return r;
-
- if (fp->is_gzip)
- {
- r = gzgetc (fp->gfp);
- }
- else
- {
- r = fgetc (fp->pfp);
- }
-
- return r;
-}
-
-char *hc_fgets (char *buf, int len, HCFILE *fp)
-{
- char *r = NULL;
-
- if (fp == NULL) return r;
-
- if (fp->is_gzip)
- {
- r = gzgets (fp->gfp, buf, len);
- }
- else
- {
- r = fgets (buf, len, fp->pfp);
- }
-
- return r;
-}
-
-int hc_vfprintf (HCFILE *fp, const char *format, va_list ap)
-{
- int r = -1;
-
- if (fp == NULL) return r;
-
- if (fp->is_gzip)
- {
- r = gzvprintf (fp->gfp, format, ap);
- }
- else
- {
- r = vfprintf (fp->pfp, format, ap);
- }
-
- return r;
-}
-
-int hc_fprintf (HCFILE *fp, const char *format, ...)
-{
- int r = -1;
-
- if (fp == NULL) return r;
-
- va_list ap;
-
- va_start (ap, format);
-
- if (fp->is_gzip)
- {
- r = gzvprintf (fp->gfp, format, ap);
- }
- else
- {
- r = vfprintf (fp->pfp, format, ap);
- }
-
- va_end (ap);
-
- return r;
-}
-
-int hc_fscanf (HCFILE *fp, const char *format, void *ptr)
-{
- if (fp == NULL) return -1;
-
- char *buf = (char *) hcmalloc (HCBUFSIZ_TINY);
-
- if (buf == NULL) return -1;
-
- char *b = hc_fgets (buf, HCBUFSIZ_TINY - 1, fp);
-
- if (b == NULL)
- {
- hcfree (buf);
-
- return -1;
- }
-
- sscanf (b, format, (void *) ptr);
-
- hcfree (buf);
-
- return 1;
-}
-
-int hc_fileno (HCFILE *fp)
-{
- if (fp == NULL) return 1;
-
- return fp->fd;
-}
-
-int hc_feof (HCFILE *fp)
-{
- int r = -1;
-
- if (fp == NULL) return r;
-
- if (fp->is_gzip)
- {
- r = gzeof (fp->gfp);
- }
- else
- {
- r = feof (fp->pfp);
- }
-
- return r;
-}
-
-void hc_fflush (HCFILE *fp)
-{
- if (fp == NULL) return;
-
- if (fp->is_gzip)
- {
- gzflush (fp->gfp, Z_SYNC_FLUSH);
- }
- else
- {
- fflush (fp->pfp);
- }
-}
-
-void hc_fclose (HCFILE *fp)
-{
- if (fp == NULL) return;
-
- if (fp->is_gzip)
- {
- gzclose (fp->gfp);
- }
- else
- {
- fclose (fp->pfp);
- }
-
- close (fp->fd);
-
- fp->fd = -1;
- fp->pfp = NULL;
- fp->is_gzip = false;
-
- fp->path = NULL;
- fp->mode = NULL;
-}
-
bool hc_same_files (char *file1, char *file2)
{
if ((file1 != NULL) && (file2 != NULL))
From 48ca02871471fa8ec6826d20d6ae300e2ba996bb Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 13 Jul 2019 07:16:03 +0200
Subject: [PATCH 006/113] (straight) remove unused *rc* vars and cleanup
---
src/straight.c | 32 ++++++++------------------------
1 file changed, 8 insertions(+), 24 deletions(-)
diff --git a/src/straight.c b/src/straight.c
index 21d1e0ee7..c00483988 100644
--- a/src/straight.c
+++ b/src/straight.c
@@ -239,15 +239,11 @@ int straight_ctx_init (hashcat_ctx_t *hashcat_ctx)
{
if (user_options->rp_files_cnt)
{
- const int rc_kernel_load = kernel_rules_load (hashcat_ctx, &straight_ctx->kernel_rules_buf, &straight_ctx->kernel_rules_cnt);
-
- if (rc_kernel_load == -1) return -1;
+ if (kernel_rules_load (hashcat_ctx, &straight_ctx->kernel_rules_buf, &straight_ctx->kernel_rules_cnt) == -1) return -1;
}
else if (user_options->rp_gen)
{
- const int rc_kernel_generate = kernel_rules_generate (hashcat_ctx, &straight_ctx->kernel_rules_buf, &straight_ctx->kernel_rules_cnt);
-
- if (rc_kernel_generate == -1) return -1;
+ if (kernel_rules_generate (hashcat_ctx, &straight_ctx->kernel_rules_buf, &straight_ctx->kernel_rules_cnt) == -1) return -1;
}
}
@@ -290,9 +286,7 @@ int straight_ctx_init (hashcat_ctx_t *hashcat_ctx)
if (hc_path_is_file (l1_filename) == true)
{
- const int rc = straight_ctx_add_wl (hashcat_ctx, l1_filename);
-
- if (rc == -1)
+ if (straight_ctx_add_wl (hashcat_ctx, l1_filename) == -1)
{
hcfree (dictionary_files);
@@ -306,9 +300,7 @@ int straight_ctx_init (hashcat_ctx_t *hashcat_ctx)
}
else
{
- const int rc = straight_ctx_add_wl (hashcat_ctx, l0_filename);
-
- if (rc == -1) return -1;
+ if (straight_ctx_add_wl (hashcat_ctx, l0_filename) == -1) return -1;
}
}
@@ -361,9 +353,7 @@ int straight_ctx_init (hashcat_ctx_t *hashcat_ctx)
if (hc_path_is_file (l1_filename) == true)
{
- const int rc = straight_ctx_add_wl (hashcat_ctx, l1_filename);
-
- if (rc == -1)
+ if (straight_ctx_add_wl (hashcat_ctx, l1_filename) == -1)
{
hcfree (dictionary_files);
@@ -377,9 +367,7 @@ int straight_ctx_init (hashcat_ctx_t *hashcat_ctx)
}
else
{
- const int rc = straight_ctx_add_wl (hashcat_ctx, l0_filename);
-
- if (rc == -1) return -1;
+ if (straight_ctx_add_wl (hashcat_ctx, l0_filename) == -1) return -1;
}
}
@@ -423,9 +411,7 @@ int straight_ctx_init (hashcat_ctx_t *hashcat_ctx)
if (hc_path_is_file (l1_filename) == true)
{
- const int rc = straight_ctx_add_wl (hashcat_ctx, l1_filename);
-
- if (rc == -1)
+ if (straight_ctx_add_wl (hashcat_ctx, l1_filename) == -1)
{
hcfree (dictionary_files);
@@ -439,9 +425,7 @@ int straight_ctx_init (hashcat_ctx_t *hashcat_ctx)
}
else
{
- const int rc = straight_ctx_add_wl (hashcat_ctx, l0_filename);
-
- if (rc == -1) return -1;
+ if (straight_ctx_add_wl (hashcat_ctx, l0_filename) == -1) return -1;
}
}
From f0a7ba14730bf3bf91a4bec122cc9364e8fe4e0a Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 13 Jul 2019 07:23:50 +0200
Subject: [PATCH 007/113] (restore) remove unused *rc* vars and cleanup
---
src/restore.c | 21 +++++----------------
1 file changed, 5 insertions(+), 16 deletions(-)
diff --git a/src/restore.c b/src/restore.c
index f5358f580..94a7a1f3d 100644
--- a/src/restore.c
+++ b/src/restore.c
@@ -180,9 +180,7 @@ static int read_restore (hashcat_ctx_t *hashcat_ctx)
pidfile_ctx_destroy (hashcat_ctx);
- const int rc_pidfile_init = pidfile_ctx_init (hashcat_ctx);
-
- if (rc_pidfile_init == -1) return -1;
+ if (pidfile_ctx_init (hashcat_ctx) == -1) return -1;
}
return 0;
@@ -254,9 +252,7 @@ int cycle_restore (hashcat_ctx_t *hashcat_ctx)
const char *eff_restore_file = restore_ctx->eff_restore_file;
const char *new_restore_file = restore_ctx->new_restore_file;
- const int rc_write_restore = write_restore (hashcat_ctx);
-
- if (rc_write_restore == -1) return -1;
+ if (write_restore (hashcat_ctx) == -1) return -1;
if (hc_path_exist (eff_restore_file) == true)
{
@@ -332,17 +328,13 @@ int restore_ctx_init (hashcat_ctx_t *hashcat_ctx, int argc, char **argv)
restore_ctx->argc = argc;
restore_ctx->argv = argv;
- const int rc_init_restore = init_restore (hashcat_ctx);
-
- if (rc_init_restore == -1) return -1;
+ if (init_restore (hashcat_ctx) == -1) return -1;
restore_ctx->enabled = true;
if (user_options->restore == true)
{
- const int rc_read_restore = read_restore (hashcat_ctx);
-
- if (rc_read_restore == -1) return -1;
+ if (read_restore (hashcat_ctx) == -1) return -1;
restore_data_t *rd = restore_ctx->rd;
@@ -355,9 +347,7 @@ int restore_ctx_init (hashcat_ctx_t *hashcat_ctx, int argc, char **argv)
user_options_init (hashcat_ctx);
- const int rc_options_getopt = user_options_getopt (hashcat_ctx, rd->argc, rd->argv);
-
- if (rc_options_getopt == -1) return -1;
+ if (user_options_getopt (hashcat_ctx, rd->argc, rd->argv) == -1) return -1;
}
return 0;
@@ -371,7 +361,6 @@ void restore_ctx_destroy (hashcat_ctx_t *hashcat_ctx)
hcfree (restore_ctx->eff_restore_file);
hcfree (restore_ctx->new_restore_file);
-
hcfree (restore_ctx->rd);
memset (restore_ctx, 0, sizeof (restore_ctx_t));
From 7e7acb0ee8688091dacbe16350cfdbf438ded338 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 13 Jul 2019 07:27:32 +0200
Subject: [PATCH 008/113] (main) remove unused *rc* vars and cleanup
---
src/main.c | 20 +++++---------------
1 file changed, 5 insertions(+), 15 deletions(-)
diff --git a/src/main.c b/src/main.c
index ad68870d7..a5123d57b 100644
--- a/src/main.c
+++ b/src/main.c
@@ -1060,9 +1060,7 @@ int main (int argc, char **argv)
hashcat_ctx_t *hashcat_ctx = (hashcat_ctx_t *) hcmalloc (sizeof (hashcat_ctx_t));
- const int rc_hashcat_init = hashcat_init (hashcat_ctx, event);
-
- if (rc_hashcat_init == -1)
+ if (hashcat_init (hashcat_ctx, event) == -1)
{
hcfree (hashcat_ctx);
@@ -1083,9 +1081,7 @@ int main (int argc, char **argv)
// initialize the user options with some defaults (you can override them later)
- const int rc_options_init = user_options_init (hashcat_ctx);
-
- if (rc_options_init == -1)
+ if (user_options_init (hashcat_ctx) == -1)
{
hcfree (hashcat_ctx);
@@ -1094,18 +1090,14 @@ int main (int argc, char **argv)
// parse commandline parameters and check them
- const int rc_options_getopt = user_options_getopt (hashcat_ctx, argc, argv);
-
- if (rc_options_getopt == -1)
+ if (user_options_getopt (hashcat_ctx, argc, argv) == -1)
{
hcfree (hashcat_ctx);
return -1;
}
- const int rc_options_sanity = user_options_sanity (hashcat_ctx);
-
- if (rc_options_sanity == -1)
+ if (user_options_sanity (hashcat_ctx) == -1)
{
hcfree (hashcat_ctx);
@@ -1140,11 +1132,9 @@ int main (int argc, char **argv)
welcome_screen (hashcat_ctx, VERSION_TAG);
- const int rc_session_init = hashcat_session_init (hashcat_ctx, install_folder, shared_folder, argc, argv, COMPTIME);
-
int rc_final = -1;
- if (rc_session_init == 0)
+ if (hashcat_session_init (hashcat_ctx, install_folder, shared_folder, argc, argv, COMPTIME) == 0)
{
if (user_options->usage == true)
{
From cdbef854a4084b5c6b121478d204ee6fe331c895 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 13 Jul 2019 07:32:15 +0200
Subject: [PATCH 009/113] (keyboard_layout) remove unused *rc* vars, change
free with hcfree
---
src/keyboard_layout.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/src/keyboard_layout.c b/src/keyboard_layout.c
index d59998a9a..b20ec6d35 100644
--- a/src/keyboard_layout.c
+++ b/src/keyboard_layout.c
@@ -48,13 +48,11 @@ bool initialize_keyboard_layout_mapping (const char *filename, keyboard_layout_m
token.sep[1] = 0x09;
token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH;
- const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, (const int) line_len, &token);
-
- if (rc_tokenizer != PARSER_OK)
+ if (input_tokenizer ((const u8 *) line_buf, (const int) line_len, &token) != PARSER_OK)
{
hc_fclose (&fp);
- free (line_buf);
+ hcfree (line_buf);
return false;
}
@@ -69,7 +67,7 @@ bool initialize_keyboard_layout_mapping (const char *filename, keyboard_layout_m
{
hc_fclose (&fp);
- free (line_buf);
+ hcfree (line_buf);
return false;
}
@@ -81,7 +79,7 @@ bool initialize_keyboard_layout_mapping (const char *filename, keyboard_layout_m
hc_fclose (&fp);
- free (line_buf);
+ hcfree (line_buf);
// we need to sort this by length to ensure the largest blocks come first in mapping
From 278cd66775ce39fdb97eaf99ece5c72249132d10 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 13 Jul 2019 07:52:54 +0200
Subject: [PATCH 010/113] (dispatch) remove unused *rc* vars and cleanup
---
src/dispatch.c | 145 +++++++++++--------------------------------------
1 file changed, 31 insertions(+), 114 deletions(-)
diff --git a/src/dispatch.c b/src/dispatch.c
index f330f690f..d64dd07ae 100644
--- a/src/dispatch.c
+++ b/src/dispatch.c
@@ -226,9 +226,7 @@ static int calc_stdin (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_par
char *iconv_ptr = iconv_tmp;
size_t iconv_sz = HCBUFSIZ_TINY;
- const size_t iconv_rc = iconv (iconv_ctx, &line_buf, &line_len, &iconv_ptr, &iconv_sz);
-
- if (iconv_rc == (size_t) -1) continue;
+ if (iconv (iconv_ctx, &line_buf, &line_len, &iconv_ptr, &iconv_sz) == (size_t) -1) continue;
line_buf = iconv_tmp;
line_len = HCBUFSIZ_TINY - iconv_sz;
@@ -293,20 +291,14 @@ static int calc_stdin (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_par
// flush
- int CL_rc;
-
- CL_rc = run_copy (hashcat_ctx, device_param, device_param->pws_cnt);
-
- if (CL_rc == -1)
+ if (run_copy (hashcat_ctx, device_param, device_param->pws_cnt) == -1)
{
hcfree (buf);
return -1;
}
- CL_rc = run_cracker (hashcat_ctx, device_param, device_param->pws_cnt);
-
- if (CL_rc == -1)
+ if (run_cracker (hashcat_ctx, device_param, device_param->pws_cnt) == -1)
{
hcfree (buf);
@@ -343,7 +335,6 @@ HC_API_CALL void *thread_calc_stdin (void *p)
thread_param_t *thread_param = (thread_param_t *) p;
hashcat_ctx_t *hashcat_ctx = thread_param->hashcat_ctx;
-
backend_ctx_t *backend_ctx = hashcat_ctx->backend_ctx;
if (backend_ctx->enabled == false) return NULL;
@@ -356,14 +347,10 @@ HC_API_CALL void *thread_calc_stdin (void *p)
if (device_param->is_cuda == true)
{
- const int rc_cuCtxSetCurrent = hc_cuCtxSetCurrent (hashcat_ctx, device_param->cuda_context);
-
- if (rc_cuCtxSetCurrent == -1) return NULL;
+ if (hc_cuCtxSetCurrent (hashcat_ctx, device_param->cuda_context) == -1) return NULL;
}
- const int rc_calc = calc_stdin (hashcat_ctx, device_param);
-
- if (rc_calc == -1)
+ if (calc_stdin (hashcat_ctx, device_param) == -1)
{
status_ctx_t *status_ctx = hashcat_ctx->status_ctx;
@@ -449,9 +436,7 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
hashcat_ctx_tmp->wl_data = (wl_data_t *) hcmalloc (sizeof (wl_data_t));
- const int rc_wl_data_init = wl_data_init (hashcat_ctx_tmp);
-
- if (rc_wl_data_init == -1)
+ if (wl_data_init (hashcat_ctx_tmp) == -1)
{
hc_fclose (&extra_info_straight.fp);
@@ -520,13 +505,10 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
brain_client_disconnect (device_param);
}
- words_extra = overlap;
-
+ words_extra = overlap;
words_extra_total += overlap;
-
- words_off += overlap;
-
- work -= overlap;
+ words_off += overlap;
+ work -= overlap;
}
}
#endif
@@ -658,29 +640,21 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
if (pws_cnt)
{
- int CL_rc;
-
- CL_rc = run_copy (hashcat_ctx, device_param, pws_cnt);
-
- if (CL_rc == -1)
+ if (run_copy (hashcat_ctx, device_param, pws_cnt) == -1)
{
hc_fclose (&extra_info_straight.fp);
hcfree (hashcat_ctx_tmp->wl_data);
-
hcfree (hashcat_ctx_tmp);
return -1;
}
- CL_rc = run_cracker (hashcat_ctx, device_param, pws_cnt);
-
- if (CL_rc == -1)
+ if (run_cracker (hashcat_ctx, device_param, pws_cnt) == -1)
{
hc_fclose (&extra_info_straight.fp);
hcfree (hashcat_ctx_tmp->wl_data);
-
hcfree (hashcat_ctx_tmp);
return -1;
@@ -703,8 +677,7 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
}
#endif
- device_param->pws_cnt = 0;
-
+ device_param->pws_cnt = 0;
device_param->pws_base_cnt = 0;
}
@@ -727,7 +700,6 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
wl_data_destroy (hashcat_ctx_tmp);
hcfree (hashcat_ctx_tmp->wl_data);
-
hcfree (hashcat_ctx_tmp);
}
else if (attack_mode == ATTACK_MODE_COMBI)
@@ -776,9 +748,7 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
hashcat_ctx_tmp->wl_data = (wl_data_t *) hcmalloc (sizeof (wl_data_t));
- const int rc_wl_data_init = wl_data_init (hashcat_ctx_tmp);
-
- if (rc_wl_data_init == -1)
+ if (wl_data_init (hashcat_ctx_tmp) == -1)
{
hc_fclose (&extra_info_combi.base_fp);
hc_fclose (&extra_info_combi.combs_fp);
@@ -849,13 +819,10 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
brain_client_disconnect (device_param);
}
- words_extra = overlap;
-
+ words_extra = overlap;
words_extra_total += overlap;
-
- words_off += overlap;
-
- work -= overlap;
+ words_off += overlap;
+ work -= overlap;
}
}
#endif
@@ -985,11 +952,7 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
if (pws_cnt)
{
- int CL_rc;
-
- CL_rc = run_copy (hashcat_ctx, device_param, pws_cnt);
-
- if (CL_rc == -1)
+ if (run_copy (hashcat_ctx, device_param, pws_cnt) == -1)
{
hc_fclose (&extra_info_combi.base_fp);
hc_fclose (&extra_info_combi.combs_fp);
@@ -1000,9 +963,7 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
return -1;
}
- CL_rc = run_cracker (hashcat_ctx, device_param, pws_cnt);
-
- if (CL_rc == -1)
+ if (run_cracker (hashcat_ctx, device_param, pws_cnt) == -1)
{
hc_fclose (&extra_info_combi.base_fp);
hc_fclose (&extra_info_combi.combs_fp);
@@ -1030,8 +991,7 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
}
#endif
- device_param->pws_cnt = 0;
-
+ device_param->pws_cnt = 0;
device_param->pws_base_cnt = 0;
}
@@ -1124,19 +1084,15 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
brain_client_disconnect (device_param);
}
- words_extra = overlap;
-
+ words_extra = overlap;
words_extra_total += overlap;
-
- words_off += overlap;
-
- work -= overlap;
+ words_off += overlap;
+ work -= overlap;
}
}
#endif
words_fin = words_off + work;
-
words_cur = words_off;
for (u64 i = words_cur; i < words_fin; i++)
@@ -1245,21 +1201,8 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
if (pws_cnt)
{
- int CL_rc;
-
- CL_rc = run_copy (hashcat_ctx, device_param, pws_cnt);
-
- if (CL_rc == -1)
- {
- return -1;
- }
-
- CL_rc = run_cracker (hashcat_ctx, device_param, pws_cnt);
-
- if (CL_rc == -1)
- {
- return -1;
- }
+ if (run_copy (hashcat_ctx, device_param, pws_cnt) == -1) return -1;
+ if (run_cracker (hashcat_ctx, device_param, pws_cnt) == -1) return -1;
#ifdef WITH_BRAIN
if (user_options->brain_client == true)
@@ -1330,15 +1273,8 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
device_param->pws_cnt = work;
- int CL_rc;
-
- CL_rc = run_copy (hashcat_ctx, device_param, device_param->pws_cnt);
-
- if (CL_rc == -1) return -1;
-
- CL_rc = run_cracker (hashcat_ctx, device_param, device_param->pws_cnt);
-
- if (CL_rc == -1) return -1;
+ if (run_copy (hashcat_ctx, device_param, device_param->pws_cnt) == -1) return -1;
+ if (run_cracker (hashcat_ctx, device_param, device_param->pws_cnt) == -1) return -1;
device_param->pws_cnt = 0;
@@ -1408,16 +1344,13 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
hashcat_ctx_tmp->wl_data = (wl_data_t *) hcmalloc (sizeof (wl_data_t));
- const int rc_wl_data_init = wl_data_init (hashcat_ctx_tmp);
-
- if (rc_wl_data_init == -1)
+ if (wl_data_init (hashcat_ctx_tmp) == -1)
{
if (attack_mode == ATTACK_MODE_COMBI) hc_fclose (&device_param->combs_fp);
hc_fclose (&fp);
hcfree (hashcat_ctx_tmp->wl_data);
-
hcfree (hashcat_ctx_tmp);
return -1;
@@ -1429,9 +1362,7 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
{
u64 words_off = 0;
u64 words_fin = 0;
-
u64 words_extra = -1u;
-
u64 words_extra_total = 0;
memset (device_param->pws_comp, 0, device_param->size_pws_comp);
@@ -1538,33 +1469,25 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
if (pws_cnt)
{
- int CL_rc;
-
- CL_rc = run_copy (hashcat_ctx, device_param, pws_cnt);
-
- if (CL_rc == -1)
+ if (run_copy (hashcat_ctx, device_param, pws_cnt) == -1)
{
if (attack_mode == ATTACK_MODE_COMBI) hc_fclose (&device_param->combs_fp);
hc_fclose (&fp);
hcfree (hashcat_ctx_tmp->wl_data);
-
hcfree (hashcat_ctx_tmp);
return -1;
}
- CL_rc = run_cracker (hashcat_ctx, device_param, pws_cnt);
-
- if (CL_rc == -1)
+ if (run_cracker (hashcat_ctx, device_param, pws_cnt) == -1)
{
if (attack_mode == ATTACK_MODE_COMBI) hc_fclose (&device_param->combs_fp);
hc_fclose (&fp);
hcfree (hashcat_ctx_tmp->wl_data);
-
hcfree (hashcat_ctx_tmp);
return -1;
@@ -1622,7 +1545,6 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
wl_data_destroy (hashcat_ctx_tmp);
hcfree (hashcat_ctx_tmp->wl_data);
-
hcfree (hashcat_ctx_tmp);
}
}
@@ -1641,7 +1563,6 @@ HC_API_CALL void *thread_calc (void *p)
thread_param_t *thread_param = (thread_param_t *) p;
hashcat_ctx_t *hashcat_ctx = thread_param->hashcat_ctx;
-
backend_ctx_t *backend_ctx = hashcat_ctx->backend_ctx;
if (backend_ctx->enabled == false) return NULL;
@@ -1654,14 +1575,10 @@ HC_API_CALL void *thread_calc (void *p)
if (device_param->is_cuda == true)
{
- const int rc_cuCtxSetCurrent = hc_cuCtxSetCurrent (hashcat_ctx, device_param->cuda_context);
-
- if (rc_cuCtxSetCurrent == -1) return NULL;
+ if (hc_cuCtxSetCurrent (hashcat_ctx, device_param->cuda_context) == -1) return NULL;
}
- const int rc_calc = calc (hashcat_ctx, device_param);
-
- if (rc_calc == -1)
+ if (calc (hashcat_ctx, device_param) == -1)
{
status_ctx_t *status_ctx = hashcat_ctx->status_ctx;
From e77d6e947ca356a2af0687fc76196554df865f72 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 13 Jul 2019 08:23:12 +0200
Subject: [PATCH 011/113] (brain) remove unused *rc* vars and cleanup
---
src/brain.c | 185 +++++++++++++++++++++++-----------------------------
1 file changed, 82 insertions(+), 103 deletions(-)
diff --git a/src/brain.c b/src/brain.c
index 94840dc9e..ce3e629b3 100644
--- a/src/brain.c
+++ b/src/brain.c
@@ -545,6 +545,8 @@ u64 brain_compute_attack_wordlist (const char *filename)
while (!hc_feof (&fp))
{
+ memset (buf, 0, sizeof (buf));
+
const size_t nread = hc_fread (buf, 1, FBUFSZ, &fp);
XXH64_update (state, buf, nread);
@@ -645,13 +647,13 @@ int brain_connect (int sockfd, const struct sockaddr *addr, socklen_t addrlen, c
// timeout not support on windows
}
- const int rc_connect = connect (sockfd, addr, addrlen);
-
- if (rc_connect == SOCKET_ERROR)
+ if (connect (sockfd, addr, addrlen) == SOCKET_ERROR)
{
int err = WSAGetLastError ();
- char msg[256] = { 0 };
+ char msg[256];
+
+ memset (msg, 0, sizeof (msg));
FormatMessage (FORMAT_MESSAGE_FROM_SYSTEM | FORMAT_MESSAGE_IGNORE_INSERTS, // flags
NULL, // lpsource
@@ -690,7 +692,7 @@ int brain_connect (int sockfd, const struct sockaddr *addr, socklen_t addrlen, c
return -1;
}
- int so_error;
+ int so_error = 0;
socklen_t len = sizeof (so_error);
@@ -786,7 +788,7 @@ bool brain_send_all (int sockfd, void *buf, size_t len, int flags, hc_device_par
if (nsend <= 0) return false;
- if (status_ctx) if (status_ctx->run_thread_level1 == false) return false;
+ if (status_ctx && status_ctx->run_thread_level1 == false) return false;
while (nsend < (ssize_t) len)
{
@@ -810,7 +812,7 @@ bool brain_send_all (int sockfd, void *buf, size_t len, int flags, hc_device_par
if (nsend_new <= 0) return false;
- if (status_ctx) if (status_ctx->run_thread_level1 == false) break;
+ if (status_ctx && status_ctx->run_thread_level1 == false) break;
nsend += nsend_new;
}
@@ -847,7 +849,7 @@ bool brain_recv_all (int sockfd, void *buf, size_t len, int flags, hc_device_par
if (nrecv <= 0) return false;
- if (status_ctx) if (status_ctx->run_thread_level1 == false) return false;
+ if (status_ctx && status_ctx->run_thread_level1 == false) return false;
while (nrecv < (ssize_t) len)
{
@@ -871,7 +873,7 @@ bool brain_recv_all (int sockfd, void *buf, size_t len, int flags, hc_device_par
if (nrecv_new <= 0) return false;
- if (status_ctx) if (status_ctx->run_thread_level1 == false) break;
+ if (status_ctx && status_ctx->run_thread_level1 == false) break;
nrecv += nrecv_new;
}
@@ -928,6 +930,8 @@ bool brain_client_connect (hc_device_param_t *device_param, const status_ctx_t *
char port_str[8];
+ memset (port_str, 0, sizeof (port_str));
+
snprintf (port_str, sizeof (port_str), "%i", port);
const char *host_real = (host == NULL) ? "127.0.0.1" : (const char *) host;
@@ -983,7 +987,7 @@ bool brain_client_connect (hc_device_param_t *device_param, const status_ctx_t *
return false;
}
- u32 brain_link_version_ok;
+ u32 brain_link_version_ok = 0;
if (brain_recv (brain_link_client_fd, &brain_link_version_ok, sizeof (brain_link_version_ok), 0, NULL, NULL) == false)
{
@@ -1003,7 +1007,7 @@ bool brain_client_connect (hc_device_param_t *device_param, const status_ctx_t *
return false;
}
- u32 challenge;
+ u32 challenge = 0;
if (brain_recv (brain_link_client_fd, &challenge, sizeof (challenge), 0, NULL, NULL) == false)
{
@@ -1025,7 +1029,7 @@ bool brain_client_connect (hc_device_param_t *device_param, const status_ctx_t *
return false;
}
- u32 password_ok;
+ u32 password_ok = 0;
if (brain_recv (brain_link_client_fd, &password_ok, sizeof (password_ok), 0, NULL, NULL) == false)
{
@@ -1103,12 +1107,10 @@ bool brain_client_reserve (hc_device_param_t *device_param, const status_ctx_t *
u8 operation = BRAIN_OPERATION_ATTACK_RESERVE;
if (brain_send (brain_link_client_fd, &operation, sizeof (operation), SEND_FLAGS, device_param, status_ctx) == false) return false;
+ if (brain_send (brain_link_client_fd, &words_off, sizeof (words_off), 0, device_param, status_ctx) == false) return false;
+ if (brain_send (brain_link_client_fd, &work, sizeof (work), 0, device_param, status_ctx) == false) return false;
- if (brain_send (brain_link_client_fd, &words_off, sizeof (words_off), 0, device_param, status_ctx) == false) return false;
-
- if (brain_send (brain_link_client_fd, &work, sizeof (work), 0, device_param, status_ctx) == false) return false;
-
- if (brain_recv (brain_link_client_fd, overlap, sizeof (u64), 0, device_param, status_ctx) == false) return false;
+ if (brain_recv (brain_link_client_fd, overlap, sizeof (u64), 0, device_param, status_ctx) == false) return false;
return true;
}
@@ -1139,23 +1141,20 @@ bool brain_client_lookup (hc_device_param_t *device_param, const status_ctx_t *s
char *recvbuf = (char *) device_param->brain_link_in_buf;
char *sendbuf = (char *) device_param->brain_link_out_buf;
+ int in_size = 0;
int out_size = device_param->pws_pre_cnt * BRAIN_HASH_SIZE;
u8 operation = BRAIN_OPERATION_HASH_LOOKUP;
if (brain_send (brain_link_client_fd, &operation, sizeof (operation), SEND_FLAGS, device_param, status_ctx) == false) return false;
+ if (brain_send (brain_link_client_fd, &out_size, sizeof (out_size), SEND_FLAGS, device_param, status_ctx) == false) return false;
+ if (brain_send (brain_link_client_fd, sendbuf, out_size, SEND_FLAGS, device_param, status_ctx) == false) return false;
- if (brain_send (brain_link_client_fd, &out_size, sizeof (out_size), SEND_FLAGS, device_param, status_ctx) == false) return false;
-
- if (brain_send (brain_link_client_fd, sendbuf, out_size, SEND_FLAGS, device_param, status_ctx) == false) return false;
-
- int in_size;
-
- if (brain_recv (brain_link_client_fd, &in_size, sizeof (in_size), 0, device_param, status_ctx) == false) return false;
+ if (brain_recv (brain_link_client_fd, &in_size, sizeof (in_size), 0, device_param, status_ctx) == false) return false;
if (in_size > (int) device_param->size_brain_link_in) return false;
- if (brain_recv (brain_link_client_fd, recvbuf, (size_t) in_size, 0, device_param, status_ctx) == false) return false;
+ if (brain_recv (brain_link_client_fd, recvbuf, (size_t) in_size, 0, device_param, status_ctx) == false) return false;
return true;
}
@@ -1171,14 +1170,12 @@ void brain_server_db_hash_init (brain_server_db_hash_t *brain_server_db_hash, co
{
brain_server_db_hash->brain_session = brain_session;
- brain_server_db_hash->long_alloc = 0;
- brain_server_db_hash->long_cnt = 0;
- brain_server_db_hash->long_buf = NULL;
-
+ brain_server_db_hash->hb = 0;
+ brain_server_db_hash->long_cnt = 0;
+ brain_server_db_hash->long_buf = NULL;
+ brain_server_db_hash->long_alloc = 0;
brain_server_db_hash->write_hashes = false;
- brain_server_db_hash->hb = 0;
-
hc_thread_mutex_init (brain_server_db_hash->mux_hr);
hc_thread_mutex_init (brain_server_db_hash->mux_hg);
}
@@ -1193,8 +1190,7 @@ bool brain_server_db_hash_realloc (brain_server_db_hash_t *brain_server_db_hash,
if (long_buf == NULL) return false;
- brain_server_db_hash->long_buf = long_buf;
-
+ brain_server_db_hash->long_buf = long_buf;
brain_server_db_hash->long_alloc += realloc_size_total;
}
@@ -1206,16 +1202,13 @@ void brain_server_db_hash_free (brain_server_db_hash_t *brain_server_db_hash)
hc_thread_mutex_delete (brain_server_db_hash->mux_hg);
hc_thread_mutex_delete (brain_server_db_hash->mux_hr);
- brain_server_db_hash->hb = 0;
-
hcfree (brain_server_db_hash->long_buf);
- brain_server_db_hash->long_alloc = 0;
- brain_server_db_hash->long_cnt = 0;
- brain_server_db_hash->long_buf = NULL;
-
- brain_server_db_hash->write_hashes = false;
-
+ brain_server_db_hash->hb = 0;
+ brain_server_db_hash->long_cnt = 0;
+ brain_server_db_hash->long_buf = NULL;
+ brain_server_db_hash->long_alloc = 0;
+ brain_server_db_hash->write_hashes = false;
brain_server_db_hash->brain_session = 0;
}
@@ -1223,18 +1216,15 @@ void brain_server_db_attack_init (brain_server_db_attack_t *brain_server_db_atta
{
brain_server_db_attack->brain_attack = brain_attack;
- brain_server_db_attack->short_alloc = 0;
- brain_server_db_attack->short_cnt = 0;
- brain_server_db_attack->short_buf = NULL;
-
- brain_server_db_attack->long_alloc = 0;
- brain_server_db_attack->long_cnt = 0;
- brain_server_db_attack->long_buf = NULL;
-
+ brain_server_db_attack->ab = 0;
+ brain_server_db_attack->short_cnt = 0;
+ brain_server_db_attack->short_buf = NULL;
+ brain_server_db_attack->short_alloc = 0;
+ brain_server_db_attack->long_cnt = 0;
+ brain_server_db_attack->long_buf = NULL;
+ brain_server_db_attack->long_alloc = 0;
brain_server_db_attack->write_attacks = false;
- brain_server_db_attack->ab = 0;
-
hc_thread_mutex_init (brain_server_db_attack->mux_ar);
hc_thread_mutex_init (brain_server_db_attack->mux_ag);
}
@@ -1249,8 +1239,7 @@ bool brain_server_db_attack_realloc (brain_server_db_attack_t *brain_server_db_a
if (long_buf == NULL) return false;
- brain_server_db_attack->long_buf = long_buf;
-
+ brain_server_db_attack->long_buf = long_buf;
brain_server_db_attack->long_alloc += realloc_size_total;
}
@@ -1262,8 +1251,7 @@ bool brain_server_db_attack_realloc (brain_server_db_attack_t *brain_server_db_a
if (short_buf == NULL) return false;
- brain_server_db_attack->short_buf = short_buf;
-
+ brain_server_db_attack->short_buf = short_buf;
brain_server_db_attack->short_alloc += realloc_size_total;
}
@@ -1275,23 +1263,18 @@ void brain_server_db_attack_free (brain_server_db_attack_t *brain_server_db_atta
hc_thread_mutex_delete (brain_server_db_attack->mux_ag);
hc_thread_mutex_delete (brain_server_db_attack->mux_ar);
- brain_server_db_attack->ab = 0;
-
hcfree (brain_server_db_attack->long_buf);
-
- brain_server_db_attack->long_alloc = 0;
- brain_server_db_attack->long_cnt = 0;
- brain_server_db_attack->long_buf = NULL;
-
hcfree (brain_server_db_attack->short_buf);
- brain_server_db_attack->short_alloc = 0;
- brain_server_db_attack->short_cnt = 0;
- brain_server_db_attack->short_buf = NULL;
-
+ brain_server_db_attack->ab = 0;
+ brain_server_db_attack->long_cnt = 0;
+ brain_server_db_attack->long_buf = NULL;
+ brain_server_db_attack->long_alloc = 0;
+ brain_server_db_attack->short_cnt = 0;
+ brain_server_db_attack->short_buf = NULL;
+ brain_server_db_attack->short_alloc = 0;
+ brain_server_db_attack->brain_attack = 0;
brain_server_db_attack->write_attacks = false;
-
- brain_server_db_attack->brain_attack = 0;
}
u64 brain_server_highest_attack (const brain_server_db_attack_t *buf)
@@ -1547,10 +1530,7 @@ bool brain_server_read_hash_dumps (brain_server_dbs_t *brain_server_dbs, const c
brain_server_db_hash_init (brain_server_db_hash, brain_session);
- if (brain_server_read_hash_dump (brain_server_db_hash, file) == false)
- {
- continue;
- }
+ if (brain_server_read_hash_dump (brain_server_db_hash, file) == false) continue;
brain_server_dbs->hash_cnt++;
}
@@ -1570,6 +1550,8 @@ bool brain_server_write_hash_dumps (brain_server_dbs_t *brain_server_dbs, const
char file[100];
+ memset (file, 0, sizeof (file));
+
snprintf (file, sizeof (file), "%s/brain.%08x.ldmp", path, brain_server_db_hash->brain_session);
brain_server_write_hash_dump (brain_server_db_hash, file);
@@ -1590,6 +1572,8 @@ bool brain_server_read_hash_dump (brain_server_db_hash_t *brain_server_db_hash,
struct stat sb;
+ memset (&sb, 0, sizeof (struct stat));
+
if (stat (file, &sb) == -1)
{
brain_logging (stderr, 0, "%s: %s\n", file, strerror (errno));
@@ -1629,8 +1613,7 @@ bool brain_server_read_hash_dump (brain_server_db_hash_t *brain_server_db_hash,
return false;
}
- brain_server_db_hash->long_cnt = temp_cnt;
-
+ brain_server_db_hash->long_cnt = temp_cnt;
brain_server_db_hash->write_hashes = false;
hc_fclose (&fp);
@@ -1685,6 +1668,8 @@ bool brain_server_write_hash_dump (brain_server_db_hash_t *brain_server_db_hash,
struct stat sb;
+ memset (&sb, 0, sizeof (struct stat));
+
if (stat (file, &sb) == -1)
{
brain_logging (stderr, 0, "%s: %s\n", file, strerror (errno));
@@ -1717,7 +1702,7 @@ bool brain_server_read_attack_dumps (brain_server_dbs_t *brain_server_dbs, const
return false;
}
- struct dirent *entry;
+ struct dirent *entry = NULL;
while ((entry = readdir (dirp)) != NULL)
{
@@ -1746,10 +1731,7 @@ bool brain_server_read_attack_dumps (brain_server_dbs_t *brain_server_dbs, const
brain_server_db_attack_init (brain_server_db_attack, brain_attack);
- if (brain_server_read_attack_dump (brain_server_db_attack, file) == false)
- {
- continue;
- }
+ if (brain_server_read_attack_dump (brain_server_db_attack, file) == false) continue;
brain_server_dbs->attack_cnt++;
}
@@ -1769,6 +1751,8 @@ bool brain_server_write_attack_dumps (brain_server_dbs_t *brain_server_dbs, cons
char file[100];
+ memset (file, 0, sizeof (file));
+
snprintf (file, sizeof (file), "%s/brain.%08x.admp", path, brain_server_db_attack->brain_attack);
brain_server_write_attack_dump (brain_server_db_attack, file);
@@ -1789,6 +1773,8 @@ bool brain_server_read_attack_dump (brain_server_db_attack_t *brain_server_db_at
struct stat sb;
+ memset (&sb, 0, sizeof (struct stat));
+
if (stat (file, &sb) == -1)
{
brain_logging (stderr, 0, "%s: %s\n", file, strerror (errno));
@@ -1828,8 +1814,7 @@ bool brain_server_read_attack_dump (brain_server_db_attack_t *brain_server_db_at
return false;
}
- brain_server_db_attack->long_cnt = temp_cnt;
-
+ brain_server_db_attack->long_cnt = temp_cnt;
brain_server_db_attack->write_attacks = false;
hc_fclose (&fp);
@@ -1886,6 +1871,8 @@ bool brain_server_write_attack_dump (brain_server_db_attack_t *brain_server_db_a
struct stat sb;
+ memset (&sb, 0, sizeof (struct stat));
+
if (stat (file, &sb) == -1)
{
brain_logging (stderr, 0, "%s: %s\n", file, strerror (errno));
@@ -1918,7 +1905,6 @@ i64 brain_server_find_hash_long (const u32 *search, const brain_server_hash_long
for (i64 l = 0, r = cnt; r; r >>= 1)
{
const i64 m = r >> 1;
-
const i64 c = l + m;
const int cmp = brain_server_sort_hash_long (search, buf + c);
@@ -1930,10 +1916,10 @@ i64 brain_server_find_hash_long (const u32 *search, const brain_server_hash_long
r--;
}
- if (cmp == 0) return (c);
+ if (cmp == 0) return c;
}
- return (-1);
+ return -1;
}
i64 brain_server_find_hash_short (const u32 *search, const brain_server_hash_short_t *buf, const i64 cnt)
@@ -1941,7 +1927,6 @@ i64 brain_server_find_hash_short (const u32 *search, const brain_server_hash_sho
for (i64 l = 0, r = cnt; r; r >>= 1)
{
const i64 m = r >> 1;
-
const i64 c = l + m;
const int cmp = brain_server_sort_hash_short (search, buf + c);
@@ -1953,10 +1938,10 @@ i64 brain_server_find_hash_short (const u32 *search, const brain_server_hash_sho
r--;
}
- if (cmp == 0) return (c);
+ if (cmp == 0) return c;
}
- return (-1);
+ return -1;
}
void brain_server_handle_signal (int signo)
@@ -2026,7 +2011,7 @@ void *brain_server_handle_client (void *p)
#endif
- u32 brain_link_version;
+ u32 brain_link_version = 0;
if (brain_recv (client_fd, &brain_link_version, sizeof (brain_link_version), 0, NULL, NULL) == false)
{
@@ -2076,7 +2061,7 @@ void *brain_server_handle_client (void *p)
return NULL;
}
- u64 response;
+ u64 response = 0;
if (brain_recv (client_fd, &response, sizeof (response), 0, NULL, NULL) == false)
{
@@ -2115,7 +2100,7 @@ void *brain_server_handle_client (void *p)
return NULL;
}
- u32 brain_session;
+ u32 brain_session = 0;
if (brain_recv (client_fd, &brain_session, sizeof (brain_session), 0, NULL, NULL) == false)
{
@@ -2154,7 +2139,7 @@ void *brain_server_handle_client (void *p)
}
}
- u32 brain_attack;
+ u32 brain_attack = 0;
if (brain_recv (client_fd, &brain_attack, sizeof (brain_attack), 0, NULL, NULL) == false)
{
@@ -2167,7 +2152,7 @@ void *brain_server_handle_client (void *p)
return NULL;
}
- i64 passwords_max;
+ i64 passwords_max = 0;
if (brain_recv (client_fd, &passwords_max, sizeof (passwords_max), 0, NULL, NULL) == false)
{
@@ -2359,7 +2344,7 @@ void *brain_server_handle_client (void *p)
// there's data
- u8 operation;
+ u8 operation = 0;
if (brain_recv (client_fd, &operation, sizeof (operation), 0, NULL, NULL) == false) break;
@@ -2545,7 +2530,6 @@ void *brain_server_handle_client (void *p)
i64 long_left = brain_server_db_hash->long_cnt - 1;
i64 short_left = brain_server_db_short->short_cnt - 1;
-
i64 long_dupes = 0;
for (i64 idx = cnt_total - 1; idx >= long_dupes; idx--)
@@ -2903,8 +2887,7 @@ void *brain_server_handle_client (void *p)
int out_size = hashes_cnt;
if (brain_send (client_fd, &out_size, sizeof (out_size), SEND_FLAGS, NULL, NULL) == false) break;
-
- if (brain_send (client_fd, send_buf, out_size, SEND_FLAGS, NULL, NULL) == false) break;
+ if (brain_send (client_fd, send_buf, out_size, SEND_FLAGS, NULL, NULL) == false) break;
}
else
{
@@ -2955,9 +2938,7 @@ int brain_server (const char *listen_host, const int listen_port, const char *br
WORD wVersionRequested = MAKEWORD (2,2);
- const int iResult = WSAStartup (wVersionRequested, &wsaData);
-
- if (iResult != NO_ERROR)
+ if (WSAStartup (wVersionRequested, &wsaData) != NO_ERROR)
{
fprintf (stderr, "WSAStartup: %s\n", strerror (errno));
@@ -3198,9 +3179,9 @@ int brain_server (const char *listen_host, const int listen_port, const char *br
{
// none of these value change
- brain_server_client_options[client_idx].brain_server_dbs = brain_server_dbs;
- brain_server_client_options[client_idx].auth_password = auth_password;
brain_server_client_options[client_idx].client_idx = client_idx;
+ brain_server_client_options[client_idx].auth_password = auth_password;
+ brain_server_client_options[client_idx].brain_server_dbs = brain_server_dbs;
brain_server_client_options[client_idx].session_whitelist_buf = session_whitelist_buf;
brain_server_client_options[client_idx].session_whitelist_cnt = session_whitelist_cnt;
}
@@ -3316,9 +3297,7 @@ int brain_server (const char *listen_host, const int listen_port, const char *br
hcfree (brain_server_dbs->hash_buf);
hcfree (brain_server_dbs->attack_buf);
-
hcfree (brain_server_dbs);
-
hcfree (brain_server_client_options);
if (brain_password == NULL) hcfree (auth_password);
From bbcb23b038fda69173e0a4eb983e5b0315d7f1dd Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 13 Jul 2019 14:43:13 +0200
Subject: [PATCH 012/113] Add hash mode 4710 - sha256(md5(pass))
---
OpenCL/m04710_a0-pure.cl | 244 ++++++++++++++++++++++++++++++++++
OpenCL/m04710_a3-pure.cl | 264 +++++++++++++++++++++++++++++++++++++
src/modules/module_04710.c | 228 ++++++++++++++++++++++++++++++++
3 files changed, 736 insertions(+)
create mode 100644 OpenCL/m04710_a0-pure.cl
create mode 100644 OpenCL/m04710_a3-pure.cl
create mode 100644 src/modules/module_04710.c
diff --git a/OpenCL/m04710_a0-pure.cl b/OpenCL/m04710_a0-pure.cl
new file mode 100644
index 000000000..966463126
--- /dev/null
+++ b/OpenCL/m04710_a0-pure.cl
@@ -0,0 +1,244 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp.h"
+#include "inc_rp.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04710_mxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ md5_ctx_t ctx0;
+
+ md5_init (&ctx0);
+
+ md5_update (&ctx0, tmp.i, tmp.pw_len);
+
+ md5_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+
+ sha256_ctx_t ctx;
+
+ sha256_init (&ctx);
+
+ ctx.w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ ctx.w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ ctx.w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ ctx.w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ ctx.w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ ctx.w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ ctx.w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ ctx.w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ ctx.w2[0] = 0;
+ ctx.w2[1] = 0;
+ ctx.w2[2] = 0;
+ ctx.w2[3] = 0;
+ ctx.w3[0] = 0;
+ ctx.w3[1] = 0;
+ ctx.w3[2] = 0;
+ ctx.w3[3] = 0;
+
+ ctx.len = 32;
+
+ sha256_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04710_sxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ md5_ctx_t ctx0;
+
+ md5_init (&ctx0);
+
+ md5_update (&ctx0, tmp.i, tmp.pw_len);
+
+ md5_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+
+ sha256_ctx_t ctx;
+
+ sha256_init (&ctx);
+
+ ctx.w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ ctx.w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ ctx.w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ ctx.w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ ctx.w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ ctx.w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ ctx.w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ ctx.w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ ctx.w2[0] = 0;
+ ctx.w2[1] = 0;
+ ctx.w2[2] = 0;
+ ctx.w2[3] = 0;
+ ctx.w3[0] = 0;
+ ctx.w3[1] = 0;
+ ctx.w3[2] = 0;
+ ctx.w3[3] = 0;
+
+ ctx.len = 32;
+
+ sha256_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m04710_a3-pure.cl b/OpenCL/m04710_a3-pure.cl
new file mode 100644
index 000000000..449da471d
--- /dev/null
+++ b/OpenCL/m04710_a3-pure.cl
@@ -0,0 +1,264 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04710_mxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ md5_ctx_vector_t ctx0;
+
+ md5_init_vector (&ctx0);
+
+ md5_update_vector (&ctx0, w, pw_len);
+
+ md5_final_vector (&ctx0);
+
+ const u32x a = ctx0.h[0];
+ const u32x b = ctx0.h[1];
+ const u32x c = ctx0.h[2];
+ const u32x d = ctx0.h[3];
+
+ sha256_ctx_vector_t ctx;
+
+ sha256_init_vector (&ctx);
+
+ ctx.w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ ctx.w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ ctx.w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ ctx.w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ ctx.w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ ctx.w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ ctx.w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ ctx.w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ ctx.w2[0] = 0;
+ ctx.w2[1] = 0;
+ ctx.w2[2] = 0;
+ ctx.w2[3] = 0;
+ ctx.w3[0] = 0;
+ ctx.w3[1] = 0;
+ ctx.w3[2] = 0;
+ ctx.w3[3] = 0;
+
+ ctx.len = 32;
+
+ sha256_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04710_sxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ md5_ctx_vector_t ctx0;
+
+ md5_init_vector (&ctx0);
+
+ md5_update_vector (&ctx0, w, pw_len);
+
+ md5_final_vector (&ctx0);
+
+ const u32x a = ctx0.h[0];
+ const u32x b = ctx0.h[1];
+ const u32x c = ctx0.h[2];
+ const u32x d = ctx0.h[3];
+
+ sha256_ctx_vector_t ctx;
+
+ sha256_init_vector (&ctx);
+
+ ctx.w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ ctx.w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ ctx.w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ ctx.w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ ctx.w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ ctx.w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ ctx.w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ ctx.w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ ctx.w2[0] = 0;
+ ctx.w2[1] = 0;
+ ctx.w2[2] = 0;
+ ctx.w2[3] = 0;
+ ctx.w3[0] = 0;
+ ctx.w3[1] = 0;
+ ctx.w3[2] = 0;
+ ctx.w3[3] = 0;
+
+ ctx.len = 32;
+
+ sha256_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SIMD (r0, r1, r2, r3);
+ }
+}
diff --git a/src/modules/module_04710.c b/src/modules/module_04710.c
new file mode 100644
index 000000000..d444b4512
--- /dev/null
+++ b/src/modules/module_04710.c
@@ -0,0 +1,228 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+
+static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL;
+static const u32 DGST_POS0 = 3;
+static const u32 DGST_POS1 = 7;
+static const u32 DGST_POS2 = 2;
+static const u32 DGST_POS3 = 6;
+static const u32 DGST_SIZE = DGST_SIZE_4_8;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
+static const char *HASH_NAME = "sha256(md5($pass))";
+static const u64 KERN_TYPE = 4710;
+static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
+ | OPTI_TYPE_PRECOMPUTE_INIT
+ | OPTI_TYPE_EARLY_SKIP
+ | OPTI_TYPE_NOT_ITERATED
+ | OPTI_TYPE_NOT_SALTED
+ | OPTI_TYPE_RAW_HASH;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_BE
+ | OPTS_TYPE_PT_ADD80
+ | OPTS_TYPE_PT_ADDBITS15;
+static const u32 SALT_TYPE = SALT_TYPE_NONE;
+static const char *ST_PASS = "hashcat";
+static const char *ST_HASH = "74ee1fae245edd6f27bf36efc3604942479fceefbadab5dc5c0b538c196eb0f1";
+
+u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
+u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
+u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
+u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
+u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
+u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
+u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
+const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
+u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
+u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
+u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
+u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
+const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
+const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+ u32 *digest = (u32 *) digest_buf;
+
+ token_t token;
+
+ token.token_cnt = 1;
+
+ token.len_min[0] = 64;
+ token.len_max[0] = 64;
+ token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_HEX;
+
+ const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+ if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+ const u8 *hash_pos = token.buf[0];
+
+ digest[0] = hex_to_u32 (hash_pos + 0);
+ digest[1] = hex_to_u32 (hash_pos + 8);
+ digest[2] = hex_to_u32 (hash_pos + 16);
+ digest[3] = hex_to_u32 (hash_pos + 24);
+ digest[4] = hex_to_u32 (hash_pos + 32);
+ digest[5] = hex_to_u32 (hash_pos + 40);
+ digest[6] = hex_to_u32 (hash_pos + 48);
+ digest[7] = hex_to_u32 (hash_pos + 56);
+
+ digest[0] = byte_swap_32 (digest[0]);
+ digest[1] = byte_swap_32 (digest[1]);
+ digest[2] = byte_swap_32 (digest[2]);
+ digest[3] = byte_swap_32 (digest[3]);
+ digest[4] = byte_swap_32 (digest[4]);
+ digest[5] = byte_swap_32 (digest[5]);
+ digest[6] = byte_swap_32 (digest[6]);
+ digest[7] = byte_swap_32 (digest[7]);
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ digest[0] -= SHA256M_A;
+ digest[1] -= SHA256M_B;
+ digest[2] -= SHA256M_C;
+ digest[3] -= SHA256M_D;
+ digest[4] -= SHA256M_E;
+ digest[5] -= SHA256M_F;
+ digest[6] -= SHA256M_G;
+ digest[7] -= SHA256M_H;
+ }
+
+ return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+ const u32 *digest = (const u32 *) digest_buf;
+
+ // we can not change anything in the original buffer, otherwise destroying sorting
+ // therefore create some local buffer
+
+ u32 tmp[8];
+
+ tmp[0] = digest[0];
+ tmp[1] = digest[1];
+ tmp[2] = digest[2];
+ tmp[3] = digest[3];
+ tmp[4] = digest[4];
+ tmp[5] = digest[5];
+ tmp[6] = digest[6];
+ tmp[7] = digest[7];
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ tmp[0] += SHA256M_A;
+ tmp[1] += SHA256M_B;
+ tmp[2] += SHA256M_C;
+ tmp[3] += SHA256M_D;
+ tmp[4] += SHA256M_E;
+ tmp[5] += SHA256M_F;
+ tmp[6] += SHA256M_G;
+ tmp[7] += SHA256M_H;
+ }
+
+ tmp[0] = byte_swap_32 (tmp[0]);
+ tmp[1] = byte_swap_32 (tmp[1]);
+ tmp[2] = byte_swap_32 (tmp[2]);
+ tmp[3] = byte_swap_32 (tmp[3]);
+ tmp[4] = byte_swap_32 (tmp[4]);
+ tmp[5] = byte_swap_32 (tmp[5]);
+ tmp[6] = byte_swap_32 (tmp[6]);
+ tmp[7] = byte_swap_32 (tmp[7]);
+
+ u8 *out_buf = (u8 *) line_buf;
+
+ u32_to_hex (tmp[0], out_buf + 0);
+ u32_to_hex (tmp[1], out_buf + 8);
+ u32_to_hex (tmp[2], out_buf + 16);
+ u32_to_hex (tmp[3], out_buf + 24);
+ u32_to_hex (tmp[4], out_buf + 32);
+ u32_to_hex (tmp[5], out_buf + 40);
+ u32_to_hex (tmp[6], out_buf + 48);
+ u32_to_hex (tmp[7], out_buf + 56);
+
+ const int out_len = 64;
+
+ return out_len;
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+ module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
+ module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
+
+ module_ctx->module_attack_exec = module_attack_exec;
+ module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_mask = MODULE_DEFAULT;
+ module_ctx->module_benchmark_salt = MODULE_DEFAULT;
+ module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
+ module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
+ module_ctx->module_dgst_pos0 = module_dgst_pos0;
+ module_ctx->module_dgst_pos1 = module_dgst_pos1;
+ module_ctx->module_dgst_pos2 = module_dgst_pos2;
+ module_ctx->module_dgst_pos3 = module_dgst_pos3;
+ module_ctx->module_dgst_size = module_dgst_size;
+ module_ctx->module_dictstat_disable = MODULE_DEFAULT;
+ module_ctx->module_esalt_size = MODULE_DEFAULT;
+ module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
+ module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_count = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_save = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
+ module_ctx->module_hash_decode = module_hash_decode;
+ module_ctx->module_hash_encode_status = MODULE_DEFAULT;
+ module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_encode = module_hash_encode;
+ module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
+ module_ctx->module_hash_mode = MODULE_DEFAULT;
+ module_ctx->module_hash_category = module_hash_category;
+ module_ctx->module_hash_name = module_hash_name;
+ module_ctx->module_hashes_count_min = MODULE_DEFAULT;
+ module_ctx->module_hashes_count_max = MODULE_DEFAULT;
+ module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
+ module_ctx->module_hook12 = MODULE_DEFAULT;
+ module_ctx->module_hook23 = MODULE_DEFAULT;
+ module_ctx->module_hook_salt_size = MODULE_DEFAULT;
+ module_ctx->module_hook_size = MODULE_DEFAULT;
+ module_ctx->module_jit_build_options = MODULE_DEFAULT;
+ module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
+ module_ctx->module_kern_type = module_kern_type;
+ module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
+ module_ctx->module_opti_type = module_opti_type;
+ module_ctx->module_opts_type = module_opts_type;
+ module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
+ module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
+ module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
+ module_ctx->module_potfile_disable = MODULE_DEFAULT;
+ module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
+ module_ctx->module_pwdump_column = MODULE_DEFAULT;
+ module_ctx->module_pw_max = MODULE_DEFAULT;
+ module_ctx->module_pw_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = MODULE_DEFAULT;
+ module_ctx->module_salt_min = MODULE_DEFAULT;
+ module_ctx->module_salt_type = module_salt_type;
+ module_ctx->module_separator = MODULE_DEFAULT;
+ module_ctx->module_st_hash = module_st_hash;
+ module_ctx->module_st_pass = module_st_pass;
+ module_ctx->module_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_unstable_warning = MODULE_DEFAULT;
+ module_ctx->module_warmup_disable = MODULE_DEFAULT;
+}
From 806b00168cb3d7486623e7f282c822f6a07b922b Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 13 Jul 2019 15:36:16 +0200
Subject: [PATCH 013/113] fix wrong OPTS_TYPE, add remaining 4710 kernels
---
OpenCL/m04710_a0-optimized.cl | 619 ++++++++++++++++++++++
OpenCL/m04710_a1-optimized.cl | 727 +++++++++++++++++++++++++
OpenCL/m04710_a1-pure.cl | 238 +++++++++
OpenCL/m04710_a3-optimized.cl | 967 ++++++++++++++++++++++++++++++++++
src/modules/module_04710.c | 2 +-
5 files changed, 2552 insertions(+), 1 deletion(-)
create mode 100644 OpenCL/m04710_a0-optimized.cl
create mode 100644 OpenCL/m04710_a1-optimized.cl
create mode 100644 OpenCL/m04710_a1-pure.cl
create mode 100644 OpenCL/m04710_a3-optimized.cl
diff --git a/OpenCL/m04710_a0-optimized.cl b/OpenCL/m04710_a0-optimized.cl
new file mode 100644
index 000000000..d2f365c25
--- /dev/null
+++ b/OpenCL/m04710_a0-optimized.cl
@@ -0,0 +1,619 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+#define SHA256_STEP_REV(a,b,c,d,e,f,g,h) \
+{ \
+ u32 t2 = SHA256_S2_S(b) + SHA256_F0o(b,c,d); \
+ u32 t1 = a - t2; \
+ a = b; \
+ b = c; \
+ c = d; \
+ d = e - t1; \
+ e = f; \
+ f = g; \
+ g = h; \
+ h = 0; \
+}
+
+KERNEL_FQ void m04710_m04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ w3[2] = out_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+ u32x f = 0;
+ u32x g = 0;
+ u32x h = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha256
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0x80000000;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 32 * 8;
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ COMPARE_M_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m04710_m08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04710_m16 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04710_s04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ u32 a_rev = digests_buf[digests_offset].digest_buf[0];
+ u32 b_rev = digests_buf[digests_offset].digest_buf[1];
+ u32 c_rev = digests_buf[digests_offset].digest_buf[2];
+ u32 d_rev = digests_buf[digests_offset].digest_buf[3];
+ u32 e_rev = digests_buf[digests_offset].digest_buf[4];
+ u32 f_rev = digests_buf[digests_offset].digest_buf[5];
+ u32 g_rev = digests_buf[digests_offset].digest_buf[6];
+ u32 h_rev = digests_buf[digests_offset].digest_buf[7];
+
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ w3[2] = out_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+ u32x f = 0;
+ u32x g = 0;
+ u32x h = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha256
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0x80000000;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 32 * 8;
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+
+ if (MATCHES_NONE_VS (h, d_rev)) continue;
+
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ COMPARE_S_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m04710_s08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04710_s16 (KERN_ATTR_RULES ())
+{
+}
diff --git a/OpenCL/m04710_a1-optimized.cl b/OpenCL/m04710_a1-optimized.cl
new file mode 100644
index 000000000..e510b235b
--- /dev/null
+++ b/OpenCL/m04710_a1-optimized.cl
@@ -0,0 +1,727 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+#define SHA256_STEP_REV(a,b,c,d,e,f,g,h) \
+{ \
+ u32 t2 = SHA256_S2_S(b) + SHA256_F0o(b,c,d); \
+ u32 t1 = a - t2; \
+ a = b; \
+ b = c; \
+ c = d; \
+ d = e - t1; \
+ e = f; \
+ f = g; \
+ g = h; \
+ h = 0; \
+}
+
+KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = pw_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+ u32x f = 0;
+ u32x g = 0;
+ u32x h = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha256
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0x80000000;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 32 * 8;
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ COMPARE_M_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m04710_m08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m04710_m16 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ u32 a_rev = digests_buf[digests_offset].digest_buf[0];
+ u32 b_rev = digests_buf[digests_offset].digest_buf[1];
+ u32 c_rev = digests_buf[digests_offset].digest_buf[2];
+ u32 d_rev = digests_buf[digests_offset].digest_buf[3];
+ u32 e_rev = digests_buf[digests_offset].digest_buf[4];
+ u32 f_rev = digests_buf[digests_offset].digest_buf[5];
+ u32 g_rev = digests_buf[digests_offset].digest_buf[6];
+ u32 h_rev = digests_buf[digests_offset].digest_buf[7];
+
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = pw_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+ u32x f = 0;
+ u32x g = 0;
+ u32x h = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha256
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0x80000000;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 32 * 8;
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+
+ if (MATCHES_NONE_VS (h, d_rev)) continue;
+
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ COMPARE_S_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m04710_s08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m04710_s16 (KERN_ATTR_BASIC ())
+{
+}
diff --git a/OpenCL/m04710_a1-pure.cl b/OpenCL/m04710_a1-pure.cl
new file mode 100644
index 000000000..044b07058
--- /dev/null
+++ b/OpenCL/m04710_a1-pure.cl
@@ -0,0 +1,238 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04710_mxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ md5_ctx_t ctx0;
+
+ md5_init (&ctx0);
+
+ md5_update_global (&ctx0, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ md5_ctx_t ctx1 = ctx0;
+
+ md5_update_global (&ctx1, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ md5_final (&ctx1);
+
+ const u32 a = ctx1.h[0];
+ const u32 b = ctx1.h[1];
+ const u32 c = ctx1.h[2];
+ const u32 d = ctx1.h[3];
+
+ sha256_ctx_t ctx;
+
+ sha256_init (&ctx);
+
+ ctx.w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ ctx.w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ ctx.w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ ctx.w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ ctx.w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ ctx.w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ ctx.w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ ctx.w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ ctx.w2[0] = 0;
+ ctx.w2[1] = 0;
+ ctx.w2[2] = 0;
+ ctx.w2[3] = 0;
+ ctx.w3[0] = 0;
+ ctx.w3[1] = 0;
+ ctx.w3[2] = 0;
+ ctx.w3[3] = 0;
+
+ ctx.len = 32;
+
+ sha256_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04710_sxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ md5_ctx_t ctx0;
+
+ md5_init (&ctx0);
+
+ md5_update_global (&ctx0, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ md5_ctx_t ctx1 = ctx0;
+
+ md5_update_global (&ctx1, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ md5_final (&ctx1);
+
+ const u32 a = ctx1.h[0];
+ const u32 b = ctx1.h[1];
+ const u32 c = ctx1.h[2];
+ const u32 d = ctx1.h[3];
+
+ sha256_ctx_t ctx;
+
+ sha256_init (&ctx);
+
+ ctx.w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ ctx.w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ ctx.w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ ctx.w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ ctx.w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ ctx.w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ ctx.w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ ctx.w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ ctx.w2[0] = 0;
+ ctx.w2[1] = 0;
+ ctx.w2[2] = 0;
+ ctx.w2[3] = 0;
+ ctx.w3[0] = 0;
+ ctx.w3[1] = 0;
+ ctx.w3[2] = 0;
+ ctx.w3[3] = 0;
+
+ ctx.len = 32;
+
+ sha256_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m04710_a3-optimized.cl b/OpenCL/m04710_a3-optimized.cl
new file mode 100644
index 000000000..cdc215c06
--- /dev/null
+++ b/OpenCL/m04710_a3-optimized.cl
@@ -0,0 +1,967 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+#define SHA256_STEP_REV(a,b,c,d,e,f,g,h) \
+{ \
+ u32 t2 = SHA256_S2_S(b) + SHA256_F0o(b,c,d); \
+ u32 t1 = a - t2; \
+ a = b; \
+ b = c; \
+ c = d; \
+ d = e - t1; \
+ e = f; \
+ f = g; \
+ g = h; \
+ h = 0; \
+}
+
+DECLSPEC void m04710m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ u32x w0_t = w0lr;
+ u32x w1_t = w0[1];
+ u32x w2_t = w0[2];
+ u32x w3_t = w0[3];
+ u32x w4_t = w1[0];
+ u32x w5_t = w1[1];
+ u32x w6_t = w1[2];
+ u32x w7_t = w1[3];
+ u32x w8_t = w2[0];
+ u32x w9_t = w2[1];
+ u32x wa_t = w2[2];
+ u32x wb_t = w2[3];
+ u32x wc_t = w3[0];
+ u32x wd_t = w3[1];
+ u32x we_t = w3[2];
+ u32x wf_t = w3[3];
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+ u32x f = 0;
+ u32x g = 0;
+ u32x h = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha256
+ */
+
+ w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ w8_t = 0x80000000;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 32 * 8;
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ COMPARE_M_SIMD (d, h, c, g);
+ }
+}
+
+DECLSPEC void m04710s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ u32 a_rev = digests_buf[digests_offset].digest_buf[0];
+ u32 b_rev = digests_buf[digests_offset].digest_buf[1];
+ u32 c_rev = digests_buf[digests_offset].digest_buf[2];
+ u32 d_rev = digests_buf[digests_offset].digest_buf[3];
+ u32 e_rev = digests_buf[digests_offset].digest_buf[4];
+ u32 f_rev = digests_buf[digests_offset].digest_buf[5];
+ u32 g_rev = digests_buf[digests_offset].digest_buf[6];
+ u32 h_rev = digests_buf[digests_offset].digest_buf[7];
+
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ u32x w0_t = w0lr;
+ u32x w1_t = w0[1];
+ u32x w2_t = w0[2];
+ u32x w3_t = w0[3];
+ u32x w4_t = w1[0];
+ u32x w5_t = w1[1];
+ u32x w6_t = w1[2];
+ u32x w7_t = w1[3];
+ u32x w8_t = w2[0];
+ u32x w9_t = w2[1];
+ u32x wa_t = w2[2];
+ u32x wb_t = w2[3];
+ u32x wc_t = w3[0];
+ u32x wd_t = w3[1];
+ u32x we_t = w3[2];
+ u32x wf_t = w3[3];
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+ u32x f = 0;
+ u32x g = 0;
+ u32x h = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha256
+ */
+
+ w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ w8_t = 0x80000000;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 32 * 8;
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+
+ if (MATCHES_NONE_VS (h, d_rev)) continue;
+
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ COMPARE_S_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_m08 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_m16 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = pws[gid].i[14];
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_s08 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_s16 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = pws[gid].i[14];
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
diff --git a/src/modules/module_04710.c b/src/modules/module_04710.c
index d444b4512..95fbdffbb 100644
--- a/src/modules/module_04710.c
+++ b/src/modules/module_04710.c
@@ -25,7 +25,7 @@ static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_NOT_ITERATED
| OPTI_TYPE_NOT_SALTED
| OPTI_TYPE_RAW_HASH;
-static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_BE
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE
| OPTS_TYPE_PT_ADD80
| OPTS_TYPE_PT_ADDBITS15;
static const u32 SALT_TYPE = SALT_TYPE_NONE;
From ed77af9207ad3a36249f87fcc36792d8416471c0 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 13 Jul 2019 16:25:31 +0200
Subject: [PATCH 014/113] fix bug with -a3 -O
---
OpenCL/m04710_a3-optimized.cl | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/OpenCL/m04710_a3-optimized.cl b/OpenCL/m04710_a3-optimized.cl
index cdc215c06..4651c8d43 100644
--- a/OpenCL/m04710_a3-optimized.cl
+++ b/OpenCL/m04710_a3-optimized.cl
@@ -604,7 +604,7 @@ KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
w3[0] = 0;
w3[1] = 0;
- w3[2] = pws[gid].i[14];
+ w3[2] = pws[gid].i[15];
w3[3] = 0;
const u32 pw_len = pws[gid].pw_len & 63;
@@ -674,7 +674,7 @@ KERNEL_FQ void m04710_m08 (KERN_ATTR_BASIC ())
w3[0] = 0;
w3[1] = 0;
- w3[2] = pws[gid].i[14];
+ w3[2] = pws[gid].i[15];
w3[3] = 0;
const u32 pw_len = pws[gid].pw_len & 63;
@@ -814,7 +814,7 @@ KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
w3[0] = 0;
w3[1] = 0;
- w3[2] = pws[gid].i[14];
+ w3[2] = pws[gid].i[15];
w3[3] = 0;
const u32 pw_len = pws[gid].pw_len & 63;
@@ -884,7 +884,7 @@ KERNEL_FQ void m04710_s08 (KERN_ATTR_BASIC ())
w3[0] = 0;
w3[1] = 0;
- w3[2] = pws[gid].i[14];
+ w3[2] = pws[gid].i[15];
w3[3] = 0;
const u32 pw_len = pws[gid].pw_len & 63;
From 10f243aa2071c60a028f2ab9678f81b8f793c0ee Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 13 Jul 2019 16:36:25 +0200
Subject: [PATCH 015/113] add test module, update credits.txt
---
docs/credits.txt | 1 +
tools/test_modules/m04710.pm | 43 ++++++++++++++++++++++++++++++++++++
2 files changed, 44 insertions(+)
create mode 100644 tools/test_modules/m04710.pm
diff --git a/docs/credits.txt b/docs/credits.txt
index bd21d35d7..c89524dab 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,6 +18,7 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
+* sha256(md5(pass)) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
diff --git a/tools/test_modules/m04710.pm b/tools/test_modules/m04710.pm
new file mode 100644
index 000000000..2b9a8a702
--- /dev/null
+++ b/tools/test_modules/m04710.pm
@@ -0,0 +1,43 @@
+#!/usr/bin/env perl
+
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use Digest::MD5 qw (md5_hex);
+use Digest::SHA qw (sha256_hex);
+
+sub module_constraints { [[0, 256], [-1, -1], [0, 55], [-1, -1], [-1, -1]] }
+
+sub module_generate_hash
+{
+ my $word = shift;
+
+ my $digest = sha256_hex (md5_hex ($word));
+
+ my $hash = sprintf ("%s", $digest);
+
+ return $hash;
+}
+
+sub module_verify_hash
+{
+ my $line = shift;
+
+ my ($hash, $word) = split (':', $line);
+
+ return unless defined $hash;
+ return unless defined $word;
+
+ my $word_packed = pack_if_HEX_notation ($word);
+
+ my $new_hash = module_generate_hash ($word_packed);
+
+ return ($new_hash, $word);
+}
+
+1;
From 1aef49d11be7afa7ee1c0d78a5091801e94e6463 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 13 Jul 2019 20:51:38 +0200
Subject: [PATCH 016/113] update readme/changes txt
---
docs/changes.txt | 1 +
docs/readme.txt | 1 +
2 files changed, 2 insertions(+)
diff --git a/docs/changes.txt b/docs/changes.txt
index 0bb228187..7062e62af 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,6 +35,7 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
+- Added hash-mode: sha256(md5($pass))
##
## Bugs
diff --git a/docs/readme.txt b/docs/readme.txt
index 9e36b73ce..91b35c4c8 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -88,6 +88,7 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- sha256($salt.$pass)
- sha256(utf16le($pass).$salt)
- sha256($salt.utf16le($pass))
+- sha256(md5($pass))
- sha512($pass.$salt)
- sha512($salt.$pass)
- sha512(utf16le($pass).$salt)
From 903722c415337bcb83ab6f57dbbe6a7292f617b8 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Mon, 15 Jul 2019 15:16:24 +0200
Subject: [PATCH 017/113] update lzma-sdk from 18.05 to 19.00
---
deps/LZMA-SDK/C/7zArcIn.c | 8 +-
deps/LZMA-SDK/C/7zDec.c | 12 +-
deps/LZMA-SDK/C/7zTypes.h | 5 +-
deps/LZMA-SDK/C/7zVersion.h | 8 +-
deps/LZMA-SDK/C/Bcj2Enc.c | 8 +-
deps/LZMA-SDK/C/CpuArch.c | 28 +-
deps/LZMA-SDK/C/CpuArch.h | 9 +-
deps/LZMA-SDK/C/DllSecur.c | 25 +-
deps/LZMA-SDK/C/DllSecur.h | 3 +-
deps/LZMA-SDK/C/LzFind.c | 164 +++--
deps/LZMA-SDK/C/LzFindMt.c | 117 ++--
deps/LZMA-SDK/C/LzFindMt.h | 14 +-
deps/LZMA-SDK/C/Lzma2Dec.c | 26 +-
deps/LZMA-SDK/C/Lzma2DecMt.c | 32 +-
deps/LZMA-SDK/C/Lzma2Enc.c | 8 +-
deps/LZMA-SDK/C/Lzma86Enc.c | 8 +-
deps/LZMA-SDK/C/LzmaDec.c | 32 +-
deps/LZMA-SDK/C/LzmaEnc.c | 739 ++++++++++++++---------
deps/LZMA-SDK/C/MtCoder.c | 8 +-
deps/LZMA-SDK/C/MtCoder.h | 6 +-
deps/LZMA-SDK/C/MtDec.c | 29 +-
deps/LZMA-SDK/C/MtDec.h | 24 +-
deps/LZMA-SDK/C/Ppmd7.c | 6 +-
deps/LZMA-SDK/C/Ppmd7.h | 6 +-
deps/LZMA-SDK/C/Ppmd7Dec.c | 4 +-
deps/LZMA-SDK/C/Util/7z/7zMain.c | 14 +-
deps/LZMA-SDK/C/Util/Lzma/LzmaUtil.c | 4 +-
deps/LZMA-SDK/C/Util/SfxSetup/SfxSetup.c | 16 +-
deps/LZMA-SDK/C/Xz.h | 20 +-
deps/LZMA-SDK/C/XzDec.c | 89 ++-
deps/LZMA-SDK/C/XzEnc.c | 8 +-
deps/LZMA-SDK/C/XzIn.c | 4 +-
32 files changed, 900 insertions(+), 584 deletions(-)
diff --git a/deps/LZMA-SDK/C/7zArcIn.c b/deps/LZMA-SDK/C/7zArcIn.c
index 70d7175e3..68cc12ff4 100644
--- a/deps/LZMA-SDK/C/7zArcIn.c
+++ b/deps/LZMA-SDK/C/7zArcIn.c
@@ -1,5 +1,5 @@
/* 7zArcIn.c -- 7z Input functions
-2017-04-03 : Igor Pavlov : Public domain */
+2018-12-31 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -19,7 +19,7 @@
{ MY_ALLOC(Byte, to, size, alloc); memcpy(to, from, size); }
#define MY_ALLOC_ZE_AND_CPY(to, size, from, alloc) \
- { if ((size) == 0) p = NULL; else { MY_ALLOC_AND_CPY(to, size, from, alloc) } }
+ { if ((size) == 0) to = NULL; else { MY_ALLOC_AND_CPY(to, size, from, alloc) } }
#define k7zMajorVersion 0
@@ -666,7 +666,7 @@ static SRes ReadUnpackInfo(CSzAr *p,
MY_ALLOC(size_t, p->FoCodersOffsets, (size_t)numFolders + 1, alloc);
MY_ALLOC(UInt32, p->FoStartPackStreamIndex, (size_t)numFolders + 1, alloc);
MY_ALLOC(UInt32, p->FoToCoderUnpackSizes, (size_t)numFolders + 1, alloc);
- MY_ALLOC(Byte, p->FoToMainUnpackSizeIndex, (size_t)numFolders, alloc);
+ MY_ALLOC_ZE(Byte, p->FoToMainUnpackSizeIndex, (size_t)numFolders, alloc);
startBufPtr = sd.Data;
@@ -1744,7 +1744,7 @@ size_t SzArEx_GetFullNameLen(const CSzArEx *p, size_t fileIndex)
UInt16 *SzArEx_GetFullNameUtf16_Back(const CSzArEx *p, size_t fileIndex, UInt16 *dest)
{
- Bool needSlash;
+ BoolInt needSlash;
if (!p->FileNameOffsets)
{
*(--dest) = 0;
diff --git a/deps/LZMA-SDK/C/7zDec.c b/deps/LZMA-SDK/C/7zDec.c
index 9c986950c..2a7b09030 100644
--- a/deps/LZMA-SDK/C/7zDec.c
+++ b/deps/LZMA-SDK/C/7zDec.c
@@ -1,5 +1,5 @@
/* 7zDec.c -- Decoding from 7z folder
-2017-04-03 : Igor Pavlov : Public domain */
+2019-02-02 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -44,7 +44,7 @@ typedef struct
const Byte *end;
const Byte *begin;
UInt64 processed;
- Bool extra;
+ BoolInt extra;
SRes res;
const ILookInStream *inStream;
} CByteInToLook;
@@ -156,7 +156,7 @@ static SRes SzDecodeLzma(const Byte *props, unsigned propsSize, UInt64 inSize, I
{
SizeT inProcessed = (SizeT)lookahead, dicPos = state.dicPos;
ELzmaStatus status;
- res = LzmaDec_DecodeToDic(&state, outSize, inBuf, &inProcessed, LZMA_FINISH_END, &status);
+ res = LzmaDec_DecodeToDic(&state, outSize, (const Byte *)inBuf, &inProcessed, LZMA_FINISH_END, &status);
lookahead -= inProcessed;
inSize -= inProcessed;
if (res != SZ_OK)
@@ -218,7 +218,7 @@ static SRes SzDecodeLzma2(const Byte *props, unsigned propsSize, UInt64 inSize,
{
SizeT inProcessed = (SizeT)lookahead, dicPos = state.decoder.dicPos;
ELzmaStatus status;
- res = Lzma2Dec_DecodeToDic(&state, outSize, inBuf, &inProcessed, LZMA_FINISH_END, &status);
+ res = Lzma2Dec_DecodeToDic(&state, outSize, (const Byte *)inBuf, &inProcessed, LZMA_FINISH_END, &status);
lookahead -= inProcessed;
inSize -= inProcessed;
if (res != SZ_OK)
@@ -269,7 +269,7 @@ static SRes SzDecodeCopy(UInt64 inSize, ILookInStream *inStream, Byte *outBuffer
return SZ_OK;
}
-static Bool IS_MAIN_METHOD(UInt32 m)
+static BoolInt IS_MAIN_METHOD(UInt32 m)
{
switch (m)
{
@@ -286,7 +286,7 @@ static Bool IS_MAIN_METHOD(UInt32 m)
return False;
}
-static Bool IS_SUPPORTED_CODER(const CSzCoderInfo *c)
+static BoolInt IS_SUPPORTED_CODER(const CSzCoderInfo *c)
{
return
c->NumStreams == 1
diff --git a/deps/LZMA-SDK/C/7zTypes.h b/deps/LZMA-SDK/C/7zTypes.h
index 4977cdaa6..593f5aa25 100644
--- a/deps/LZMA-SDK/C/7zTypes.h
+++ b/deps/LZMA-SDK/C/7zTypes.h
@@ -1,5 +1,5 @@
/* 7zTypes.h -- Basic types
-2017-07-17 : Igor Pavlov : Public domain */
+2018-08-04 : Igor Pavlov : Public domain */
#ifndef __7Z_TYPES_H
#define __7Z_TYPES_H
@@ -103,7 +103,8 @@ typedef UInt32 SizeT;
typedef size_t SizeT;
#endif
-typedef int Bool;
+typedef int BoolInt;
+/* typedef BoolInt Bool; */
#define True 1
#define False 0
diff --git a/deps/LZMA-SDK/C/7zVersion.h b/deps/LZMA-SDK/C/7zVersion.h
index ed3aa9427..0074c64be 100644
--- a/deps/LZMA-SDK/C/7zVersion.h
+++ b/deps/LZMA-SDK/C/7zVersion.h
@@ -1,7 +1,7 @@
-#define MY_VER_MAJOR 18
-#define MY_VER_MINOR 05
+#define MY_VER_MAJOR 19
+#define MY_VER_MINOR 00
#define MY_VER_BUILD 0
-#define MY_VERSION_NUMBERS "18.05"
+#define MY_VERSION_NUMBERS "19.00"
#define MY_VERSION MY_VERSION_NUMBERS
#ifdef MY_CPU_NAME
@@ -10,7 +10,7 @@
#define MY_VERSION_CPU MY_VERSION
#endif
-#define MY_DATE "2018-04-30"
+#define MY_DATE "2019-02-21"
#undef MY_COPYRIGHT
#undef MY_VERSION_COPYRIGHT_DATE
#define MY_AUTHOR_NAME "Igor Pavlov"
diff --git a/deps/LZMA-SDK/C/Bcj2Enc.c b/deps/LZMA-SDK/C/Bcj2Enc.c
index b0bc7593d..7a02ecde2 100644
--- a/deps/LZMA-SDK/C/Bcj2Enc.c
+++ b/deps/LZMA-SDK/C/Bcj2Enc.c
@@ -1,5 +1,5 @@
/* Bcj2Enc.c -- BCJ2 Encoder (Converter for x86 code)
-2017-04-28 : Igor Pavlov : Public domain */
+2019-02-02 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -52,7 +52,7 @@ void Bcj2Enc_Init(CBcj2Enc *p)
p->probs[i] = kBitModelTotal >> 1;
}
-static Bool MY_FAST_CALL RangeEnc_ShiftLow(CBcj2Enc *p)
+static BoolInt MY_FAST_CALL RangeEnc_ShiftLow(CBcj2Enc *p)
{
if ((UInt32)p->low < (UInt32)0xFF000000 || (UInt32)(p->low >> 32) != 0)
{
@@ -165,7 +165,7 @@ static void Bcj2Enc_Encode_2(CBcj2Enc *p)
{
Byte context = (Byte)(num == 0 ? p->prevByte : src[-1]);
- Bool needConvert;
+ BoolInt needConvert;
p->bufs[BCJ2_STREAM_MAIN] = dest + 1;
p->ip += (UInt32)num + 1;
@@ -253,7 +253,7 @@ void Bcj2Enc_Encode(CBcj2Enc *p)
{
const Byte *src = p->src;
const Byte *srcLim = p->srcLim;
- unsigned finishMode = p->finishMode;
+ EBcj2Enc_FinishMode finishMode = p->finishMode;
p->src = p->temp;
p->srcLim = p->temp + p->tempPos;
diff --git a/deps/LZMA-SDK/C/CpuArch.c b/deps/LZMA-SDK/C/CpuArch.c
index f835c2b7b..ff1890e7f 100644
--- a/deps/LZMA-SDK/C/CpuArch.c
+++ b/deps/LZMA-SDK/C/CpuArch.c
@@ -1,5 +1,5 @@
/* CpuArch.c -- CPU specific code
-2016-02-25: Igor Pavlov : Public domain */
+2018-02-18: Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -115,7 +115,7 @@ void MyCPUID(UInt32 function, UInt32 *a, UInt32 *b, UInt32 *c, UInt32 *d)
#endif
}
-Bool x86cpuid_CheckAndRead(Cx86cpuid *p)
+BoolInt x86cpuid_CheckAndRead(Cx86cpuid *p)
{
CHECK_CPUID_IS_SUPPORTED
MyCPUID(0, &p->maxFunc, &p->vendor[0], &p->vendor[2], &p->vendor[1]);
@@ -144,7 +144,7 @@ int x86cpuid_GetFirm(const Cx86cpuid *p)
return -1;
}
-Bool CPU_Is_InOrder()
+BoolInt CPU_Is_InOrder()
{
Cx86cpuid p;
int firm;
@@ -175,7 +175,7 @@ Bool CPU_Is_InOrder()
#if !defined(MY_CPU_AMD64) && defined(_WIN32)
#include <windows.h>
-static Bool CPU_Sys_Is_SSE_Supported()
+static BoolInt CPU_Sys_Is_SSE_Supported()
{
OSVERSIONINFO vi;
vi.dwOSVersionInfoSize = sizeof(vi);
@@ -188,7 +188,7 @@ static Bool CPU_Sys_Is_SSE_Supported()
#define CHECK_SYS_SSE_SUPPORT
#endif
-Bool CPU_Is_Aes_Supported()
+BoolInt CPU_Is_Aes_Supported()
{
Cx86cpuid p;
CHECK_SYS_SSE_SUPPORT
@@ -197,4 +197,22 @@ Bool CPU_Is_Aes_Supported()
return (p.c >> 25) & 1;
}
+BoolInt CPU_IsSupported_PageGB()
+{
+ Cx86cpuid cpuid;
+ if (!x86cpuid_CheckAndRead(&cpuid))
+ return False;
+ {
+ UInt32 d[4] = { 0 };
+ MyCPUID(0x80000000, &d[0], &d[1], &d[2], &d[3]);
+ if (d[0] < 0x80000001)
+ return False;
+ }
+ {
+ UInt32 d[4] = { 0 };
+ MyCPUID(0x80000001, &d[0], &d[1], &d[2], &d[3]);
+ return (d[3] >> 26) & 1;
+ }
+}
+
#endif
diff --git a/deps/LZMA-SDK/C/CpuArch.h b/deps/LZMA-SDK/C/CpuArch.h
index 7fb27282c..5f74c1c0c 100644
--- a/deps/LZMA-SDK/C/CpuArch.h
+++ b/deps/LZMA-SDK/C/CpuArch.h
@@ -1,5 +1,5 @@
/* CpuArch.h -- CPU specific code
-2017-09-04 : Igor Pavlov : Public domain */
+2018-02-18 : Igor Pavlov : Public domain */
#ifndef __CPU_ARCH_H
#define __CPU_ARCH_H
@@ -318,15 +318,16 @@ enum
void MyCPUID(UInt32 function, UInt32 *a, UInt32 *b, UInt32 *c, UInt32 *d);
-Bool x86cpuid_CheckAndRead(Cx86cpuid *p);
+BoolInt x86cpuid_CheckAndRead(Cx86cpuid *p);
int x86cpuid_GetFirm(const Cx86cpuid *p);
#define x86cpuid_GetFamily(ver) (((ver >> 16) & 0xFF0) | ((ver >> 8) & 0xF))
#define x86cpuid_GetModel(ver) (((ver >> 12) & 0xF0) | ((ver >> 4) & 0xF))
#define x86cpuid_GetStepping(ver) (ver & 0xF)
-Bool CPU_Is_InOrder();
-Bool CPU_Is_Aes_Supported();
+BoolInt CPU_Is_InOrder();
+BoolInt CPU_Is_Aes_Supported();
+BoolInt CPU_IsSupported_PageGB();
#endif
diff --git a/deps/LZMA-SDK/C/DllSecur.c b/deps/LZMA-SDK/C/DllSecur.c
index 8745421ac..19a22a9f0 100644
--- a/deps/LZMA-SDK/C/DllSecur.c
+++ b/deps/LZMA-SDK/C/DllSecur.c
@@ -1,5 +1,5 @@
/* DllSecur.c -- DLL loading security
-2016-10-04 : Igor Pavlov : Public domain */
+2018-02-21 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -28,10 +28,31 @@ static const char * const g_Dlls =
"CRYPTBASE\0"
"OLEACC\0"
"CLBCATQ\0"
+ "VERSION\0"
;
#endif
+void My_SetDefaultDllDirectories()
+{
+ #ifndef UNDER_CE
+
+ OSVERSIONINFO vi;
+ vi.dwOSVersionInfoSize = sizeof(vi);
+ GetVersionEx(&vi);
+ if (!GetVersionEx(&vi) || vi.dwMajorVersion != 6 || vi.dwMinorVersion != 0)
+ {
+ Func_SetDefaultDllDirectories setDllDirs = (Func_SetDefaultDllDirectories)
+ GetProcAddress(GetModuleHandle(TEXT("kernel32.dll")), "SetDefaultDllDirectories");
+ if (setDllDirs)
+ if (setDllDirs(MY_LOAD_LIBRARY_SEARCH_SYSTEM32 | MY_LOAD_LIBRARY_SEARCH_USER_DIRS))
+ return;
+ }
+
+ #endif
+}
+
+
void LoadSecurityDlls()
{
#ifndef UNDER_CE
@@ -70,7 +91,7 @@ void LoadSecurityDlls()
for (;;)
{
char c = *dll++;
- buf[pos + k] = c;
+ buf[pos + k] = (Byte)c;
k++;
if (c == 0)
break;
diff --git a/deps/LZMA-SDK/C/DllSecur.h b/deps/LZMA-SDK/C/DllSecur.h
index 023c50960..4c113568e 100644
--- a/deps/LZMA-SDK/C/DllSecur.h
+++ b/deps/LZMA-SDK/C/DllSecur.h
@@ -1,5 +1,5 @@
/* DllSecur.h -- DLL loading for security
-2016-06-08 : Igor Pavlov : Public domain */
+2018-02-19 : Igor Pavlov : Public domain */
#ifndef __DLL_SECUR_H
#define __DLL_SECUR_H
@@ -10,6 +10,7 @@ EXTERN_C_BEGIN
#ifdef _WIN32
+void My_SetDefaultDllDirectories();
void LoadSecurityDlls();
#endif
diff --git a/deps/LZMA-SDK/C/LzFind.c b/deps/LZMA-SDK/C/LzFind.c
index 6ea82a9b5..4eefc17dd 100644
--- a/deps/LZMA-SDK/C/LzFind.c
+++ b/deps/LZMA-SDK/C/LzFind.c
@@ -1,5 +1,5 @@
/* LzFind.c -- Match finder for LZ algorithms
-2017-06-10 : Igor Pavlov : Public domain */
+2018-07-08 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -138,7 +138,7 @@ static void MatchFinder_SetDefaultSettings(CMatchFinder *p)
void MatchFinder_Construct(CMatchFinder *p)
{
- UInt32 i;
+ unsigned i;
p->bufferBase = NULL;
p->directInput = 0;
p->hash = NULL;
@@ -147,7 +147,7 @@ void MatchFinder_Construct(CMatchFinder *p)
for (i = 0; i < 256; i++)
{
- UInt32 r = i;
+ UInt32 r = (UInt32)i;
unsigned j;
for (j = 0; j < 8; j++)
r = (r >> 1) ^ (kCrcPoly & ((UInt32)0 - (r & 1)));
@@ -368,6 +368,8 @@ static void MatchFinder_Normalize(CMatchFinder *p)
MatchFinder_ReduceOffsets(p, subValue);
}
+
+MY_NO_INLINE
static void MatchFinder_CheckLimits(CMatchFinder *p)
{
if (p->pos == kMaxValForNormalize)
@@ -379,10 +381,16 @@ static void MatchFinder_CheckLimits(CMatchFinder *p)
MatchFinder_SetLimits(p);
}
-static UInt32 * Hc_GetMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byte *cur, CLzRef *son,
+
+/*
+ (lenLimit > maxLen)
+*/
+MY_FORCE_INLINE
+static UInt32 * Hc_GetMatchesSpec(unsigned lenLimit, UInt32 curMatch, UInt32 pos, const Byte *cur, CLzRef *son,
UInt32 _cyclicBufferPos, UInt32 _cyclicBufferSize, UInt32 cutValue,
- UInt32 *distances, UInt32 maxLen)
+ UInt32 *distances, unsigned maxLen)
{
+ /*
son[_cyclicBufferPos] = curMatch;
for (;;)
{
@@ -400,7 +408,8 @@ static UInt32 * Hc_GetMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos,
break;
if (maxLen < len)
{
- *distances++ = maxLen = len;
+ maxLen = len;
+ *distances++ = len;
*distances++ = delta - 1;
if (len == lenLimit)
return distances;
@@ -408,15 +417,58 @@ static UInt32 * Hc_GetMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos,
}
}
}
+ */
+
+ const Byte *lim = cur + lenLimit;
+ son[_cyclicBufferPos] = curMatch;
+ do
+ {
+ UInt32 delta = pos - curMatch;
+ if (delta >= _cyclicBufferSize)
+ break;
+ {
+ ptrdiff_t diff;
+ curMatch = son[_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)];
+ diff = (ptrdiff_t)0 - delta;
+ if (cur[maxLen] == cur[maxLen + diff])
+ {
+ const Byte *c = cur;
+ while (*c == c[diff])
+ {
+ if (++c == lim)
+ {
+ distances[0] = (UInt32)(lim - cur);
+ distances[1] = delta - 1;
+ return distances + 2;
+ }
+ }
+ {
+ unsigned len = (unsigned)(c - cur);
+ if (maxLen < len)
+ {
+ maxLen = len;
+ distances[0] = (UInt32)len;
+ distances[1] = delta - 1;
+ distances += 2;
+ }
+ }
+ }
+ }
+ }
+ while (--cutValue);
+
+ return distances;
}
+
+MY_FORCE_INLINE
UInt32 * GetMatchesSpec1(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byte *cur, CLzRef *son,
UInt32 _cyclicBufferPos, UInt32 _cyclicBufferSize, UInt32 cutValue,
UInt32 *distances, UInt32 maxLen)
{
- CLzRef *ptr0 = son + (_cyclicBufferPos << 1) + 1;
- CLzRef *ptr1 = son + (_cyclicBufferPos << 1);
- UInt32 len0 = 0, len1 = 0;
+ CLzRef *ptr0 = son + ((size_t)_cyclicBufferPos << 1) + 1;
+ CLzRef *ptr1 = son + ((size_t)_cyclicBufferPos << 1);
+ unsigned len0 = 0, len1 = 0;
for (;;)
{
UInt32 delta = pos - curMatch;
@@ -426,9 +478,10 @@ UInt32 * GetMatchesSpec1(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byt
return distances;
}
{
- CLzRef *pair = son + ((_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)) << 1);
+ CLzRef *pair = son + ((size_t)(_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)) << 1);
const Byte *pb = cur - delta;
- UInt32 len = (len0 < len1 ? len0 : len1);
+ unsigned len = (len0 < len1 ? len0 : len1);
+ UInt32 pair0 = pair[0];
if (pb[len] == cur[len])
{
if (++len != lenLimit && pb[len] == cur[len])
@@ -437,11 +490,12 @@ UInt32 * GetMatchesSpec1(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byt
break;
if (maxLen < len)
{
- *distances++ = maxLen = len;
+ maxLen = (UInt32)len;
+ *distances++ = (UInt32)len;
*distances++ = delta - 1;
if (len == lenLimit)
{
- *ptr1 = pair[0];
+ *ptr1 = pair0;
*ptr0 = pair[1];
return distances;
}
@@ -468,9 +522,9 @@ UInt32 * GetMatchesSpec1(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byt
static void SkipMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byte *cur, CLzRef *son,
UInt32 _cyclicBufferPos, UInt32 _cyclicBufferSize, UInt32 cutValue)
{
- CLzRef *ptr0 = son + (_cyclicBufferPos << 1) + 1;
- CLzRef *ptr1 = son + (_cyclicBufferPos << 1);
- UInt32 len0 = 0, len1 = 0;
+ CLzRef *ptr0 = son + ((size_t)_cyclicBufferPos << 1) + 1;
+ CLzRef *ptr1 = son + ((size_t)_cyclicBufferPos << 1);
+ unsigned len0 = 0, len1 = 0;
for (;;)
{
UInt32 delta = pos - curMatch;
@@ -480,9 +534,9 @@ static void SkipMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const
return;
}
{
- CLzRef *pair = son + ((_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)) << 1);
+ CLzRef *pair = son + ((size_t)(_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)) << 1);
const Byte *pb = cur - delta;
- UInt32 len = (len0 < len1 ? len0 : len1);
+ unsigned len = (len0 < len1 ? len0 : len1);
if (pb[len] == cur[len])
{
while (++len != lenLimit)
@@ -520,13 +574,13 @@ static void SkipMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const
p->buffer++; \
if (++p->pos == p->posLimit) MatchFinder_CheckLimits(p);
-#define MOVE_POS_RET MOVE_POS return offset;
+#define MOVE_POS_RET MOVE_POS return (UInt32)offset;
static void MatchFinder_MovePos(CMatchFinder *p) { MOVE_POS; }
#define GET_MATCHES_HEADER2(minLen, ret_op) \
- UInt32 lenLimit; UInt32 hv; const Byte *cur; UInt32 curMatch; \
- lenLimit = p->lenLimit; { if (lenLimit < minLen) { MatchFinder_MovePos(p); ret_op; }} \
+ unsigned lenLimit; UInt32 hv; const Byte *cur; UInt32 curMatch; \
+ lenLimit = (unsigned)p->lenLimit; { if (lenLimit < minLen) { MatchFinder_MovePos(p); ret_op; }} \
cur = p->buffer;
#define GET_MATCHES_HEADER(minLen) GET_MATCHES_HEADER2(minLen, return 0)
@@ -535,22 +589,22 @@ static void MatchFinder_MovePos(CMatchFinder *p) { MOVE_POS; }
#define MF_PARAMS(p) p->pos, p->buffer, p->son, p->cyclicBufferPos, p->cyclicBufferSize, p->cutValue
#define GET_MATCHES_FOOTER(offset, maxLen) \
- offset = (UInt32)(GetMatchesSpec1(lenLimit, curMatch, MF_PARAMS(p), \
- distances + offset, maxLen) - distances); MOVE_POS_RET;
+ offset = (unsigned)(GetMatchesSpec1((UInt32)lenLimit, curMatch, MF_PARAMS(p), \
+ distances + offset, (UInt32)maxLen) - distances); MOVE_POS_RET;
#define SKIP_FOOTER \
- SkipMatchesSpec(lenLimit, curMatch, MF_PARAMS(p)); MOVE_POS;
+ SkipMatchesSpec((UInt32)lenLimit, curMatch, MF_PARAMS(p)); MOVE_POS;
#define UPDATE_maxLen { \
ptrdiff_t diff = (ptrdiff_t)0 - d2; \
const Byte *c = cur + maxLen; \
const Byte *lim = cur + lenLimit; \
for (; c != lim; c++) if (*(c + diff) != *c) break; \
- maxLen = (UInt32)(c - cur); }
+ maxLen = (unsigned)(c - cur); }
static UInt32 Bt2_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
{
- UInt32 offset;
+ unsigned offset;
GET_MATCHES_HEADER(2)
HASH2_CALC;
curMatch = p->hash[hv];
@@ -561,7 +615,7 @@ static UInt32 Bt2_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
UInt32 Bt3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
{
- UInt32 offset;
+ unsigned offset;
GET_MATCHES_HEADER(3)
HASH_ZIP_CALC;
curMatch = p->hash[hv];
@@ -572,7 +626,8 @@ UInt32 Bt3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
static UInt32 Bt3_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
{
- UInt32 h2, d2, maxLen, offset, pos;
+ UInt32 h2, d2, pos;
+ unsigned maxLen, offset;
UInt32 *hash;
GET_MATCHES_HEADER(3)
@@ -594,12 +649,12 @@ static UInt32 Bt3_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
if (d2 < p->cyclicBufferSize && *(cur - d2) == *cur)
{
UPDATE_maxLen
- distances[0] = maxLen;
+ distances[0] = (UInt32)maxLen;
distances[1] = d2 - 1;
offset = 2;
if (maxLen == lenLimit)
{
- SkipMatchesSpec(lenLimit, curMatch, MF_PARAMS(p));
+ SkipMatchesSpec((UInt32)lenLimit, curMatch, MF_PARAMS(p));
MOVE_POS_RET;
}
}
@@ -609,7 +664,8 @@ static UInt32 Bt3_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
static UInt32 Bt4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
{
- UInt32 h2, h3, d2, d3, maxLen, offset, pos;
+ UInt32 h2, h3, d2, d3, pos;
+ unsigned maxLen, offset;
UInt32 *hash;
GET_MATCHES_HEADER(4)
@@ -618,12 +674,12 @@ static UInt32 Bt4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
hash = p->hash;
pos = p->pos;
- d2 = pos - hash[ h2];
+ d2 = pos - hash [h2];
d3 = pos - (hash + kFix3HashSize)[h3];
curMatch = (hash + kFix4HashSize)[hv];
- hash[ h2] = pos;
+ hash [h2] = pos;
(hash + kFix3HashSize)[h3] = pos;
(hash + kFix4HashSize)[hv] = pos;
@@ -632,7 +688,8 @@ static UInt32 Bt4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
if (d2 < p->cyclicBufferSize && *(cur - d2) == *cur)
{
- distances[0] = maxLen = 2;
+ maxLen = 2;
+ distances[0] = 2;
distances[1] = d2 - 1;
offset = 2;
}
@@ -648,10 +705,10 @@ static UInt32 Bt4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
if (offset != 0)
{
UPDATE_maxLen
- distances[(size_t)offset - 2] = maxLen;
+ distances[(size_t)offset - 2] = (UInt32)maxLen;
if (maxLen == lenLimit)
{
- SkipMatchesSpec(lenLimit, curMatch, MF_PARAMS(p));
+ SkipMatchesSpec((UInt32)lenLimit, curMatch, MF_PARAMS(p));
MOVE_POS_RET;
}
}
@@ -674,13 +731,13 @@ static UInt32 Bt5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
hash = p->hash;
pos = p->pos;
- d2 = pos - hash[ h2];
+ d2 = pos - hash [h2];
d3 = pos - (hash + kFix3HashSize)[h3];
d4 = pos - (hash + kFix4HashSize)[h4];
curMatch = (hash + kFix5HashSize)[hv];
- hash[ h2] = pos;
+ hash [h2] = pos;
(hash + kFix3HashSize)[h3] = pos;
(hash + kFix4HashSize)[h4] = pos;
(hash + kFix5HashSize)[hv] = pos;
@@ -741,7 +798,8 @@ static UInt32 Bt5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
static UInt32 Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
{
- UInt32 h2, h3, d2, d3, maxLen, offset, pos;
+ UInt32 h2, h3, d2, d3, pos;
+ unsigned maxLen, offset;
UInt32 *hash;
GET_MATCHES_HEADER(4)
@@ -750,12 +808,11 @@ static UInt32 Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
hash = p->hash;
pos = p->pos;
- d2 = pos - hash[ h2];
+ d2 = pos - hash [h2];
d3 = pos - (hash + kFix3HashSize)[h3];
-
curMatch = (hash + kFix4HashSize)[hv];
- hash[ h2] = pos;
+ hash [h2] = pos;
(hash + kFix3HashSize)[h3] = pos;
(hash + kFix4HashSize)[hv] = pos;
@@ -764,7 +821,8 @@ static UInt32 Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
if (d2 < p->cyclicBufferSize && *(cur - d2) == *cur)
{
- distances[0] = maxLen = 2;
+ maxLen = 2;
+ distances[0] = 2;
distances[1] = d2 - 1;
offset = 2;
}
@@ -780,7 +838,7 @@ static UInt32 Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
if (offset != 0)
{
UPDATE_maxLen
- distances[(size_t)offset - 2] = maxLen;
+ distances[(size_t)offset - 2] = (UInt32)maxLen;
if (maxLen == lenLimit)
{
p->son[p->cyclicBufferPos] = curMatch;
@@ -791,7 +849,7 @@ static UInt32 Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
if (maxLen < 3)
maxLen = 3;
- offset = (UInt32)(Hc_GetMatchesSpec(lenLimit, curMatch, MF_PARAMS(p),
+ offset = (unsigned)(Hc_GetMatchesSpec(lenLimit, curMatch, MF_PARAMS(p),
distances + offset, maxLen) - (distances));
MOVE_POS_RET
}
@@ -808,13 +866,13 @@ static UInt32 Hc5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
hash = p->hash;
pos = p->pos;
- d2 = pos - hash[ h2];
+ d2 = pos - hash [h2];
d3 = pos - (hash + kFix3HashSize)[h3];
d4 = pos - (hash + kFix4HashSize)[h4];
curMatch = (hash + kFix5HashSize)[hv];
- hash[ h2] = pos;
+ hash [h2] = pos;
(hash + kFix3HashSize)[h3] = pos;
(hash + kFix4HashSize)[h4] = pos;
(hash + kFix5HashSize)[hv] = pos;
@@ -877,12 +935,12 @@ static UInt32 Hc5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
UInt32 Hc3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances)
{
- UInt32 offset;
+ unsigned offset;
GET_MATCHES_HEADER(3)
HASH_ZIP_CALC;
curMatch = p->hash[hv];
p->hash[hv] = p->pos;
- offset = (UInt32)(Hc_GetMatchesSpec(lenLimit, curMatch, MF_PARAMS(p),
+ offset = (unsigned)(Hc_GetMatchesSpec(lenLimit, curMatch, MF_PARAMS(p),
distances, 2) - (distances));
MOVE_POS_RET
}
@@ -940,7 +998,7 @@ static void Bt4_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
HASH4_CALC;
hash = p->hash;
curMatch = (hash + kFix4HashSize)[hv];
- hash[ h2] =
+ hash [h2] =
(hash + kFix3HashSize)[h3] =
(hash + kFix4HashSize)[hv] = p->pos;
SKIP_FOOTER
@@ -959,7 +1017,7 @@ static void Bt5_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
HASH5_CALC;
hash = p->hash;
curMatch = (hash + kFix5HashSize)[hv];
- hash[ h2] =
+ hash [h2] =
(hash + kFix3HashSize)[h3] =
(hash + kFix4HashSize)[h4] =
(hash + kFix5HashSize)[hv] = p->pos;
@@ -979,7 +1037,7 @@ static void Hc4_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
HASH4_CALC;
hash = p->hash;
curMatch = (hash + kFix4HashSize)[hv];
- hash[ h2] =
+ hash [h2] =
(hash + kFix3HashSize)[h3] =
(hash + kFix4HashSize)[hv] = p->pos;
p->son[p->cyclicBufferPos] = curMatch;
@@ -999,7 +1057,7 @@ static void Hc5_MatchFinder_Skip(CMatchFinder *p, UInt32 num)
HASH5_CALC;
hash = p->hash;
curMatch = hash + kFix5HashSize)[hv];
- hash[ h2] =
+ hash [h2] =
(hash + kFix3HashSize)[h3] =
(hash + kFix4HashSize)[h4] =
(hash + kFix5HashSize)[hv] = p->pos;
diff --git a/deps/LZMA-SDK/C/LzFindMt.c b/deps/LZMA-SDK/C/LzFindMt.c
index 2563824fc..df32146f9 100644
--- a/deps/LZMA-SDK/C/LzFindMt.c
+++ b/deps/LZMA-SDK/C/LzFindMt.c
@@ -1,5 +1,5 @@
/* LzFindMt.c -- multithreaded Match finder for LZ algorithms
-2017-06-10 : Igor Pavlov : Public domain */
+2018-12-29 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -232,38 +232,57 @@ static void MatchFinderMt_GetNextBlock_Hash(CMatchFinderMt *p)
#define kEmptyHashValue 0
-/* #define MFMT_GM_INLINE */
+#define MFMT_GM_INLINE
#ifdef MFMT_GM_INLINE
-#define NO_INLINE MY_FAST_CALL
+/*
+ we use size_t for _cyclicBufferPos instead of UInt32
+ to eliminate "movsx" BUG in old MSVC x64 compiler.
+*/
-static Int32 NO_INLINE GetMatchesSpecN(UInt32 lenLimit, UInt32 pos, const Byte *cur, CLzRef *son,
- UInt32 _cyclicBufferPos, UInt32 _cyclicBufferSize, UInt32 _cutValue,
- UInt32 *_distances, UInt32 _maxLen, const UInt32 *hash, Int32 limit, UInt32 size, UInt32 *posRes)
+MY_NO_INLINE
+static UInt32 *GetMatchesSpecN(UInt32 lenLimit, UInt32 pos, const Byte *cur, CLzRef *son,
+ size_t _cyclicBufferPos, UInt32 _cyclicBufferSize, UInt32 _cutValue,
+ UInt32 *distances, UInt32 _maxLen, const UInt32 *hash, const UInt32 *limit, UInt32 size, UInt32 *posRes)
{
do
{
- UInt32 *distances = _distances + 1;
- UInt32 curMatch = pos - *hash++;
+ UInt32 *_distances = ++distances;
+ UInt32 delta = *hash++;
- CLzRef *ptr0 = son + (_cyclicBufferPos << 1) + 1;
- CLzRef *ptr1 = son + (_cyclicBufferPos << 1);
- UInt32 len0 = 0, len1 = 0;
+ CLzRef *ptr0 = son + ((size_t)_cyclicBufferPos << 1) + 1;
+ CLzRef *ptr1 = son + ((size_t)_cyclicBufferPos << 1);
+ unsigned len0 = 0, len1 = 0;
UInt32 cutValue = _cutValue;
- UInt32 maxLen = _maxLen;
- for (;;)
+ unsigned maxLen = (unsigned)_maxLen;
+
+ /*
+ if (size > 1)
{
- UInt32 delta = pos - curMatch;
- if (cutValue-- == 0 || delta >= _cyclicBufferSize)
+ UInt32 delta = *hash;
+ if (delta < _cyclicBufferSize)
{
- *ptr0 = *ptr1 = kEmptyHashValue;
- break;
+ UInt32 cyc1 = _cyclicBufferPos + 1;
+ CLzRef *pair = son + ((size_t)(cyc1 - delta + ((delta > cyc1) ? _cyclicBufferSize : 0)) << 1);
+ Byte b = *(cur + 1 - delta);
+ _distances[0] = pair[0];
+ _distances[1] = b;
}
+ }
+ */
+ if (cutValue == 0 || delta >= _cyclicBufferSize)
+ {
+ *ptr0 = *ptr1 = kEmptyHashValue;
+ }
+ else
+ for(;;)
+ {
{
- CLzRef *pair = son + ((_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)) << 1);
+ CLzRef *pair = son + ((size_t)(_cyclicBufferPos - delta + ((_cyclicBufferPos < delta) ? _cyclicBufferSize : 0)) << 1);
const Byte *pb = cur - delta;
- UInt32 len = (len0 < len1 ? len0 : len1);
+ unsigned len = (len0 < len1 ? len0 : len1);
+ UInt32 pair0 = *pair;
if (pb[len] == cur[len])
{
if (++len != lenLimit && pb[len] == cur[len])
@@ -272,54 +291,66 @@ static Int32 NO_INLINE GetMatchesSpecN(UInt32 lenLimit, UInt32 pos, const Byte *
break;
if (maxLen < len)
{
- *distances++ = maxLen = len;
+ maxLen = len;
+ *distances++ = (UInt32)len;
*distances++ = delta - 1;
if (len == lenLimit)
{
- *ptr1 = pair[0];
- *ptr0 = pair[1];
+ UInt32 pair1 = pair[1];
+ *ptr1 = pair0;
+ *ptr0 = pair1;
break;
}
}
}
- if (pb[len] < cur[len])
{
- *ptr1 = curMatch;
- ptr1 = pair + 1;
- curMatch = *ptr1;
- len1 = len;
- }
- else
- {
- *ptr0 = curMatch;
- ptr0 = pair;
- curMatch = *ptr0;
- len0 = len;
+ UInt32 curMatch = pos - delta;
+ // delta = pos - *pair;
+ // delta = pos - pair[((UInt32)pb[len] - (UInt32)cur[len]) >> 31];
+ if (pb[len] < cur[len])
+ {
+ delta = pos - pair[1];
+ *ptr1 = curMatch;
+ ptr1 = pair + 1;
+ len1 = len;
+ }
+ else
+ {
+ delta = pos - *pair;
+ *ptr0 = curMatch;
+ ptr0 = pair;
+ len0 = len;
+ }
}
}
+ if (--cutValue == 0 || delta >= _cyclicBufferSize)
+ {
+ *ptr0 = *ptr1 = kEmptyHashValue;
+ break;
+ }
}
pos++;
_cyclicBufferPos++;
cur++;
{
UInt32 num = (UInt32)(distances - _distances);
- *_distances = num - 1;
- _distances += num;
- limit -= num;
+ _distances[-1] = num;
}
}
- while (limit > 0 && --size != 0);
+ while (distances < limit && --size != 0);
*posRes = pos;
- return limit;
+ return distances;
}
#endif
+
+
static void BtGetMatches(CMatchFinderMt *p, UInt32 *distances)
{
UInt32 numProcessed = 0;
UInt32 curPos = 2;
- UInt32 limit = kMtBtBlockSize - (p->matchMaxLen * 2);
+ UInt32 limit = kMtBtBlockSize - (p->matchMaxLen * 2); // * 2
distances[1] = p->hashNumAvail;
@@ -369,8 +400,10 @@ static void BtGetMatches(CMatchFinderMt *p, UInt32 *distances)
#else
{
UInt32 posRes;
- curPos = limit - GetMatchesSpecN(lenLimit, pos, p->buffer, p->son, cyclicBufferPos, p->cyclicBufferSize, p->cutValue,
- distances + curPos, p->numHashBytes - 1, p->hashBuf + p->hashBufPos, (Int32)(limit - curPos), size, &posRes);
+ curPos = (UInt32)(GetMatchesSpecN(lenLimit, pos, p->buffer, p->son, cyclicBufferPos, p->cyclicBufferSize, p->cutValue,
+ distances + curPos, p->numHashBytes - 1, p->hashBuf + p->hashBufPos,
+ distances + limit,
+ size, &posRes) - distances);
p->hashBufPos += posRes - pos;
cyclicBufferPos += posRes - pos;
p->buffer += posRes - pos;
diff --git a/deps/LZMA-SDK/C/LzFindMt.h b/deps/LZMA-SDK/C/LzFindMt.h
index 3d86c788f..fdd17008c 100644
--- a/deps/LZMA-SDK/C/LzFindMt.h
+++ b/deps/LZMA-SDK/C/LzFindMt.h
@@ -1,5 +1,5 @@
/* LzFindMt.h -- multithreaded Match finder for LZ algorithms
-2017-04-03 : Igor Pavlov : Public domain */
+2018-07-04 : Igor Pavlov : Public domain */
#ifndef __LZ_FIND_MT_H
#define __LZ_FIND_MT_H
@@ -19,10 +19,10 @@ EXTERN_C_BEGIN
typedef struct _CMtSync
{
- Bool wasCreated;
- Bool needStart;
- Bool exit;
- Bool stopWriting;
+ BoolInt wasCreated;
+ BoolInt needStart;
+ BoolInt exit;
+ BoolInt stopWriting;
CThread thread;
CAutoResetEvent canStart;
@@ -30,8 +30,8 @@ typedef struct _CMtSync
CAutoResetEvent wasStopped;
CSemaphore freeSemaphore;
CSemaphore filledSemaphore;
- Bool csWasInitialized;
- Bool csWasEntered;
+ BoolInt csWasInitialized;
+ BoolInt csWasEntered;
CCriticalSection cs;
UInt32 numProcessedBlocks;
} CMtSync;
diff --git a/deps/LZMA-SDK/C/Lzma2Dec.c b/deps/LZMA-SDK/C/Lzma2Dec.c
index 57e7f346e..2e631051b 100644
--- a/deps/LZMA-SDK/C/Lzma2Dec.c
+++ b/deps/LZMA-SDK/C/Lzma2Dec.c
@@ -1,5 +1,5 @@
/* Lzma2Dec.c -- LZMA2 Decoder
-2018-02-19 : Igor Pavlov : Public domain */
+2019-02-02 : Igor Pavlov : Public domain */
/* #define SHOW_DEBUG_INFO */
@@ -169,7 +169,7 @@ static void LzmaDec_UpdateWithUncompressed(CLzmaDec *p, const Byte *src, SizeT s
p->processedPos += (UInt32)size;
}
-void LzmaDec_InitDicAndState(CLzmaDec *p, Bool initDic, Bool initState);
+void LzmaDec_InitDicAndState(CLzmaDec *p, BoolInt initDic, BoolInt initState);
SRes Lzma2Dec_DecodeToDic(CLzma2Dec *p, SizeT dicLimit,
@@ -232,7 +232,7 @@ SRes Lzma2Dec_DecodeToDic(CLzma2Dec *p, SizeT dicLimit,
if (p->state == LZMA2_STATE_DATA)
{
- Bool initDic = (p->control == LZMA2_CONTROL_COPY_RESET_DIC);
+ BoolInt initDic = (p->control == LZMA2_CONTROL_COPY_RESET_DIC);
LzmaDec_InitDicAndState(&p->decoder, initDic, False);
}
@@ -254,8 +254,8 @@ SRes Lzma2Dec_DecodeToDic(CLzma2Dec *p, SizeT dicLimit,
if (p->state == LZMA2_STATE_DATA)
{
- Bool initDic = (p->control >= 0xE0);
- Bool initState = (p->control >= 0xA0);
+ BoolInt initDic = (p->control >= 0xE0);
+ BoolInt initState = (p->control >= 0xA0);
LzmaDec_InitDicAndState(&p->decoder, initDic, initState);
p->state = LZMA2_STATE_DATA_CONT;
}
@@ -314,15 +314,15 @@ ELzma2ParseStatus Lzma2Dec_Parse(CLzma2Dec *p,
while (p->state != LZMA2_STATE_ERROR)
{
if (p->state == LZMA2_STATE_FINISHED)
- return LZMA_STATUS_FINISHED_WITH_MARK;
+ return (ELzma2ParseStatus)LZMA_STATUS_FINISHED_WITH_MARK;
if (outSize == 0 && !checkFinishBlock)
- return LZMA_STATUS_NOT_FINISHED;
+ return (ELzma2ParseStatus)LZMA_STATUS_NOT_FINISHED;
if (p->state != LZMA2_STATE_DATA && p->state != LZMA2_STATE_DATA_CONT)
{
if (*srcLen == inSize)
- return LZMA_STATUS_NEEDS_MORE_INPUT;
+ return (ELzma2ParseStatus)LZMA_STATUS_NEEDS_MORE_INPUT;
(*srcLen)++;
p->state = Lzma2Dec_UpdateState(p, *src++);
@@ -344,7 +344,7 @@ ELzma2ParseStatus Lzma2Dec_Parse(CLzma2Dec *p,
// checkFinishBlock is true. So we expect that block must be finished,
// We can return LZMA_STATUS_NOT_SPECIFIED or LZMA_STATUS_NOT_FINISHED here
// break;
- return LZMA_STATUS_NOT_FINISHED;
+ return (ELzma2ParseStatus)LZMA_STATUS_NOT_FINISHED;
}
if (p->state == LZMA2_STATE_DATA)
@@ -354,7 +354,7 @@ ELzma2ParseStatus Lzma2Dec_Parse(CLzma2Dec *p,
}
if (outSize == 0)
- return LZMA_STATUS_NOT_FINISHED;
+ return (ELzma2ParseStatus)LZMA_STATUS_NOT_FINISHED;
{
SizeT inCur = inSize - *srcLen;
@@ -362,7 +362,7 @@ ELzma2ParseStatus Lzma2Dec_Parse(CLzma2Dec *p,
if (LZMA2_IS_UNCOMPRESSED_STATE(p))
{
if (inCur == 0)
- return LZMA_STATUS_NEEDS_MORE_INPUT;
+ return (ELzma2ParseStatus)LZMA_STATUS_NEEDS_MORE_INPUT;
if (inCur > p->unpackSize)
inCur = p->unpackSize;
if (inCur > outSize)
@@ -381,7 +381,7 @@ ELzma2ParseStatus Lzma2Dec_Parse(CLzma2Dec *p,
if (inCur == 0)
{
if (p->packSize != 0)
- return LZMA_STATUS_NEEDS_MORE_INPUT;
+ return (ELzma2ParseStatus)LZMA_STATUS_NEEDS_MORE_INPUT;
}
else if (p->state == LZMA2_STATE_DATA)
{
@@ -418,7 +418,7 @@ ELzma2ParseStatus Lzma2Dec_Parse(CLzma2Dec *p,
}
p->state = LZMA2_STATE_ERROR;
- return LZMA_STATUS_NOT_SPECIFIED;
+ return (ELzma2ParseStatus)LZMA_STATUS_NOT_SPECIFIED;
}
diff --git a/deps/LZMA-SDK/C/Lzma2DecMt.c b/deps/LZMA-SDK/C/Lzma2DecMt.c
index be698cbeb..87d5567ad 100644
--- a/deps/LZMA-SDK/C/Lzma2DecMt.c
+++ b/deps/LZMA-SDK/C/Lzma2DecMt.c
@@ -1,5 +1,5 @@
/* Lzma2DecMt.c -- LZMA2 Decoder Multi-thread
-2018-03-02 : Igor Pavlov : Public domain */
+2019-02-02 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -94,13 +94,13 @@ typedef struct
ISeqOutStream *outStream;
ICompressProgress *progress;
- Bool finishMode;
- Bool outSize_Defined;
+ BoolInt finishMode;
+ BoolInt outSize_Defined;
UInt64 outSize;
UInt64 outProcessed;
UInt64 inProcessed;
- Bool readWasFinished;
+ BoolInt readWasFinished;
SRes readRes;
Byte *inBuf;
@@ -113,7 +113,7 @@ typedef struct
#ifndef _7ZIP_ST
UInt64 outProcessed_Parse;
- Bool mtc_WasConstructed;
+ BoolInt mtc_WasConstructed;
CMtDec mtc;
CLzma2DecMtThread coders[MTDEC__THREADS_MAX];
#endif
@@ -265,7 +265,7 @@ static void Lzma2DecMt_MtCallback_Parse(void *obj, unsigned coderIndex, CMtDecCa
t->outPreSize = 0;
// t->blockWasFinished = False;
// t->finishedWithMark = False;
- t->parseStatus = LZMA_STATUS_NOT_SPECIFIED;
+ t->parseStatus = (ELzma2ParseStatus)LZMA_STATUS_NOT_SPECIFIED;
t->state = MTDEC_PARSE_CONTINUE;
t->inCodeSize = 0;
@@ -277,7 +277,7 @@ static void Lzma2DecMt_MtCallback_Parse(void *obj, unsigned coderIndex, CMtDecCa
{
ELzma2ParseStatus status;
- Bool overflow;
+ BoolInt overflow;
UInt32 unpackRem = 0;
int checkFinishBlock = True;
@@ -477,7 +477,7 @@ static SRes Lzma2DecMt_MtCallback_Code(void *pp, unsigned coderIndex,
{
ELzmaStatus status;
size_t srcProcessed = srcSize;
- Bool blockWasFinished =
+ BoolInt blockWasFinished =
((int)t->parseStatus == LZMA_STATUS_FINISHED_WITH_MARK
|| t->parseStatus == LZMA2_PARSE_STATUS_NEW_BLOCK);
@@ -526,15 +526,15 @@ static SRes Lzma2DecMt_MtCallback_Code(void *pp, unsigned coderIndex,
#define LZMA2DECMT_STREAM_WRITE_STEP (1 << 24)
static SRes Lzma2DecMt_MtCallback_Write(void *pp, unsigned coderIndex,
- Bool needWriteToStream,
+ BoolInt needWriteToStream,
const Byte *src, size_t srcSize,
- Bool *needContinue, Bool *canRecode)
+ BoolInt *needContinue, BoolInt *canRecode)
{
CLzma2DecMt *me = (CLzma2DecMt *)pp;
const CLzma2DecMtThread *t = &me->coders[coderIndex];
size_t size = t->outCodeSize;
const Byte *data = t->outBuf;
- Bool needContinue2 = True;
+ BoolInt needContinue2 = True;
PRF_STR_INT_2("Write", coderIndex, srcSize);
@@ -633,7 +633,7 @@ static SRes Lzma2Dec_Prepare_ST(CLzma2DecMt *p)
static SRes Lzma2Dec_Decode_ST(CLzma2DecMt *p
#ifndef _7ZIP_ST
- , Bool tMode
+ , BoolInt tMode
#endif
)
{
@@ -674,8 +674,8 @@ static SRes Lzma2Dec_Decode_ST(CLzma2DecMt *p
SRes res;
SizeT outProcessed;
- Bool outFinished;
- Bool needStop;
+ BoolInt outFinished;
+ BoolInt needStop;
if (inPos == inLim)
{
@@ -810,7 +810,7 @@ SRes Lzma2DecMt_Decode(CLzma2DecMtHandle pp,
{
CLzma2DecMt *p = (CLzma2DecMt *)pp;
#ifndef _7ZIP_ST
- Bool tMode;
+ BoolInt tMode;
#endif
*inProcessed = 0;
@@ -903,7 +903,7 @@ SRes Lzma2DecMt_Decode(CLzma2DecMtHandle pp,
vt.Write = Lzma2DecMt_MtCallback_Write;
{
- Bool needContinue = False;
+ BoolInt needContinue = False;
SRes res = MtDec_Code(&p->mtc);
diff --git a/deps/LZMA-SDK/C/Lzma2Enc.c b/deps/LZMA-SDK/C/Lzma2Enc.c
index 5098195c1..d54147752 100644
--- a/deps/LZMA-SDK/C/Lzma2Enc.c
+++ b/deps/LZMA-SDK/C/Lzma2Enc.c
@@ -1,5 +1,5 @@
/* Lzma2Enc.c -- LZMA2 Encoder
-2018-04-27 : Igor Pavlov : Public domain */
+2018-07-04 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -115,7 +115,7 @@ SRes LzmaEnc_PrepareForLzma2(CLzmaEncHandle pp, ISeqInStream *inStream, UInt32 k
ISzAllocPtr alloc, ISzAllocPtr allocBig);
SRes LzmaEnc_MemPrepare(CLzmaEncHandle pp, const Byte *src, SizeT srcLen,
UInt32 keepWindowSize, ISzAllocPtr alloc, ISzAllocPtr allocBig);
-SRes LzmaEnc_CodeOneMemBlock(CLzmaEncHandle pp, Bool reInit,
+SRes LzmaEnc_CodeOneMemBlock(CLzmaEncHandle pp, BoolInt reInit,
Byte *dest, size_t *destLen, UInt32 desiredPackSize, UInt32 *unpackSize);
const Byte *LzmaEnc_GetCurBuf(CLzmaEncHandle pp);
void LzmaEnc_Finish(CLzmaEncHandle pp);
@@ -133,7 +133,7 @@ static SRes Lzma2EncInt_EncodeSubblock(CLzma2EncInt *p, Byte *outBuf,
size_t packSize = packSizeLimit;
UInt32 unpackSize = LZMA2_UNPACK_SIZE_MAX;
unsigned lzHeaderSize = 5 + (p->needInitProp ? 1 : 0);
- Bool useCopyBlock;
+ BoolInt useCopyBlock;
SRes res;
*packSizeRes = 0;
@@ -373,7 +373,7 @@ typedef struct
size_t outBufSize; /* size of allocated outBufs[i] */
size_t outBufsDataSizes[MTCODER__BLOCKS_MAX];
- Bool mtCoder_WasConstructed;
+ BoolInt mtCoder_WasConstructed;
CMtCoder mtCoder;
Byte *outBufs[MTCODER__BLOCKS_MAX];
diff --git a/deps/LZMA-SDK/C/Lzma86Enc.c b/deps/LZMA-SDK/C/Lzma86Enc.c
index ee59fb7d7..8d35e6dc5 100644
--- a/deps/LZMA-SDK/C/Lzma86Enc.c
+++ b/deps/LZMA-SDK/C/Lzma86Enc.c
@@ -1,5 +1,5 @@
/* Lzma86Enc.c -- LZMA + x86 (BCJ) Filter Encoder
-2016-05-16 : Igor Pavlov : Public domain */
+2018-07-04 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -18,7 +18,7 @@ int Lzma86_Encode(Byte *dest, size_t *destLen, const Byte *src, size_t srcLen,
{
size_t outSize2 = *destLen;
Byte *filteredStream;
- Bool useFilter;
+ BoolInt useFilter;
int mainResult = SZ_ERROR_OUTPUT_EOF;
CLzmaEncProps props;
LzmaEncProps_Init(&props);
@@ -56,7 +56,7 @@ int Lzma86_Encode(Byte *dest, size_t *destLen, const Byte *src, size_t srcLen,
{
size_t minSize = 0;
- Bool bestIsFiltered = False;
+ BoolInt bestIsFiltered = False;
/* passes for SZ_FILTER_AUTO:
0 - BCJ + LZMA
@@ -71,7 +71,7 @@ int Lzma86_Encode(Byte *dest, size_t *destLen, const Byte *src, size_t srcLen,
size_t outSizeProcessed = outSize2 - LZMA86_HEADER_SIZE;
size_t outPropsSize = 5;
SRes curRes;
- Bool curModeIsFiltered = (numPasses > 1 && i == numPasses - 1);
+ BoolInt curModeIsFiltered = (numPasses > 1 && i == numPasses - 1);
if (curModeIsFiltered && !bestIsFiltered)
break;
if (useFilter && i == 0)
diff --git a/deps/LZMA-SDK/C/LzmaDec.c b/deps/LZMA-SDK/C/LzmaDec.c
index 962b94bb6..4d1576419 100644
--- a/deps/LZMA-SDK/C/LzmaDec.c
+++ b/deps/LZMA-SDK/C/LzmaDec.c
@@ -1,13 +1,13 @@
/* LzmaDec.c -- LZMA Decoder
-2018-02-28 : Igor Pavlov : Public domain */
+2018-07-04 : Igor Pavlov : Public domain */
#include "Precomp.h"
+#include <string.h>
+
/* #include "CpuArch.h" */
#include "LzmaDec.h"
-#include <string.h>
-
#define kNumTopBits 24
#define kTopValue ((UInt32)1 << kNumTopBits)
@@ -19,7 +19,7 @@
#define NORMALIZE if (range < kTopValue) { range <<= 8; code = (code << 8) | (*buf++); }
-#define IF_BIT_0(p) ttt = *(p); NORMALIZE; bound = (range >> kNumBitModelTotalBits) * ttt; if (code < bound)
+#define IF_BIT_0(p) ttt = *(p); NORMALIZE; bound = (range >> kNumBitModelTotalBits) * (UInt32)ttt; if (code < bound)
#define UPDATE_0(p) range = bound; *(p) = (CLzmaProb)(ttt + ((kBitModelTotal - ttt) >> kNumMoveBits));
#define UPDATE_1(p) range -= bound; code -= bound; *(p) = (CLzmaProb)(ttt - (ttt >> kNumMoveBits));
#define GET_BIT2(p, i, A0, A1) IF_BIT_0(p) \
@@ -66,7 +66,7 @@
#define NORMALIZE_CHECK if (range < kTopValue) { if (buf >= bufLimit) return DUMMY_ERROR; range <<= 8; code = (code << 8) | (*buf++); }
-#define IF_BIT_0_CHECK(p) ttt = *(p); NORMALIZE_CHECK; bound = (range >> kNumBitModelTotalBits) * ttt; if (code < bound)
+#define IF_BIT_0_CHECK(p) ttt = *(p); NORMALIZE_CHECK; bound = (range >> kNumBitModelTotalBits) * (UInt32)ttt; if (code < bound)
#define UPDATE_0_CHECK range = bound;
#define UPDATE_1_CHECK range -= bound; code -= bound;
#define GET_BIT2_CHECK(p, i, A0, A1) IF_BIT_0_CHECK(p) \
@@ -539,7 +539,7 @@ int MY_FAST_CALL LZMA_DECODE_REAL(CLzmaDec *p, SizeT limit, const Byte *bufLimit
curLen = ((rem < len) ? (unsigned)rem : len);
pos = dicPos - rep0 + (dicPos < rep0 ? dicBufSize : 0);
- processedPos += curLen;
+ processedPos += (UInt32)curLen;
len -= curLen;
if (curLen <= dicBufSize - pos)
@@ -547,7 +547,7 @@ int MY_FAST_CALL LZMA_DECODE_REAL(CLzmaDec *p, SizeT limit, const Byte *bufLimit
Byte *dest = dic + dicPos;
ptrdiff_t src = (ptrdiff_t)pos - (ptrdiff_t)dicPos;
const Byte *lim = dest + curLen;
- dicPos += curLen;
+ dicPos += (SizeT)curLen;
do
*(dest) = (Byte)*(dest + src);
while (++dest != lim);
@@ -572,14 +572,14 @@ int MY_FAST_CALL LZMA_DECODE_REAL(CLzmaDec *p, SizeT limit, const Byte *bufLimit
p->buf = buf;
p->range = range;
p->code = code;
- p->remainLen = len;
+ p->remainLen = (UInt32)len;
p->dicPos = dicPos;
p->processedPos = processedPos;
p->reps[0] = rep0;
p->reps[1] = rep1;
p->reps[2] = rep2;
p->reps[3] = rep3;
- p->state = state;
+ p->state = (UInt32)state;
return SZ_OK;
}
@@ -601,8 +601,8 @@ static void MY_FAST_CALL LzmaDec_WriteRem(CLzmaDec *p, SizeT limit)
if (p->checkDicSize == 0 && p->prop.dicSize - p->processedPos <= len)
p->checkDicSize = p->prop.dicSize;
- p->processedPos += len;
- p->remainLen -= len;
+ p->processedPos += (UInt32)len;
+ p->remainLen -= (UInt32)len;
while (len != 0)
{
len--;
@@ -850,7 +850,7 @@ static ELzmaDummy LzmaDec_TryDummy(const CLzmaDec *p, const Byte *buf, SizeT inS
}
-void LzmaDec_InitDicAndState(CLzmaDec *p, Bool initDic, Bool initState)
+void LzmaDec_InitDicAndState(CLzmaDec *p, BoolInt initDic, BoolInt initState)
{
p->remainLen = kMatchSpecLenStart + 1;
p->tempBufSize = 0;
@@ -979,10 +979,10 @@ SRes LzmaDec_DecodeToDic(CLzmaDec *p, SizeT dicLimit, const Byte *src, SizeT *sr
p->tempBufSize = rem;
if (rem < LZMA_REQUIRED_INPUT_MAX || checkEndMarkNow)
{
- int dummyRes = LzmaDec_TryDummy(p, p->tempBuf, rem);
+ int dummyRes = LzmaDec_TryDummy(p, p->tempBuf, (SizeT)rem);
if (dummyRes == DUMMY_ERROR)
{
- (*srcLen) += lookAhead;
+ (*srcLen) += (SizeT)lookAhead;
*status = LZMA_STATUS_NEEDS_MORE_INPUT;
return SZ_OK;
}
@@ -1005,9 +1005,9 @@ SRes LzmaDec_DecodeToDic(CLzmaDec *p, SizeT dicLimit, const Byte *src, SizeT *sr
return SZ_ERROR_FAIL; /* some internal error */
lookAhead -= rem;
}
- (*srcLen) += lookAhead;
+ (*srcLen) += (SizeT)lookAhead;
src += lookAhead;
- inSize -= lookAhead;
+ inSize -= (SizeT)lookAhead;
p->tempBufSize = 0;
}
}
diff --git a/deps/LZMA-SDK/C/LzmaEnc.c b/deps/LZMA-SDK/C/LzmaEnc.c
index bebe664d3..14086fc4f 100644
--- a/deps/LZMA-SDK/C/LzmaEnc.c
+++ b/deps/LZMA-SDK/C/LzmaEnc.c
@@ -1,5 +1,5 @@
/* LzmaEnc.c -- LZMA Encoder
-2018-04-29 : Igor Pavlov : Public domain */
+2019-01-10: Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -38,6 +38,8 @@ static unsigned g_STAT_OFFSET = 0;
#define kNumBitPriceShiftBits 4
#define kBitPrice (1 << kNumBitPriceShiftBits)
+#define REP_LEN_COUNT 64
+
void LzmaEncProps_Init(CLzmaEncProps *p)
{
p->level = 5;
@@ -183,8 +185,11 @@ typedef struct
} COptimal;
-#define kNumOpts (1 << 12)
-#define kPackReserve (1 + kNumOpts * 2)
+// 18.06
+#define kNumOpts (1 << 11)
+#define kPackReserve (kNumOpts * 8)
+// #define kNumOpts (1 << 12)
+// #define kPackReserve (1 + kNumOpts * 2)
#define kNumLenToPosStates 4
#define kNumPosSlotBits 6
@@ -236,10 +241,18 @@ typedef struct
typedef struct
{
unsigned tableSize;
- unsigned counters[LZMA_NUM_PB_STATES_MAX];
UInt32 prices[LZMA_NUM_PB_STATES_MAX][kLenNumSymbolsTotal];
+ // UInt32 prices1[LZMA_NUM_PB_STATES_MAX][kLenNumLowSymbols * 2];
+ // UInt32 prices2[kLenNumSymbolsTotal];
} CLenPriceEnc;
+#define GET_PRICE_LEN(p, posState, len) \
+ ((p)->prices[posState][(size_t)(len) - LZMA_MATCH_LEN_MIN])
+
+/*
+#define GET_PRICE_LEN(p, posState, len) \
+ ((p)->prices2[(size_t)(len) - 2] + ((p)->prices1[posState][((len) - 2) & (kLenNumLowSymbols * 2 - 1)] & (((len) - 2 - kLenNumLowSymbols * 2) >> 9)))
+*/
typedef struct
{
@@ -308,16 +321,18 @@ typedef struct
unsigned lc, lp, pb;
unsigned lclp;
- Bool fastMode;
- Bool writeEndMark;
- Bool finished;
- Bool multiThread;
- Bool needInit;
+ BoolInt fastMode;
+ BoolInt writeEndMark;
+ BoolInt finished;
+ BoolInt multiThread;
+ BoolInt needInit;
+ // BoolInt _maxMode;
UInt64 nowPos64;
unsigned matchPriceCount;
- unsigned alignPriceCount;
+ // unsigned alignPriceCount;
+ int repLenEncCounter;
unsigned distTableSize;
@@ -325,7 +340,7 @@ typedef struct
SRes result;
#ifndef _7ZIP_ST
- Bool mtMode;
+ BoolInt mtMode;
// begin of CMatchFinderMt is used in LZ thread
CMatchFinderMt matchFinderMt;
// end of CMatchFinderMt is used in BT and HASH threads
@@ -458,6 +473,7 @@ SRes LzmaEnc_SetProps(CLzmaEncHandle pp, const CLzmaEncProps *props2)
p->lp = props.lp;
p->pb = props.pb;
p->fastMode = (props.algo == 0);
+ // p->_maxMode = True;
p->matchFinderBase.btMode = (Byte)(props.btMode ? 1 : 0);
{
unsigned numHashBytes = 4;
@@ -618,9 +634,9 @@ static void RangeEnc_FlushData(CRangeEnc *p)
#ifdef _LZMA_ENC_USE_BRANCH
-#define RC_BIT(p, prob, symbol) { \
+#define RC_BIT(p, prob, bit) { \
RC_BIT_PRE(p, prob) \
- if (symbol == 0) { range = newBound; ttt += (kBitModelTotal - ttt) >> kNumMoveBits; } \
+ if (bit == 0) { range = newBound; ttt += (kBitModelTotal - ttt) >> kNumMoveBits; } \
else { (p)->low += newBound; range -= newBound; ttt -= ttt >> kNumMoveBits; } \
*(prob) = (CLzmaProb)ttt; \
RC_NORM(p) \
@@ -628,15 +644,15 @@ static void RangeEnc_FlushData(CRangeEnc *p)
#else
-#define RC_BIT(p, prob, symbol) { \
+#define RC_BIT(p, prob, bit) { \
UInt32 mask; \
RC_BIT_PRE(p, prob) \
- mask = 0 - (UInt32)symbol; \
+ mask = 0 - (UInt32)bit; \
range &= mask; \
mask &= newBound; \
range -= mask; \
(p)->low += mask; \
- mask = (UInt32)symbol - 1; \
+ mask = (UInt32)bit - 1; \
range += newBound & mask; \
mask &= (kBitModelTotal - ((1 << kNumMoveBits) - 1)); \
mask += ((1 << kNumMoveBits) - 1); \
@@ -673,42 +689,42 @@ static void RangeEnc_EncodeBit_0(CRangeEnc *p, CLzmaProb *prob)
p->range = range;
}
-static void LitEnc_Encode(CRangeEnc *p, CLzmaProb *probs, UInt32 symbol)
+static void LitEnc_Encode(CRangeEnc *p, CLzmaProb *probs, UInt32 sym)
{
UInt32 range = p->range;
- symbol |= 0x100;
+ sym |= 0x100;
do
{
UInt32 ttt, newBound;
- // RangeEnc_EncodeBit(p, probs + (symbol >> 8), (symbol >> 7) & 1);
- CLzmaProb *prob = probs + (symbol >> 8);
- UInt32 bit = (symbol >> 7) & 1;
- symbol <<= 1;
+ // RangeEnc_EncodeBit(p, probs + (sym >> 8), (sym >> 7) & 1);
+ CLzmaProb *prob = probs + (sym >> 8);
+ UInt32 bit = (sym >> 7) & 1;
+ sym <<= 1;
RC_BIT(p, prob, bit);
}
- while (symbol < 0x10000);
+ while (sym < 0x10000);
p->range = range;
}
-static void LitEnc_EncodeMatched(CRangeEnc *p, CLzmaProb *probs, UInt32 symbol, UInt32 matchByte)
+static void LitEnc_EncodeMatched(CRangeEnc *p, CLzmaProb *probs, UInt32 sym, UInt32 matchByte)
{
UInt32 range = p->range;
UInt32 offs = 0x100;
- symbol |= 0x100;
+ sym |= 0x100;
do
{
UInt32 ttt, newBound;
CLzmaProb *prob;
UInt32 bit;
matchByte <<= 1;
- // RangeEnc_EncodeBit(p, probs + (offs + (matchByte & offs) + (symbol >> 8)), (symbol >> 7) & 1);
- prob = probs + (offs + (matchByte & offs) + (symbol >> 8));
- bit = (symbol >> 7) & 1;
- symbol <<= 1;
- offs &= ~(matchByte ^ symbol);
+ // RangeEnc_EncodeBit(p, probs + (offs + (matchByte & offs) + (sym >> 8)), (sym >> 7) & 1);
+ prob = probs + (offs + (matchByte & offs) + (sym >> 8));
+ bit = (sym >> 7) & 1;
+ sym <<= 1;
+ offs &= ~(matchByte ^ sym);
RC_BIT(p, prob, bit);
}
- while (symbol < 0x10000);
+ while (sym < 0x10000);
p->range = range;
}
@@ -739,11 +755,11 @@ static void LzmaEnc_InitPriceTables(CProbPrice *ProbPrices)
}
-#define GET_PRICE(prob, symbol) \
- p->ProbPrices[((prob) ^ (unsigned)(((-(int)(symbol))) & (kBitModelTotal - 1))) >> kNumMoveReducingBits];
+#define GET_PRICE(prob, bit) \
+ p->ProbPrices[((prob) ^ (unsigned)(((-(int)(bit))) & (kBitModelTotal - 1))) >> kNumMoveReducingBits];
-#define GET_PRICEa(prob, symbol) \
- ProbPrices[((prob) ^ (unsigned)((-((int)(symbol))) & (kBitModelTotal - 1))) >> kNumMoveReducingBits];
+#define GET_PRICEa(prob, bit) \
+ ProbPrices[((prob) ^ (unsigned)((-((int)(bit))) & (kBitModelTotal - 1))) >> kNumMoveReducingBits];
#define GET_PRICE_0(prob) p->ProbPrices[(prob) >> kNumMoveReducingBits]
#define GET_PRICE_1(prob) p->ProbPrices[((prob) ^ (kBitModelTotal - 1)) >> kNumMoveReducingBits]
@@ -752,48 +768,48 @@ static void LzmaEnc_InitPriceTables(CProbPrice *ProbPrices)
#define GET_PRICEa_1(prob) ProbPrices[((prob) ^ (kBitModelTotal - 1)) >> kNumMoveReducingBits]
-static UInt32 LitEnc_GetPrice(const CLzmaProb *probs, UInt32 symbol, const CProbPrice *ProbPrices)
+static UInt32 LitEnc_GetPrice(const CLzmaProb *probs, UInt32 sym, const CProbPrice *ProbPrices)
{
UInt32 price = 0;
- symbol |= 0x100;
+ sym |= 0x100;
do
{
- unsigned bit = symbol & 1;
- symbol >>= 1;
- price += GET_PRICEa(probs[symbol], bit);
+ unsigned bit = sym & 1;
+ sym >>= 1;
+ price += GET_PRICEa(probs[sym], bit);
}
- while (symbol >= 2);
+ while (sym >= 2);
return price;
}
-static UInt32 LitEnc_Matched_GetPrice(const CLzmaProb *probs, UInt32 symbol, UInt32 matchByte, const CProbPrice *ProbPrices)
+static UInt32 LitEnc_Matched_GetPrice(const CLzmaProb *probs, UInt32 sym, UInt32 matchByte, const CProbPrice *ProbPrices)
{
UInt32 price = 0;
UInt32 offs = 0x100;
- symbol |= 0x100;
+ sym |= 0x100;
do
{
matchByte <<= 1;
- price += GET_PRICEa(probs[offs + (matchByte & offs) + (symbol >> 8)], (symbol >> 7) & 1);
- symbol <<= 1;
- offs &= ~(matchByte ^ symbol);
+ price += GET_PRICEa(probs[offs + (matchByte & offs) + (sym >> 8)], (sym >> 7) & 1);
+ sym <<= 1;
+ offs &= ~(matchByte ^ sym);
}
- while (symbol < 0x10000);
+ while (sym < 0x10000);
return price;
}
-static void RcTree_ReverseEncode(CRangeEnc *rc, CLzmaProb *probs, unsigned numBits, UInt32 symbol)
+static void RcTree_ReverseEncode(CRangeEnc *rc, CLzmaProb *probs, unsigned numBits, unsigned sym)
{
UInt32 range = rc->range;
unsigned m = 1;
do
{
UInt32 ttt, newBound;
- unsigned bit = symbol & 1;
+ unsigned bit = sym & 1;
// RangeEnc_EncodeBit(rc, probs + m, bit);
- symbol >>= 1;
+ sym >>= 1;
RC_BIT(rc, probs + m, bit);
m = (m << 1) | bit;
}
@@ -812,37 +828,37 @@ static void LenEnc_Init(CLenEnc *p)
p->high[i] = kProbInitValue;
}
-static void LenEnc_Encode(CLenEnc *p, CRangeEnc *rc, unsigned symbol, unsigned posState)
+static void LenEnc_Encode(CLenEnc *p, CRangeEnc *rc, unsigned sym, unsigned posState)
{
UInt32 range, ttt, newBound;
CLzmaProb *probs = p->low;
range = rc->range;
RC_BIT_PRE(rc, probs);
- if (symbol >= kLenNumLowSymbols)
+ if (sym >= kLenNumLowSymbols)
{
RC_BIT_1(rc, probs);
probs += kLenNumLowSymbols;
RC_BIT_PRE(rc, probs);
- if (symbol >= kLenNumLowSymbols * 2)
+ if (sym >= kLenNumLowSymbols * 2)
{
RC_BIT_1(rc, probs);
rc->range = range;
- // RcTree_Encode(rc, p->high, kLenNumHighBits, symbol - kLenNumLowSymbols * 2);
- LitEnc_Encode(rc, p->high, symbol - kLenNumLowSymbols * 2);
+ // RcTree_Encode(rc, p->high, kLenNumHighBits, sym - kLenNumLowSymbols * 2);
+ LitEnc_Encode(rc, p->high, sym - kLenNumLowSymbols * 2);
return;
}
- symbol -= kLenNumLowSymbols;
+ sym -= kLenNumLowSymbols;
}
- // RcTree_Encode(rc, probs + (posState << kLenNumLowBits), kLenNumLowBits, symbol);
+ // RcTree_Encode(rc, probs + (posState << kLenNumLowBits), kLenNumLowBits, sym);
{
unsigned m;
unsigned bit;
RC_BIT_0(rc, probs);
probs += (posState << (1 + kLenNumLowBits));
- bit = (symbol >> 2) ; RC_BIT(rc, probs + 1, bit); m = (1 << 1) + bit;
- bit = (symbol >> 1) & 1; RC_BIT(rc, probs + m, bit); m = (m << 1) + bit;
- bit = symbol & 1; RC_BIT(rc, probs + m, bit);
+ bit = (sym >> 2) ; RC_BIT(rc, probs + 1, bit); m = (1 << 1) + bit;
+ bit = (sym >> 1) & 1; RC_BIT(rc, probs + m, bit); m = (m << 1) + bit;
+ bit = sym & 1; RC_BIT(rc, probs + m, bit);
rc->range = range;
}
}
@@ -863,51 +879,94 @@ static void SetPrices_3(const CLzmaProb *probs, UInt32 startPrice, UInt32 *price
}
-MY_NO_INLINE static void MY_FAST_CALL LenPriceEnc_UpdateTable(
- CLenPriceEnc *p, unsigned posState,
+MY_NO_INLINE static void MY_FAST_CALL LenPriceEnc_UpdateTables(
+ CLenPriceEnc *p,
+ unsigned numPosStates,
const CLenEnc *enc,
const CProbPrice *ProbPrices)
{
- // int y; for (y = 0; y < 100; y++) {
- UInt32 a;
- unsigned i, numSymbols;
-
- UInt32 *prices = p->prices[posState];
+ UInt32 b;
+
{
- const CLzmaProb *probs = enc->low + (posState << (1 + kLenNumLowBits));
- SetPrices_3(probs, GET_PRICEa_0(enc->low[0]), prices, ProbPrices);
+ unsigned prob = enc->low[0];
+ UInt32 a, c;
+ unsigned posState;
+ b = GET_PRICEa_1(prob);
+ a = GET_PRICEa_0(prob);
+ c = b + GET_PRICEa_0(enc->low[kLenNumLowSymbols]);
+ for (posState = 0; posState < numPosStates; posState++)
+ {
+ UInt32 *prices = p->prices[posState];
+ const CLzmaProb *probs = enc->low + (posState << (1 + kLenNumLowBits));
+ SetPrices_3(probs, a, prices, ProbPrices);
+ SetPrices_3(probs + kLenNumLowSymbols, c, prices + kLenNumLowSymbols, ProbPrices);
+ }
+ }
+
+ /*
+ {
+ unsigned i;
+ UInt32 b;
+ a = GET_PRICEa_0(enc->low[0]);
+ for (i = 0; i < kLenNumLowSymbols; i++)
+ p->prices2[i] = a;
a = GET_PRICEa_1(enc->low[0]);
- SetPrices_3(probs + kLenNumLowSymbols, a + GET_PRICEa_0(enc->low[kLenNumLowSymbols]), prices + kLenNumLowSymbols, ProbPrices);
+ b = a + GET_PRICEa_0(enc->low[kLenNumLowSymbols]);
+ for (i = kLenNumLowSymbols; i < kLenNumLowSymbols * 2; i++)
+ p->prices2[i] = b;
a += GET_PRICEa_1(enc->low[kLenNumLowSymbols]);
}
- numSymbols = p->tableSize;
- p->counters[posState] = numSymbols;
- for (i = kLenNumLowSymbols * 2; i < numSymbols; i += 1)
+ */
+
+ // p->counter = numSymbols;
+ // p->counter = 64;
+
{
- prices[i] = a +
- // RcTree_GetPrice(enc->high, kLenNumHighBits, i - kLenNumLowSymbols * 2, ProbPrices);
- LitEnc_GetPrice(enc->high, i - kLenNumLowSymbols * 2, ProbPrices);
- /*
- unsigned sym = (i - kLenNumLowSymbols * 2) >> 1;
- UInt32 price = a + RcTree_GetPrice(enc->high, kLenNumHighBits - 1, sym, ProbPrices);
- UInt32 prob = enc->high[(1 << 7) + sym];
- prices[i ] = price + GET_PRICEa_0(prob);
- prices[i + 1] = price + GET_PRICEa_1(prob);
- */
+ unsigned i = p->tableSize;
+
+ if (i > kLenNumLowSymbols * 2)
+ {
+ const CLzmaProb *probs = enc->high;
+ UInt32 *prices = p->prices[0] + kLenNumLowSymbols * 2;
+ i -= kLenNumLowSymbols * 2 - 1;
+ i >>= 1;
+ b += GET_PRICEa_1(enc->low[kLenNumLowSymbols]);
+ do
+ {
+ /*
+ p->prices2[i] = a +
+ // RcTree_GetPrice(enc->high, kLenNumHighBits, i - kLenNumLowSymbols * 2, ProbPrices);
+ LitEnc_GetPrice(probs, i - kLenNumLowSymbols * 2, ProbPrices);
+ */
+ // UInt32 price = a + RcTree_GetPrice(probs, kLenNumHighBits - 1, sym, ProbPrices);
+ unsigned sym = --i + (1 << (kLenNumHighBits - 1));
+ UInt32 price = b;
+ do
+ {
+ unsigned bit = sym & 1;
+ sym >>= 1;
+ price += GET_PRICEa(probs[sym], bit);
+ }
+ while (sym >= 2);
+
+ {
+ unsigned prob = probs[(size_t)i + (1 << (kLenNumHighBits - 1))];
+ prices[(size_t)i * 2 ] = price + GET_PRICEa_0(prob);
+ prices[(size_t)i * 2 + 1] = price + GET_PRICEa_1(prob);
+ }
+ }
+ while (i);
+
+ {
+ unsigned posState;
+ size_t num = (p->tableSize - kLenNumLowSymbols * 2) * sizeof(p->prices[0][0]);
+ for (posState = 1; posState < numPosStates; posState++)
+ memcpy(p->prices[posState] + kLenNumLowSymbols * 2, p->prices[0] + kLenNumLowSymbols * 2, num);
+ }
+ }
}
- // }
}
-static void LenPriceEnc_UpdateTables(CLenPriceEnc *p, unsigned numPosStates,
- const CLenEnc *enc,
- const CProbPrice *ProbPrices)
-{
- unsigned posState;
- for (posState = 0; posState < numPosStates; posState++)
- LenPriceEnc_UpdateTable(p, posState, enc, ProbPrices);
-}
-
-
/*
#ifdef SHOW_STAT
g_STAT_OFFSET += num;
@@ -917,7 +976,7 @@ static void LenPriceEnc_UpdateTables(CLenPriceEnc *p, unsigned numPosStates,
#define MOVE_POS(p, num) { \
p->additionalOffset += (num); \
- p->matchFinder.Skip(p->matchFinderObj, (num)); }
+ p->matchFinder.Skip(p->matchFinderObj, (UInt32)(num)); }
static unsigned ReadMatchDistances(CLzmaEnc *p, unsigned *numPairsRes)
@@ -954,7 +1013,8 @@ static unsigned ReadMatchDistances(CLzmaEnc *p, unsigned *numPairsRes)
const Byte *p2 = p1 + len;
ptrdiff_t dif = (ptrdiff_t)-1 - p->matches[(size_t)numPairs - 1];
const Byte *lim = p1 + numAvail;
- for (; p2 != lim && *p2 == p2[dif]; p2++);
+ for (; p2 != lim && *p2 == p2[dif]; p2++)
+ {}
return (unsigned)(p2 - p1);
}
}
@@ -977,7 +1037,7 @@ static unsigned ReadMatchDistances(CLzmaEnc *p, unsigned *numPairsRes)
+ GET_PRICE_1(p->isRep[state]) \
+ GET_PRICE_0(p->isRepG0[state])
-
+MY_FORCE_INLINE
static UInt32 GetPrice_PureRep(const CLzmaEnc *p, unsigned repIndex, size_t state, size_t posState)
{
UInt32 price;
@@ -1011,14 +1071,14 @@ static unsigned Backward(CLzmaEnc *p, unsigned cur)
for (;;)
{
UInt32 dist = p->opt[cur].dist;
- UInt32 len = p->opt[cur].len;
- UInt32 extra = p->opt[cur].extra;
+ unsigned len = (unsigned)p->opt[cur].len;
+ unsigned extra = (unsigned)p->opt[cur].extra;
cur -= len;
if (extra)
{
wr--;
- p->opt[wr].len = len;
+ p->opt[wr].len = (UInt32)len;
cur -= extra;
len = extra;
if (extra == 1)
@@ -1045,7 +1105,7 @@ static unsigned Backward(CLzmaEnc *p, unsigned cur)
wr--;
p->opt[wr].dist = dist;
- p->opt[wr].len = len;
+ p->opt[wr].len = (UInt32)len;
}
}
@@ -1102,7 +1162,8 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
repLens[i] = 0;
continue;
}
- for (len = 2; len < numAvail && data[len] == data2[len]; len++);
+ for (len = 2; len < numAvail && data[len] == data2[len]; len++)
+ {}
repLens[i] = len;
if (len > repLens[repMaxIndex])
repMaxIndex = i;
@@ -1111,7 +1172,7 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
if (repLens[repMaxIndex] >= p->numFastBytes)
{
unsigned len;
- p->backRes = repMaxIndex;
+ p->backRes = (UInt32)repMaxIndex;
len = repLens[repMaxIndex];
MOVE_POS(p, len - 1)
return len;
@@ -1128,8 +1189,12 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
curByte = *data;
matchByte = *(data - reps[0]);
+
+ last = repLens[repMaxIndex];
+ if (last <= mainLen)
+ last = mainLen;
- if (mainLen < 2 && curByte != matchByte && repLens[repMaxIndex] < 2)
+ if (last < 2 && curByte != matchByte)
{
p->backRes = MARK_LIT;
return 1;
@@ -1146,13 +1211,14 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
LitEnc_Matched_GetPrice(probs, curByte, matchByte, p->ProbPrices) :
LitEnc_GetPrice(probs, curByte, p->ProbPrices));
}
-
+
MakeAs_Lit(&p->opt[1]);
matchPrice = GET_PRICE_1(p->isMatch[p->state][posState]);
repMatchPrice = matchPrice + GET_PRICE_1(p->isRep[p->state]);
- if (matchByte == curByte)
+ // 18.06
+ if (matchByte == curByte && repLens[0] == 0)
{
UInt32 shortRepPrice = repMatchPrice + GetPrice_ShortRep(p, p->state, posState);
if (shortRepPrice < p->opt[1].price)
@@ -1160,16 +1226,13 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
p->opt[1].price = shortRepPrice;
MakeAs_ShortRep(&p->opt[1]);
}
+ if (last < 2)
+ {
+ p->backRes = p->opt[1].dist;
+ return 1;
+ }
}
-
- last = (mainLen >= repLens[repMaxIndex] ? mainLen : repLens[repMaxIndex]);
-
- if (last < 2)
- {
- p->backRes = p->opt[1].dist;
- return 1;
- }
-
+
p->opt[1].len = 1;
p->opt[0].reps[0] = reps[0];
@@ -1177,13 +1240,6 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
p->opt[0].reps[2] = reps[2];
p->opt[0].reps[3] = reps[3];
- {
- unsigned len = last;
- do
- p->opt[len--].price = kInfinityPrice;
- while (len >= 2);
- }
-
// ---------- REP ----------
for (i = 0; i < LZMA_NUM_REPS; i++)
@@ -1195,13 +1251,13 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
price = repMatchPrice + GetPrice_PureRep(p, i, p->state, posState);
do
{
- UInt32 price2 = price + p->repLenEnc.prices[posState][(size_t)repLen - 2];
+ UInt32 price2 = price + GET_PRICE_LEN(&p->repLenEnc, posState, repLen);
COptimal *opt = &p->opt[repLen];
if (price2 < opt->price)
{
opt->price = price2;
- opt->len = repLen;
- opt->dist = i;
+ opt->len = (UInt32)repLen;
+ opt->dist = (UInt32)i;
opt->extra = 0;
}
}
@@ -1211,38 +1267,41 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
// ---------- MATCH ----------
{
- unsigned len = ((repLens[0] >= 2) ? repLens[0] + 1 : 2);
+ unsigned len = repLens[0] + 1;
if (len <= mainLen)
{
unsigned offs = 0;
UInt32 normalMatchPrice = matchPrice + GET_PRICE_0(p->isRep[p->state]);
- while (len > matches[offs])
- offs += 2;
+ if (len < 2)
+ len = 2;
+ else
+ while (len > matches[offs])
+ offs += 2;
for (; ; len++)
{
COptimal *opt;
UInt32 dist = matches[(size_t)offs + 1];
- UInt32 price2 = normalMatchPrice + p->lenEnc.prices[posState][(size_t)len - LZMA_MATCH_LEN_MIN];
+ UInt32 price = normalMatchPrice + GET_PRICE_LEN(&p->lenEnc, posState, len);
unsigned lenToPosState = GetLenToPosState(len);
if (dist < kNumFullDistances)
- price2 += p->distancesPrices[lenToPosState][dist & (kNumFullDistances - 1)];
+ price += p->distancesPrices[lenToPosState][dist & (kNumFullDistances - 1)];
else
{
unsigned slot;
GetPosSlot2(dist, slot);
- price2 += p->alignPrices[dist & kAlignMask];
- price2 += p->posSlotPrices[lenToPosState][slot];
+ price += p->alignPrices[dist & kAlignMask];
+ price += p->posSlotPrices[lenToPosState][slot];
}
opt = &p->opt[len];
- if (price2 < opt->price)
+ if (price < opt->price)
{
- opt->price = price2;
- opt->len = len;
+ opt->price = price;
+ opt->len = (UInt32)len;
opt->dist = dist + LZMA_NUM_REPS;
opt->extra = 0;
}
@@ -1277,16 +1336,43 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
for (;;)
{
- UInt32 numAvail, numAvailFull;
+ unsigned numAvail;
+ UInt32 numAvailFull;
unsigned newLen, numPairs, prev, state, posState, startLen;
- UInt32 curPrice, litPrice, matchPrice, repMatchPrice;
- Bool nextIsLit;
+ UInt32 litPrice, matchPrice, repMatchPrice;
+ BoolInt nextIsLit;
Byte curByte, matchByte;
const Byte *data;
COptimal *curOpt, *nextOpt;
if (++cur == last)
- return Backward(p, cur);
+ break;
+
+ // 18.06
+ if (cur >= kNumOpts - 64)
+ {
+ unsigned j, best;
+ UInt32 price = p->opt[cur].price;
+ best = cur;
+ for (j = cur + 1; j <= last; j++)
+ {
+ UInt32 price2 = p->opt[j].price;
+ if (price >= price2)
+ {
+ price = price2;
+ best = j;
+ }
+ }
+ {
+ unsigned delta = best - cur;
+ if (delta != 0)
+ {
+ MOVE_POS(p, delta);
+ }
+ }
+ cur = best;
+ break;
+ }
newLen = ReadMatchDistances(p, &numPairs);
@@ -1294,15 +1380,24 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
{
p->numPairs = numPairs;
p->longestMatchLen = newLen;
- return Backward(p, cur);
+ break;
}
curOpt = &p->opt[cur];
+
+ position++;
+
+ // we need that check here, if skip_items in p->opt are possible
+ /*
+ if (curOpt->price >= kInfinityPrice)
+ continue;
+ */
+
prev = cur - curOpt->len;
-
+
if (curOpt->len == 1)
{
- state = p->opt[prev].state;
+ state = (unsigned)p->opt[prev].state;
if (IsShortRep(curOpt))
state = kShortRepNextStates[state];
else
@@ -1316,14 +1411,14 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
if (curOpt->extra)
{
- prev -= curOpt->extra;
+ prev -= (unsigned)curOpt->extra;
state = kState_RepAfterLit;
if (curOpt->extra == 1)
- state = (dist < LZMA_NUM_REPS) ? kState_RepAfterLit : kState_MatchAfterLit;
+ state = (dist < LZMA_NUM_REPS ? kState_RepAfterLit : kState_MatchAfterLit);
}
else
{
- state = p->opt[prev].state;
+ state = (unsigned)p->opt[prev].state;
if (dist < LZMA_NUM_REPS)
state = kRepNextStates[state];
else
@@ -1379,7 +1474,6 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
curByte = *data;
matchByte = *(data - reps[0]);
- position++;
posState = (position & p->pbMask);
/*
@@ -1391,13 +1485,25 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
< MATCH [ : LIT : REP_0 ]
*/
- curPrice = curOpt->price;
- litPrice = curPrice + GET_PRICE_0(p->isMatch[state][posState]);
+ {
+ UInt32 curPrice = curOpt->price;
+ unsigned prob = p->isMatch[state][posState];
+ matchPrice = curPrice + GET_PRICE_1(prob);
+ litPrice = curPrice + GET_PRICE_0(prob);
+ }
nextOpt = &p->opt[(size_t)cur + 1];
nextIsLit = False;
- // if (litPrice >= nextOpt->price) litPrice = 0; else // 18.new
+ // here we can allow skip_items in p->opt, if we don't check (nextOpt->price < kInfinityPrice)
+ // 18.new.06
+ if ((nextOpt->price < kInfinityPrice
+ // && !IsLitState(state)
+ && matchByte == curByte)
+ || litPrice > nextOpt->price
+ )
+ litPrice = 0;
+ else
{
const CLzmaProb *probs = LIT_PROBS(position, *(data - 1));
litPrice += (!IsLitState(state) ?
@@ -1413,21 +1519,32 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
}
}
- matchPrice = curPrice + GET_PRICE_1(p->isMatch[state][posState]);
repMatchPrice = matchPrice + GET_PRICE_1(p->isRep[state]);
+ numAvailFull = p->numAvail;
+ {
+ unsigned temp = kNumOpts - 1 - cur;
+ if (numAvailFull > temp)
+ numAvailFull = (UInt32)temp;
+ }
+
+ // 18.06
// ---------- SHORT_REP ----------
- // if (IsLitState(state)) // 18.new
+ if (IsLitState(state)) // 18.new
if (matchByte == curByte)
- // if (repMatchPrice < nextOpt->price) // 18.new
- if (nextOpt->len < 2
+ if (repMatchPrice < nextOpt->price) // 18.new
+ // if (numAvailFull < 2 || data[1] != *(data - reps[0] + 1))
+ if (
+ // nextOpt->price >= kInfinityPrice ||
+ nextOpt->len < 2 // we can check nextOpt->len, if skip items are not allowed in p->opt
|| (nextOpt->dist != 0
- && nextOpt->extra <= 1 // 17.old
- ))
+ // && nextOpt->extra <= 1 // 17.old
+ )
+ )
{
UInt32 shortRepPrice = repMatchPrice + GetPrice_ShortRep(p, state, posState);
- if (shortRepPrice <= nextOpt->price) // 17.old
- // if (shortRepPrice < nextOpt->price) // 18.new
+ // if (shortRepPrice <= nextOpt->price) // 17.old
+ if (shortRepPrice < nextOpt->price) // 18.new
{
nextOpt->price = shortRepPrice;
nextOpt->len = 1;
@@ -1436,13 +1553,6 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
}
}
- numAvailFull = p->numAvail;
- {
- UInt32 temp = kNumOpts - 1 - cur;
- if (numAvailFull > temp)
- numAvailFull = temp;
- }
-
if (numAvailFull < 2)
continue;
numAvail = (numAvailFull <= p->numFastBytes ? numAvailFull : p->numFastBytes);
@@ -1451,9 +1561,8 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
// ---------- LIT : REP_0 ----------
- if (
- // litPrice != 0 && // 18.new
- !nextIsLit
+ if (!nextIsLit
+ && litPrice != 0 // 18.new
&& matchByte != curByte
&& numAvailFull > 2)
{
@@ -1464,7 +1573,8 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
unsigned limit = p->numFastBytes + 1;
if (limit > numAvailFull)
limit = numAvailFull;
- for (len = 3; len < limit && data[len] == data2[len]; len++);
+ for (len = 3; len < limit && data[len] == data2[len]; len++)
+ {}
{
unsigned state2 = kLiteralNextStates[state];
@@ -1472,8 +1582,9 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
UInt32 price = litPrice + GetPrice_Rep_0(p, state2, posState2);
{
unsigned offset = cur + len;
- while (last < offset)
- p->opt[++last].price = kInfinityPrice;
+
+ if (last < offset)
+ last = offset;
// do
{
@@ -1481,14 +1592,14 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
COptimal *opt;
len--;
// price2 = price + GetPrice_Len_Rep_0(p, len, state2, posState2);
- price2 = price + p->repLenEnc.prices[posState2][len - LZMA_MATCH_LEN_MIN];
+ price2 = price + GET_PRICE_LEN(&p->repLenEnc, posState2, len);
opt = &p->opt[offset];
// offset--;
if (price2 < opt->price)
{
opt->price = price2;
- opt->len = len;
+ opt->len = (UInt32)len;
opt->dist = 0;
opt->extra = 1;
}
@@ -1500,6 +1611,7 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
}
startLen = 2; /* speed optimization */
+
{
// ---------- REP ----------
unsigned repIndex = 0; // 17.old
@@ -1512,24 +1624,28 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
if (data[0] != data2[0] || data[1] != data2[1])
continue;
- for (len = 2; len < numAvail && data[len] == data2[len]; len++);
+ for (len = 2; len < numAvail && data[len] == data2[len]; len++)
+ {}
// if (len < startLen) continue; // 18.new: speed optimization
- while (last < cur + len)
- p->opt[++last].price = kInfinityPrice;
+ {
+ unsigned offset = cur + len;
+ if (last < offset)
+ last = offset;
+ }
{
unsigned len2 = len;
price = repMatchPrice + GetPrice_PureRep(p, repIndex, state, posState);
do
{
- UInt32 price2 = price + p->repLenEnc.prices[posState][(size_t)len2 - 2];
+ UInt32 price2 = price + GET_PRICE_LEN(&p->repLenEnc, posState, len2);
COptimal *opt = &p->opt[cur + len2];
if (price2 < opt->price)
{
opt->price = price2;
- opt->len = len2;
- opt->dist = repIndex;
+ opt->len = (UInt32)len2;
+ opt->dist = (UInt32)repIndex;
opt->extra = 0;
}
}
@@ -1549,15 +1665,14 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
if (limit > numAvailFull)
limit = numAvailFull;
- for (; len2 < limit && data[len2] == data2[len2]; len2++);
-
- len2 -= len;
- if (len2 >= 3)
+ len2 += 2;
+ if (len2 <= limit)
+ if (data[len2 - 2] == data2[len2 - 2])
+ if (data[len2 - 1] == data2[len2 - 1])
{
unsigned state2 = kRepNextStates[state];
unsigned posState2 = (position + len) & p->pbMask;
- price +=
- p->repLenEnc.prices[posState][(size_t)len - 2]
+ price += GET_PRICE_LEN(&p->repLenEnc, posState, len)
+ GET_PRICE_0(p->isMatch[state2][posState2])
+ LitEnc_Matched_GetPrice(LIT_PROBS(position + len, data[(size_t)len - 1]),
data[len], data2[len], p->ProbPrices);
@@ -1568,31 +1683,40 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
price += GetPrice_Rep_0(p, state2, posState2);
+
+ for (; len2 < limit && data[len2] == data2[len2]; len2++)
+ {}
+
+ len2 -= len;
+ // if (len2 >= 3)
+ {
{
unsigned offset = cur + len + len2;
- while (last < offset)
- p->opt[++last].price = kInfinityPrice;
+
+ if (last < offset)
+ last = offset;
// do
{
- unsigned price2;
+ UInt32 price2;
COptimal *opt;
len2--;
// price2 = price + GetPrice_Len_Rep_0(p, len2, state2, posState2);
- price2 = price + p->repLenEnc.prices[posState2][len2 - LZMA_MATCH_LEN_MIN];
+ price2 = price + GET_PRICE_LEN(&p->repLenEnc, posState2, len2);
opt = &p->opt[offset];
// offset--;
if (price2 < opt->price)
{
opt->price = price2;
- opt->len = len2;
+ opt->len = (UInt32)len2;
opt->extra = (CExtra)(len + 1);
- opt->dist = repIndex;
+ opt->dist = (UInt32)repIndex;
}
}
// while (len2 >= 3);
}
}
+ }
}
}
}
@@ -1604,17 +1728,23 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
{
newLen = numAvail;
for (numPairs = 0; newLen > matches[numPairs]; numPairs += 2);
- matches[numPairs] = newLen;
+ matches[numPairs] = (UInt32)newLen;
numPairs += 2;
}
+ // startLen = 2; /* speed optimization */
+
if (newLen >= startLen)
{
UInt32 normalMatchPrice = matchPrice + GET_PRICE_0(p->isRep[state]);
UInt32 dist;
unsigned offs, posSlot, len;
- while (last < cur + newLen)
- p->opt[++last].price = kInfinityPrice;
+
+ {
+ unsigned offset = cur + newLen;
+ if (last < offset)
+ last = offset;
+ }
offs = 0;
while (startLen > matches[offs])
@@ -1626,27 +1756,29 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
for (len = /*2*/ startLen; ; len++)
{
- UInt32 price = normalMatchPrice + p->lenEnc.prices[posState][(size_t)len - LZMA_MATCH_LEN_MIN];
+ UInt32 price = normalMatchPrice + GET_PRICE_LEN(&p->lenEnc, posState, len);
{
COptimal *opt;
- unsigned lenToPosState = len - 2; lenToPosState = GetLenToPosState2(lenToPosState);
+ unsigned lenNorm = len - 2;
+ lenNorm = GetLenToPosState2(lenNorm);
if (dist < kNumFullDistances)
- price += p->distancesPrices[lenToPosState][dist & (kNumFullDistances - 1)];
+ price += p->distancesPrices[lenNorm][dist & (kNumFullDistances - 1)];
else
- price += p->posSlotPrices[lenToPosState][posSlot] + p->alignPrices[dist & kAlignMask];
+ price += p->posSlotPrices[lenNorm][posSlot] + p->alignPrices[dist & kAlignMask];
opt = &p->opt[cur + len];
if (price < opt->price)
{
opt->price = price;
- opt->len = len;
+ opt->len = (UInt32)len;
opt->dist = dist + LZMA_NUM_REPS;
opt->extra = 0;
}
}
- if (/*_maxMode && */ len == matches[offs])
+ if (len == matches[offs])
{
+ // if (p->_maxMode) {
// MATCH : LIT : REP_0
const Byte *data2 = data - dist - 1;
@@ -1655,11 +1787,17 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
if (limit > numAvailFull)
limit = numAvailFull;
- for (; len2 < limit && data[len2] == data2[len2]; len2++);
+ len2 += 2;
+ if (len2 <= limit)
+ if (data[len2 - 2] == data2[len2 - 2])
+ if (data[len2 - 1] == data2[len2 - 1])
+ {
+ for (; len2 < limit && data[len2] == data2[len2]; len2++)
+ {}
len2 -= len;
- if (len2 >= 3)
+ // if (len2 >= 3)
{
unsigned state2 = kMatchNextStates[state];
unsigned posState2 = (position + len) & p->pbMask;
@@ -1675,27 +1813,30 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
price += GetPrice_Rep_0(p, state2, posState2);
offset = cur + len + len2;
- while (last < offset)
- p->opt[++last].price = kInfinityPrice;
+
+ if (last < offset)
+ last = offset;
// do
{
UInt32 price2;
COptimal *opt;
len2--;
// price2 = price + GetPrice_Len_Rep_0(p, len2, state2, posState2);
- price2 = price + p->repLenEnc.prices[posState2][len2 - LZMA_MATCH_LEN_MIN];
+ price2 = price + GET_PRICE_LEN(&p->repLenEnc, posState2, len2);
opt = &p->opt[offset];
// offset--;
if (price2 < opt->price)
{
opt->price = price2;
- opt->len = len2;
+ opt->len = (UInt32)len2;
opt->extra = (CExtra)(len + 1);
opt->dist = dist + LZMA_NUM_REPS;
}
}
// while (len2 >= 3);
}
+
+ }
offs += 2;
if (offs == numPairs)
@@ -1707,6 +1848,12 @@ static unsigned GetOptimum(CLzmaEnc *p, UInt32 position)
}
}
}
+
+ do
+ p->opt[last].price = kInfinityPrice;
+ while (--last);
+
+ return Backward(p, cur);
}
@@ -1733,6 +1880,7 @@ static unsigned GetOptimumFast(CLzmaEnc *p)
p->backRes = MARK_LIT;
if (numAvail < 2)
return 1;
+ // if (mainLen < 2 && p->state == 0) return 1; // 18.06.notused
if (numAvail > LZMA_MATCH_LEN_MAX)
numAvail = LZMA_MATCH_LEN_MAX;
data = p->matchFinder.GetPointerToCurrentPos(p->matchFinderObj) - 1;
@@ -1744,10 +1892,11 @@ static unsigned GetOptimumFast(CLzmaEnc *p)
const Byte *data2 = data - p->reps[i];
if (data[0] != data2[0] || data[1] != data2[1])
continue;
- for (len = 2; len < numAvail && data[len] == data2[len]; len++);
+ for (len = 2; len < numAvail && data[len] == data2[len]; len++)
+ {}
if (len >= p->numFastBytes)
{
- p->backRes = i;
+ p->backRes = (UInt32)i;
MOVE_POS(p, len - 1)
return len;
}
@@ -1791,7 +1940,7 @@ static unsigned GetOptimumFast(CLzmaEnc *p)
|| (repLen + 2 >= mainLen && mainDist >= (1 << 9))
|| (repLen + 3 >= mainLen && mainDist >= (1 << 15)))
{
- p->backRes = repIndex;
+ p->backRes = (UInt32)repIndex;
MOVE_POS(p, repLen - 1)
return repLen;
}
@@ -1930,23 +2079,22 @@ MY_NO_INLINE static SRes Flush(CLzmaEnc *p, UInt32 nowPos)
}
-
-static void FillAlignPrices(CLzmaEnc *p)
+MY_NO_INLINE static void FillAlignPrices(CLzmaEnc *p)
{
unsigned i;
const CProbPrice *ProbPrices = p->ProbPrices;
const CLzmaProb *probs = p->posAlignEncoder;
- p->alignPriceCount = 0;
+ // p->alignPriceCount = 0;
for (i = 0; i < kAlignTableSize / 2; i++)
{
UInt32 price = 0;
- unsigned symbol = i;
+ unsigned sym = i;
unsigned m = 1;
unsigned bit;
UInt32 prob;
- bit = symbol & 1; symbol >>= 1; price += GET_PRICEa(probs[m], bit); m = (m << 1) + bit;
- bit = symbol & 1; symbol >>= 1; price += GET_PRICEa(probs[m], bit); m = (m << 1) + bit;
- bit = symbol & 1; symbol >>= 1; price += GET_PRICEa(probs[m], bit); m = (m << 1) + bit;
+ bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[m], bit); m = (m << 1) + bit;
+ bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[m], bit); m = (m << 1) + bit;
+ bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[m], bit); m = (m << 1) + bit;
prob = probs[m];
p->alignPrices[i ] = price + GET_PRICEa_0(prob);
p->alignPrices[i + 8] = price + GET_PRICEa_1(prob);
@@ -1955,78 +2103,97 @@ static void FillAlignPrices(CLzmaEnc *p)
}
-static void FillDistancesPrices(CLzmaEnc *p)
+MY_NO_INLINE static void FillDistancesPrices(CLzmaEnc *p)
{
+ // int y; for (y = 0; y < 100; y++) {
+
UInt32 tempPrices[kNumFullDistances];
- unsigned i, lenToPosState;
+ unsigned i, lps;
const CProbPrice *ProbPrices = p->ProbPrices;
p->matchPriceCount = 0;
- for (i = kStartPosModelIndex; i < kNumFullDistances; i++)
+ for (i = kStartPosModelIndex / 2; i < kNumFullDistances / 2; i++)
{
unsigned posSlot = GetPosSlot1(i);
- unsigned footerBits = ((posSlot >> 1) - 1);
+ unsigned footerBits = (posSlot >> 1) - 1;
unsigned base = ((2 | (posSlot & 1)) << footerBits);
+ const CLzmaProb *probs = p->posEncoders + (size_t)base * 2;
// tempPrices[i] = RcTree_ReverseGetPrice(p->posEncoders + base, footerBits, i - base, p->ProbPrices);
-
- const CLzmaProb *probs = p->posEncoders + base;
UInt32 price = 0;
unsigned m = 1;
- unsigned symbol = i - base;
+ unsigned sym = i;
+ unsigned offset = (unsigned)1 << footerBits;
+ base += i;
+
+ if (footerBits)
do
{
- unsigned bit = symbol & 1;
- symbol >>= 1;
+ unsigned bit = sym & 1;
+ sym >>= 1;
price += GET_PRICEa(probs[m], bit);
m = (m << 1) + bit;
}
while (--footerBits);
- tempPrices[i] = price;
+
+ {
+ unsigned prob = probs[m];
+ tempPrices[base ] = price + GET_PRICEa_0(prob);
+ tempPrices[base + offset] = price + GET_PRICEa_1(prob);
+ }
}
- for (lenToPosState = 0; lenToPosState < kNumLenToPosStates; lenToPosState++)
+ for (lps = 0; lps < kNumLenToPosStates; lps++)
{
- unsigned posSlot;
- const CLzmaProb *encoder = p->posSlotEncoder[lenToPosState];
- UInt32 *posSlotPrices = p->posSlotPrices[lenToPosState];
- unsigned distTableSize = p->distTableSize;
- const CLzmaProb *probs = encoder;
- for (posSlot = 0; posSlot < distTableSize; posSlot += 2)
+ unsigned slot;
+ unsigned distTableSize2 = (p->distTableSize + 1) >> 1;
+ UInt32 *posSlotPrices = p->posSlotPrices[lps];
+ const CLzmaProb *probs = p->posSlotEncoder[lps];
+
+ for (slot = 0; slot < distTableSize2; slot++)
{
- // posSlotPrices[posSlot] = RcTree_GetPrice(encoder, kNumPosSlotBits, posSlot, p->ProbPrices);
- UInt32 price = 0;
+ // posSlotPrices[slot] = RcTree_GetPrice(encoder, kNumPosSlotBits, slot, p->ProbPrices);
+ UInt32 price;
unsigned bit;
- unsigned symbol = (posSlot >> 1) + (1 << (kNumPosSlotBits - 1));
- UInt32 prob;
- bit = symbol & 1; symbol >>= 1; price += GET_PRICEa(probs[symbol], bit);
- bit = symbol & 1; symbol >>= 1; price += GET_PRICEa(probs[symbol], bit);
- bit = symbol & 1; symbol >>= 1; price += GET_PRICEa(probs[symbol], bit);
- bit = symbol & 1; symbol >>= 1; price += GET_PRICEa(probs[symbol], bit);
- bit = symbol & 1; symbol >>= 1; price += GET_PRICEa(probs[symbol], bit);
- prob = probs[(posSlot >> 1) + (1 << (kNumPosSlotBits - 1))];
- posSlotPrices[posSlot ] = price + GET_PRICEa_0(prob);
- posSlotPrices[posSlot + 1] = price + GET_PRICEa_1(prob);
+ unsigned sym = slot + (1 << (kNumPosSlotBits - 1));
+ unsigned prob;
+ bit = sym & 1; sym >>= 1; price = GET_PRICEa(probs[sym], bit);
+ bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[sym], bit);
+ bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[sym], bit);
+ bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[sym], bit);
+ bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[sym], bit);
+ prob = probs[(size_t)slot + (1 << (kNumPosSlotBits - 1))];
+ posSlotPrices[(size_t)slot * 2 ] = price + GET_PRICEa_0(prob);
+ posSlotPrices[(size_t)slot * 2 + 1] = price + GET_PRICEa_1(prob);
+ }
+
+ {
+ UInt32 delta = ((UInt32)((kEndPosModelIndex / 2 - 1) - kNumAlignBits) << kNumBitPriceShiftBits);
+ for (slot = kEndPosModelIndex / 2; slot < distTableSize2; slot++)
+ {
+ posSlotPrices[(size_t)slot * 2 ] += delta;
+ posSlotPrices[(size_t)slot * 2 + 1] += delta;
+ delta += ((UInt32)1 << kNumBitPriceShiftBits);
+ }
}
- for (posSlot = kEndPosModelIndex; posSlot < distTableSize; posSlot++)
- posSlotPrices[posSlot] += ((UInt32)(((posSlot >> 1) - 1) - kNumAlignBits) << kNumBitPriceShiftBits);
{
- UInt32 *distancesPrices = p->distancesPrices[lenToPosState];
- {
- distancesPrices[0] = posSlotPrices[0];
- distancesPrices[1] = posSlotPrices[1];
- distancesPrices[2] = posSlotPrices[2];
- distancesPrices[3] = posSlotPrices[3];
- }
+ UInt32 *dp = p->distancesPrices[lps];
+
+ dp[0] = posSlotPrices[0];
+ dp[1] = posSlotPrices[1];
+ dp[2] = posSlotPrices[2];
+ dp[3] = posSlotPrices[3];
+
for (i = 4; i < kNumFullDistances; i += 2)
{
UInt32 slotPrice = posSlotPrices[GetPosSlot1(i)];
- distancesPrices[i ] = slotPrice + tempPrices[i];
- distancesPrices[i + 1] = slotPrice + tempPrices[i + 1];
+ dp[i ] = slotPrice + tempPrices[i];
+ dp[i + 1] = slotPrice + tempPrices[i + 1];
}
}
}
+ // }
}
@@ -2243,10 +2410,7 @@ static SRes LzmaEnc_CodeOneBlock(CLzmaEnc *p, UInt32 maxPackSize, UInt32 maxUnpa
if (len != 1)
{
LenEnc_Encode(&p->repLenProbs, &p->rc, len - LZMA_MATCH_LEN_MIN, posState);
- if (!p->fastMode)
- if (--p->repLenEnc.counters[posState] == 0)
- LenPriceEnc_UpdateTable(&p->repLenEnc, posState, &p->repLenProbs, p->ProbPrices);
-
+ --p->repLenEncCounter;
p->state = kRepNextStates[p->state];
}
}
@@ -2258,9 +2422,7 @@ static SRes LzmaEnc_CodeOneBlock(CLzmaEnc *p, UInt32 maxPackSize, UInt32 maxUnpa
p->state = kMatchNextStates[p->state];
LenEnc_Encode(&p->lenProbs, &p->rc, len - LZMA_MATCH_LEN_MIN, posState);
- if (!p->fastMode)
- if (--p->lenEnc.counters[posState] == 0)
- LenPriceEnc_UpdateTable(&p->lenEnc, posState, &p->lenProbs, p->ProbPrices);
+ // --p->lenEnc.counter;
dist -= LZMA_NUM_REPS;
p->reps[3] = p->reps[2];
@@ -2272,17 +2434,17 @@ static SRes LzmaEnc_CodeOneBlock(CLzmaEnc *p, UInt32 maxPackSize, UInt32 maxUnpa
GetPosSlot(dist, posSlot);
// RcTree_Encode_PosSlot(&p->rc, p->posSlotEncoder[GetLenToPosState(len)], posSlot);
{
- UInt32 symbol = posSlot + (1 << kNumPosSlotBits);
+ UInt32 sym = (UInt32)posSlot + (1 << kNumPosSlotBits);
range = p->rc.range;
probs = p->posSlotEncoder[GetLenToPosState(len)];
do
{
- CLzmaProb *prob = probs + (symbol >> kNumPosSlotBits);
- UInt32 bit = (symbol >> (kNumPosSlotBits - 1)) & 1;
- symbol <<= 1;
+ CLzmaProb *prob = probs + (sym >> kNumPosSlotBits);
+ UInt32 bit = (sym >> (kNumPosSlotBits - 1)) & 1;
+ sym <<= 1;
RC_BIT(&p->rc, prob, bit);
}
- while (symbol < (1 << kNumPosSlotBits * 2));
+ while (sym < (1 << kNumPosSlotBits * 2));
p->rc.range = range;
}
@@ -2293,7 +2455,7 @@ static SRes LzmaEnc_CodeOneBlock(CLzmaEnc *p, UInt32 maxPackSize, UInt32 maxUnpa
if (dist < kNumFullDistances)
{
unsigned base = ((2 | (posSlot & 1)) << footerBits);
- RcTree_ReverseEncode(&p->rc, p->posEncoders + base, footerBits, dist - base);
+ RcTree_ReverseEncode(&p->rc, p->posEncoders + base, footerBits, (unsigned)(dist /* - base */));
}
else
{
@@ -2329,14 +2491,14 @@ static SRes LzmaEnc_CodeOneBlock(CLzmaEnc *p, UInt32 maxPackSize, UInt32 maxUnpa
bit = dist & 1; dist >>= 1; RC_BIT(&p->rc, p->posAlignEncoder + m, bit); m = (m << 1) + bit;
bit = dist & 1; RC_BIT(&p->rc, p->posAlignEncoder + m, bit);
p->rc.range = range;
- p->alignPriceCount++;
+ // p->alignPriceCount++;
}
}
}
}
}
- nowPos32 += len;
+ nowPos32 += (UInt32)len;
p->additionalOffset -= len;
if (p->additionalOffset == 0)
@@ -2345,10 +2507,27 @@ static SRes LzmaEnc_CodeOneBlock(CLzmaEnc *p, UInt32 maxPackSize, UInt32 maxUnpa
if (!p->fastMode)
{
- if (p->matchPriceCount >= (1 << 7))
- FillDistancesPrices(p);
- if (p->alignPriceCount >= kAlignTableSize)
+ /*
+ if (p->alignPriceCount >= 16) // kAlignTableSize
FillAlignPrices(p);
+ if (p->matchPriceCount >= 128)
+ FillDistancesPrices(p);
+ if (p->lenEnc.counter <= 0)
+ LenPriceEnc_UpdateTables(&p->lenEnc, 1 << p->pb, &p->lenProbs, p->ProbPrices);
+ */
+ if (p->matchPriceCount >= 64)
+ {
+ FillAlignPrices(p);
+ // { int y; for (y = 0; y < 100; y++) {
+ FillDistancesPrices(p);
+ // }}
+ LenPriceEnc_UpdateTables(&p->lenEnc, 1 << p->pb, &p->lenProbs, p->ProbPrices);
+ }
+ if (p->repLenEncCounter <= 0)
+ {
+ p->repLenEncCounter = REP_LEN_COUNT;
+ LenPriceEnc_UpdateTables(&p->repLenEnc, 1 << p->pb, &p->repLenProbs, p->ProbPrices);
+ }
}
if (p->matchFinder.GetNumAvailableBytes(p->matchFinderObj) == 0)
@@ -2488,12 +2667,19 @@ void LzmaEnc_Init(CLzmaEnc *p)
p->optEnd = 0;
p->optCur = 0;
+
+ {
+ for (i = 0; i < kNumOpts; i++)
+ p->opt[i].price = kInfinityPrice;
+ }
+
p->additionalOffset = 0;
p->pbMask = (1 << p->pb) - 1;
p->lpMask = ((UInt32)0x100 << p->lp) - ((unsigned)0x100 >> p->lc);
}
+
void LzmaEnc_InitPrices(CLzmaEnc *p)
{
if (!p->fastMode)
@@ -2505,6 +2691,9 @@ void LzmaEnc_InitPrices(CLzmaEnc *p)
p->lenEnc.tableSize =
p->repLenEnc.tableSize =
p->numFastBytes + 1 - LZMA_MATCH_LEN_MIN;
+
+ p->repLenEncCounter = REP_LEN_COUNT;
+
LenPriceEnc_UpdateTables(&p->lenEnc, 1 << p->pb, &p->lenProbs, p->ProbPrices);
LenPriceEnc_UpdateTables(&p->repLenEnc, 1 << p->pb, &p->repLenProbs, p->ProbPrices);
}
@@ -2581,7 +2770,7 @@ typedef struct
ISeqOutStream vt;
Byte *data;
SizeT rem;
- Bool overflow;
+ BoolInt overflow;
} CLzmaEnc_SeqOutStreamBuf;
static size_t SeqOutStreamBuf_Write(const ISeqOutStream *pp, const void *data, size_t size)
@@ -2613,7 +2802,7 @@ const Byte *LzmaEnc_GetCurBuf(CLzmaEncHandle pp)
}
-SRes LzmaEnc_CodeOneMemBlock(CLzmaEncHandle pp, Bool reInit,
+SRes LzmaEnc_CodeOneMemBlock(CLzmaEncHandle pp, BoolInt reInit,
Byte *dest, size_t *destLen, UInt32 desiredPackSize, UInt32 *unpackSize)
{
CLzmaEnc *p = (CLzmaEnc *)pp;
diff --git a/deps/LZMA-SDK/C/MtCoder.c b/deps/LZMA-SDK/C/MtCoder.c
index ddc7c0285..5667f2d5b 100644
--- a/deps/LZMA-SDK/C/MtCoder.c
+++ b/deps/LZMA-SDK/C/MtCoder.c
@@ -1,5 +1,5 @@
/* MtCoder.c -- Multi-thread Coder
-2018-02-21 : Igor Pavlov : Public domain */
+2018-07-04 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -119,7 +119,7 @@ static SRes ThreadFunc2(CMtCoderThread *t)
unsigned bi;
SRes res;
SRes res2;
- Bool finished;
+ BoolInt finished;
unsigned bufIndex;
size_t size;
const Byte *inData;
@@ -294,7 +294,7 @@ static SRes ThreadFunc2(CMtCoderThread *t)
if (++wi >= mtc->numBlocksMax)
wi = 0;
{
- Bool isReady;
+ BoolInt isReady;
CriticalSection_Enter(&mtc->cs);
@@ -547,7 +547,7 @@ SRes MtCoder_Code(CMtCoder *p)
{
const CMtCoderBlock *block = &p->blocks[bi];
unsigned bufIndex = block->bufIndex;
- Bool finished = block->finished;
+ BoolInt finished = block->finished;
if (res == SZ_OK && block->res != SZ_OK)
res = block->res;
diff --git a/deps/LZMA-SDK/C/MtCoder.h b/deps/LZMA-SDK/C/MtCoder.h
index 7982e847c..603329d36 100644
--- a/deps/LZMA-SDK/C/MtCoder.h
+++ b/deps/LZMA-SDK/C/MtCoder.h
@@ -1,5 +1,5 @@
/* MtCoder.h -- Multi-thread Coder
-2018-02-21 : Igor Pavlov : Public domain */
+2018-07-04 : Igor Pavlov : Public domain */
#ifndef __MT_CODER_H
#define __MT_CODER_H
@@ -67,7 +67,7 @@ typedef struct
{
SRes res;
unsigned bufIndex;
- Bool finished;
+ BoolInt finished;
} CMtCoderBlock;
@@ -97,7 +97,7 @@ typedef struct _CMtCoder
CAutoResetEvent readEvent;
CSemaphore blocksSemaphore;
- Bool stopReading;
+ BoolInt stopReading;
SRes readRes;
#ifdef MTCODER__USE_WRITE_THREAD
diff --git a/deps/LZMA-SDK/C/MtDec.c b/deps/LZMA-SDK/C/MtDec.c
index 60d31b07c..25a8b046d 100644
--- a/deps/LZMA-SDK/C/MtDec.c
+++ b/deps/LZMA-SDK/C/MtDec.c
@@ -1,5 +1,5 @@
/* MtDec.c -- Multi-thread Decoder
-2018-03-02 : Igor Pavlov : Public domain */
+2019-02-02 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -88,12 +88,13 @@ static WRes ArEvent_OptCreate_And_Reset(CEvent *p)
}
-
-typedef struct
+struct __CMtDecBufLink
{
- void *next;
+ struct __CMtDecBufLink *next;
void *pad[3];
-} CMtDecBufLink;
+};
+
+typedef struct __CMtDecBufLink CMtDecBufLink;
#define MTDEC__LINK_DATA_OFFSET sizeof(CMtDecBufLink)
#define MTDEC__DATA_PTR_FROM_LINK(link) ((Byte *)(link) + MTDEC__LINK_DATA_OFFSET)
@@ -197,7 +198,7 @@ static SRes FullRead(ISeqInStream *stream, Byte *data, size_t *processedSize)
}
-static SRes MtDec_GetError_Spec(CMtDec *p, UInt64 interruptIndex, Bool *wasInterrupted)
+static SRes MtDec_GetError_Spec(CMtDec *p, UInt64 interruptIndex, BoolInt *wasInterrupted)
{
SRes res;
CriticalSection_Enter(&p->mtProgress.cs);
@@ -207,7 +208,7 @@ static SRes MtDec_GetError_Spec(CMtDec *p, UInt64 interruptIndex, Bool *wasInter
return res;
}
-static SRes MtDec_Progress_GetError_Spec(CMtDec *p, UInt64 inSize, UInt64 outSize, UInt64 interruptIndex, Bool *wasInterrupted)
+static SRes MtDec_Progress_GetError_Spec(CMtDec *p, UInt64 inSize, UInt64 outSize, UInt64 interruptIndex, BoolInt *wasInterrupted)
{
SRes res;
CriticalSection_Enter(&p->mtProgress.cs);
@@ -271,9 +272,9 @@ static WRes ThreadFunc2(CMtDecThread *t)
for (;;)
{
SRes res, codeRes;
- Bool wasInterrupted, isAllocError, overflow, finish;
+ BoolInt wasInterrupted, isAllocError, overflow, finish;
SRes threadingErrorSRes;
- Bool needCode, needWrite, needContinue;
+ BoolInt needCode, needWrite, needContinue;
size_t inDataSize_Start;
UInt64 inDataSize;
@@ -289,7 +290,7 @@ static WRes ThreadFunc2(CMtDecThread *t)
Byte *afterEndData = NULL;
size_t afterEndData_Size = 0;
- Bool canCreateNewThread = False;
+ BoolInt canCreateNewThread = False;
// CMtDecCallbackInfo parse;
CMtDecThread *nextThread;
@@ -629,7 +630,7 @@ static WRes ThreadFunc2(CMtDecThread *t)
if (res == SZ_OK && needCode && codeRes == SZ_OK)
{
- Bool isStartBlock = True;
+ BoolInt isStartBlock = True;
CMtDecBufLink *link = (CMtDecBufLink *)t->inBuf;
for (;;)
@@ -691,9 +692,9 @@ static WRes ThreadFunc2(CMtDecThread *t)
RINOK_THREAD(Event_Wait(&t->canWrite));
{
- Bool isErrorMode = False;
- Bool canRecode = True;
- Bool needWriteToStream = needWrite;
+ BoolInt isErrorMode = False;
+ BoolInt canRecode = True;
+ BoolInt needWriteToStream = needWrite;
if (p->exitThread) return 0; // it's never executed in normal cases
diff --git a/deps/LZMA-SDK/C/MtDec.h b/deps/LZMA-SDK/C/MtDec.h
index b445bc9d0..9864cc874 100644
--- a/deps/LZMA-SDK/C/MtDec.h
+++ b/deps/LZMA-SDK/C/MtDec.h
@@ -1,5 +1,5 @@
/* MtDec.h -- Multi-thread Decoder
-2018-03-02 : Igor Pavlov : Public domain */
+2018-07-04 : Igor Pavlov : Public domain */
#ifndef __MT_DEC_H
#define __MT_DEC_H
@@ -76,7 +76,7 @@ typedef struct
// out
EMtDecParseState state;
- Bool canCreateNewThread;
+ BoolInt canCreateNewThread;
UInt64 outPos; // check it (size_t)
} CMtDecCallbackInfo;
@@ -107,11 +107,11 @@ typedef struct
if (*canRecode), we didn't flush current block data, so we still can decode current block later.
*/
SRes (*Write)(void *p, unsigned coderIndex,
- Bool needWriteToStream,
+ BoolInt needWriteToStream,
const Byte *src, size_t srcSize,
// int srcFinished,
- Bool *needContinue,
- Bool *canRecode);
+ BoolInt *needContinue,
+ BoolInt *canRecode);
} IMtDecCallback;
@@ -140,22 +140,22 @@ typedef struct _CMtDec
size_t allocatedBufsSize;
- Bool exitThread;
+ BoolInt exitThread;
WRes exitThreadWRes;
UInt64 blockIndex;
- Bool isAllocError;
- Bool overflow;
+ BoolInt isAllocError;
+ BoolInt overflow;
SRes threadingErrorSRes;
- Bool needContinue;
+ BoolInt needContinue;
// CAutoResetEvent finishedEvent;
SRes readRes;
SRes codeRes;
- Bool wasInterrupted;
+ BoolInt wasInterrupted;
unsigned numStartedThreads_Limit;
unsigned numStartedThreads;
@@ -164,14 +164,14 @@ typedef struct _CMtDec
size_t crossStart;
size_t crossEnd;
UInt64 readProcessed;
- Bool readWasFinished;
+ BoolInt readWasFinished;
UInt64 inProcessed;
unsigned filledThreadStart;
unsigned numFilledThreads;
#ifndef _7ZIP_ST
- Bool needInterrupt;
+ BoolInt needInterrupt;
UInt64 interruptIndex;
CMtProgress mtProgress;
CMtDecThread threads[MTDEC__THREADS_MAX];
diff --git a/deps/LZMA-SDK/C/Ppmd7.c b/deps/LZMA-SDK/C/Ppmd7.c
index ef93cb2d4..80e7de9a6 100644
--- a/deps/LZMA-SDK/C/Ppmd7.c
+++ b/deps/LZMA-SDK/C/Ppmd7.c
@@ -1,5 +1,5 @@
/* Ppmd7.c -- PPMdH codec
-2017-04-03 : Igor Pavlov : Public domain
+2018-07-04 : Igor Pavlov : Public domain
This code is based on PPMd var.H (2001): Dmitry Shkarin : Public domain */
#include "Precomp.h"
@@ -95,7 +95,7 @@ void Ppmd7_Free(CPpmd7 *p, ISzAllocPtr alloc)
p->Base = 0;
}
-Bool Ppmd7_Alloc(CPpmd7 *p, UInt32 size, ISzAllocPtr alloc)
+BoolInt Ppmd7_Alloc(CPpmd7 *p, UInt32 size, ISzAllocPtr alloc)
{
if (!p->Base || p->Size != size)
{
@@ -342,7 +342,7 @@ void Ppmd7_Init(CPpmd7 *p, unsigned maxOrder)
p->DummySee.Count = 64; /* unused */
}
-static CTX_PTR CreateSuccessors(CPpmd7 *p, Bool skip)
+static CTX_PTR CreateSuccessors(CPpmd7 *p, BoolInt skip)
{
CPpmd_State upState;
CTX_PTR c = p->MinContext;
diff --git a/deps/LZMA-SDK/C/Ppmd7.h b/deps/LZMA-SDK/C/Ppmd7.h
index ee2c035d0..cce93f120 100644
--- a/deps/LZMA-SDK/C/Ppmd7.h
+++ b/deps/LZMA-SDK/C/Ppmd7.h
@@ -1,5 +1,5 @@
/* Ppmd7.h -- PPMdH compression codec
-2017-04-03 : Igor Pavlov : Public domain
+2018-07-04 : Igor Pavlov : Public domain
This code is based on PPMd var.H (2001): Dmitry Shkarin : Public domain */
/* This code supports virtual RangeDecoder and includes the implementation
@@ -60,7 +60,7 @@ typedef struct
} CPpmd7;
void Ppmd7_Construct(CPpmd7 *p);
-Bool Ppmd7_Alloc(CPpmd7 *p, UInt32 size, ISzAllocPtr alloc);
+BoolInt Ppmd7_Alloc(CPpmd7 *p, UInt32 size, ISzAllocPtr alloc);
void Ppmd7_Free(CPpmd7 *p, ISzAllocPtr alloc);
void Ppmd7_Init(CPpmd7 *p, unsigned maxOrder);
#define Ppmd7_WasAllocated(p) ((p)->Base != NULL)
@@ -115,7 +115,7 @@ typedef struct
} CPpmd7z_RangeDec;
void Ppmd7z_RangeDec_CreateVTable(CPpmd7z_RangeDec *p);
-Bool Ppmd7z_RangeDec_Init(CPpmd7z_RangeDec *p);
+BoolInt Ppmd7z_RangeDec_Init(CPpmd7z_RangeDec *p);
#define Ppmd7z_RangeDec_IsFinishedOK(p) ((p)->Code == 0)
int Ppmd7_DecodeSymbol(CPpmd7 *p, const IPpmd7_RangeDec *rc);
diff --git a/deps/LZMA-SDK/C/Ppmd7Dec.c b/deps/LZMA-SDK/C/Ppmd7Dec.c
index 3023b6776..202640710 100644
--- a/deps/LZMA-SDK/C/Ppmd7Dec.c
+++ b/deps/LZMA-SDK/C/Ppmd7Dec.c
@@ -1,5 +1,5 @@
/* Ppmd7Dec.c -- PPMdH Decoder
-2017-04-03 : Igor Pavlov : Public domain
+2018-07-04 : Igor Pavlov : Public domain
This code is based on PPMd var.H (2001): Dmitry Shkarin : Public domain */
#include "Precomp.h"
@@ -8,7 +8,7 @@ This code is based on PPMd var.H (2001): Dmitry Shkarin : Public domain */
#define kTopValue (1 << 24)
-Bool Ppmd7z_RangeDec_Init(CPpmd7z_RangeDec *p)
+BoolInt Ppmd7z_RangeDec_Init(CPpmd7z_RangeDec *p)
{
unsigned i;
p->Code = 0;
diff --git a/deps/LZMA-SDK/C/Util/7z/7zMain.c b/deps/LZMA-SDK/C/Util/7z/7zMain.c
index 82aac89eb..1c02b48ec 100644
--- a/deps/LZMA-SDK/C/Util/7z/7zMain.c
+++ b/deps/LZMA-SDK/C/Util/7z/7zMain.c
@@ -1,5 +1,5 @@
/* 7zMain.c - Test application for 7z Decoder
-2018-04-19 : Igor Pavlov : Public domain */
+2019-02-02 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -176,7 +176,7 @@ static SRes Utf16_To_Char(CBuf *buf, const UInt16 *s
char defaultChar = '_';
BOOL defUsed;
unsigned numChars = 0;
- numChars = WideCharToMultiByte(codePage, 0, s, len, (char *)buf->data, size, &defaultChar, &defUsed);
+ numChars = WideCharToMultiByte(codePage, 0, (LPCWSTR)s, len, (char *)buf->data, size, &defaultChar, &defUsed);
if (numChars == 0 || numChars >= size)
return SZ_ERROR_FAIL;
buf->data[numChars] = 0;
@@ -202,7 +202,7 @@ static WRes MyCreateDir(const UInt16 *name)
{
#ifdef USE_WINDOWS_FILE
- return CreateDirectoryW(name, NULL) ? 0 : GetLastError();
+ return CreateDirectoryW((LPCWSTR)name, NULL) ? 0 : GetLastError();
#else
@@ -227,7 +227,7 @@ static WRes MyCreateDir(const UInt16 *name)
static WRes OutFile_OpenUtf16(CSzFile *p, const UInt16 *name)
{
#ifdef USE_WINDOWS_FILE
- return OutFile_OpenW(p, name);
+ return OutFile_OpenW(p, (LPCWSTR)name);
#else
CBuf buf;
WRes res;
@@ -354,7 +354,7 @@ static void PrintError(char *s)
PrintLF();
}
-static void GetAttribString(UInt32 wa, Bool isDir, char *s)
+static void GetAttribString(UInt32 wa, BoolInt isDir, char *s)
{
#ifdef USE_WINDOWS_FILE
s[0] = (char)(((wa & FILE_ATTRIBUTE_DIRECTORY) != 0 || isDir) ? 'D' : '.');
@@ -430,7 +430,7 @@ int MY_CDECL main(int numargs, char *args[])
res = SZ_OK;
{
- lookStream.buf = ISzAlloc_Alloc(&allocImp, kInputBufSize);
+ lookStream.buf = (Byte *)ISzAlloc_Alloc(&allocImp, kInputBufSize);
if (!lookStream.buf)
res = SZ_ERROR_MEM;
else
@@ -647,7 +647,7 @@ int MY_CDECL main(int numargs, char *args[])
We remove posix bits, if we detect posix mode field */
if ((attrib & 0xF0000000) != 0)
attrib &= 0x7FFF;
- SetFileAttributesW(destPath, attrib);
+ SetFileAttributesW((LPCWSTR)destPath, attrib);
}
#endif
}
diff --git a/deps/LZMA-SDK/C/Util/Lzma/LzmaUtil.c b/deps/LZMA-SDK/C/Util/Lzma/LzmaUtil.c
index cf88c7778..82130e85d 100644
--- a/deps/LZMA-SDK/C/Util/Lzma/LzmaUtil.c
+++ b/deps/LZMA-SDK/C/Util/Lzma/LzmaUtil.c
@@ -1,5 +1,5 @@
/* LzmaUtil.c -- Test application for LZMA compression
-2017-04-27 : Igor Pavlov : Public domain */
+2018-07-04 : Igor Pavlov : Public domain */
#include "../../Precomp.h"
@@ -177,7 +177,7 @@ static int main2(int numArgs, const char *args[], char *rs)
char c;
int res;
int encodeMode;
- Bool useOutFile = False;
+ BoolInt useOutFile = False;
FileSeqInStream_CreateVTable(&inStream);
File_Construct(&inStream.file);
diff --git a/deps/LZMA-SDK/C/Util/SfxSetup/SfxSetup.c b/deps/LZMA-SDK/C/Util/SfxSetup/SfxSetup.c
index bfbf43025..394369abd 100644
--- a/deps/LZMA-SDK/C/Util/SfxSetup/SfxSetup.c
+++ b/deps/LZMA-SDK/C/Util/SfxSetup/SfxSetup.c
@@ -1,5 +1,5 @@
/* SfxSetup.c - 7z SFX Setup
-2017-04-04 : Igor Pavlov : Public domain */
+2019-02-02 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -127,7 +127,7 @@ static WRes MyCreateDir(const WCHAR *name)
#define kSignatureSearchLimit (1 << 22)
-static Bool FindSignature(CSzFile *stream, UInt64 *resPos)
+static BoolInt FindSignature(CSzFile *stream, UInt64 *resPos)
{
Byte buf[kBufferSize];
size_t numPrevBytes = 0;
@@ -163,7 +163,7 @@ static Bool FindSignature(CSzFile *stream, UInt64 *resPos)
}
}
-static Bool DoesFileOrDirExist(const WCHAR *path)
+static BoolInt DoesFileOrDirExist(const WCHAR *path)
{
WIN32_FIND_DATAW fd;
HANDLE handle;
@@ -254,7 +254,7 @@ int APIENTRY WinMain(HINSTANCE hInstance, HINSTANCE hPrevInstance,
DWORD winRes;
const wchar_t *cmdLineParams;
const char *errorMessage = NULL;
- Bool useShellExecute = True;
+ BoolInt useShellExecute = True;
DWORD exitCode = 0;
LoadSecurityDlls();
@@ -287,7 +287,7 @@ int APIENTRY WinMain(HINSTANCE hInstance, HINSTANCE hPrevInstance,
cmdLineParams = GetCommandLineW();
#ifndef UNDER_CE
{
- Bool quoteMode = False;
+ BoolInt quoteMode = False;
for (;; cmdLineParams++)
{
wchar_t c = *cmdLineParams;
@@ -379,7 +379,7 @@ int APIENTRY WinMain(HINSTANCE hInstance, HINSTANCE hPrevInstance,
if (res == SZ_OK)
{
- lookStream.buf = ISzAlloc_Alloc(&allocImp, kInputBufSize);
+ lookStream.buf = (Byte *)ISzAlloc_Alloc(&allocImp, kInputBufSize);
if (!lookStream.buf)
res = SZ_ERROR_MEM;
else
@@ -420,7 +420,7 @@ int APIENTRY WinMain(HINSTANCE hInstance, HINSTANCE hPrevInstance,
temp = path + pathLen;
- SzArEx_GetFileNameUtf16(&db, i, temp);
+ SzArEx_GetFileNameUtf16(&db, i, (UInt16 *)temp);
{
res = SzArEx_Extract(&db, &lookStream.vt, i,
&blockIndex, &outBuffer, &outBufferSize,
@@ -527,7 +527,7 @@ int APIENTRY WinMain(HINSTANCE hInstance, HINSTANCE hPrevInstance,
{
WCHAR *temp = path + pathLen;
UInt32 j;
- SzArEx_GetFileNameUtf16(&db, executeFileIndex, temp);
+ SzArEx_GetFileNameUtf16(&db, executeFileIndex, (UInt16 *)temp);
for (j = 0; temp[j] != 0; j++)
if (temp[j] == '/')
temp[j] = CHAR_PATH_SEPARATOR;
diff --git a/deps/LZMA-SDK/C/Xz.h b/deps/LZMA-SDK/C/Xz.h
index 7b88f516a..fad56a3fb 100644
--- a/deps/LZMA-SDK/C/Xz.h
+++ b/deps/LZMA-SDK/C/Xz.h
@@ -1,5 +1,5 @@
/* Xz.h - Xz interface
-2018-02-28 : Igor Pavlov : Public domain */
+2018-07-04 : Igor Pavlov : Public domain */
#ifndef __XZ_H
#define __XZ_H
@@ -53,7 +53,7 @@ typedef struct
#define XzBlock_HasUnsupportedFlags(p) (((p)->flags & ~(XZ_BF_NUM_FILTERS_MASK | XZ_BF_PACK_SIZE | XZ_BF_UNPACK_SIZE)) != 0)
SRes XzBlock_Parse(CXzBlock *p, const Byte *header);
-SRes XzBlock_ReadHeader(CXzBlock *p, ISeqInStream *inStream, Bool *isIndex, UInt32 *headerSizeRes);
+SRes XzBlock_ReadHeader(CXzBlock *p, ISeqInStream *inStream, BoolInt *isIndex, UInt32 *headerSizeRes);
/* ---------- xz stream ---------- */
@@ -186,10 +186,10 @@ typedef struct
Byte *outBuf;
size_t outBufSize;
size_t outWritten; // is equal to lzmaDecoder.dicPos (in outBuf mode)
- Bool wasFinished;
+ BoolInt wasFinished;
SRes res;
ECoderStatus status;
- // Bool SingleBufMode;
+ // BoolInt SingleBufMode;
int finished[MIXCODER_NUM_FILTERS_MAX - 1];
size_t pos[MIXCODER_NUM_FILTERS_MAX - 1];
@@ -241,9 +241,9 @@ typedef struct
CXzCheck check;
CSha256 sha;
- Bool parseMode;
- Bool headerParsedOk;
- Bool decodeToStreamSignature;
+ BoolInt parseMode;
+ BoolInt headerParsedOk;
+ BoolInt decodeToStreamSignature;
unsigned decodeOnlyOneBlock;
Byte *outBuf;
@@ -335,7 +335,7 @@ SRes XzUnpacker_CodeFull(CXzUnpacker *p, Byte *dest, SizeT *destLen,
const Byte *src, SizeT *srcLen,
ECoderFinishMode finishMode, ECoderStatus *status);
-Bool XzUnpacker_IsStreamWasFinished(const CXzUnpacker *p);
+BoolInt XzUnpacker_IsStreamWasFinished(const CXzUnpacker *p);
/*
XzUnpacker_GetExtraSize() returns then number of uncofirmed bytes,
@@ -365,7 +365,7 @@ UInt64 XzUnpacker_GetExtraSize(const CXzUnpacker *p);
*/
void XzUnpacker_PrepareToRandomBlockDecoding(CXzUnpacker *p);
-Bool XzUnpacker_IsBlockFinished(const CXzUnpacker *p);
+BoolInt XzUnpacker_IsBlockFinished(const CXzUnpacker *p);
#define XzUnpacker_GetPackSizeForIndex(p) ((p)->packSize + (p)->blockHeaderSize + XzFlags_GetCheckSize((p)->streamFlags))
@@ -378,7 +378,7 @@ typedef struct
{
size_t inBufSize_ST;
size_t outStep_ST;
- Bool ignoreErrors;
+ BoolInt ignoreErrors;
#ifndef _7ZIP_ST
unsigned numThreads;
diff --git a/deps/LZMA-SDK/C/XzDec.c b/deps/LZMA-SDK/C/XzDec.c
index ebf198336..4f5327207 100644
--- a/deps/LZMA-SDK/C/XzDec.c
+++ b/deps/LZMA-SDK/C/XzDec.c
@@ -1,5 +1,5 @@
/* XzDec.c -- Xz Decode
-2018-04-24 : Igor Pavlov : Public domain */
+2019-02-02 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -245,7 +245,7 @@ SRes BraState_SetFromMethod(IStateCoder *p, UInt64 id, int encodeMode, ISzAllocP
CBraState *decoder;
if (id < XZ_ID_Delta || id > XZ_ID_SPARC)
return SZ_ERROR_UNSUPPORTED;
- decoder = p->p;
+ decoder = (CBraState *)p->p;
if (!decoder)
{
decoder = (CBraState *)ISzAlloc_Alloc(alloc, sizeof(CBraState));
@@ -341,7 +341,7 @@ static SRes SbState_SetFromMethod(IStateCoder *p, ISzAllocPtr alloc)
typedef struct
{
CLzma2Dec decoder;
- Bool outBufMode;
+ BoolInt outBufMode;
} CLzma2Dec_Spec;
@@ -400,7 +400,7 @@ static SRes Lzma2State_Code2(void *pp, Byte *dest, SizeT *destLen, const Byte *s
res = Lzma2Dec_DecodeToBuf(&spec->decoder, dest, destLen, src, srcLen, (ELzmaFinishMode)finishMode, &status2);
// *wasFinished = (status2 == LZMA_STATUS_FINISHED_WITH_MARK);
// ECoderStatus values are identical to ELzmaStatus values of LZMA2 decoder
- *status = status2;
+ *status = (ECoderStatus)status2;
return res;
}
@@ -637,8 +637,8 @@ static SRes MixCoder_Code(CMixCoder *p,
for (;;)
{
- Bool processed = False;
- Bool allFinished = True;
+ BoolInt processed = False;
+ BoolInt allFinished = True;
SRes resMain = SZ_OK;
unsigned i;
@@ -761,7 +761,7 @@ SRes Xz_ParseHeader(CXzStreamFlags *p, const Byte *buf)
return XzFlags_IsSupported(*p) ? SZ_OK : SZ_ERROR_UNSUPPORTED;
}
-static Bool Xz_CheckFooter(CXzStreamFlags flags, UInt64 indexSize, const Byte *buf)
+static BoolInt Xz_CheckFooter(CXzStreamFlags flags, UInt64 indexSize, const Byte *buf)
{
return indexSize == (((UInt64)GetUi32(buf + 4) + 1) << 2)
&& GetUi32(buf) == CrcCalc(buf + 4, 6)
@@ -775,7 +775,7 @@ static Bool Xz_CheckFooter(CXzStreamFlags flags, UInt64 indexSize, const Byte *b
if (s == 0) return SZ_ERROR_ARCHIVE; pos += s; }
-static Bool XzBlock_AreSupportedFilters(const CXzBlock *p)
+static BoolInt XzBlock_AreSupportedFilters(const CXzBlock *p)
{
unsigned numFilters = XzBlock_GetNumFilters(p) - 1;
unsigned i;
@@ -866,7 +866,7 @@ SRes XzBlock_Parse(CXzBlock *p, const Byte *header)
static SRes XzDecMix_Init(CMixCoder *p, const CXzBlock *block, Byte *outBuf, size_t outBufSize)
{
unsigned i;
- Bool needReInit = True;
+ BoolInt needReInit = True;
unsigned numFilters = XzBlock_GetNumFilters(block);
if (numFilters == p->numCoders && ((p->outBuf && outBuf) || (!p->outBuf && !outBuf)))
@@ -999,8 +999,8 @@ SRes XzUnpacker_Code(CXzUnpacker *p, Byte *dest, SizeT *destLen,
SRes res;
ECoderFinishMode finishMode2 = finishMode;
- Bool srcFinished2 = srcFinished;
- Bool destFinish = False;
+ BoolInt srcFinished2 = srcFinished;
+ BoolInt destFinish = False;
if (p->block.packSize != (UInt64)(Int64)-1)
{
@@ -1346,12 +1346,12 @@ SRes XzUnpacker_CodeFull(CXzUnpacker *p, Byte *dest, SizeT *destLen,
}
-Bool XzUnpacker_IsBlockFinished(const CXzUnpacker *p)
+BoolInt XzUnpacker_IsBlockFinished(const CXzUnpacker *p)
{
return (p->state == XZ_STATE_BLOCK_HEADER) && (p->pos == 0);
}
-Bool XzUnpacker_IsStreamWasFinished(const CXzUnpacker *p)
+BoolInt XzUnpacker_IsStreamWasFinished(const CXzUnpacker *p)
{
return (p->state == XZ_STATE_STREAM_PADDING) && (((UInt32)p->padSize & 3) == 0);
}
@@ -1423,18 +1423,18 @@ typedef struct
size_t outCodeSize;
ECoderStatus status;
SRes codeRes;
- Bool skipMode;
- // Bool finishedWithMark;
+ BoolInt skipMode;
+ // BoolInt finishedWithMark;
EMtDecParseState parseState;
- Bool parsing_Truncated;
- Bool atBlockHeader;
+ BoolInt parsing_Truncated;
+ BoolInt atBlockHeader;
CXzStreamFlags streamFlags;
// UInt64 numFinishedStreams
UInt64 numStreams;
UInt64 numTotalBlocks;
UInt64 numBlocks;
- Bool dec_created;
+ BoolInt dec_created;
CXzUnpacker dec;
Byte mtPad[1 << 7];
@@ -1458,14 +1458,14 @@ typedef struct
ICompressProgress *progress;
// CXzStatInfo *stat;
- Bool finishMode;
- Bool outSize_Defined;
+ BoolInt finishMode;
+ BoolInt outSize_Defined;
UInt64 outSize;
UInt64 outProcessed;
UInt64 inProcessed;
UInt64 readProcessed;
- Bool readWasFinished;
+ BoolInt readWasFinished;
SRes readRes;
SRes writeRes;
@@ -1473,14 +1473,14 @@ typedef struct
size_t outBufSize;
Byte *inBuf;
size_t inBufSize;
- Bool dec_created;
+
CXzUnpacker dec;
ECoderStatus status;
SRes codeRes;
#ifndef _7ZIP_ST
- Bool mainDecoderWasCalled;
+ BoolInt mainDecoderWasCalled;
// int statErrorDefined;
int finishedDecoderIndex;
@@ -1494,12 +1494,12 @@ typedef struct
// UInt64 numBadBlocks;
SRes mainErrorCode;
- Bool isBlockHeaderState_Parse;
- Bool isBlockHeaderState_Write;
+ BoolInt isBlockHeaderState_Parse;
+ BoolInt isBlockHeaderState_Write;
UInt64 outProcessed_Parse;
- Bool parsing_Truncated;
+ BoolInt parsing_Truncated;
- Bool mtc_WasConstructed;
+ BoolInt mtc_WasConstructed;
CMtDec mtc;
CXzDecMtThread coders[MTDEC__THREADS_MAX];
#endif
@@ -1525,7 +1525,8 @@ CXzDecMtHandle XzDecMt_Create(ISzAllocPtr alloc, ISzAllocPtr allocMid)
p->outBufSize = 0;
p->inBuf = NULL;
p->inBufSize = 0;
- p->dec_created = False;
+
+ XzUnpacker_Construct(&p->dec, &p->alignOffsetAlloc.vt);
p->unpackBlockMaxSize = 0;
@@ -1573,11 +1574,7 @@ static void XzDecMt_FreeOutBufs(CXzDecMt *p)
static void XzDecMt_FreeSt(CXzDecMt *p)
{
- if (p->dec_created)
- {
- XzUnpacker_Free(&p->dec);
- p->dec_created = False;
- }
+ XzUnpacker_Free(&p->dec);
if (p->outBuf)
{
@@ -1968,11 +1965,11 @@ static SRes XzDecMt_Callback_Code(void *pp, unsigned coderIndex,
#define XZDECMT_STREAM_WRITE_STEP (1 << 24)
static SRes XzDecMt_Callback_Write(void *pp, unsigned coderIndex,
- Bool needWriteToStream,
+ BoolInt needWriteToStream,
const Byte *src, size_t srcSize,
// int srcFinished,
- Bool *needContinue,
- Bool *canRecode)
+ BoolInt *needContinue,
+ BoolInt *canRecode)
{
CXzDecMt *me = (CXzDecMt *)pp;
const CXzDecMtThread *coder = &me->coders[coderIndex];
@@ -2302,7 +2299,7 @@ void XzStatInfo_Clear(CXzStatInfo *p)
static SRes XzDecMt_Decode_ST(CXzDecMt *p
#ifndef _7ZIP_ST
- , Bool tMode
+ , BoolInt tMode
#endif
, CXzStatInfo *stat)
{
@@ -2358,7 +2355,7 @@ static SRes XzDecMt_Decode_ST(CXzDecMt *p
for (;;)
{
SizeT outSize;
- Bool finished;
+ BoolInt finished;
ECoderFinishMode finishMode;
SizeT inProcessed;
ECoderStatus status;
@@ -2466,7 +2463,7 @@ static SRes XzStatInfo_SetStat(const CXzUnpacker *dec,
int finishMode,
UInt64 readProcessed, UInt64 inProcessed,
SRes res, ECoderStatus status,
- Bool decodingTruncated,
+ BoolInt decodingTruncated,
CXzStatInfo *stat)
{
UInt64 extraSize;
@@ -2531,7 +2528,7 @@ SRes XzDecMt_Decode(CXzDecMtHandle pp,
{
CXzDecMt *p = (CXzDecMt *)pp;
#ifndef _7ZIP_ST
- Bool tMode;
+ BoolInt tMode;
#endif
XzStatInfo_Clear(stat);
@@ -2564,13 +2561,7 @@ SRes XzDecMt_Decode(CXzDecMtHandle pp,
p->codeRes = 0;
p->status = CODER_STATUS_NOT_SPECIFIED;
- if (!p->dec_created)
- {
- XzUnpacker_Construct(&p->dec, &p->alignOffsetAlloc.vt);
- p->dec_created = True;
- }
XzUnpacker_Init(&p->dec);
-
*isMT = False;
@@ -2600,6 +2591,8 @@ SRes XzDecMt_Decode(CXzDecMtHandle pp,
{
IMtDecCallback vt;
+ // we just free ST buffers here
+ // but we still keep state variables, that was set in XzUnpacker_Init()
XzDecMt_FreeSt(p);
p->outProcessed_Parse = 0;
@@ -2636,7 +2629,7 @@ SRes XzDecMt_Decode(CXzDecMtHandle pp,
vt.Write = XzDecMt_Callback_Write;
{
- Bool needContinue;
+ BoolInt needContinue;
SRes res = MtDec_Code(&p->mtc);
@@ -2665,7 +2658,7 @@ SRes XzDecMt_Decode(CXzDecMtHandle pp,
if (!needContinue)
{
SRes codeRes;
- Bool truncated = False;
+ BoolInt truncated = False;
ECoderStatus status;
CXzUnpacker *dec;
diff --git a/deps/LZMA-SDK/C/XzEnc.c b/deps/LZMA-SDK/C/XzEnc.c
index 432cbfe79..309eca949 100644
--- a/deps/LZMA-SDK/C/XzEnc.c
+++ b/deps/LZMA-SDK/C/XzEnc.c
@@ -1,5 +1,5 @@
/* XzEnc.c -- Xz Encode
-2018-04-28 : Igor Pavlov : Public domain */
+2019-02-02 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -366,7 +366,7 @@ static SRes SeqInFilter_Read(const ISeqInStream *pp, void *data, size_t *size)
SRes res;
*size = sizeOriginal;
res = p->StateCoder.Code2(p->StateCoder.p,
- data, size,
+ (Byte *)data, size,
p->buf + p->curPos, &srcLen,
p->srcWasFinished, CODER_FINISH_ANY,
&status);
@@ -814,7 +814,7 @@ static SRes Xz_CompressBlock(
SRes res;
Byte *outBuf = NULL;
size_t outSize = 0;
- Bool useStream = (fp || inStream);
+ BoolInt useStream = (fp || inStream);
// useStream = True;
if (!useStream)
@@ -940,7 +940,7 @@ typedef struct
#ifndef _7ZIP_ST
unsigned checkType;
ISeqOutStream *outStream;
- Bool mtCoder_WasConstructed;
+ BoolInt mtCoder_WasConstructed;
CMtCoder mtCoder;
CXzEncBlockInfo EncBlocks[MTCODER__BLOCKS_MAX];
#endif
diff --git a/deps/LZMA-SDK/C/XzIn.c b/deps/LZMA-SDK/C/XzIn.c
index 42da1dece..792a61786 100644
--- a/deps/LZMA-SDK/C/XzIn.c
+++ b/deps/LZMA-SDK/C/XzIn.c
@@ -1,5 +1,5 @@
/* XzIn.c - Xz input
-2018-02-02 : Igor Pavlov : Public domain */
+2018-07-04 : Igor Pavlov : Public domain */
#include "Precomp.h"
@@ -28,7 +28,7 @@ SRes Xz_ReadHeader(CXzStreamFlags *p, ISeqInStream *inStream)
{ unsigned s = Xz_ReadVarInt(buf + pos, size - pos, res); \
if (s == 0) return SZ_ERROR_ARCHIVE; pos += s; }
-SRes XzBlock_ReadHeader(CXzBlock *p, ISeqInStream *inStream, Bool *isIndex, UInt32 *headerSizeRes)
+SRes XzBlock_ReadHeader(CXzBlock *p, ISeqInStream *inStream, BoolInt *isIndex, UInt32 *headerSizeRes)
{
Byte header[XZ_BLOCK_HEADER_SIZE_MAX];
unsigned headerSize;
From 35e07fec288f2d7b8ada278f8a7f2681e358f608 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Mon, 15 Jul 2019 15:34:03 +0200
Subject: [PATCH 018/113] update OpenCL-Headers deps
---
deps/OpenCL-Headers/CL/cl.h | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/deps/OpenCL-Headers/CL/cl.h b/deps/OpenCL-Headers/CL/cl.h
index 3521676d5..32ae73fc5 100644
--- a/deps/OpenCL-Headers/CL/cl.h
+++ b/deps/OpenCL-Headers/CL/cl.h
@@ -137,19 +137,23 @@ typedef struct _cl_image_desc {
size_t image_slice_pitch;
cl_uint num_mip_levels;
cl_uint num_samples;
+#ifdef CL_VERSION_2_0
#ifdef __GNUC__
__extension__ /* Prevents warnings about anonymous union in -pedantic builds */
#endif
#ifdef _MSC_VER
-#pragma warning( push )
+#pragma warning( push )
#pragma warning( disable : 4201 ) /* Prevents warning about nameless struct/union in /W4 /Za builds */
#endif
union {
+#endif
cl_mem buffer;
+#ifdef CL_VERSION_2_0
cl_mem mem_object;
};
#ifdef _MSC_VER
-#pragma warning( pop )
+#pragma warning( pop )
+#endif
#endif
} cl_image_desc;
From e724e0dadc3ebda7c7864543519328875d8ab927 Mon Sep 17 00:00:00 2001
From: Jack Schmidt <github@mowsey.org>
Date: Thu, 18 Jul 2019 08:06:00 -0400
Subject: [PATCH 019/113] nsec3 m 8300: salt can be empty
---
src/modules/module_08300.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/modules/module_08300.c b/src/modules/module_08300.c
index e0faa0b37..c5fc7f352 100644
--- a/src/modules/module_08300.c
+++ b/src/modules/module_08300.c
@@ -61,7 +61,7 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH;
token.sep[2] = ':';
- token.len_min[2] = 1;
+ token.len_min[2] = 0;
token.len_max[2] = 32;
token.attr[2] = TOKEN_ATTR_VERIFY_LENGTH;
From 038bce131fe053a0bb7092c6027237b22ed0b5be Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 20 Jul 2019 21:06:46 +0200
Subject: [PATCH 020/113] Add Double sha256 kernel module
---
OpenCL/m01470_a0-optimized.cl | 574 +++++++++++++++++++++++++++
OpenCL/m01470_a0-pure.cl | 147 +++++++
OpenCL/m01470_a1-optimized.cl | 688 ++++++++++++++++++++++++++++++++
OpenCL/m01470_a1-pure.cl | 141 +++++++
OpenCL/m01470_a3-optimized.cl | 728 ++++++++++++++++++++++++++++++++++
OpenCL/m01470_a3-pure.cl | 171 ++++++++
docs/changes.txt | 3 +-
docs/credits.txt | 1 +
docs/readme.txt | 1 +
src/modules/module_01470.c | 228 +++++++++++
tools/test_modules/m01470.pm | 41 ++
11 files changed, 2722 insertions(+), 1 deletion(-)
create mode 100644 OpenCL/m01470_a0-optimized.cl
create mode 100644 OpenCL/m01470_a0-pure.cl
create mode 100644 OpenCL/m01470_a1-optimized.cl
create mode 100644 OpenCL/m01470_a1-pure.cl
create mode 100644 OpenCL/m01470_a3-optimized.cl
create mode 100644 OpenCL/m01470_a3-pure.cl
create mode 100644 src/modules/module_01470.c
create mode 100644 tools/test_modules/m01470.pm
diff --git a/OpenCL/m01470_a0-optimized.cl b/OpenCL/m01470_a0-optimized.cl
new file mode 100644
index 000000000..5acf8ae17
--- /dev/null
+++ b/OpenCL/m01470_a0-optimized.cl
@@ -0,0 +1,574 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#define SHA256_STEP_REV(a,b,c,d,e,f,g,h) \
+{ \
+ u32 t2 = SHA256_S2_S(b) + SHA256_F0o(b,c,d); \
+ u32 t1 = a - t2; \
+ a = b; \
+ b = c; \
+ c = d; \
+ d = e - t1; \
+ e = f; \
+ f = g; \
+ g = h; \
+ h = 0; \
+}
+
+KERNEL_FQ void m01470_m04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ /**
+ * sha256
+ */
+
+ u32x w0_t = hc_swap32 (w0[0]);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = out_len * 8;
+
+ u32x a = SHA256M_A;
+ u32x b = SHA256M_B;
+ u32x c = SHA256M_C;
+ u32x d = SHA256M_D;
+ u32x e = SHA256M_E;
+ u32x f = SHA256M_F;
+ u32x g = SHA256M_G;
+ u32x h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ // 2nd round
+
+ /**
+ * sha256
+ */
+
+ w0_t = a + SHA256M_A;
+ w1_t = b + SHA256M_B;
+ w2_t = c + SHA256M_C;
+ w3_t = d + SHA256M_D;
+ w4_t = e + SHA256M_E;
+ w5_t = f + SHA256M_F;
+ w6_t = g + SHA256M_G;
+ w7_t = h + SHA256M_H;
+ w8_t = 0x80000000;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 32 * 8;
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ COMPARE_M_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m01470_m08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m01470_m16 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m01470_s04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ u32 a_rev = digests_buf[digests_offset].digest_buf[0];
+ u32 b_rev = digests_buf[digests_offset].digest_buf[1];
+ u32 c_rev = digests_buf[digests_offset].digest_buf[2];
+ u32 d_rev = digests_buf[digests_offset].digest_buf[3];
+ u32 e_rev = digests_buf[digests_offset].digest_buf[4];
+ u32 f_rev = digests_buf[digests_offset].digest_buf[5];
+ u32 g_rev = digests_buf[digests_offset].digest_buf[6];
+ u32 h_rev = digests_buf[digests_offset].digest_buf[7];
+
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ /**
+ * sha256
+ */
+
+ u32x w0_t = hc_swap32 (w0[0]);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = out_len * 8;
+
+ u32x a = SHA256M_A;
+ u32x b = SHA256M_B;
+ u32x c = SHA256M_C;
+ u32x d = SHA256M_D;
+ u32x e = SHA256M_E;
+ u32x f = SHA256M_F;
+ u32x g = SHA256M_G;
+ u32x h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ // start 2nd round
+
+ /**
+ * sha256
+ */
+
+ w0_t = a + SHA256M_A;
+ w1_t = b + SHA256M_B;
+ w2_t = c + SHA256M_C;
+ w3_t = d + SHA256M_D;
+ w4_t = e + SHA256M_E;
+ w5_t = f + SHA256M_F;
+ w6_t = g + SHA256M_G;
+ w7_t = h + SHA256M_H;
+ w8_t = 0x80000000;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 32 * 8;
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+
+ if (MATCHES_NONE_VS (h, d_rev)) continue;
+
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ COMPARE_S_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m01470_s08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m01470_s16 (KERN_ATTR_RULES ())
+{
+}
diff --git a/OpenCL/m01470_a0-pure.cl b/OpenCL/m01470_a0-pure.cl
new file mode 100644
index 000000000..e9926a7b8
--- /dev/null
+++ b/OpenCL/m01470_a0-pure.cl
@@ -0,0 +1,147 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp.h"
+#include "inc_rp.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+KERNEL_FQ void m01470_mxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ sha256_ctx_t ctx0;
+
+ sha256_init (&ctx0);
+
+ sha256_update_swap (&ctx0, tmp.i, tmp.pw_len);
+
+ sha256_final (&ctx0);
+
+ sha256_ctx_t ctx;
+
+ sha256_init (&ctx);
+
+ u32 _w0[4];
+ _w0[0] = ctx0.h[0]; _w0[1] = ctx0.h[1]; _w0[2] = ctx0.h[2]; _w0[3] = ctx0.h[3];
+ u32 _w1[4];
+ _w1[0] = ctx0.h[4]; _w1[1] = ctx0.h[5]; _w1[2] = ctx0.h[6]; _w1[3] = ctx0.h[7];
+ u32 _w2[4] = { 0, 0, 0, 0 };
+ u32 _w3[4] = { 0, 0, 0, 0 };
+
+ sha256_update_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ sha256_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m01470_sxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ sha256_ctx_t ctx0;
+
+ sha256_init (&ctx0);
+
+ sha256_update_swap (&ctx0, tmp.i, tmp.pw_len);
+
+ sha256_final (&ctx0);
+
+ sha256_ctx_t ctx;
+
+ sha256_init (&ctx);
+
+ u32 _w0[4];
+ _w0[0] = ctx0.h[0]; _w0[1] = ctx0.h[1]; _w0[2] = ctx0.h[2]; _w0[3] = ctx0.h[3];
+ u32 _w1[4];
+ _w1[0] = ctx0.h[4]; _w1[1] = ctx0.h[5]; _w1[2] = ctx0.h[6]; _w1[3] = ctx0.h[7];
+ u32 _w2[4] = { 0, 0, 0, 0 };
+ u32 _w3[4] = { 0, 0, 0, 0 };
+
+ sha256_update_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ sha256_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m01470_a1-optimized.cl b/OpenCL/m01470_a1-optimized.cl
new file mode 100644
index 000000000..cfe607622
--- /dev/null
+++ b/OpenCL/m01470_a1-optimized.cl
@@ -0,0 +1,688 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#define SHA256_STEP_REV(a,b,c,d,e,f,g,h) \
+{ \
+ u32 t2 = SHA256_S2_S(b) + SHA256_F0o(b,c,d); \
+ u32 t1 = a - t2; \
+ a = b; \
+ b = c; \
+ c = d; \
+ d = e - t1; \
+ e = f; \
+ f = g; \
+ g = h; \
+ h = 0; \
+}
+
+KERNEL_FQ void m01470_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = wordl3[2] | wordr3[2];
+ w3[3] = wordl3[3] | wordr3[3];
+
+ /**
+ * sha256
+ */
+
+ u32x w0_t = hc_swap32 (w0[0]);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = pw_len * 8;
+
+ u32x a = SHA256M_A;
+ u32x b = SHA256M_B;
+ u32x c = SHA256M_C;
+ u32x d = SHA256M_D;
+ u32x e = SHA256M_E;
+ u32x f = SHA256M_F;
+ u32x g = SHA256M_G;
+ u32x h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ // 2nd round
+
+ /**
+ * sha256
+ */
+
+ w0_t = a + SHA256M_A;
+ w1_t = b + SHA256M_B;
+ w2_t = c + SHA256M_C;
+ w3_t = d + SHA256M_D;
+ w4_t = e + SHA256M_E;
+ w5_t = f + SHA256M_F;
+ w6_t = g + SHA256M_G;
+ w7_t = h + SHA256M_H;
+ w8_t = 0x80000000;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 32 * 8;
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ COMPARE_M_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m01470_m08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m01470_m16 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m01470_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ u32 a_rev = digests_buf[digests_offset].digest_buf[0];
+ u32 b_rev = digests_buf[digests_offset].digest_buf[1];
+ u32 c_rev = digests_buf[digests_offset].digest_buf[2];
+ u32 d_rev = digests_buf[digests_offset].digest_buf[3];
+ u32 e_rev = digests_buf[digests_offset].digest_buf[4];
+ u32 f_rev = digests_buf[digests_offset].digest_buf[5];
+ u32 g_rev = digests_buf[digests_offset].digest_buf[6];
+ u32 h_rev = digests_buf[digests_offset].digest_buf[7];
+
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = wordl3[2] | wordr3[2];
+ w3[3] = wordl3[3] | wordr3[3];
+
+ /**
+ * sha256
+ */
+
+ u32x w0_t = hc_swap32 (w0[0]);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = pw_len * 8;
+
+ u32x a = SHA256M_A;
+ u32x b = SHA256M_B;
+ u32x c = SHA256M_C;
+ u32x d = SHA256M_D;
+ u32x e = SHA256M_E;
+ u32x f = SHA256M_F;
+ u32x g = SHA256M_G;
+ u32x h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ // start 2nd round
+
+ /**
+ * sha256
+ */
+
+ w0_t = a + SHA256M_A;
+ w1_t = b + SHA256M_B;
+ w2_t = c + SHA256M_C;
+ w3_t = d + SHA256M_D;
+ w4_t = e + SHA256M_E;
+ w5_t = f + SHA256M_F;
+ w6_t = g + SHA256M_G;
+ w7_t = h + SHA256M_H;
+ w8_t = 0x80000000;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 32 * 8;
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+
+ if (MATCHES_NONE_VS (h, d_rev)) continue;
+
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ COMPARE_S_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m01470_s08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m01470_s16 (KERN_ATTR_BASIC ())
+{
+}
diff --git a/OpenCL/m01470_a1-pure.cl b/OpenCL/m01470_a1-pure.cl
new file mode 100644
index 000000000..eae6a32e8
--- /dev/null
+++ b/OpenCL/m01470_a1-pure.cl
@@ -0,0 +1,141 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+KERNEL_FQ void m01470_mxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ sha256_ctx_t ctx1;
+
+ sha256_init (&ctx1);
+
+ sha256_update_global_swap (&ctx1, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ sha256_ctx_t ctx0 = ctx1;
+
+ sha256_update_global_swap (&ctx0, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ sha256_final (&ctx0);
+
+ sha256_ctx_t ctx;
+
+ sha256_init (&ctx);
+
+ u32 _w0[4];
+ _w0[0] = ctx0.h[0]; _w0[1] = ctx0.h[1]; _w0[2] = ctx0.h[2]; _w0[3] = ctx0.h[3];
+ u32 _w1[4];
+ _w1[0] = ctx0.h[4]; _w1[1] = ctx0.h[5]; _w1[2] = ctx0.h[6]; _w1[3] = ctx0.h[7];
+ u32 _w2[4] = { 0, 0, 0, 0 };
+ u32 _w3[4] = { 0, 0, 0, 0 };
+
+ sha256_update_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ sha256_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m01470_sxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ sha256_ctx_t ctx1;
+
+ sha256_init (&ctx1);
+
+ sha256_update_global_swap (&ctx1, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ sha256_ctx_t ctx0 = ctx1;
+
+ sha256_update_global_swap (&ctx0, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ sha256_final (&ctx0);
+
+ sha256_ctx_t ctx;
+
+ sha256_init (&ctx);
+
+ u32 _w0[4];
+ _w0[0] = ctx0.h[0]; _w0[1] = ctx0.h[1]; _w0[2] = ctx0.h[2]; _w0[3] = ctx0.h[3];
+ u32 _w1[4];
+ _w1[0] = ctx0.h[4]; _w1[1] = ctx0.h[5]; _w1[2] = ctx0.h[6]; _w1[3] = ctx0.h[7];
+ u32 _w2[4] = { 0, 0, 0, 0 };
+ u32 _w3[4] = { 0, 0, 0, 0 };
+
+ sha256_update_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ sha256_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m01470_a3-optimized.cl b/OpenCL/m01470_a3-optimized.cl
new file mode 100644
index 000000000..4df35b766
--- /dev/null
+++ b/OpenCL/m01470_a3-optimized.cl
@@ -0,0 +1,728 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#define SHA256_STEP_REV(a,b,c,d,e,f,g,h) \
+{ \
+ u32 t2 = SHA256_S2_S(b) + SHA256_F0o(b,c,d); \
+ u32 t1 = a - t2; \
+ a = b; \
+ b = c; \
+ c = d; \
+ d = e - t1; \
+ e = f; \
+ f = g; \
+ g = h; \
+ h = 0; \
+}
+
+DECLSPEC void m01470m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ u32x w0_t = w0;
+ u32x w1_t = w[ 1];
+ u32x w2_t = w[ 2];
+ u32x w3_t = w[ 3];
+ u32x w4_t = w[ 4];
+ u32x w5_t = w[ 5];
+ u32x w6_t = w[ 6];
+ u32x w7_t = w[ 7];
+ u32x w8_t = w[ 8];
+ u32x w9_t = w[ 9];
+ u32x wa_t = w[10];
+ u32x wb_t = w[11];
+ u32x wc_t = w[12];
+ u32x wd_t = w[13];
+ u32x we_t = w[14];
+ u32x wf_t = w[15];
+
+ u32x a = SHA256M_A;
+ u32x b = SHA256M_B;
+ u32x c = SHA256M_C;
+ u32x d = SHA256M_D;
+ u32x e = SHA256M_E;
+ u32x f = SHA256M_F;
+ u32x g = SHA256M_G;
+ u32x h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ // 2nd round
+
+ /**
+ * sha256
+ */
+
+ w0_t = a + SHA256M_A;
+ w1_t = b + SHA256M_B;
+ w2_t = c + SHA256M_C;
+ w3_t = d + SHA256M_D;
+ w4_t = e + SHA256M_E;
+ w5_t = f + SHA256M_F;
+ w6_t = g + SHA256M_G;
+ w7_t = h + SHA256M_H;
+ w8_t = 0x80000000;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 32 * 8;
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ COMPARE_M_SIMD (d, h, c, g);
+ }
+}
+
+DECLSPEC void m01470s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ u32 a_rev = digests_buf[digests_offset].digest_buf[0];
+ u32 b_rev = digests_buf[digests_offset].digest_buf[1];
+ u32 c_rev = digests_buf[digests_offset].digest_buf[2];
+ u32 d_rev = digests_buf[digests_offset].digest_buf[3];
+ u32 e_rev = digests_buf[digests_offset].digest_buf[4];
+ u32 f_rev = digests_buf[digests_offset].digest_buf[5];
+ u32 g_rev = digests_buf[digests_offset].digest_buf[6];
+ u32 h_rev = digests_buf[digests_offset].digest_buf[7];
+
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+ SHA256_STEP_REV (a_rev, b_rev, c_rev, d_rev, e_rev, f_rev, g_rev, h_rev);
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ u32x w0_t = w0;
+ u32x w1_t = w[ 1];
+ u32x w2_t = w[ 2];
+ u32x w3_t = w[ 3];
+ u32x w4_t = w[ 4];
+ u32x w5_t = w[ 5];
+ u32x w6_t = w[ 6];
+ u32x w7_t = w[ 7];
+ u32x w8_t = w[ 8];
+ u32x w9_t = w[ 9];
+ u32x wa_t = w[10];
+ u32x wb_t = w[11];
+ u32x wc_t = w[12];
+ u32x wd_t = w[13];
+ u32x we_t = w[14];
+ u32x wf_t = w[15];
+
+ u32x a = SHA256M_A;
+ u32x b = SHA256M_B;
+ u32x c = SHA256M_C;
+ u32x d = SHA256M_D;
+ u32x e = SHA256M_E;
+ u32x f = SHA256M_F;
+ u32x g = SHA256M_G;
+ u32x h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ // start 2nd round
+
+ /**
+ * sha256
+ */
+
+ w0_t = a + SHA256M_A;
+ w1_t = b + SHA256M_B;
+ w2_t = c + SHA256M_C;
+ w3_t = d + SHA256M_D;
+ w4_t = e + SHA256M_E;
+ w5_t = f + SHA256M_F;
+ w6_t = g + SHA256M_G;
+ w7_t = h + SHA256M_H;
+ w8_t = 0x80000000;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 32 * 8;
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+
+ if (MATCHES_NONE_VS (h, d_rev)) continue;
+
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ COMPARE_S_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m01470_m04 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = 0;
+ w[ 5] = 0;
+ w[ 6] = 0;
+ w[ 7] = 0;
+ w[ 8] = 0;
+ w[ 9] = 0;
+ w[10] = 0;
+ w[11] = 0;
+ w[12] = 0;
+ w[13] = 0;
+ w[14] = 0;
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m01470m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+}
+
+KERNEL_FQ void m01470_m08 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = pws[gid].i[ 4];
+ w[ 5] = pws[gid].i[ 5];
+ w[ 6] = pws[gid].i[ 6];
+ w[ 7] = pws[gid].i[ 7];
+ w[ 8] = 0;
+ w[ 9] = 0;
+ w[10] = 0;
+ w[11] = 0;
+ w[12] = 0;
+ w[13] = 0;
+ w[14] = 0;
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m01470m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+}
+
+KERNEL_FQ void m01470_m16 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = pws[gid].i[ 4];
+ w[ 5] = pws[gid].i[ 5];
+ w[ 6] = pws[gid].i[ 6];
+ w[ 7] = pws[gid].i[ 7];
+ w[ 8] = pws[gid].i[ 8];
+ w[ 9] = pws[gid].i[ 9];
+ w[10] = pws[gid].i[10];
+ w[11] = pws[gid].i[11];
+ w[12] = pws[gid].i[12];
+ w[13] = pws[gid].i[13];
+ w[14] = pws[gid].i[14];
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m01470m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+}
+
+KERNEL_FQ void m01470_s04 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = 0;
+ w[ 5] = 0;
+ w[ 6] = 0;
+ w[ 7] = 0;
+ w[ 8] = 0;
+ w[ 9] = 0;
+ w[10] = 0;
+ w[11] = 0;
+ w[12] = 0;
+ w[13] = 0;
+ w[14] = 0;
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m01470s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+}
+
+KERNEL_FQ void m01470_s08 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = pws[gid].i[ 4];
+ w[ 5] = pws[gid].i[ 5];
+ w[ 6] = pws[gid].i[ 6];
+ w[ 7] = pws[gid].i[ 7];
+ w[ 8] = 0;
+ w[ 9] = 0;
+ w[10] = 0;
+ w[11] = 0;
+ w[12] = 0;
+ w[13] = 0;
+ w[14] = 0;
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m01470s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+}
+
+KERNEL_FQ void m01470_s16 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = pws[gid].i[ 4];
+ w[ 5] = pws[gid].i[ 5];
+ w[ 6] = pws[gid].i[ 6];
+ w[ 7] = pws[gid].i[ 7];
+ w[ 8] = pws[gid].i[ 8];
+ w[ 9] = pws[gid].i[ 9];
+ w[10] = pws[gid].i[10];
+ w[11] = pws[gid].i[11];
+ w[12] = pws[gid].i[12];
+ w[13] = pws[gid].i[13];
+ w[14] = pws[gid].i[14];
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m01470s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+}
diff --git a/OpenCL/m01470_a3-pure.cl b/OpenCL/m01470_a3-pure.cl
new file mode 100644
index 000000000..18071aae9
--- /dev/null
+++ b/OpenCL/m01470_a3-pure.cl
@@ -0,0 +1,171 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+KERNEL_FQ void m01470_mxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ sha256_ctx_vector_t ctx0;
+
+ sha256_init_vector (&ctx0);
+
+ sha256_update_vector (&ctx0, w, pw_len);
+
+ sha256_final_vector (&ctx0);
+
+ sha256_ctx_vector_t ctx;
+
+ sha256_init_vector (&ctx);
+
+ u32x _w0[4];
+ _w0[0] = ctx0.h[0]; _w0[1] = ctx0.h[1]; _w0[2] = ctx0.h[2]; _w0[3] = ctx0.h[3];
+ u32x _w1[4];
+ _w1[0] = ctx0.h[4]; _w1[1] = ctx0.h[5]; _w1[2] = ctx0.h[6]; _w1[3] = ctx0.h[7];
+ u32x _w2[4];
+ _w2[0] = 0; _w2[1] = 0; _w2[2] = 0; _w2[3] = 0;
+ u32x _w3[4];
+ _w3[0] = 0; _w3[1] = 0; _w3[2] = 0; _w3[3] = 0;
+
+ sha256_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ sha256_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m01470_sxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ sha256_ctx_vector_t ctx0;
+
+ sha256_init_vector (&ctx0);
+
+ sha256_update_vector (&ctx0, w, pw_len);
+
+ sha256_final_vector (&ctx0);
+
+ sha256_ctx_vector_t ctx;
+
+ sha256_init_vector (&ctx);
+
+ u32x _w0[4];
+ _w0[0] = ctx0.h[0]; _w0[1] = ctx0.h[1]; _w0[2] = ctx0.h[2]; _w0[3] = ctx0.h[3];
+ u32x _w1[4];
+ _w1[0] = ctx0.h[4]; _w1[1] = ctx0.h[5]; _w1[2] = ctx0.h[6]; _w1[3] = ctx0.h[7];
+ u32x _w2[4];
+ _w2[0] = 0; _w2[1] = 0; _w2[2] = 0; _w2[3] = 0;
+ u32x _w3[4];
+ _w3[0] = 0; _w3[1] = 0; _w3[2] = 0; _w3[3] = 0;
+
+ sha256_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ sha256_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SIMD (r0, r1, r2, r3);
+ }
+}
diff --git a/docs/changes.txt b/docs/changes.txt
index 0bb228187..8c4b77069 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -1,4 +1,4 @@
-* changes v5.1.0 -> v5.x.x
+OpenCL/m01470_a* changes v5.1.0 -> v5.x.x
##
## Feature
@@ -35,6 +35,7 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
+- Added hash-mode: Double sha256
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index bd21d35d7..02f4b0873 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,6 +18,7 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
+* Double sha256 kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
diff --git a/docs/readme.txt b/docs/readme.txt
index 9e36b73ce..4afef8d2c 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -84,6 +84,7 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- sha1(md5(md5($pass)))
- sha1($salt.$pass.$salt)
- sha1(CX)
+- Double sha256
- sha256($pass.$salt)
- sha256($salt.$pass)
- sha256(utf16le($pass).$salt)
diff --git a/src/modules/module_01470.c b/src/modules/module_01470.c
new file mode 100644
index 000000000..100407a2d
--- /dev/null
+++ b/src/modules/module_01470.c
@@ -0,0 +1,228 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+
+static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL;
+static const u32 DGST_POS0 = 3;
+static const u32 DGST_POS1 = 7;
+static const u32 DGST_POS2 = 2;
+static const u32 DGST_POS3 = 6;
+static const u32 DGST_SIZE = DGST_SIZE_4_8;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH;
+static const char *HASH_NAME = "Double sha256";
+static const u64 KERN_TYPE = 1470;
+static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
+ | OPTI_TYPE_PRECOMPUTE_INIT
+ | OPTI_TYPE_EARLY_SKIP
+ | OPTI_TYPE_NOT_ITERATED
+ | OPTI_TYPE_NOT_SALTED
+ | OPTI_TYPE_RAW_HASH;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_BE
+ | OPTS_TYPE_PT_ADD80
+ | OPTS_TYPE_PT_ADDBITS15;
+static const u32 SALT_TYPE = SALT_TYPE_NONE;
+static const char *ST_PASS = "hashcat";
+static const char *ST_HASH = "0cc1b58a543f372327aa0281e97ab56e345267ee46feabf7709515debb7ec43c";
+
+u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
+u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
+u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
+u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
+u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
+u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
+u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
+const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
+u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
+u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
+u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
+u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
+const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
+const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+ u32 *digest = (u32 *) digest_buf;
+
+ token_t token;
+
+ token.token_cnt = 1;
+
+ token.len_min[0] = 64;
+ token.len_max[0] = 64;
+ token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_HEX;
+
+ const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+ if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+ const u8 *hash_pos = token.buf[0];
+
+ digest[0] = hex_to_u32 (hash_pos + 0);
+ digest[1] = hex_to_u32 (hash_pos + 8);
+ digest[2] = hex_to_u32 (hash_pos + 16);
+ digest[3] = hex_to_u32 (hash_pos + 24);
+ digest[4] = hex_to_u32 (hash_pos + 32);
+ digest[5] = hex_to_u32 (hash_pos + 40);
+ digest[6] = hex_to_u32 (hash_pos + 48);
+ digest[7] = hex_to_u32 (hash_pos + 56);
+
+ digest[0] = byte_swap_32 (digest[0]);
+ digest[1] = byte_swap_32 (digest[1]);
+ digest[2] = byte_swap_32 (digest[2]);
+ digest[3] = byte_swap_32 (digest[3]);
+ digest[4] = byte_swap_32 (digest[4]);
+ digest[5] = byte_swap_32 (digest[5]);
+ digest[6] = byte_swap_32 (digest[6]);
+ digest[7] = byte_swap_32 (digest[7]);
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ digest[0] -= SHA256M_A;
+ digest[1] -= SHA256M_B;
+ digest[2] -= SHA256M_C;
+ digest[3] -= SHA256M_D;
+ digest[4] -= SHA256M_E;
+ digest[5] -= SHA256M_F;
+ digest[6] -= SHA256M_G;
+ digest[7] -= SHA256M_H;
+ }
+
+ return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+ const u32 *digest = (const u32 *) digest_buf;
+
+ // we can not change anything in the original buffer, otherwise destroying sorting
+ // therefore create some local buffer
+
+ u32 tmp[8];
+
+ tmp[0] = digest[0];
+ tmp[1] = digest[1];
+ tmp[2] = digest[2];
+ tmp[3] = digest[3];
+ tmp[4] = digest[4];
+ tmp[5] = digest[5];
+ tmp[6] = digest[6];
+ tmp[7] = digest[7];
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ tmp[0] += SHA256M_A;
+ tmp[1] += SHA256M_B;
+ tmp[2] += SHA256M_C;
+ tmp[3] += SHA256M_D;
+ tmp[4] += SHA256M_E;
+ tmp[5] += SHA256M_F;
+ tmp[6] += SHA256M_G;
+ tmp[7] += SHA256M_H;
+ }
+
+ tmp[0] = byte_swap_32 (tmp[0]);
+ tmp[1] = byte_swap_32 (tmp[1]);
+ tmp[2] = byte_swap_32 (tmp[2]);
+ tmp[3] = byte_swap_32 (tmp[3]);
+ tmp[4] = byte_swap_32 (tmp[4]);
+ tmp[5] = byte_swap_32 (tmp[5]);
+ tmp[6] = byte_swap_32 (tmp[6]);
+ tmp[7] = byte_swap_32 (tmp[7]);
+
+ u8 *out_buf = (u8 *) line_buf;
+
+ u32_to_hex (tmp[0], out_buf + 0);
+ u32_to_hex (tmp[1], out_buf + 8);
+ u32_to_hex (tmp[2], out_buf + 16);
+ u32_to_hex (tmp[3], out_buf + 24);
+ u32_to_hex (tmp[4], out_buf + 32);
+ u32_to_hex (tmp[5], out_buf + 40);
+ u32_to_hex (tmp[6], out_buf + 48);
+ u32_to_hex (tmp[7], out_buf + 56);
+
+ const int out_len = 64;
+
+ return out_len;
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+ module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
+ module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
+
+ module_ctx->module_attack_exec = module_attack_exec;
+ module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_mask = MODULE_DEFAULT;
+ module_ctx->module_benchmark_salt = MODULE_DEFAULT;
+ module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
+ module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
+ module_ctx->module_dgst_pos0 = module_dgst_pos0;
+ module_ctx->module_dgst_pos1 = module_dgst_pos1;
+ module_ctx->module_dgst_pos2 = module_dgst_pos2;
+ module_ctx->module_dgst_pos3 = module_dgst_pos3;
+ module_ctx->module_dgst_size = module_dgst_size;
+ module_ctx->module_dictstat_disable = MODULE_DEFAULT;
+ module_ctx->module_esalt_size = MODULE_DEFAULT;
+ module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
+ module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_count = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_save = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
+ module_ctx->module_hash_decode = module_hash_decode;
+ module_ctx->module_hash_encode_status = MODULE_DEFAULT;
+ module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_encode = module_hash_encode;
+ module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
+ module_ctx->module_hash_mode = MODULE_DEFAULT;
+ module_ctx->module_hash_category = module_hash_category;
+ module_ctx->module_hash_name = module_hash_name;
+ module_ctx->module_hashes_count_min = MODULE_DEFAULT;
+ module_ctx->module_hashes_count_max = MODULE_DEFAULT;
+ module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
+ module_ctx->module_hook12 = MODULE_DEFAULT;
+ module_ctx->module_hook23 = MODULE_DEFAULT;
+ module_ctx->module_hook_salt_size = MODULE_DEFAULT;
+ module_ctx->module_hook_size = MODULE_DEFAULT;
+ module_ctx->module_jit_build_options = MODULE_DEFAULT;
+ module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
+ module_ctx->module_kern_type = module_kern_type;
+ module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
+ module_ctx->module_opti_type = module_opti_type;
+ module_ctx->module_opts_type = module_opts_type;
+ module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
+ module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
+ module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
+ module_ctx->module_potfile_disable = MODULE_DEFAULT;
+ module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
+ module_ctx->module_pwdump_column = MODULE_DEFAULT;
+ module_ctx->module_pw_max = MODULE_DEFAULT;
+ module_ctx->module_pw_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = MODULE_DEFAULT;
+ module_ctx->module_salt_min = MODULE_DEFAULT;
+ module_ctx->module_salt_type = module_salt_type;
+ module_ctx->module_separator = MODULE_DEFAULT;
+ module_ctx->module_st_hash = module_st_hash;
+ module_ctx->module_st_pass = module_st_pass;
+ module_ctx->module_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_unstable_warning = MODULE_DEFAULT;
+ module_ctx->module_warmup_disable = MODULE_DEFAULT;
+}
diff --git a/tools/test_modules/m01470.pm b/tools/test_modules/m01470.pm
new file mode 100644
index 000000000..7446133b3
--- /dev/null
+++ b/tools/test_modules/m01470.pm
@@ -0,0 +1,41 @@
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use Digest::SHA qw (sha256_hex);
+use Digest::SHA qw (sha256);
+
+sub module_constraints { [[0, 256], [-1, -1], [0, 55], [-1, -1], [-1, -1]] }
+
+sub module_generate_hash
+{
+ my $word = shift;
+
+ my $digest = sha256_hex (sha256 ($word));
+
+ my $hash = sprintf ("%s", $digest);
+
+ return $hash;
+}
+
+sub module_verify_hash
+{
+ my $line = shift;
+
+ my ($hash, $word) = split (':', $line);
+
+ return unless defined $hash;
+ return unless defined $word;
+
+ my $word_packed = pack_if_HEX_notation ($word);
+
+ my $new_hash = module_generate_hash ($word_packed);
+
+ return ($new_hash, $word);
+}
+
+1;
From 37f392de63b9bc5222e43729779e314a1b864cdd Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Mon, 22 Jul 2019 13:25:58 +0200
Subject: [PATCH 021/113] fix docs/changes.txt
---
docs/changes.txt | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/docs/changes.txt b/docs/changes.txt
index 8c4b77069..07dc343c9 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -1,4 +1,4 @@
-OpenCL/m01470_a* changes v5.1.0 -> v5.x.x
+* changes v5.1.0 -> v5.x.x
##
## Feature
From c166242996fcbce31f266901757e4335ae7b96af Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 23 Jul 2019 19:23:06 +0200
Subject: [PATCH 022/113] Add AuthMe - sha256(sha256().) kernel module
---
OpenCL/m19400_a0-pure.cl | 265 +++++++++++++++++++++++++++++++
OpenCL/m19400_a1-pure.cl | 259 +++++++++++++++++++++++++++++++
OpenCL/m19400_a3-pure.cl | 285 ++++++++++++++++++++++++++++++++++
docs/changes.txt | 1 +
docs/readme.txt | 1 +
src/modules/module_19400.c | 293 +++++++++++++++++++++++++++++++++++
src/mpsp.c | 2 +-
tools/test_modules/m19400.pm | 48 ++++++
8 files changed, 1153 insertions(+), 1 deletion(-)
create mode 100644 OpenCL/m19400_a0-pure.cl
create mode 100644 OpenCL/m19400_a1-pure.cl
create mode 100644 OpenCL/m19400_a3-pure.cl
create mode 100644 src/modules/module_19400.c
create mode 100644 tools/test_modules/m19400.pm
diff --git a/OpenCL/m19400_a0-pure.cl b/OpenCL/m19400_a0-pure.cl
new file mode 100644
index 000000000..f35929826
--- /dev/null
+++ b/OpenCL/m19400_a0-pure.cl
@@ -0,0 +1,265 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp.h"
+#include "inc_rp.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m19400_mxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ COPY_PW (pws[gid]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (int i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
+ }
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ sha256_ctx_t ctx0;
+
+ sha256_init (&ctx0);
+
+ sha256_update_swap (&ctx0, tmp.i, tmp.pw_len);
+
+ sha256_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+ const u32 e = ctx0.h[4];
+ const u32 f = ctx0.h[5];
+ const u32 g = ctx0.h[6];
+ const u32 h = ctx0.h[7];
+
+ sha256_ctx_t ctx;
+
+ sha256_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+ w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
+ w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+ w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
+ w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+ w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
+ w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+ w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
+ w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+ w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
+ w2[2] = uint_to_hex_lower8_le ((f >> 16) & 255) << 0 | uint_to_hex_lower8_le ((f >> 24) & 255) << 16;
+ w2[3] = uint_to_hex_lower8_le ((f >> 0) & 255) << 0 | uint_to_hex_lower8_le ((f >> 8) & 255) << 16;
+ w3[0] = uint_to_hex_lower8_le ((g >> 16) & 255) << 0 | uint_to_hex_lower8_le ((g >> 24) & 255) << 16;
+ w3[1] = uint_to_hex_lower8_le ((g >> 0) & 255) << 0 | uint_to_hex_lower8_le ((g >> 8) & 255) << 16;
+ w3[2] = uint_to_hex_lower8_le ((h >> 16) & 255) << 0 | uint_to_hex_lower8_le ((h >> 24) & 255) << 16;
+ w3[3] = uint_to_hex_lower8_le ((h >> 0) & 255) << 0 | uint_to_hex_lower8_le ((h >> 8) & 255) << 16;
+
+ sha256_update_64 (&ctx, w0, w1, w2, w3, 64);
+
+ sha256_update (&ctx, s, salt_len);
+
+ sha256_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m19400_sxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ COPY_PW (pws[gid]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (int i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
+ }
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ sha256_ctx_t ctx0;
+
+ sha256_init (&ctx0);
+
+ sha256_update_swap (&ctx0, tmp.i, tmp.pw_len);
+
+ sha256_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+ const u32 e = ctx0.h[4];
+ const u32 f = ctx0.h[5];
+ const u32 g = ctx0.h[6];
+ const u32 h = ctx0.h[7];
+
+ sha256_ctx_t ctx;
+
+ sha256_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+ w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
+ w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+ w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
+ w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+ w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
+ w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+ w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
+ w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+ w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
+ w2[2] = uint_to_hex_lower8_le ((f >> 16) & 255) << 0 | uint_to_hex_lower8_le ((f >> 24) & 255) << 16;
+ w2[3] = uint_to_hex_lower8_le ((f >> 0) & 255) << 0 | uint_to_hex_lower8_le ((f >> 8) & 255) << 16;
+ w3[0] = uint_to_hex_lower8_le ((g >> 16) & 255) << 0 | uint_to_hex_lower8_le ((g >> 24) & 255) << 16;
+ w3[1] = uint_to_hex_lower8_le ((g >> 0) & 255) << 0 | uint_to_hex_lower8_le ((g >> 8) & 255) << 16;
+ w3[2] = uint_to_hex_lower8_le ((h >> 16) & 255) << 0 | uint_to_hex_lower8_le ((h >> 24) & 255) << 16;
+ w3[3] = uint_to_hex_lower8_le ((h >> 0) & 255) << 0 | uint_to_hex_lower8_le ((h >> 8) & 255) << 16;
+
+ sha256_update_64 (&ctx, w0, w1, w2, w3, 64);
+
+ sha256_update (&ctx, s, salt_len);
+
+ sha256_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m19400_a1-pure.cl b/OpenCL/m19400_a1-pure.cl
new file mode 100644
index 000000000..9b4a2b346
--- /dev/null
+++ b/OpenCL/m19400_a1-pure.cl
@@ -0,0 +1,259 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m19400_mxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ u32 s[64] = { 0 };
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ for (int i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
+ }
+
+ sha256_ctx_t ctx1;
+
+ sha256_init (&ctx1);
+
+ sha256_update_global_swap (&ctx1, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ sha256_ctx_t ctx0 = ctx1;
+
+ sha256_update_global_swap (&ctx0, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ sha256_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+ const u32 e = ctx0.h[4];
+ const u32 f = ctx0.h[5];
+ const u32 g = ctx0.h[6];
+ const u32 h = ctx0.h[7];
+
+ sha256_ctx_t ctx;
+
+ sha256_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+ w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
+ w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+ w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
+ w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+ w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
+ w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+ w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
+ w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+ w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
+ w2[2] = uint_to_hex_lower8_le ((f >> 16) & 255) << 0 | uint_to_hex_lower8_le ((f >> 24) & 255) << 16;
+ w2[3] = uint_to_hex_lower8_le ((f >> 0) & 255) << 0 | uint_to_hex_lower8_le ((f >> 8) & 255) << 16;
+ w3[0] = uint_to_hex_lower8_le ((g >> 16) & 255) << 0 | uint_to_hex_lower8_le ((g >> 24) & 255) << 16;
+ w3[1] = uint_to_hex_lower8_le ((g >> 0) & 255) << 0 | uint_to_hex_lower8_le ((g >> 8) & 255) << 16;
+ w3[2] = uint_to_hex_lower8_le ((h >> 16) & 255) << 0 | uint_to_hex_lower8_le ((h >> 24) & 255) << 16;
+ w3[3] = uint_to_hex_lower8_le ((h >> 0) & 255) << 0 | uint_to_hex_lower8_le ((h >> 8) & 255) << 16;
+
+ sha256_update_64 (&ctx, w0, w1, w2, w3, 64);
+
+ sha256_update (&ctx, s, salt_len);
+
+ sha256_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m19400_sxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (int i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
+ }
+
+ sha256_ctx_t ctx1;
+
+ sha256_init (&ctx1);
+
+ sha256_update_global_swap (&ctx1, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ sha256_ctx_t ctx0 = ctx1;
+
+ sha256_update_global_swap (&ctx0, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ sha256_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+ const u32 e = ctx0.h[4];
+ const u32 f = ctx0.h[5];
+ const u32 g = ctx0.h[6];
+ const u32 h = ctx0.h[7];
+
+ sha256_ctx_t ctx;
+
+ sha256_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+ w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
+ w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+ w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
+ w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+ w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
+ w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+ w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
+ w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+ w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
+ w2[2] = uint_to_hex_lower8_le ((f >> 16) & 255) << 0 | uint_to_hex_lower8_le ((f >> 24) & 255) << 16;
+ w2[3] = uint_to_hex_lower8_le ((f >> 0) & 255) << 0 | uint_to_hex_lower8_le ((f >> 8) & 255) << 16;
+ w3[0] = uint_to_hex_lower8_le ((g >> 16) & 255) << 0 | uint_to_hex_lower8_le ((g >> 24) & 255) << 16;
+ w3[1] = uint_to_hex_lower8_le ((g >> 0) & 255) << 0 | uint_to_hex_lower8_le ((g >> 8) & 255) << 16;
+ w3[2] = uint_to_hex_lower8_le ((h >> 16) & 255) << 0 | uint_to_hex_lower8_le ((h >> 24) & 255) << 16;
+ w3[3] = uint_to_hex_lower8_le ((h >> 0) & 255) << 0 | uint_to_hex_lower8_le ((h >> 8) & 255) << 16;
+
+ sha256_update_64 (&ctx, w0, w1, w2, w3, 64);
+
+ sha256_update (&ctx, s, salt_len);
+
+ sha256_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m19400_a3-pure.cl b/OpenCL/m19400_a3-pure.cl
new file mode 100644
index 000000000..7798664b6
--- /dev/null
+++ b/OpenCL/m19400_a3-pure.cl
@@ -0,0 +1,285 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m19400_mxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32x s[64] = { 0 };
+
+ for (int i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
+ }
+
+ /**
+ * loop
+ */
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ sha256_ctx_vector_t ctx0;
+
+ sha256_init_vector (&ctx0);
+
+ sha256_update_vector (&ctx0, w, pw_len);
+
+ sha256_final_vector (&ctx0);
+
+ const u32x a = ctx0.h[0];
+ const u32x b = ctx0.h[1];
+ const u32x c = ctx0.h[2];
+ const u32x d = ctx0.h[3];
+ const u32x e = ctx0.h[4];
+ const u32x f = ctx0.h[5];
+ const u32x g = ctx0.h[6];
+ const u32x h = ctx0.h[7];
+
+ sha256_ctx_vector_t ctx;
+
+ sha256_init_vector (&ctx);
+
+ _w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
+ _w2[2] = uint_to_hex_lower8_le ((f >> 16) & 255) << 0 | uint_to_hex_lower8_le ((f >> 24) & 255) << 16;
+ _w2[3] = uint_to_hex_lower8_le ((f >> 0) & 255) << 0 | uint_to_hex_lower8_le ((f >> 8) & 255) << 16;
+ _w3[0] = uint_to_hex_lower8_le ((g >> 16) & 255) << 0 | uint_to_hex_lower8_le ((g >> 24) & 255) << 16;
+ _w3[1] = uint_to_hex_lower8_le ((g >> 0) & 255) << 0 | uint_to_hex_lower8_le ((g >> 8) & 255) << 16;
+ _w3[2] = uint_to_hex_lower8_le ((h >> 16) & 255) << 0 | uint_to_hex_lower8_le ((h >> 24) & 255) << 16;
+ _w3[3] = uint_to_hex_lower8_le ((h >> 0) & 255) << 0 | uint_to_hex_lower8_le ((h >> 8) & 255) << 16;
+
+ sha256_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 64);
+
+ sha256_update_vector (&ctx, s, salt_len);
+
+ sha256_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m19400_sxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32x s[64] = { 0 };
+
+ for (int i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
+ }
+
+ /**
+ * loop
+ */
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ sha256_ctx_vector_t ctx0;
+
+ sha256_init_vector (&ctx0);
+
+ sha256_update_vector (&ctx0, w, pw_len);
+
+ sha256_final_vector (&ctx0);
+
+ const u32x a = ctx0.h[0];
+ const u32x b = ctx0.h[1];
+ const u32x c = ctx0.h[2];
+ const u32x d = ctx0.h[3];
+ const u32x e = ctx0.h[4];
+ const u32x f = ctx0.h[5];
+ const u32x g = ctx0.h[6];
+ const u32x h = ctx0.h[7];
+
+ sha256_ctx_vector_t ctx;
+
+ sha256_init_vector (&ctx);
+
+ _w0[0] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
+ _w2[2] = uint_to_hex_lower8_le ((f >> 16) & 255) << 0 | uint_to_hex_lower8_le ((f >> 24) & 255) << 16;
+ _w2[3] = uint_to_hex_lower8_le ((f >> 0) & 255) << 0 | uint_to_hex_lower8_le ((f >> 8) & 255) << 16;
+ _w3[0] = uint_to_hex_lower8_le ((g >> 16) & 255) << 0 | uint_to_hex_lower8_le ((g >> 24) & 255) << 16;
+ _w3[1] = uint_to_hex_lower8_le ((g >> 0) & 255) << 0 | uint_to_hex_lower8_le ((g >> 8) & 255) << 16;
+ _w3[2] = uint_to_hex_lower8_le ((h >> 16) & 255) << 0 | uint_to_hex_lower8_le ((h >> 24) & 255) << 16;
+ _w3[3] = uint_to_hex_lower8_le ((h >> 0) & 255) << 0 | uint_to_hex_lower8_le ((h >> 8) & 255) << 16;
+
+ sha256_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 64);
+
+ sha256_update_vector (&ctx, s, salt_len);
+
+ sha256_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SIMD (r0, r1, r2, r3);
+ }
+}
diff --git a/docs/changes.txt b/docs/changes.txt
index 0bb228187..ca110004f 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,6 +35,7 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
+- Added hash-mode: AuthMe - sha256(sha256($pass).$salt)
##
## Bugs
diff --git a/docs/readme.txt b/docs/readme.txt
index 9e36b73ce..71963b378 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -92,6 +92,7 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- sha512($salt.$pass)
- sha512(utf16le($pass).$salt)
- sha512($salt.utf16le($pass))
+- AuthMe - sha256(sha256($pass).$salt)
- HMAC-MD5 (key = $pass)
- HMAC-MD5 (key = $salt)
- HMAC-SHA1 (key = $pass)
diff --git a/src/modules/module_19400.c b/src/modules/module_19400.c
new file mode 100644
index 000000000..35adb27b2
--- /dev/null
+++ b/src/modules/module_19400.c
@@ -0,0 +1,293 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+#include "memory.h"
+
+static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL;
+static const u32 DGST_POS0 = 3;
+static const u32 DGST_POS1 = 7;
+static const u32 DGST_POS2 = 2;
+static const u32 DGST_POS3 = 6;
+static const u32 DGST_SIZE = DGST_SIZE_4_8;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
+static const char *HASH_NAME = "AuthMe - sha256(sha256($pass).$salt)";
+static const u64 KERN_TYPE = 19400;
+static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
+ | OPTI_TYPE_PRECOMPUTE_INIT
+ | OPTI_TYPE_EARLY_SKIP
+ | OPTI_TYPE_NOT_ITERATED
+ | OPTI_TYPE_RAW_HASH;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_BE
+ | OPTS_TYPE_PT_ADD80
+ | OPTS_TYPE_PT_ADDBITS15;
+static const u32 SALT_TYPE = SALT_TYPE_EMBEDDED;
+static const char *ST_PASS = "hashcat";
+static const char *ST_HASH = "$SHA$7218532375810603$bfede293ecf6539211a7305ea218b9f3f608953130405cda9eaba6fb6250f824";
+
+u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
+u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
+u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
+u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
+u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
+u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
+u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
+const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
+u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
+u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
+u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
+u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
+const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
+const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+
+u32 module_salt_min (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+ const u32 salt_min = 16;
+
+ return salt_min;
+}
+
+u32 module_salt_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+ const u32 salt_max = 16;
+
+ return salt_max;
+}
+
+u32 module_pw_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+ const u32 pw_max = 32;
+
+ return pw_max;
+}
+
+static const char *SIGNATURE_AUTHME = "$SHA$";
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+ u32 *digest = (u32 *) digest_buf;
+
+ token_t token;
+
+ token.token_cnt = 3;
+
+ token.signatures_cnt = 1;
+ token.signatures_buf[0] = SIGNATURE_AUTHME;
+
+ token.len[0] = 5;
+ token.attr[0] = TOKEN_ATTR_FIXED_LENGTH
+ | TOKEN_ATTR_VERIFY_SIGNATURE;
+
+ token.sep[1] = '$';
+ token.len_min[1] = 16;
+ token.len_max[1] = 16;
+ token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_DIGIT;
+
+ token.sep[2] = '$';
+ token.len_min[2] = 64;
+ token.len_max[2] = 64;
+ token.attr[2] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_HEX;
+
+ const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+ if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+ // salt
+
+ const u8 *salt_pos = token.buf[1];
+ const int salt_len = token.len[1];
+
+ memcpy ((u8 *) salt->salt_buf, salt_pos, salt_len);
+
+ salt->salt_len = salt_len;
+
+ // hash
+
+ const u8 *hash_pos = token.buf[2];
+
+ digest[0] = hex_to_u32 (hash_pos + 0);
+ digest[1] = hex_to_u32 (hash_pos + 8);
+ digest[2] = hex_to_u32 (hash_pos + 16);
+ digest[3] = hex_to_u32 (hash_pos + 24);
+ digest[4] = hex_to_u32 (hash_pos + 32);
+ digest[5] = hex_to_u32 (hash_pos + 40);
+ digest[6] = hex_to_u32 (hash_pos + 48);
+ digest[7] = hex_to_u32 (hash_pos + 56);
+
+ digest[0] = byte_swap_32 (digest[0]);
+ digest[1] = byte_swap_32 (digest[1]);
+ digest[2] = byte_swap_32 (digest[2]);
+ digest[3] = byte_swap_32 (digest[3]);
+ digest[4] = byte_swap_32 (digest[4]);
+ digest[5] = byte_swap_32 (digest[5]);
+ digest[6] = byte_swap_32 (digest[6]);
+ digest[7] = byte_swap_32 (digest[7]);
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ digest[0] -= SHA256M_A;
+ digest[1] -= SHA256M_B;
+ digest[2] -= SHA256M_C;
+ digest[3] -= SHA256M_D;
+ digest[4] -= SHA256M_E;
+ digest[5] -= SHA256M_F;
+ digest[6] -= SHA256M_G;
+ digest[7] -= SHA256M_H;
+ }
+
+ return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+ const u32 *digest = (const u32 *) digest_buf;
+
+ int line_len = 0;
+
+ // signature
+
+ line_buf[line_len++] = '$';
+ line_buf[line_len++] = 'S';
+ line_buf[line_len++] = 'H';
+ line_buf[line_len++] = 'A';
+ line_buf[line_len++] = '$';
+
+ // salt
+
+ memcpy (line_buf + line_len, salt->salt_buf, salt->salt_len);
+
+ line_len += salt->salt_len;
+
+ line_buf[line_len++] = '$';
+
+ // digest
+
+ u32 tmp[8];
+
+ tmp[0] = digest[0];
+ tmp[1] = digest[1];
+ tmp[2] = digest[2];
+ tmp[3] = digest[3];
+ tmp[4] = digest[4];
+ tmp[5] = digest[5];
+ tmp[6] = digest[6];
+ tmp[7] = digest[7];
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ tmp[0] += SHA256M_A;
+ tmp[1] += SHA256M_B;
+ tmp[2] += SHA256M_C;
+ tmp[3] += SHA256M_D;
+ tmp[4] += SHA256M_E;
+ tmp[5] += SHA256M_F;
+ tmp[6] += SHA256M_G;
+ tmp[7] += SHA256M_H;
+ }
+
+ tmp[0] = byte_swap_32 (tmp[0]);
+ tmp[1] = byte_swap_32 (tmp[1]);
+ tmp[2] = byte_swap_32 (tmp[2]);
+ tmp[3] = byte_swap_32 (tmp[3]);
+ tmp[4] = byte_swap_32 (tmp[4]);
+ tmp[5] = byte_swap_32 (tmp[5]);
+ tmp[6] = byte_swap_32 (tmp[6]);
+ tmp[7] = byte_swap_32 (tmp[7]);
+
+ u8 *out_buf = (u8 *) line_buf;
+
+ u32_to_hex (tmp[0], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[1], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[2], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[3], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[4], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[5], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[6], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[7], out_buf + line_len); line_len += 8;
+
+ line_buf[line_len] = 0;
+
+ return line_len;
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+ module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
+ module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
+
+ module_ctx->module_attack_exec = module_attack_exec;
+ module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_mask = MODULE_DEFAULT;
+ module_ctx->module_benchmark_salt = MODULE_DEFAULT;
+ module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
+ module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
+ module_ctx->module_dgst_pos0 = module_dgst_pos0;
+ module_ctx->module_dgst_pos1 = module_dgst_pos1;
+ module_ctx->module_dgst_pos2 = module_dgst_pos2;
+ module_ctx->module_dgst_pos3 = module_dgst_pos3;
+ module_ctx->module_dgst_size = module_dgst_size;
+ module_ctx->module_dictstat_disable = MODULE_DEFAULT;
+ module_ctx->module_esalt_size = MODULE_DEFAULT;
+ module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
+ module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_count = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_save = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
+ module_ctx->module_hash_decode = module_hash_decode;
+ module_ctx->module_hash_encode_status = MODULE_DEFAULT;
+ module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_encode = module_hash_encode;
+ module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
+ module_ctx->module_hash_mode = MODULE_DEFAULT;
+ module_ctx->module_hash_category = module_hash_category;
+ module_ctx->module_hash_name = module_hash_name;
+ module_ctx->module_hashes_count_min = MODULE_DEFAULT;
+ module_ctx->module_hashes_count_max = MODULE_DEFAULT;
+ module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
+ module_ctx->module_hook12 = MODULE_DEFAULT;
+ module_ctx->module_hook23 = MODULE_DEFAULT;
+ module_ctx->module_hook_salt_size = MODULE_DEFAULT;
+ module_ctx->module_hook_size = MODULE_DEFAULT;
+ module_ctx->module_jit_build_options = MODULE_DEFAULT;
+ module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
+ module_ctx->module_kern_type = module_kern_type;
+ module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
+ module_ctx->module_opti_type = module_opti_type;
+ module_ctx->module_opts_type = module_opts_type;
+ module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
+ module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
+ module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
+ module_ctx->module_potfile_disable = MODULE_DEFAULT;
+ module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
+ module_ctx->module_pwdump_column = MODULE_DEFAULT;
+ module_ctx->module_pw_max = module_pw_max;
+ module_ctx->module_pw_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = module_salt_max;
+ module_ctx->module_salt_min = module_salt_min;
+ module_ctx->module_salt_type = module_salt_type;
+ module_ctx->module_separator = MODULE_DEFAULT;
+ module_ctx->module_st_hash = module_st_hash;
+ module_ctx->module_st_pass = module_st_pass;
+ module_ctx->module_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_unstable_warning = MODULE_DEFAULT;
+ module_ctx->module_warmup_disable = MODULE_DEFAULT;
+}
diff --git a/src/mpsp.c b/src/mpsp.c
index 0fce4d5fb..89a1b41e4 100644
--- a/src/mpsp.c
+++ b/src/mpsp.c
@@ -1232,7 +1232,7 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
sp_tbl_to_css (mask_ctx->root_table_buf, mask_ctx->markov_table_buf, mask_ctx->root_css_buf, mask_ctx->markov_css_buf, user_options->markov_threshold, uniq_tbls);
- if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1) return -1;
+ if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1)
{
event_log_error (hashcat_ctx, "Integer overflow detected in keyspace of mask: %s", mask_ctx->mask);
diff --git a/tools/test_modules/m19400.pm b/tools/test_modules/m19400.pm
new file mode 100644
index 000000000..f2fddb511
--- /dev/null
+++ b/tools/test_modules/m19400.pm
@@ -0,0 +1,48 @@
+#!/usr/bin/env perl
+
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use Digest::SHA qw (sha256_hex);
+
+sub module_constraints { [[1, 32], [16, 16], [-1, -1], [-1, -1], [-1, -1]] }
+
+sub module_generate_hash
+{
+ my $word = shift;
+ my $salt = shift;
+
+ my $digest = sha256_hex (sha256_hex ($word) . $salt);
+
+ my $hash = sprintf ("\$SHA\$%s\$%s", $salt, $digest);
+
+ return $hash;
+}
+
+sub module_verify_hash
+{
+ my $line = shift;
+
+ my ($digest, $word) = split (':', $line);
+
+ return unless defined $digest;
+ return unless defined $word;
+
+ my (undef, $signature, $salt, $hash) = split ('\$', $digest);
+
+ return unless ($signature eq 'SHA');
+ return unless length ($salt) == 16;
+
+ my $word_packed = pack_if_HEX_notation ($word);
+
+ my $new_hash = module_generate_hash ($word_packed, $salt);
+
+ return ($new_hash, $word);
+}
+
+1;
From eedceb698f4dffeb959c31212a2f15797a4c5872 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Thu, 25 Jul 2019 23:56:20 +0200
Subject: [PATCH 023/113] Added hash-mode: md5(sha1().md5().sha1())
---
OpenCL/m04410_a0-pure.cl | 402 +++++++++++++++++++++++++++++++++
OpenCL/m04410_a1-pure.cl | 404 +++++++++++++++++++++++++++++++++
OpenCL/m04410_a3-pure.cl | 422 +++++++++++++++++++++++++++++++++++
docs/changes.txt | 1 +
docs/credits.txt | 1 +
docs/readme.txt | 1 +
src/modules/module_04410.c | 190 ++++++++++++++++
src/mpsp.c | 2 +-
tools/test_modules/m04410.pm | 43 ++++
9 files changed, 1465 insertions(+), 1 deletion(-)
create mode 100644 OpenCL/m04410_a0-pure.cl
create mode 100644 OpenCL/m04410_a1-pure.cl
create mode 100644 OpenCL/m04410_a3-pure.cl
create mode 100644 src/modules/module_04410.c
create mode 100644 tools/test_modules/m04410.pm
diff --git a/OpenCL/m04410_a0-pure.cl b/OpenCL/m04410_a0-pure.cl
new file mode 100644
index 000000000..bd4c96415
--- /dev/null
+++ b/OpenCL/m04410_a0-pure.cl
@@ -0,0 +1,402 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp.h"
+#include "inc_rp.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04410_mxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ sha1_ctx_t ctx0;
+
+ sha1_init (&ctx0);
+
+ sha1_update_swap (&ctx0, tmp.i, tmp.pw_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a0 = ctx0.h[0];
+ const u32 b0 = ctx0.h[1];
+ const u32 c0 = ctx0.h[2];
+ const u32 d0 = ctx0.h[3];
+ const u32 e0 = ctx0.h[4];
+
+ md5_ctx_t ctx1;
+
+ md5_init (&ctx1);
+
+ md5_update (&ctx1, tmp.i, tmp.pw_len);
+
+ md5_final (&ctx1);
+
+ const u32 a1 = hc_swap32 (ctx1.h[0]);
+ const u32 b1 = hc_swap32 (ctx1.h[1]);
+ const u32 c1 = hc_swap32 (ctx1.h[2]);
+ const u32 d1 = hc_swap32 (ctx1.h[3]);
+
+ md5_ctx_t ctx;
+
+ md5_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ md5_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04410_sxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ sha1_ctx_t ctx0;
+
+ sha1_init (&ctx0);
+
+ sha1_update_swap (&ctx0, tmp.i, tmp.pw_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a0 = ctx0.h[0];
+ const u32 b0 = ctx0.h[1];
+ const u32 c0 = ctx0.h[2];
+ const u32 d0 = ctx0.h[3];
+ const u32 e0 = ctx0.h[4];
+
+ md5_ctx_t ctx1;
+
+ md5_init (&ctx1);
+
+ md5_update (&ctx1, tmp.i, tmp.pw_len);
+
+ md5_final (&ctx1);
+
+ const u32 a1 = hc_swap32 (ctx1.h[0]);
+ const u32 b1 = hc_swap32 (ctx1.h[1]);
+ const u32 c1 = hc_swap32 (ctx1.h[2]);
+ const u32 d1 = hc_swap32 (ctx1.h[3]);
+
+ md5_ctx_t ctx;
+
+ md5_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ md5_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m04410_a1-pure.cl b/OpenCL/m04410_a1-pure.cl
new file mode 100644
index 000000000..45953c61b
--- /dev/null
+++ b/OpenCL/m04410_a1-pure.cl
@@ -0,0 +1,404 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04410_mxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ sha1_ctx_t ctx00;
+
+ sha1_init (&ctx00);
+
+ sha1_update_global_swap (&ctx00, pws[gid].i, pws[gid].pw_len);
+
+ md5_ctx_t ctx11;
+
+ md5_init (&ctx11);
+
+ md5_update_global (&ctx11, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ sha1_ctx_t ctx0 = ctx00;
+
+ sha1_update_global_swap (&ctx0, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a0 = ctx0.h[0];
+ const u32 b0 = ctx0.h[1];
+ const u32 c0 = ctx0.h[2];
+ const u32 d0 = ctx0.h[3];
+ const u32 e0 = ctx0.h[4];
+
+ md5_ctx_t ctx1 = ctx11;
+
+ md5_update_global (&ctx1, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ md5_final (&ctx1);
+
+ const u32 a1 = hc_swap32 (ctx1.h[0]);
+ const u32 b1 = hc_swap32 (ctx1.h[1]);
+ const u32 c1 = hc_swap32 (ctx1.h[2]);
+ const u32 d1 = hc_swap32 (ctx1.h[3]);
+
+ md5_ctx_t ctx;
+
+ md5_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ md5_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04410_sxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ sha1_ctx_t ctx00;
+
+ sha1_init (&ctx00);
+
+ sha1_update_global_swap (&ctx00, pws[gid].i, pws[gid].pw_len);
+
+ md5_ctx_t ctx11;
+
+ md5_init (&ctx11);
+
+ md5_update_global (&ctx11, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ sha1_ctx_t ctx0 = ctx00;
+
+ sha1_update_global_swap (&ctx0, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a0 = ctx0.h[0];
+ const u32 b0 = ctx0.h[1];
+ const u32 c0 = ctx0.h[2];
+ const u32 d0 = ctx0.h[3];
+ const u32 e0 = ctx0.h[4];
+
+ md5_ctx_t ctx1 = ctx11;
+
+ md5_update_global (&ctx1, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ md5_final (&ctx1);
+
+ const u32 a1 = hc_swap32 (ctx1.h[0]);
+ const u32 b1 = hc_swap32 (ctx1.h[1]);
+ const u32 c1 = hc_swap32 (ctx1.h[2]);
+ const u32 d1 = hc_swap32 (ctx1.h[3]);
+
+ md5_ctx_t ctx;
+
+ md5_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ md5_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m04410_a3-pure.cl b/OpenCL/m04410_a3-pure.cl
new file mode 100644
index 000000000..c93d52b70
--- /dev/null
+++ b/OpenCL/m04410_a3-pure.cl
@@ -0,0 +1,422 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04410_mxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ sha1_ctx_vector_t ctx0;
+
+ sha1_init_vector (&ctx0);
+
+ sha1_update_vector_swap (&ctx0, w, pw_len);
+
+ sha1_final_vector (&ctx0);
+
+ const u32x a0 = ctx0.h[0];
+ const u32x b0 = ctx0.h[1];
+ const u32x c0 = ctx0.h[2];
+ const u32x d0 = ctx0.h[3];
+ const u32x e0 = ctx0.h[4];
+
+ md5_ctx_vector_t ctx1;
+
+ md5_init_vector (&ctx1);
+
+ md5_update_vector (&ctx1, w, pw_len);
+
+ md5_final_vector (&ctx1);
+
+ const u32x a1 = hc_swap32 (ctx1.h[0]);
+ const u32x b1 = hc_swap32 (ctx1.h[1]);
+ const u32x c1 = hc_swap32 (ctx1.h[2]);
+ const u32x d1 = hc_swap32 (ctx1.h[3]);
+
+ md5_ctx_vector_t ctx;
+
+ md5_init_vector (&ctx);
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ md5_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 40);
+
+ _w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ md5_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ md5_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 40);
+
+ md5_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04410_sxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ sha1_ctx_vector_t ctx0;
+
+ sha1_init_vector (&ctx0);
+
+ sha1_update_vector_swap (&ctx0, w, pw_len);
+
+ sha1_final_vector (&ctx0);
+
+ const u32x a0 = ctx0.h[0];
+ const u32x b0 = ctx0.h[1];
+ const u32x c0 = ctx0.h[2];
+ const u32x d0 = ctx0.h[3];
+ const u32x e0 = ctx0.h[4];
+
+ md5_ctx_vector_t ctx1;
+
+ md5_init_vector (&ctx1);
+
+ md5_update_vector (&ctx1, w, pw_len);
+
+ md5_final_vector (&ctx1);
+
+ const u32x a1 = hc_swap32 (ctx1.h[0]);
+ const u32x b1 = hc_swap32 (ctx1.h[1]);
+ const u32x c1 = hc_swap32 (ctx1.h[2]);
+ const u32x d1 = hc_swap32 (ctx1.h[3]);
+
+ md5_ctx_vector_t ctx;
+
+ md5_init_vector (&ctx);
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ md5_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 40);
+
+ _w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ md5_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ md5_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 40);
+
+ md5_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SIMD (r0, r1, r2, r3);
+ }
+}
diff --git a/docs/changes.txt b/docs/changes.txt
index 0bb228187..76388fccc 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,6 +35,7 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
+- Added hash-mode: md5(sha1($pass).md5($pass).sha1($pass))
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index bd21d35d7..73e07221c 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,6 +18,7 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
+* md5(sha1($pass).md5($pass).sha1($pass)) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
diff --git a/docs/readme.txt b/docs/readme.txt
index 9e36b73ce..7eac7a963 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -74,6 +74,7 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- md5(md5($pass).md5($salt))
- md5(strtoupper(md5($pass)))
- md5(sha1($pass))
+- md5(sha1($pass).md5($pass).sha1($pass))
- sha1($pass.$salt)
- sha1($salt.$pass)
- sha1(utf16le($pass).$salt)
diff --git a/src/modules/module_04410.c b/src/modules/module_04410.c
new file mode 100644
index 000000000..36ca3de20
--- /dev/null
+++ b/src/modules/module_04410.c
@@ -0,0 +1,190 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+
+static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL;
+static const u32 DGST_POS0 = 0;
+static const u32 DGST_POS1 = 3;
+static const u32 DGST_POS2 = 2;
+static const u32 DGST_POS3 = 1;
+static const u32 DGST_SIZE = DGST_SIZE_4_4;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
+static const char *HASH_NAME = "md5(sha1($pass).md5($pass).sha1($pass))";
+static const u64 KERN_TYPE = 4410;
+static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
+ | OPTI_TYPE_PRECOMPUTE_INIT
+ | OPTI_TYPE_EARLY_SKIP
+ | OPTI_TYPE_NOT_ITERATED
+ | OPTI_TYPE_NOT_SALTED
+ | OPTI_TYPE_RAW_HASH;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE
+ | OPTS_TYPE_PT_ADD80
+ | OPTS_TYPE_PT_ADDBITS14;
+static const u32 SALT_TYPE = SALT_TYPE_NONE;
+static const char *ST_PASS = "hashcat";
+static const char *ST_HASH = "100b3a4fc1dc8d60d9bf40688d8b740a";
+
+u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
+u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
+u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
+u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
+u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
+u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
+u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
+const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
+u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
+u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
+u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
+u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
+const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
+const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+ u32 *digest = (u32 *) digest_buf;
+
+ token_t token;
+
+ token.token_cnt = 1;
+
+ token.len_min[0] = 32;
+ token.len_max[0] = 32;
+ token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_HEX;
+
+ const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+ if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+ const u8 *hash_pos = token.buf[0];
+
+ digest[0] = hex_to_u32 (hash_pos + 0);
+ digest[1] = hex_to_u32 (hash_pos + 8);
+ digest[2] = hex_to_u32 (hash_pos + 16);
+ digest[3] = hex_to_u32 (hash_pos + 24);
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ digest[0] -= MD5M_A;
+ digest[1] -= MD5M_B;
+ digest[2] -= MD5M_C;
+ digest[3] -= MD5M_D;
+ }
+
+ return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+ const u32 *digest = (const u32 *) digest_buf;
+
+ // we can not change anything in the original buffer, otherwise destroying sorting
+ // therefore create some local buffer
+
+ u32 tmp[4];
+
+ tmp[0] = digest[0];
+ tmp[1] = digest[1];
+ tmp[2] = digest[2];
+ tmp[3] = digest[3];
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ tmp[0] += MD5M_A;
+ tmp[1] += MD5M_B;
+ tmp[2] += MD5M_C;
+ tmp[3] += MD5M_D;
+ }
+
+ u8 *out_buf = (u8 *) line_buf;
+
+ int out_len = 0;
+
+ u32_to_hex (tmp[0], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[1], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[2], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[3], out_buf + out_len); out_len += 8;
+
+ return out_len;
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+ module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
+ module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
+
+ module_ctx->module_attack_exec = module_attack_exec;
+ module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_mask = MODULE_DEFAULT;
+ module_ctx->module_benchmark_salt = MODULE_DEFAULT;
+ module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
+ module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
+ module_ctx->module_dgst_pos0 = module_dgst_pos0;
+ module_ctx->module_dgst_pos1 = module_dgst_pos1;
+ module_ctx->module_dgst_pos2 = module_dgst_pos2;
+ module_ctx->module_dgst_pos3 = module_dgst_pos3;
+ module_ctx->module_dgst_size = module_dgst_size;
+ module_ctx->module_dictstat_disable = MODULE_DEFAULT;
+ module_ctx->module_esalt_size = MODULE_DEFAULT;
+ module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
+ module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_count = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_save = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
+ module_ctx->module_hash_decode = module_hash_decode;
+ module_ctx->module_hash_encode_status = MODULE_DEFAULT;
+ module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_encode = module_hash_encode;
+ module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
+ module_ctx->module_hash_mode = MODULE_DEFAULT;
+ module_ctx->module_hash_category = module_hash_category;
+ module_ctx->module_hash_name = module_hash_name;
+ module_ctx->module_hashes_count_min = MODULE_DEFAULT;
+ module_ctx->module_hashes_count_max = MODULE_DEFAULT;
+ module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
+ module_ctx->module_hook12 = MODULE_DEFAULT;
+ module_ctx->module_hook23 = MODULE_DEFAULT;
+ module_ctx->module_hook_salt_size = MODULE_DEFAULT;
+ module_ctx->module_hook_size = MODULE_DEFAULT;
+ module_ctx->module_jit_build_options = MODULE_DEFAULT;
+ module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
+ module_ctx->module_kern_type = module_kern_type;
+ module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
+ module_ctx->module_opti_type = module_opti_type;
+ module_ctx->module_opts_type = module_opts_type;
+ module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
+ module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
+ module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
+ module_ctx->module_potfile_disable = MODULE_DEFAULT;
+ module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
+ module_ctx->module_pwdump_column = MODULE_DEFAULT;
+ module_ctx->module_pw_max = MODULE_DEFAULT;
+ module_ctx->module_pw_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = MODULE_DEFAULT;
+ module_ctx->module_salt_min = MODULE_DEFAULT;
+ module_ctx->module_salt_type = module_salt_type;
+ module_ctx->module_separator = MODULE_DEFAULT;
+ module_ctx->module_st_hash = module_st_hash;
+ module_ctx->module_st_pass = module_st_pass;
+ module_ctx->module_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_unstable_warning = MODULE_DEFAULT;
+ module_ctx->module_warmup_disable = MODULE_DEFAULT;
+}
diff --git a/src/mpsp.c b/src/mpsp.c
index 0fce4d5fb..89a1b41e4 100644
--- a/src/mpsp.c
+++ b/src/mpsp.c
@@ -1232,7 +1232,7 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
sp_tbl_to_css (mask_ctx->root_table_buf, mask_ctx->markov_table_buf, mask_ctx->root_css_buf, mask_ctx->markov_css_buf, user_options->markov_threshold, uniq_tbls);
- if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1) return -1;
+ if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1)
{
event_log_error (hashcat_ctx, "Integer overflow detected in keyspace of mask: %s", mask_ctx->mask);
diff --git a/tools/test_modules/m04410.pm b/tools/test_modules/m04410.pm
new file mode 100644
index 000000000..968e6f574
--- /dev/null
+++ b/tools/test_modules/m04410.pm
@@ -0,0 +1,43 @@
+#!/usr/bin/env perl
+
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use Digest::MD5 qw (md5_hex);
+use Digest::SHA qw (sha1_hex);
+
+sub module_constraints { [[0, 256], [-1, -1], [0, 55], [-1, -1], [-1, -1]] }
+
+sub module_generate_hash
+{
+ my $word = shift;
+
+ my $digest = md5_hex (sha1_hex ($word) . md5_hex ($word) . sha1_hex ($word));
+
+ my $hash = sprintf ("%s", $digest);
+
+ return $hash;
+}
+
+sub module_verify_hash
+{
+ my $line = shift;
+
+ my ($hash, $word) = split (':', $line);
+
+ return unless defined $hash;
+ return unless defined $word;
+
+ my $word_packed = pack_if_HEX_notation ($word);
+
+ my $new_hash = module_generate_hash ($word_packed);
+
+ return ($new_hash, $word);
+}
+
+1;
From 49436f10502fea3895d8cdea3c442f454df74c0e Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Fri, 26 Jul 2019 00:04:22 +0200
Subject: [PATCH 024/113] update credits
---
docs/credits.txt | 1 +
1 file changed, 1 insertion(+)
diff --git a/docs/credits.txt b/docs/credits.txt
index bd21d35d7..bd08200cc 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,6 +18,7 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
+* AuthMe - sha256(sha256($pass).$salt) kernel module (thanks to @0xbsec)
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
From bbee1890cdc947ce74b7b30f86aed39315158ba1 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Fri, 26 Jul 2019 01:46:43 +0200
Subject: [PATCH 025/113] Added hash-mode: sha1(md5(pass).salt)
---
OpenCL/m04710_a0-pure.cl | 276 ++++++++++++++++++++++++++++++++
OpenCL/m04710_a1-pure.cl | 270 ++++++++++++++++++++++++++++++++
OpenCL/m04710_a3-pure.cl | 296 +++++++++++++++++++++++++++++++++++
docs/changes.txt | 1 +
docs/credits.txt | 1 +
docs/readme.txt | 1 +
src/modules/module_04710.c | 224 ++++++++++++++++++++++++++
src/mpsp.c | 2 +-
tools/test_modules/m04710.pm | 45 ++++++
9 files changed, 1115 insertions(+), 1 deletion(-)
create mode 100644 OpenCL/m04710_a0-pure.cl
create mode 100644 OpenCL/m04710_a1-pure.cl
create mode 100644 OpenCL/m04710_a3-pure.cl
create mode 100644 src/modules/module_04710.c
create mode 100644 tools/test_modules/m04710.pm
diff --git a/OpenCL/m04710_a0-pure.cl b/OpenCL/m04710_a0-pure.cl
new file mode 100644
index 000000000..e11df4fd9
--- /dev/null
+++ b/OpenCL/m04710_a0-pure.cl
@@ -0,0 +1,276 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp.h"
+#include "inc_rp.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04710_mxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
+ }
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ md5_ctx_t ctx0;
+
+ md5_init (&ctx0);
+
+ md5_update (&ctx0, tmp.i, tmp.pw_len);
+
+ md5_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+
+ sha1_ctx_t ctx;
+
+ sha1_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha1_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ sha1_update (&ctx, s, salt_len);
+
+ sha1_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04710_sxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
+ }
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ md5_ctx_t ctx0;
+
+ md5_init (&ctx0);
+
+ md5_update (&ctx0, tmp.i, tmp.pw_len);
+
+ md5_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+
+ sha1_ctx_t ctx;
+
+ sha1_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha1_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ sha1_update (&ctx, s, salt_len);
+
+ sha1_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m04710_a1-pure.cl b/OpenCL/m04710_a1-pure.cl
new file mode 100644
index 000000000..50d7d3ddd
--- /dev/null
+++ b/OpenCL/m04710_a1-pure.cl
@@ -0,0 +1,270 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04710_mxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
+ }
+
+ md5_ctx_t ctx0;
+
+ md5_init (&ctx0);
+
+ md5_update_global (&ctx0, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ md5_ctx_t ctx1 = ctx0;
+
+ md5_update_global (&ctx1, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ md5_final (&ctx1);
+
+ const u32 a = ctx1.h[0];
+ const u32 b = ctx1.h[1];
+ const u32 c = ctx1.h[2];
+ const u32 d = ctx1.h[3];
+
+ sha1_ctx_t ctx;
+
+ sha1_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha1_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ sha1_update (&ctx, s, salt_len);
+
+ sha1_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04710_sxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
+ }
+
+ md5_ctx_t ctx0;
+
+ md5_init (&ctx0);
+
+ md5_update_global (&ctx0, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ md5_ctx_t ctx1 = ctx0;
+
+ md5_update_global (&ctx1, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ md5_final (&ctx1);
+
+ const u32 a = ctx1.h[0];
+ const u32 b = ctx1.h[1];
+ const u32 c = ctx1.h[2];
+ const u32 d = ctx1.h[3];
+
+ sha1_ctx_t ctx;
+
+ sha1_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha1_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ sha1_update (&ctx, s, salt_len);
+
+ sha1_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m04710_a3-pure.cl b/OpenCL/m04710_a3-pure.cl
new file mode 100644
index 000000000..23d62d71e
--- /dev/null
+++ b/OpenCL/m04710_a3-pure.cl
@@ -0,0 +1,296 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04710_mxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
+ }
+
+ /**
+ * loop
+ */
+
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ md5_ctx_vector_t ctx0;
+
+ md5_init_vector (&ctx0);
+
+ md5_update_vector (&ctx0, w, pw_len);
+
+ md5_final_vector (&ctx0);
+
+ const u32x a = ctx0.h[0];
+ const u32x b = ctx0.h[1];
+ const u32x c = ctx0.h[2];
+ const u32x d = ctx0.h[3];
+
+ sha1_ctx_vector_t ctx;
+
+ sha1_init_vector (&ctx);
+
+ _w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ sha1_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ sha1_update_vector (&ctx, s, salt_len);
+
+ sha1_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04710_sxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[idx]);
+ }
+
+ /**
+ * loop
+ */
+
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ md5_ctx_vector_t ctx0;
+
+ md5_init_vector (&ctx0);
+
+ md5_update_vector (&ctx0, w, pw_len);
+
+ md5_final_vector (&ctx0);
+
+ const u32x a = ctx0.h[0];
+ const u32x b = ctx0.h[1];
+ const u32x c = ctx0.h[2];
+ const u32x d = ctx0.h[3];
+
+ sha1_ctx_vector_t ctx;
+
+ sha1_init_vector (&ctx);
+
+ _w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ sha1_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ sha1_update_vector (&ctx, s, salt_len);
+
+ sha1_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SIMD (r0, r1, r2, r3);
+ }
+}
diff --git a/docs/changes.txt b/docs/changes.txt
index 0bb228187..0356f8522 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,6 +35,7 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
+- Added hash-mode: sha1(md5($pass).$salt)
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index bd21d35d7..9eb7b0dac 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,6 +18,7 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
+* sha1(md5($pass).$salt) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
diff --git a/docs/readme.txt b/docs/readme.txt
index 9e36b73ce..af2b146eb 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -81,6 +81,7 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- sha1(sha1($pass))
- sha1($salt.sha1($pass))
- sha1(md5($pass))
+- sha1(md5($pass).$salt)
- sha1(md5(md5($pass)))
- sha1($salt.$pass.$salt)
- sha1(CX)
diff --git a/src/modules/module_04710.c b/src/modules/module_04710.c
new file mode 100644
index 000000000..a229e280a
--- /dev/null
+++ b/src/modules/module_04710.c
@@ -0,0 +1,224 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+
+static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL;
+static const u32 DGST_POS0 = 3;
+static const u32 DGST_POS1 = 4;
+static const u32 DGST_POS2 = 2;
+static const u32 DGST_POS3 = 1;
+static const u32 DGST_SIZE = DGST_SIZE_4_5;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
+static const char *HASH_NAME = "sha1(md5($pass).$salt)";
+static const u64 KERN_TYPE = 4710;
+static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
+ | OPTI_TYPE_PRECOMPUTE_INIT
+ | OPTI_TYPE_EARLY_SKIP
+ | OPTI_TYPE_NOT_ITERATED
+ | OPTI_TYPE_RAW_HASH;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE
+ | OPTS_TYPE_PT_ADD80
+ | OPTS_TYPE_PT_ADDBITS14;
+static const u32 SALT_TYPE = SALT_TYPE_EMBEDDED;
+static const char *ST_PASS = "hashcat";
+static const char *ST_HASH = "53c724b7f34f09787ed3f1b316215fc35c789504:hashcat1";
+
+u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
+u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
+u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
+u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
+u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
+u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
+u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
+const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
+u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
+u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
+u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
+u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
+const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
+const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+ u32 *digest = (u32 *) digest_buf;
+
+ token_t token;
+
+ token.token_cnt = 2;
+
+ token.sep[0] = hashconfig->separator;
+ token.len_min[0] = 40;
+ token.len_max[0] = 40;
+ token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_HEX;
+
+ token.len_min[1] = 8;
+ token.len_max[1] = 8;
+ token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH;
+
+ const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+ if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+ const u8 *hash_pos = token.buf[0];
+
+ digest[0] = hex_to_u32 (hash_pos + 0);
+ digest[1] = hex_to_u32 (hash_pos + 8);
+ digest[2] = hex_to_u32 (hash_pos + 16);
+ digest[3] = hex_to_u32 (hash_pos + 24);
+ digest[4] = hex_to_u32 (hash_pos + 32);
+
+ digest[0] = byte_swap_32 (digest[0]);
+ digest[1] = byte_swap_32 (digest[1]);
+ digest[2] = byte_swap_32 (digest[2]);
+ digest[3] = byte_swap_32 (digest[3]);
+ digest[4] = byte_swap_32 (digest[4]);
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ digest[0] -= SHA1M_A;
+ digest[1] -= SHA1M_B;
+ digest[2] -= SHA1M_C;
+ digest[3] -= SHA1M_D;
+ digest[4] -= SHA1M_E;
+ }
+
+ const u8 *salt_pos = token.buf[1];
+ const int salt_len = token.len[1];
+
+ const bool parse_rc = generic_salt_decode (hashconfig, salt_pos, salt_len, (u8 *) salt->salt_buf, (int *) &salt->salt_len);
+
+ if (parse_rc == false) return (PARSER_SALT_LENGTH);
+
+ return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+ const u32 *digest = (const u32 *) digest_buf;
+
+ // we can not change anything in the original buffer, otherwise destroying sorting
+ // therefore create some local buffer
+
+ u32 tmp[5];
+
+ tmp[0] = digest[0];
+ tmp[1] = digest[1];
+ tmp[2] = digest[2];
+ tmp[3] = digest[3];
+ tmp[4] = digest[4];
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ tmp[0] += SHA1M_A;
+ tmp[1] += SHA1M_B;
+ tmp[2] += SHA1M_C;
+ tmp[3] += SHA1M_D;
+ tmp[4] += SHA1M_E;
+ }
+
+ tmp[0] = byte_swap_32 (tmp[0]);
+ tmp[1] = byte_swap_32 (tmp[1]);
+ tmp[2] = byte_swap_32 (tmp[2]);
+ tmp[3] = byte_swap_32 (tmp[3]);
+ tmp[4] = byte_swap_32 (tmp[4]);
+
+ u8 *out_buf = (u8 *) line_buf;
+
+ int out_len = 0;
+
+ u32_to_hex (tmp[0], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[1], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[2], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[3], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[4], out_buf + out_len); out_len += 8;
+
+ out_buf[out_len] = hashconfig->separator;
+
+ out_len += 1;
+
+ out_len += generic_salt_encode (hashconfig, (const u8 *) salt->salt_buf, (const int) salt->salt_len, (u8 *) out_buf + out_len);
+
+ return out_len;
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+ module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
+ module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
+
+ module_ctx->module_attack_exec = module_attack_exec;
+ module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_mask = MODULE_DEFAULT;
+ module_ctx->module_benchmark_salt = MODULE_DEFAULT;
+ module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
+ module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
+ module_ctx->module_dgst_pos0 = module_dgst_pos0;
+ module_ctx->module_dgst_pos1 = module_dgst_pos1;
+ module_ctx->module_dgst_pos2 = module_dgst_pos2;
+ module_ctx->module_dgst_pos3 = module_dgst_pos3;
+ module_ctx->module_dgst_size = module_dgst_size;
+ module_ctx->module_dictstat_disable = MODULE_DEFAULT;
+ module_ctx->module_esalt_size = MODULE_DEFAULT;
+ module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
+ module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_count = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_save = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
+ module_ctx->module_hash_decode = module_hash_decode;
+ module_ctx->module_hash_encode_status = MODULE_DEFAULT;
+ module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_encode = module_hash_encode;
+ module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
+ module_ctx->module_hash_mode = MODULE_DEFAULT;
+ module_ctx->module_hash_category = module_hash_category;
+ module_ctx->module_hash_name = module_hash_name;
+ module_ctx->module_hashes_count_min = MODULE_DEFAULT;
+ module_ctx->module_hashes_count_max = MODULE_DEFAULT;
+ module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
+ module_ctx->module_hook12 = MODULE_DEFAULT;
+ module_ctx->module_hook23 = MODULE_DEFAULT;
+ module_ctx->module_hook_salt_size = MODULE_DEFAULT;
+ module_ctx->module_hook_size = MODULE_DEFAULT;
+ module_ctx->module_jit_build_options = MODULE_DEFAULT;
+ module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
+ module_ctx->module_kern_type = module_kern_type;
+ module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
+ module_ctx->module_opti_type = module_opti_type;
+ module_ctx->module_opts_type = module_opts_type;
+ module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
+ module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
+ module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
+ module_ctx->module_potfile_disable = MODULE_DEFAULT;
+ module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
+ module_ctx->module_pwdump_column = MODULE_DEFAULT;
+ module_ctx->module_pw_max = MODULE_DEFAULT;
+ module_ctx->module_pw_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = MODULE_DEFAULT;
+ module_ctx->module_salt_min = MODULE_DEFAULT;
+ module_ctx->module_salt_type = module_salt_type;
+ module_ctx->module_separator = MODULE_DEFAULT;
+ module_ctx->module_st_hash = module_st_hash;
+ module_ctx->module_st_pass = module_st_pass;
+ module_ctx->module_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_unstable_warning = MODULE_DEFAULT;
+ module_ctx->module_warmup_disable = MODULE_DEFAULT;
+}
diff --git a/src/mpsp.c b/src/mpsp.c
index 0fce4d5fb..89a1b41e4 100644
--- a/src/mpsp.c
+++ b/src/mpsp.c
@@ -1232,7 +1232,7 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
sp_tbl_to_css (mask_ctx->root_table_buf, mask_ctx->markov_table_buf, mask_ctx->root_css_buf, mask_ctx->markov_css_buf, user_options->markov_threshold, uniq_tbls);
- if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1) return -1;
+ if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1)
{
event_log_error (hashcat_ctx, "Integer overflow detected in keyspace of mask: %s", mask_ctx->mask);
diff --git a/tools/test_modules/m04710.pm b/tools/test_modules/m04710.pm
new file mode 100644
index 000000000..e74a1596a
--- /dev/null
+++ b/tools/test_modules/m04710.pm
@@ -0,0 +1,45 @@
+#!/usr/bin/env perl
+
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use Digest::MD5 qw (md5_hex);
+use Digest::SHA qw (sha1_hex);
+
+sub module_constraints { [[0, 256], [-1, -1], [0, 55], [-1, -1], [-1, -1]] }
+
+sub module_generate_hash
+{
+ my $salt = random_hex_string (8, 8);
+ my $word = shift;
+
+ my $digest = sha1_hex (md5_hex ($word) . $salt);
+
+ my $hash = sprintf ("%s:%s", $digest, $salt);
+
+ return $hash;
+}
+
+sub module_verify_hash
+{
+ my $line = shift;
+
+ my ($hash, $salt, $word) = split (':', $line);
+
+ return unless defined $hash;
+ return unless defined $salt;
+ return unless defined $word;
+
+ my $word_packed = pack_if_HEX_notation ($word);
+
+ my $new_hash = module_generate_hash ($word_packed, $salt);
+
+ return ($new_hash, $word);
+}
+
+1;
From bf5d8af890842a9f04e6ec2ff250cdbc7dac5915 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Fri, 26 Jul 2019 12:17:44 +0200
Subject: [PATCH 026/113] remove the changes to src/mpsp.c
---
src/mpsp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/mpsp.c b/src/mpsp.c
index 89a1b41e4..0fce4d5fb 100644
--- a/src/mpsp.c
+++ b/src/mpsp.c
@@ -1232,7 +1232,7 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
sp_tbl_to_css (mask_ctx->root_table_buf, mask_ctx->markov_table_buf, mask_ctx->root_css_buf, mask_ctx->markov_css_buf, user_options->markov_threshold, uniq_tbls);
- if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1)
+ if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1) return -1;
{
event_log_error (hashcat_ctx, "Integer overflow detected in keyspace of mask: %s", mask_ctx->mask);
From 8ad2261a01f278670852bebf6799f4578c60bf5d Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Fri, 26 Jul 2019 12:35:14 +0200
Subject: [PATCH 027/113] remove the changes to src/mpsp.c
---
src/mpsp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/mpsp.c b/src/mpsp.c
index 89a1b41e4..0fce4d5fb 100644
--- a/src/mpsp.c
+++ b/src/mpsp.c
@@ -1232,7 +1232,7 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
sp_tbl_to_css (mask_ctx->root_table_buf, mask_ctx->markov_table_buf, mask_ctx->root_css_buf, mask_ctx->markov_css_buf, user_options->markov_threshold, uniq_tbls);
- if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1)
+ if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1) return -1;
{
event_log_error (hashcat_ctx, "Integer overflow detected in keyspace of mask: %s", mask_ctx->mask);
From b1d8035707ee441155fda2a52dcab36d3be1a6d1 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Fri, 26 Jul 2019 12:38:33 +0200
Subject: [PATCH 028/113] remove the changes to src/mpsp.c
---
src/mpsp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/mpsp.c b/src/mpsp.c
index 89a1b41e4..0fce4d5fb 100644
--- a/src/mpsp.c
+++ b/src/mpsp.c
@@ -1232,7 +1232,7 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
sp_tbl_to_css (mask_ctx->root_table_buf, mask_ctx->markov_table_buf, mask_ctx->root_css_buf, mask_ctx->markov_css_buf, user_options->markov_threshold, uniq_tbls);
- if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1)
+ if (sp_get_sum (0, mask_ctx->css_cnt, mask_ctx->root_css_buf, &combinator_ctx->combs_cnt) == -1) return -1;
{
event_log_error (hashcat_ctx, "Integer overflow detected in keyspace of mask: %s", mask_ctx->mask);
From af622f6df5e421b6695cc401ec4c407027698278 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Fri, 26 Jul 2019 23:47:32 +0200
Subject: [PATCH 029/113] Added hash-mode: BitShares v0.x -
sha512(sha512(pass))
---
OpenCL/m01770_a0-optimized.cl | 436 +++++++++++++++++++++++
OpenCL/m01770_a0-pure.cl | 171 +++++++++
OpenCL/m01770_a1-optimized.cl | 605 +++++++++++++++++++++++++++++++
OpenCL/m01770_a1-pure.cl | 165 +++++++++
OpenCL/m01770_a3-optimized.cl | 645 ++++++++++++++++++++++++++++++++++
OpenCL/m01770_a3-pure.cl | 191 ++++++++++
docs/changes.txt | 1 +
docs/credits.txt | 1 +
docs/readme.txt | 1 +
src/modules/module_01770.c | 230 ++++++++++++
tools/test_modules/m01770.pm | 43 +++
11 files changed, 2489 insertions(+)
create mode 100644 OpenCL/m01770_a0-optimized.cl
create mode 100644 OpenCL/m01770_a0-pure.cl
create mode 100644 OpenCL/m01770_a1-optimized.cl
create mode 100644 OpenCL/m01770_a1-pure.cl
create mode 100644 OpenCL/m01770_a3-optimized.cl
create mode 100644 OpenCL/m01770_a3-pure.cl
create mode 100644 src/modules/module_01770.c
create mode 100644 tools/test_modules/m01770.pm
diff --git a/OpenCL/m01770_a0-optimized.cl b/OpenCL/m01770_a0-optimized.cl
new file mode 100644
index 000000000..ebca7fe35
--- /dev/null
+++ b/OpenCL/m01770_a0-optimized.cl
@@ -0,0 +1,436 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha512.cl"
+#endif
+
+DECLSPEC void sha512_transform_opt (const u32x *w0, const u32x *w1, const u32x *w2, const u32x *w3, u64x *digest)
+{
+ u32x wend = 0x80000000;
+ u32x wlen = 64*8;
+
+ u64x w0_t = hl32_to_64 (w0[0], w0[1]);
+ u64x w1_t = hl32_to_64 (w0[2], w0[3]);
+ u64x w2_t = hl32_to_64 (w1[0], w1[1]);
+ u64x w3_t = hl32_to_64 (w1[2], w1[3]);
+ u64x w4_t = hl32_to_64 (w2[0], w2[1]);
+ u64x w5_t = hl32_to_64 (w2[2], w2[3]);
+ u64x w6_t = hl32_to_64 (w3[0], w3[1]);
+ u64x w7_t = hl32_to_64 (w3[2], w3[3]);
+ u64x w8_t = hl32_to_64 (wend, 0);
+ u64x w9_t = 0;
+ u64x wa_t = 0;
+ u64x wb_t = 0;
+ u64x wc_t = 0;
+ u64x wd_t = 0;
+ u64x we_t = 0;
+ u64x wf_t = hl32_to_64 (0, wlen);
+
+ u64x a = digest[0];
+ u64x b = digest[1];
+ u64x c = digest[2];
+ u64x d = digest[3];
+ u64x e = digest[4];
+ u64x f = digest[5];
+ u64x g = digest[6];
+ u64x h = digest[7];
+
+ #define ROUND_EXPAND() \
+ { \
+ w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
+ w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
+ w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
+ w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
+ w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
+ w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
+ w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
+ w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
+ w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
+ w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
+ wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
+ wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
+ wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
+ wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
+ we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
+ wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
+ }
+
+ #define ROUND_STEP(i) \
+ { \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
+ }
+
+ ROUND_STEP (0);
+
+ #ifdef IS_CUDA
+ ROUND_EXPAND (); ROUND_STEP (16);
+ ROUND_EXPAND (); ROUND_STEP (32);
+ ROUND_EXPAND (); ROUND_STEP (48);
+ ROUND_EXPAND (); ROUND_STEP (64);
+ #else
+ #ifdef _unroll
+ #pragma unroll
+ #endif
+ for (int i = 16; i < 80; i += 16)
+ {
+ ROUND_EXPAND (); ROUND_STEP (i);
+ }
+ #endif
+
+ /* rev
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+ */
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+}
+
+KERNEL_FQ void m01770_m04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ /**
+ * sha512
+ */
+
+ u32x w0_t[4];
+ u32x w1_t[4];
+ u32x w2_t[4];
+ u32x w3_t[4];
+ u32x w4_t[4];
+ u32x w5_t[4];
+ u32x w6_t[4];
+ u32x w7_t[4];
+
+ w0_t[0] = hc_swap32 (w0[0]);
+ w0_t[1] = hc_swap32 (w0[1]);
+ w0_t[2] = hc_swap32 (w0[2]);
+ w0_t[3] = hc_swap32 (w0[3]);
+ w1_t[0] = hc_swap32 (w1[0]);
+ w1_t[1] = hc_swap32 (w1[1]);
+ w1_t[2] = hc_swap32 (w1[2]);
+ w1_t[3] = hc_swap32 (w1[3]);
+ w2_t[0] = hc_swap32 (w2[0]);
+ w2_t[1] = hc_swap32 (w2[1]);
+ w2_t[2] = hc_swap32 (w2[2]);
+ w2_t[3] = hc_swap32 (w2[3]);
+ w3_t[0] = hc_swap32 (w3[0]);
+ w3_t[1] = hc_swap32 (w3[1]);
+ w3_t[2] = 0;
+ w3_t[3] = 0;
+ w4_t[0] = 0;
+ w4_t[1] = 0;
+ w4_t[2] = 0;
+ w4_t[3] = 0;
+ w5_t[0] = 0;
+ w5_t[1] = 0;
+ w5_t[2] = 0;
+ w5_t[3] = 0;
+ w6_t[0] = 0;
+ w6_t[1] = 0;
+ w6_t[2] = 0;
+ w6_t[3] = 0;
+ w7_t[0] = 0;
+ w7_t[1] = 0;
+ w7_t[2] = 0;
+ w7_t[3] = out_len * 8;
+
+ u64x digest[8];
+
+ digest[0] = SHA512M_A;
+ digest[1] = SHA512M_B;
+ digest[2] = SHA512M_C;
+ digest[3] = SHA512M_D;
+ digest[4] = SHA512M_E;
+ digest[5] = SHA512M_F;
+ digest[6] = SHA512M_G;
+ digest[7] = SHA512M_H;
+
+ sha512_transform_vector (w0_t, w1_t, w2_t, w3_t, w4_t, w5_t, w6_t, w7_t, digest);
+
+ w0_t[0] = h32_from_64 (digest[0]);
+ w0_t[1] = l32_from_64 (digest[0]);
+ w0_t[2] = h32_from_64 (digest[1]);
+ w0_t[3] = l32_from_64 (digest[1]);
+ w1_t[0] = h32_from_64 (digest[2]);
+ w1_t[1] = l32_from_64 (digest[2]);
+ w1_t[2] = h32_from_64 (digest[3]);
+ w1_t[3] = l32_from_64 (digest[3]);
+ w2_t[0] = h32_from_64 (digest[4]);
+ w2_t[1] = l32_from_64 (digest[4]);
+ w2_t[2] = h32_from_64 (digest[5]);
+ w2_t[3] = l32_from_64 (digest[5]);
+ w3_t[0] = h32_from_64 (digest[6]);
+ w3_t[1] = l32_from_64 (digest[6]);
+ w3_t[2] = h32_from_64 (digest[7]);
+ w3_t[3] = l32_from_64 (digest[7]);
+
+ digest[0] = SHA512M_A;
+ digest[1] = SHA512M_B;
+ digest[2] = SHA512M_C;
+ digest[3] = SHA512M_D;
+ digest[4] = SHA512M_E;
+ digest[5] = SHA512M_F;
+ digest[6] = SHA512M_G;
+ digest[7] = SHA512M_H;
+
+ sha512_transform_opt (w0_t, w1_t, w2_t, w3_t, digest);
+
+ const u32x r0 = l32_from_64 (digest[7]);
+ const u32x r1 = h32_from_64 (digest[7]);
+ const u32x r2 = l32_from_64 (digest[3]);
+ const u32x r3 = h32_from_64 (digest[3]);
+
+ COMPARE_M_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m01770_m08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m01770_m16 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m01770_s04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ /**
+ * sha512
+ */
+
+ u32x w0_t[4];
+ u32x w1_t[4];
+ u32x w2_t[4];
+ u32x w3_t[4];
+ u32x w4_t[4];
+ u32x w5_t[4];
+ u32x w6_t[4];
+ u32x w7_t[4];
+
+ w0_t[0] = hc_swap32 (w0[0]);
+ w0_t[1] = hc_swap32 (w0[1]);
+ w0_t[2] = hc_swap32 (w0[2]);
+ w0_t[3] = hc_swap32 (w0[3]);
+ w1_t[0] = hc_swap32 (w1[0]);
+ w1_t[1] = hc_swap32 (w1[1]);
+ w1_t[2] = hc_swap32 (w1[2]);
+ w1_t[3] = hc_swap32 (w1[3]);
+ w2_t[0] = hc_swap32 (w2[0]);
+ w2_t[1] = hc_swap32 (w2[1]);
+ w2_t[2] = hc_swap32 (w2[2]);
+ w2_t[3] = hc_swap32 (w2[3]);
+ w3_t[0] = hc_swap32 (w3[0]);
+ w3_t[1] = hc_swap32 (w3[1]);
+ w3_t[2] = 0;
+ w3_t[3] = 0;
+ w4_t[0] = 0;
+ w4_t[1] = 0;
+ w4_t[2] = 0;
+ w4_t[3] = 0;
+ w5_t[0] = 0;
+ w5_t[1] = 0;
+ w5_t[2] = 0;
+ w5_t[3] = 0;
+ w6_t[0] = 0;
+ w6_t[1] = 0;
+ w6_t[2] = 0;
+ w6_t[3] = 0;
+ w7_t[0] = 0;
+ w7_t[1] = 0;
+ w7_t[2] = 0;
+ w7_t[3] = out_len * 8;
+
+ u64x digest[8];
+
+ digest[0] = SHA512M_A;
+ digest[1] = SHA512M_B;
+ digest[2] = SHA512M_C;
+ digest[3] = SHA512M_D;
+ digest[4] = SHA512M_E;
+ digest[5] = SHA512M_F;
+ digest[6] = SHA512M_G;
+ digest[7] = SHA512M_H;
+
+ sha512_transform_vector (w0_t, w1_t, w2_t, w3_t, w4_t, w5_t, w6_t, w7_t, digest);
+
+ w0_t[0] = h32_from_64 (digest[0]);
+ w0_t[1] = l32_from_64 (digest[0]);
+ w0_t[2] = h32_from_64 (digest[1]);
+ w0_t[3] = l32_from_64 (digest[1]);
+ w1_t[0] = h32_from_64 (digest[2]);
+ w1_t[1] = l32_from_64 (digest[2]);
+ w1_t[2] = h32_from_64 (digest[3]);
+ w1_t[3] = l32_from_64 (digest[3]);
+ w2_t[0] = h32_from_64 (digest[4]);
+ w2_t[1] = l32_from_64 (digest[4]);
+ w2_t[2] = h32_from_64 (digest[5]);
+ w2_t[3] = l32_from_64 (digest[5]);
+ w3_t[0] = h32_from_64 (digest[6]);
+ w3_t[1] = l32_from_64 (digest[6]);
+ w3_t[2] = h32_from_64 (digest[7]);
+ w3_t[3] = l32_from_64 (digest[7]);
+
+ digest[0] = SHA512M_A;
+ digest[1] = SHA512M_B;
+ digest[2] = SHA512M_C;
+ digest[3] = SHA512M_D;
+ digest[4] = SHA512M_E;
+ digest[5] = SHA512M_F;
+ digest[6] = SHA512M_G;
+ digest[7] = SHA512M_H;
+
+ sha512_transform_opt (w0_t, w1_t, w2_t, w3_t, digest);
+
+ const u32x r0 = l32_from_64 (digest[7]);
+ const u32x r1 = h32_from_64 (digest[7]);
+ const u32x r2 = l32_from_64 (digest[3]);
+ const u32x r3 = h32_from_64 (digest[3]);
+
+ COMPARE_S_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m01770_s08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m01770_s16 (KERN_ATTR_RULES ())
+{
+}
diff --git a/OpenCL/m01770_a0-pure.cl b/OpenCL/m01770_a0-pure.cl
new file mode 100644
index 000000000..b69f9528c
--- /dev/null
+++ b/OpenCL/m01770_a0-pure.cl
@@ -0,0 +1,171 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp.h"
+#include "inc_rp.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_sha512.cl"
+#endif
+
+KERNEL_FQ void m01770_mxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ sha512_ctx_t ctx0;
+
+ sha512_init (&ctx0);
+
+ sha512_update_swap (&ctx0, tmp.i, tmp.pw_len);
+
+ sha512_final (&ctx0);
+
+ sha512_ctx_t ctx;
+
+ sha512_init (&ctx);
+
+ u32 final[32] = { 0 };
+
+ final[ 0] = h32_from_64_S (ctx0.h[0]);
+ final[ 1] = l32_from_64_S (ctx0.h[0]);
+ final[ 2] = h32_from_64_S (ctx0.h[1]);
+ final[ 3] = l32_from_64_S (ctx0.h[1]);
+ final[ 4] = h32_from_64_S (ctx0.h[2]);
+ final[ 5] = l32_from_64_S (ctx0.h[2]);
+ final[ 6] = h32_from_64_S (ctx0.h[3]);
+ final[ 7] = l32_from_64_S (ctx0.h[3]);
+ final[ 8] = h32_from_64_S (ctx0.h[4]);
+ final[ 9] = l32_from_64_S (ctx0.h[4]);
+ final[10] = h32_from_64_S (ctx0.h[5]);
+ final[11] = l32_from_64_S (ctx0.h[5]);
+ final[12] = h32_from_64_S (ctx0.h[6]);
+ final[13] = l32_from_64_S (ctx0.h[6]);
+ final[14] = h32_from_64_S (ctx0.h[7]);
+ final[15] = l32_from_64_S (ctx0.h[7]);
+
+ sha512_update (&ctx, final, 64);
+
+ sha512_final (&ctx);
+
+ const u32 r0 = l32_from_64_S (ctx.h[7]);
+ const u32 r1 = h32_from_64_S (ctx.h[7]);
+ const u32 r2 = l32_from_64_S (ctx.h[3]);
+ const u32 r3 = h32_from_64_S (ctx.h[3]);
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m01770_sxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ sha512_ctx_t ctx0;
+
+ sha512_init (&ctx0);
+
+ sha512_update_swap (&ctx0, tmp.i, tmp.pw_len);
+
+ sha512_final (&ctx0);
+
+ sha512_ctx_t ctx;
+
+ sha512_init (&ctx);
+
+ u32 final[32] = { 0 };
+
+ final[ 0] = h32_from_64_S (ctx0.h[0]);
+ final[ 1] = l32_from_64_S (ctx0.h[0]);
+ final[ 2] = h32_from_64_S (ctx0.h[1]);
+ final[ 3] = l32_from_64_S (ctx0.h[1]);
+ final[ 4] = h32_from_64_S (ctx0.h[2]);
+ final[ 5] = l32_from_64_S (ctx0.h[2]);
+ final[ 6] = h32_from_64_S (ctx0.h[3]);
+ final[ 7] = l32_from_64_S (ctx0.h[3]);
+ final[ 8] = h32_from_64_S (ctx0.h[4]);
+ final[ 9] = l32_from_64_S (ctx0.h[4]);
+ final[10] = h32_from_64_S (ctx0.h[5]);
+ final[11] = l32_from_64_S (ctx0.h[5]);
+ final[12] = h32_from_64_S (ctx0.h[6]);
+ final[13] = l32_from_64_S (ctx0.h[6]);
+ final[14] = h32_from_64_S (ctx0.h[7]);
+ final[15] = l32_from_64_S (ctx0.h[7]);
+
+ sha512_update (&ctx, final, 64);
+
+ sha512_final (&ctx);
+
+ const u32 r0 = l32_from_64_S (ctx.h[7]);
+ const u32 r1 = h32_from_64_S (ctx.h[7]);
+ const u32 r2 = l32_from_64_S (ctx.h[3]);
+ const u32 r3 = h32_from_64_S (ctx.h[3]);
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m01770_a1-optimized.cl b/OpenCL/m01770_a1-optimized.cl
new file mode 100644
index 000000000..346be147f
--- /dev/null
+++ b/OpenCL/m01770_a1-optimized.cl
@@ -0,0 +1,605 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha512.cl"
+#endif
+
+DECLSPEC void sha512_transform_full (const u32x *w0, const u32x *w1, const u32x *w2, const u32x *w3, u64x *digest)
+{
+ u64x w0_t = hl32_to_64 (w0[0], w0[1]);
+ u64x w1_t = hl32_to_64 (w0[2], w0[3]);
+ u64x w2_t = hl32_to_64 (w1[0], w1[1]);
+ u64x w3_t = hl32_to_64 (w1[2], w1[3]);
+ u64x w4_t = hl32_to_64 (w2[0], w2[1]);
+ u64x w5_t = hl32_to_64 (w2[2], w2[3]);
+ u64x w6_t = hl32_to_64 (w3[0], w3[1]);
+ u64x w7_t = 0;
+ u64x w8_t = 0;
+ u64x w9_t = 0;
+ u64x wa_t = 0;
+ u64x wb_t = 0;
+ u64x wc_t = 0;
+ u64x wd_t = 0;
+ u64x we_t = 0;
+ u64x wf_t = hl32_to_64 (w3[2], w3[3]);
+
+ u64x a = digest[0];
+ u64x b = digest[1];
+ u64x c = digest[2];
+ u64x d = digest[3];
+ u64x e = digest[4];
+ u64x f = digest[5];
+ u64x g = digest[6];
+ u64x h = digest[7];
+
+ #define ROUND_EXPAND() \
+ { \
+ w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
+ w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
+ w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
+ w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
+ w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
+ w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
+ w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
+ w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
+ w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
+ w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
+ wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
+ wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
+ wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
+ wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
+ we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
+ wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
+ }
+
+ #define ROUND_STEP(i) \
+ { \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
+ }
+
+ ROUND_STEP (0);
+
+ #ifdef IS_CUDA
+ ROUND_EXPAND (); ROUND_STEP (16);
+ ROUND_EXPAND (); ROUND_STEP (32);
+ ROUND_EXPAND (); ROUND_STEP (48);
+ ROUND_EXPAND (); ROUND_STEP (64);
+ #else
+ #ifdef _unroll
+ #pragma unroll
+ #endif
+ for (int i = 16; i < 80; i += 16)
+ {
+ ROUND_EXPAND (); ROUND_STEP (i);
+ }
+ #endif
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+}
+
+DECLSPEC void sha512_transform_opt (const u32x *w0, const u32x *w1, const u32x *w2, const u32x *w3, u64x *digest)
+{
+ u32x wend = 0x80000000;
+ u32x wlen = 64*8;
+
+ u64x w0_t = hl32_to_64 (w0[0], w0[1]);
+ u64x w1_t = hl32_to_64 (w0[2], w0[3]);
+ u64x w2_t = hl32_to_64 (w1[0], w1[1]);
+ u64x w3_t = hl32_to_64 (w1[2], w1[3]);
+ u64x w4_t = hl32_to_64 (w2[0], w2[1]);
+ u64x w5_t = hl32_to_64 (w2[2], w2[3]);
+ u64x w6_t = hl32_to_64 (w3[0], w3[1]);
+ u64x w7_t = hl32_to_64 (w3[2], w3[3]);
+ u64x w8_t = hl32_to_64 (wend, 0);;
+ u64x w9_t = 0;
+ u64x wa_t = 0;
+ u64x wb_t = 0;
+ u64x wc_t = 0;
+ u64x wd_t = 0;
+ u64x we_t = 0;
+ u64x wf_t = hl32_to_64 (0, wlen);
+
+ u64x a = digest[0];
+ u64x b = digest[1];
+ u64x c = digest[2];
+ u64x d = digest[3];
+ u64x e = digest[4];
+ u64x f = digest[5];
+ u64x g = digest[6];
+ u64x h = digest[7];
+
+ #define ROUND_EXPAND() \
+ { \
+ w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
+ w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
+ w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
+ w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
+ w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
+ w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
+ w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
+ w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
+ w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
+ w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
+ wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
+ wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
+ wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
+ wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
+ we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
+ wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
+ }
+
+ #define ROUND_STEP(i) \
+ { \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
+ }
+
+ ROUND_STEP (0);
+
+ #ifdef IS_CUDA
+ ROUND_EXPAND (); ROUND_STEP (16);
+ ROUND_EXPAND (); ROUND_STEP (32);
+ ROUND_EXPAND (); ROUND_STEP (48);
+ ROUND_EXPAND (); ROUND_STEP (64);
+ #else
+ #ifdef _unroll
+ #pragma unroll
+ #endif
+ for (int i = 16; i < 80; i += 16)
+ {
+ ROUND_EXPAND (); ROUND_STEP (i);
+ }
+ #endif
+
+ /* rev
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+ */
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+}
+
+KERNEL_FQ void m01770_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = wordl3[2] | wordr3[2];
+ w3[3] = wordl3[3] | wordr3[3];
+
+ /**
+ * sha512
+ */
+
+ u32x w0_t[4];
+ u32x w1_t[4];
+ u32x w2_t[4];
+ u32x w3_t[4];
+
+ w0_t[0] = hc_swap32 (w0[0]);
+ w0_t[1] = hc_swap32 (w0[1]);
+ w0_t[2] = hc_swap32 (w0[2]);
+ w0_t[3] = hc_swap32 (w0[3]);
+ w1_t[0] = hc_swap32 (w1[0]);
+ w1_t[1] = hc_swap32 (w1[1]);
+ w1_t[2] = hc_swap32 (w1[2]);
+ w1_t[3] = hc_swap32 (w1[3]);
+ w2_t[0] = hc_swap32 (w2[0]);
+ w2_t[1] = hc_swap32 (w2[1]);
+ w2_t[2] = hc_swap32 (w2[2]);
+ w2_t[3] = hc_swap32 (w2[3]);
+ w3_t[0] = hc_swap32 (w3[0]);
+ w3_t[1] = hc_swap32 (w3[1]);
+ w3_t[2] = 0;
+ w3_t[3] = pw_len * 8;
+
+ u64x digest[8];
+
+ digest[0] = SHA512M_A;
+ digest[1] = SHA512M_B;
+ digest[2] = SHA512M_C;
+ digest[3] = SHA512M_D;
+ digest[4] = SHA512M_E;
+ digest[5] = SHA512M_F;
+ digest[6] = SHA512M_G;
+ digest[7] = SHA512M_H;
+
+ sha512_transform_full (w0_t, w1_t, w2_t, w3_t, digest);
+
+ w0_t[0] = h32_from_64 (digest[0]);
+ w0_t[1] = l32_from_64 (digest[0]);
+ w0_t[2] = h32_from_64 (digest[1]);
+ w0_t[3] = l32_from_64 (digest[1]);
+ w1_t[0] = h32_from_64 (digest[2]);
+ w1_t[1] = l32_from_64 (digest[2]);
+ w1_t[2] = h32_from_64 (digest[3]);
+ w1_t[3] = l32_from_64 (digest[3]);
+ w2_t[0] = h32_from_64 (digest[4]);
+ w2_t[1] = l32_from_64 (digest[4]);
+ w2_t[2] = h32_from_64 (digest[5]);
+ w2_t[3] = l32_from_64 (digest[5]);
+ w3_t[0] = h32_from_64 (digest[6]);
+ w3_t[1] = l32_from_64 (digest[6]);
+ w3_t[2] = h32_from_64 (digest[7]);
+ w3_t[3] = l32_from_64 (digest[7]);
+
+ digest[0] = SHA512M_A;
+ digest[1] = SHA512M_B;
+ digest[2] = SHA512M_C;
+ digest[3] = SHA512M_D;
+ digest[4] = SHA512M_E;
+ digest[5] = SHA512M_F;
+ digest[6] = SHA512M_G;
+ digest[7] = SHA512M_H;
+
+ sha512_transform_opt (w0_t, w1_t, w2_t, w3_t, digest);
+
+ const u32x r0 = l32_from_64 (digest[7]);
+ const u32x r1 = h32_from_64 (digest[7]);
+ const u32x r2 = l32_from_64 (digest[3]);
+ const u32x r3 = h32_from_64 (digest[3]);
+
+ COMPARE_M_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m01770_m08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m01770_m16 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m01770_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = wordl3[2] | wordr3[2];
+ w3[3] = wordl3[3] | wordr3[3];
+
+ /**
+ * sha512
+ */
+
+ u32x w0_t[4];
+ u32x w1_t[4];
+ u32x w2_t[4];
+ u32x w3_t[4];
+
+ w0_t[0] = hc_swap32 (w0[0]);
+ w0_t[1] = hc_swap32 (w0[1]);
+ w0_t[2] = hc_swap32 (w0[2]);
+ w0_t[3] = hc_swap32 (w0[3]);
+ w1_t[0] = hc_swap32 (w1[0]);
+ w1_t[1] = hc_swap32 (w1[1]);
+ w1_t[2] = hc_swap32 (w1[2]);
+ w1_t[3] = hc_swap32 (w1[3]);
+ w2_t[0] = hc_swap32 (w2[0]);
+ w2_t[1] = hc_swap32 (w2[1]);
+ w2_t[2] = hc_swap32 (w2[2]);
+ w2_t[3] = hc_swap32 (w2[3]);
+ w3_t[0] = hc_swap32 (w3[0]);
+ w3_t[1] = hc_swap32 (w3[1]);
+ w3_t[2] = 0;
+ w3_t[3] = pw_len * 8;
+
+ u64x digest[8];
+
+ digest[0] = SHA512M_A;
+ digest[1] = SHA512M_B;
+ digest[2] = SHA512M_C;
+ digest[3] = SHA512M_D;
+ digest[4] = SHA512M_E;
+ digest[5] = SHA512M_F;
+ digest[6] = SHA512M_G;
+ digest[7] = SHA512M_H;
+
+ sha512_transform_full (w0_t, w1_t, w2_t, w3_t, digest);
+
+ w0_t[0] = h32_from_64 (digest[0]);
+ w0_t[1] = l32_from_64 (digest[0]);
+ w0_t[2] = h32_from_64 (digest[1]);
+ w0_t[3] = l32_from_64 (digest[1]);
+ w1_t[0] = h32_from_64 (digest[2]);
+ w1_t[1] = l32_from_64 (digest[2]);
+ w1_t[2] = h32_from_64 (digest[3]);
+ w1_t[3] = l32_from_64 (digest[3]);
+ w2_t[0] = h32_from_64 (digest[4]);
+ w2_t[1] = l32_from_64 (digest[4]);
+ w2_t[2] = h32_from_64 (digest[5]);
+ w2_t[3] = l32_from_64 (digest[5]);
+ w3_t[0] = h32_from_64 (digest[6]);
+ w3_t[1] = l32_from_64 (digest[6]);
+ w3_t[2] = h32_from_64 (digest[7]);
+ w3_t[3] = l32_from_64 (digest[7]);
+
+ digest[0] = SHA512M_A;
+ digest[1] = SHA512M_B;
+ digest[2] = SHA512M_C;
+ digest[3] = SHA512M_D;
+ digest[4] = SHA512M_E;
+ digest[5] = SHA512M_F;
+ digest[6] = SHA512M_G;
+ digest[7] = SHA512M_H;
+
+ sha512_transform_opt (w0_t, w1_t, w2_t, w3_t, digest);
+
+ const u32x r0 = l32_from_64 (digest[7]);
+ const u32x r1 = h32_from_64 (digest[7]);
+ const u32x r2 = l32_from_64 (digest[3]);
+ const u32x r3 = h32_from_64 (digest[3]);
+
+ COMPARE_S_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m01770_s08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m01770_s16 (KERN_ATTR_BASIC ())
+{
+}
diff --git a/OpenCL/m01770_a1-pure.cl b/OpenCL/m01770_a1-pure.cl
new file mode 100644
index 000000000..3c57255d6
--- /dev/null
+++ b/OpenCL/m01770_a1-pure.cl
@@ -0,0 +1,165 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_sha512.cl"
+#endif
+
+KERNEL_FQ void m01770_mxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ sha512_ctx_t ctx00;
+
+ sha512_init (&ctx00);
+
+ sha512_update_global_swap (&ctx00, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ sha512_ctx_t ctx0 = ctx00;
+
+ sha512_update_global_swap (&ctx0, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ sha512_final (&ctx0);
+
+ sha512_ctx_t ctx;
+
+ sha512_init (&ctx);
+
+ u32 final[32] = { 0 };
+
+ final[ 0] = h32_from_64_S (ctx0.h[0]);
+ final[ 1] = l32_from_64_S (ctx0.h[0]);
+ final[ 2] = h32_from_64_S (ctx0.h[1]);
+ final[ 3] = l32_from_64_S (ctx0.h[1]);
+ final[ 4] = h32_from_64_S (ctx0.h[2]);
+ final[ 5] = l32_from_64_S (ctx0.h[2]);
+ final[ 6] = h32_from_64_S (ctx0.h[3]);
+ final[ 7] = l32_from_64_S (ctx0.h[3]);
+ final[ 8] = h32_from_64_S (ctx0.h[4]);
+ final[ 9] = l32_from_64_S (ctx0.h[4]);
+ final[10] = h32_from_64_S (ctx0.h[5]);
+ final[11] = l32_from_64_S (ctx0.h[5]);
+ final[12] = h32_from_64_S (ctx0.h[6]);
+ final[13] = l32_from_64_S (ctx0.h[6]);
+ final[14] = h32_from_64_S (ctx0.h[7]);
+ final[15] = l32_from_64_S (ctx0.h[7]);
+
+ sha512_update (&ctx, final, 64);
+
+ sha512_final (&ctx);
+
+ const u32 r0 = l32_from_64_S (ctx.h[7]);
+ const u32 r1 = h32_from_64_S (ctx.h[7]);
+ const u32 r2 = l32_from_64_S (ctx.h[3]);
+ const u32 r3 = h32_from_64_S (ctx.h[3]);
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m01770_sxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ sha512_ctx_t ctx00;
+
+ sha512_init (&ctx00);
+
+ sha512_update_global_swap (&ctx00, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ sha512_ctx_t ctx0 = ctx00;
+
+ sha512_update_global_swap (&ctx0, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ sha512_final (&ctx0);
+
+ sha512_ctx_t ctx;
+
+ sha512_init (&ctx);
+
+ u32 final[32] = { 0 };
+
+ final[ 0] = h32_from_64_S (ctx0.h[0]);
+ final[ 1] = l32_from_64_S (ctx0.h[0]);
+ final[ 2] = h32_from_64_S (ctx0.h[1]);
+ final[ 3] = l32_from_64_S (ctx0.h[1]);
+ final[ 4] = h32_from_64_S (ctx0.h[2]);
+ final[ 5] = l32_from_64_S (ctx0.h[2]);
+ final[ 6] = h32_from_64_S (ctx0.h[3]);
+ final[ 7] = l32_from_64_S (ctx0.h[3]);
+ final[ 8] = h32_from_64_S (ctx0.h[4]);
+ final[ 9] = l32_from_64_S (ctx0.h[4]);
+ final[10] = h32_from_64_S (ctx0.h[5]);
+ final[11] = l32_from_64_S (ctx0.h[5]);
+ final[12] = h32_from_64_S (ctx0.h[6]);
+ final[13] = l32_from_64_S (ctx0.h[6]);
+ final[14] = h32_from_64_S (ctx0.h[7]);
+ final[15] = l32_from_64_S (ctx0.h[7]);
+
+ sha512_update (&ctx, final, 64);
+
+ sha512_final (&ctx);
+
+ const u32 r0 = l32_from_64_S (ctx.h[7]);
+ const u32 r1 = h32_from_64_S (ctx.h[7]);
+ const u32 r2 = l32_from_64_S (ctx.h[3]);
+ const u32 r3 = h32_from_64_S (ctx.h[3]);
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m01770_a3-optimized.cl b/OpenCL/m01770_a3-optimized.cl
new file mode 100644
index 000000000..541110eab
--- /dev/null
+++ b/OpenCL/m01770_a3-optimized.cl
@@ -0,0 +1,645 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha512.cl"
+#endif
+
+DECLSPEC void sha512_transform_full (const u32x *w0, const u32x *w1, const u32x *w2, const u32x *w3, u64x *digest)
+{
+ u64x w0_t = hl32_to_64 (w0[0], w0[1]);
+ u64x w1_t = hl32_to_64 (w0[2], w0[3]);
+ u64x w2_t = hl32_to_64 (w1[0], w1[1]);
+ u64x w3_t = hl32_to_64 (w1[2], w1[3]);
+ u64x w4_t = hl32_to_64 (w2[0], w2[1]);
+ u64x w5_t = hl32_to_64 (w2[2], w2[3]);
+ u64x w6_t = hl32_to_64 (w3[0], w3[1]);
+ u64x w7_t = 0;
+ u64x w8_t = 0;
+ u64x w9_t = 0;
+ u64x wa_t = 0;
+ u64x wb_t = 0;
+ u64x wc_t = 0;
+ u64x wd_t = 0;
+ u64x we_t = 0;
+ u64x wf_t = hl32_to_64 (w3[2], w3[3]);
+
+ u64x a = digest[0];
+ u64x b = digest[1];
+ u64x c = digest[2];
+ u64x d = digest[3];
+ u64x e = digest[4];
+ u64x f = digest[5];
+ u64x g = digest[6];
+ u64x h = digest[7];
+
+ #define ROUND_EXPAND() \
+ { \
+ w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
+ w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
+ w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
+ w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
+ w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
+ w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
+ w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
+ w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
+ w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
+ w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
+ wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
+ wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
+ wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
+ wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
+ we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
+ wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
+ }
+
+ #define ROUND_STEP(i) \
+ { \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
+ }
+
+ ROUND_STEP (0);
+
+ #ifdef IS_CUDA
+ ROUND_EXPAND (); ROUND_STEP (16);
+ ROUND_EXPAND (); ROUND_STEP (32);
+ ROUND_EXPAND (); ROUND_STEP (48);
+ ROUND_EXPAND (); ROUND_STEP (64);
+ #else
+ #ifdef _unroll
+ #pragma unroll
+ #endif
+ for (int i = 16; i < 80; i += 16)
+ {
+ ROUND_EXPAND (); ROUND_STEP (i);
+ }
+ #endif
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+}
+
+DECLSPEC void sha512_transform_opt (const u32x *w0, const u32x *w1, const u32x *w2, const u32x *w3, u64x *digest)
+{
+ u32x wend = 0x80000000;
+ u32x wlen = 64*8;
+
+ u64x w0_t = hl32_to_64 (w0[0], w0[1]);
+ u64x w1_t = hl32_to_64 (w0[2], w0[3]);
+ u64x w2_t = hl32_to_64 (w1[0], w1[1]);
+ u64x w3_t = hl32_to_64 (w1[2], w1[3]);
+ u64x w4_t = hl32_to_64 (w2[0], w2[1]);
+ u64x w5_t = hl32_to_64 (w2[2], w2[3]);
+ u64x w6_t = hl32_to_64 (w3[0], w3[1]);
+ u64x w7_t = hl32_to_64 (w3[2], w3[3]);
+ u64x w8_t = hl32_to_64 (wend, 0);;
+ u64x w9_t = 0;
+ u64x wa_t = 0;
+ u64x wb_t = 0;
+ u64x wc_t = 0;
+ u64x wd_t = 0;
+ u64x we_t = 0;
+ u64x wf_t = hl32_to_64 (0, wlen);
+
+ u64x a = digest[0];
+ u64x b = digest[1];
+ u64x c = digest[2];
+ u64x d = digest[3];
+ u64x e = digest[4];
+ u64x f = digest[5];
+ u64x g = digest[6];
+ u64x h = digest[7];
+
+ #define ROUND_EXPAND() \
+ { \
+ w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
+ w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
+ w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
+ w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
+ w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
+ w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
+ w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
+ w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
+ w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
+ w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
+ wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
+ wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
+ wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
+ wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
+ we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
+ wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
+ }
+
+ #define ROUND_STEP(i) \
+ { \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
+ SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
+ }
+
+ ROUND_STEP (0);
+
+ #ifdef IS_CUDA
+ ROUND_EXPAND (); ROUND_STEP (16);
+ ROUND_EXPAND (); ROUND_STEP (32);
+ ROUND_EXPAND (); ROUND_STEP (48);
+ ROUND_EXPAND (); ROUND_STEP (64);
+ #else
+ #ifdef _unroll
+ #pragma unroll
+ #endif
+ for (int i = 16; i < 80; i += 16)
+ {
+ ROUND_EXPAND (); ROUND_STEP (i);
+ }
+ #endif
+
+ /* rev
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+ */
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+}
+
+DECLSPEC void m01770m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ u32x w0_t[4];
+ u32x w1_t[4];
+ u32x w2_t[4];
+ u32x w3_t[4];
+
+ w0_t[0] = w0;
+ w0_t[1] = w[ 1];
+ w0_t[2] = w[ 2];
+ w0_t[3] = w[ 3];
+ w1_t[0] = w[ 4];
+ w1_t[1] = w[ 5];
+ w1_t[2] = w[ 6];
+ w1_t[3] = w[ 7];
+ w2_t[0] = w[ 8];
+ w2_t[1] = w[ 9];
+ w2_t[2] = w[10];
+ w2_t[3] = w[11];
+ w3_t[0] = w[12];
+ w3_t[1] = w[13];
+ w3_t[2] = w[14];
+ w3_t[3] = w[15];
+
+ u64x digest[8];
+
+ digest[0] = SHA512M_A;
+ digest[1] = SHA512M_B;
+ digest[2] = SHA512M_C;
+ digest[3] = SHA512M_D;
+ digest[4] = SHA512M_E;
+ digest[5] = SHA512M_F;
+ digest[6] = SHA512M_G;
+ digest[7] = SHA512M_H;
+
+ sha512_transform_full (w0_t, w1_t, w2_t, w3_t, digest);
+
+ w0_t[0] = h32_from_64 (digest[0]);
+ w0_t[1] = l32_from_64 (digest[0]);
+ w0_t[2] = h32_from_64 (digest[1]);
+ w0_t[3] = l32_from_64 (digest[1]);
+ w1_t[0] = h32_from_64 (digest[2]);
+ w1_t[1] = l32_from_64 (digest[2]);
+ w1_t[2] = h32_from_64 (digest[3]);
+ w1_t[3] = l32_from_64 (digest[3]);
+ w2_t[0] = h32_from_64 (digest[4]);
+ w2_t[1] = l32_from_64 (digest[4]);
+ w2_t[2] = h32_from_64 (digest[5]);
+ w2_t[3] = l32_from_64 (digest[5]);
+ w3_t[0] = h32_from_64 (digest[6]);
+ w3_t[1] = l32_from_64 (digest[6]);
+ w3_t[2] = h32_from_64 (digest[7]);
+ w3_t[3] = l32_from_64 (digest[7]);
+
+ digest[0] = SHA512M_A;
+ digest[1] = SHA512M_B;
+ digest[2] = SHA512M_C;
+ digest[3] = SHA512M_D;
+ digest[4] = SHA512M_E;
+ digest[5] = SHA512M_F;
+ digest[6] = SHA512M_G;
+ digest[7] = SHA512M_H;
+
+ sha512_transform_opt (w0_t, w1_t, w2_t, w3_t, digest);
+
+ const u32x r0 = l32_from_64 (digest[7]);
+ const u32x r1 = h32_from_64 (digest[7]);
+ const u32x r2 = l32_from_64 (digest[3]);
+ const u32x r3 = h32_from_64 (digest[3]);
+
+ COMPARE_M_SIMD (r0, r1, r2, r3);
+ }
+}
+
+DECLSPEC void m01770s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ u32x w0_t[4];
+ u32x w1_t[4];
+ u32x w2_t[4];
+ u32x w3_t[4];
+
+ w0_t[0] = w0;
+ w0_t[1] = w[ 1];
+ w0_t[2] = w[ 2];
+ w0_t[3] = w[ 3];
+ w1_t[0] = w[ 4];
+ w1_t[1] = w[ 5];
+ w1_t[2] = w[ 6];
+ w1_t[3] = w[ 7];
+ w2_t[0] = w[ 8];
+ w2_t[1] = w[ 9];
+ w2_t[2] = w[10];
+ w2_t[3] = w[11];
+ w3_t[0] = w[12];
+ w3_t[1] = w[13];
+ w3_t[2] = w[14];
+ w3_t[3] = w[15];
+
+ u64x digest[8];
+
+ digest[0] = SHA512M_A;
+ digest[1] = SHA512M_B;
+ digest[2] = SHA512M_C;
+ digest[3] = SHA512M_D;
+ digest[4] = SHA512M_E;
+ digest[5] = SHA512M_F;
+ digest[6] = SHA512M_G;
+ digest[7] = SHA512M_H;
+
+ sha512_transform_full (w0_t, w1_t, w2_t, w3_t, digest);
+
+ w0_t[0] = h32_from_64 (digest[0]);
+ w0_t[1] = l32_from_64 (digest[0]);
+ w0_t[2] = h32_from_64 (digest[1]);
+ w0_t[3] = l32_from_64 (digest[1]);
+ w1_t[0] = h32_from_64 (digest[2]);
+ w1_t[1] = l32_from_64 (digest[2]);
+ w1_t[2] = h32_from_64 (digest[3]);
+ w1_t[3] = l32_from_64 (digest[3]);
+ w2_t[0] = h32_from_64 (digest[4]);
+ w2_t[1] = l32_from_64 (digest[4]);
+ w2_t[2] = h32_from_64 (digest[5]);
+ w2_t[3] = l32_from_64 (digest[5]);
+ w3_t[0] = h32_from_64 (digest[6]);
+ w3_t[1] = l32_from_64 (digest[6]);
+ w3_t[2] = h32_from_64 (digest[7]);
+ w3_t[3] = l32_from_64 (digest[7]);
+
+ digest[0] = SHA512M_A;
+ digest[1] = SHA512M_B;
+ digest[2] = SHA512M_C;
+ digest[3] = SHA512M_D;
+ digest[4] = SHA512M_E;
+ digest[5] = SHA512M_F;
+ digest[6] = SHA512M_G;
+ digest[7] = SHA512M_H;
+
+ sha512_transform_opt (w0_t, w1_t, w2_t, w3_t, digest);
+
+ const u32x r0 = l32_from_64 (digest[7]);
+ const u32x r1 = h32_from_64 (digest[7]);
+ const u32x r2 = l32_from_64 (digest[3]);
+ const u32x r3 = h32_from_64 (digest[3]);
+
+ COMPARE_S_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m01770_m04 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = 0;
+ w[ 5] = 0;
+ w[ 6] = 0;
+ w[ 7] = 0;
+ w[ 8] = 0;
+ w[ 9] = 0;
+ w[10] = 0;
+ w[11] = 0;
+ w[12] = 0;
+ w[13] = 0;
+ w[14] = 0;
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m01770m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+}
+
+KERNEL_FQ void m01770_m08 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = pws[gid].i[ 4];
+ w[ 5] = pws[gid].i[ 5];
+ w[ 6] = pws[gid].i[ 6];
+ w[ 7] = pws[gid].i[ 7];
+ w[ 8] = 0;
+ w[ 9] = 0;
+ w[10] = 0;
+ w[11] = 0;
+ w[12] = 0;
+ w[13] = 0;
+ w[14] = 0;
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m01770m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+}
+
+KERNEL_FQ void m01770_m16 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = pws[gid].i[ 4];
+ w[ 5] = pws[gid].i[ 5];
+ w[ 6] = pws[gid].i[ 6];
+ w[ 7] = pws[gid].i[ 7];
+ w[ 8] = pws[gid].i[ 8];
+ w[ 9] = pws[gid].i[ 9];
+ w[10] = pws[gid].i[10];
+ w[11] = pws[gid].i[11];
+ w[12] = pws[gid].i[12];
+ w[13] = pws[gid].i[13];
+ w[14] = pws[gid].i[14];
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m01770m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+}
+
+KERNEL_FQ void m01770_s04 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = 0;
+ w[ 5] = 0;
+ w[ 6] = 0;
+ w[ 7] = 0;
+ w[ 8] = 0;
+ w[ 9] = 0;
+ w[10] = 0;
+ w[11] = 0;
+ w[12] = 0;
+ w[13] = 0;
+ w[14] = 0;
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m01770s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+}
+
+KERNEL_FQ void m01770_s08 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = pws[gid].i[ 4];
+ w[ 5] = pws[gid].i[ 5];
+ w[ 6] = pws[gid].i[ 6];
+ w[ 7] = pws[gid].i[ 7];
+ w[ 8] = 0;
+ w[ 9] = 0;
+ w[10] = 0;
+ w[11] = 0;
+ w[12] = 0;
+ w[13] = 0;
+ w[14] = 0;
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m01770s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+}
+
+KERNEL_FQ void m01770_s16 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = pws[gid].i[ 4];
+ w[ 5] = pws[gid].i[ 5];
+ w[ 6] = pws[gid].i[ 6];
+ w[ 7] = pws[gid].i[ 7];
+ w[ 8] = pws[gid].i[ 8];
+ w[ 9] = pws[gid].i[ 9];
+ w[10] = pws[gid].i[10];
+ w[11] = pws[gid].i[11];
+ w[12] = pws[gid].i[12];
+ w[13] = pws[gid].i[13];
+ w[14] = pws[gid].i[14];
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m01770s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+}
diff --git a/OpenCL/m01770_a3-pure.cl b/OpenCL/m01770_a3-pure.cl
new file mode 100644
index 000000000..3a4a27c14
--- /dev/null
+++ b/OpenCL/m01770_a3-pure.cl
@@ -0,0 +1,191 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha512.cl"
+#endif
+
+KERNEL_FQ void m01770_mxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ sha512_ctx_vector_t ctx0;
+
+ sha512_init_vector (&ctx0);
+
+ sha512_update_vector (&ctx0, w, pw_len);
+
+ sha512_final_vector (&ctx0);
+
+ sha512_ctx_t ctx;
+
+ sha512_init_vector (&ctx);
+
+ u32x final[32] = { 0 };
+
+ final[ 0] = h32_from_64_S (ctx0.h[0]);
+ final[ 1] = l32_from_64_S (ctx0.h[0]);
+ final[ 2] = h32_from_64_S (ctx0.h[1]);
+ final[ 3] = l32_from_64_S (ctx0.h[1]);
+ final[ 4] = h32_from_64_S (ctx0.h[2]);
+ final[ 5] = l32_from_64_S (ctx0.h[2]);
+ final[ 6] = h32_from_64_S (ctx0.h[3]);
+ final[ 7] = l32_from_64_S (ctx0.h[3]);
+ final[ 8] = h32_from_64_S (ctx0.h[4]);
+ final[ 9] = l32_from_64_S (ctx0.h[4]);
+ final[10] = h32_from_64_S (ctx0.h[5]);
+ final[11] = l32_from_64_S (ctx0.h[5]);
+ final[12] = h32_from_64_S (ctx0.h[6]);
+ final[13] = l32_from_64_S (ctx0.h[6]);
+ final[14] = h32_from_64_S (ctx0.h[7]);
+ final[15] = l32_from_64_S (ctx0.h[7]);
+
+ sha512_update_vector (&ctx, final, 64);
+
+ sha512_final_vector (&ctx);
+
+ const u32x r0 = l32_from_64 (ctx.h[7]);
+ const u32x r1 = h32_from_64 (ctx.h[7]);
+ const u32x r2 = l32_from_64 (ctx.h[3]);
+ const u32x r3 = h32_from_64 (ctx.h[3]);
+
+ COMPARE_M_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m01770_sxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 lid = get_local_id (0);
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ sha512_ctx_vector_t ctx0;
+
+ sha512_init_vector (&ctx0);
+
+ sha512_update_vector (&ctx0, w, pw_len);
+
+ sha512_final_vector (&ctx0);
+
+ sha512_ctx_t ctx;
+
+ sha512_init_vector (&ctx);
+
+ u32x final[32] = { 0 };
+
+ final[ 0] = h32_from_64_S (ctx0.h[0]);
+ final[ 1] = l32_from_64_S (ctx0.h[0]);
+ final[ 2] = h32_from_64_S (ctx0.h[1]);
+ final[ 3] = l32_from_64_S (ctx0.h[1]);
+ final[ 4] = h32_from_64_S (ctx0.h[2]);
+ final[ 5] = l32_from_64_S (ctx0.h[2]);
+ final[ 6] = h32_from_64_S (ctx0.h[3]);
+ final[ 7] = l32_from_64_S (ctx0.h[3]);
+ final[ 8] = h32_from_64_S (ctx0.h[4]);
+ final[ 9] = l32_from_64_S (ctx0.h[4]);
+ final[10] = h32_from_64_S (ctx0.h[5]);
+ final[11] = l32_from_64_S (ctx0.h[5]);
+ final[12] = h32_from_64_S (ctx0.h[6]);
+ final[13] = l32_from_64_S (ctx0.h[6]);
+ final[14] = h32_from_64_S (ctx0.h[7]);
+ final[15] = l32_from_64_S (ctx0.h[7]);
+
+ sha512_update_vector (&ctx, final, 64);
+
+ sha512_final_vector (&ctx);
+
+ const u32x r0 = l32_from_64 (ctx.h[7]);
+ const u32x r1 = h32_from_64 (ctx.h[7]);
+ const u32x r2 = l32_from_64 (ctx.h[3]);
+ const u32x r3 = h32_from_64 (ctx.h[3]);
+
+ COMPARE_S_SIMD (r0, r1, r2, r3);
+ }
+}
diff --git a/docs/changes.txt b/docs/changes.txt
index 0bb228187..809c29c3b 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,6 +35,7 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
+- Added hash-mode: BitShares v0.x - sha512(sha512(pass))
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index bd21d35d7..a70e4506e 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,6 +18,7 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
+* BitShares v0.x - sha512(sha512(pass)) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
diff --git a/docs/readme.txt b/docs/readme.txt
index 9e36b73ce..6ab191951 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -92,6 +92,7 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- sha512($salt.$pass)
- sha512(utf16le($pass).$salt)
- sha512($salt.utf16le($pass))
+- BitShares v0.x - sha512(sha512(pass))
- HMAC-MD5 (key = $pass)
- HMAC-MD5 (key = $salt)
- HMAC-SHA1 (key = $pass)
diff --git a/src/modules/module_01770.c b/src/modules/module_01770.c
new file mode 100644
index 000000000..a12c4b53f
--- /dev/null
+++ b/src/modules/module_01770.c
@@ -0,0 +1,230 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+
+static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL;
+static const u32 DGST_POS0 = 14;
+static const u32 DGST_POS1 = 15;
+static const u32 DGST_POS2 = 6;
+static const u32 DGST_POS3 = 7;
+static const u32 DGST_SIZE = DGST_SIZE_8_8;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH;
+static const char *HASH_NAME = "BitShares v0.x - sha512(sha512(pass))";
+static const u64 KERN_TYPE = 1770;
+static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
+ | OPTI_TYPE_PRECOMPUTE_INIT
+ | OPTI_TYPE_EARLY_SKIP
+ | OPTI_TYPE_NOT_ITERATED
+ | OPTI_TYPE_NOT_SALTED
+ | OPTI_TYPE_USES_BITS_64
+ | OPTI_TYPE_RAW_HASH;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_BE
+ | OPTS_TYPE_PT_ADD80
+ | OPTS_TYPE_PT_ADDBITS15;
+static const u32 SALT_TYPE = SALT_TYPE_NONE;
+static const char *ST_PASS = "hashcat";
+static const char *ST_HASH = "caec04bdf7c17f763a9ec7439f7c9abda112f1bfc9b1bb684fef9b6142636979b9896cfc236896d821a69a961a143dd19c96d59777258201f1bbe5ecc2a2ecf5";
+
+u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
+u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
+u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
+u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
+u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
+u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
+u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
+const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
+u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
+u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
+u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
+u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
+const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
+const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+ u64 *digest = (u64 *) digest_buf;
+
+ token_t token;
+
+ token.token_cnt = 1;
+
+ token.len_min[0] = 128;
+ token.len_max[0] = 128;
+ token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_HEX;
+
+ const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+ if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+ const u8 *hash_pos = token.buf[0];
+
+ digest[0] = hex_to_u64 (hash_pos + 0);
+ digest[1] = hex_to_u64 (hash_pos + 16);
+ digest[2] = hex_to_u64 (hash_pos + 32);
+ digest[3] = hex_to_u64 (hash_pos + 48);
+ digest[4] = hex_to_u64 (hash_pos + 64);
+ digest[5] = hex_to_u64 (hash_pos + 80);
+ digest[6] = hex_to_u64 (hash_pos + 96);
+ digest[7] = hex_to_u64 (hash_pos + 112);
+
+ digest[0] = byte_swap_64 (digest[0]);
+ digest[1] = byte_swap_64 (digest[1]);
+ digest[2] = byte_swap_64 (digest[2]);
+ digest[3] = byte_swap_64 (digest[3]);
+ digest[4] = byte_swap_64 (digest[4]);
+ digest[5] = byte_swap_64 (digest[5]);
+ digest[6] = byte_swap_64 (digest[6]);
+ digest[7] = byte_swap_64 (digest[7]);
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ digest[0] -= SHA512M_A;
+ digest[1] -= SHA512M_B;
+ digest[2] -= SHA512M_C;
+ digest[3] -= SHA512M_D;
+ digest[4] -= SHA512M_E;
+ digest[5] -= SHA512M_F;
+ digest[6] -= SHA512M_G;
+ digest[7] -= SHA512M_H;
+ }
+
+ return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+ const u64 *digest = (const u64 *) digest_buf;
+
+ // we can not change anything in the original buffer, otherwise destroying sorting
+ // therefore create some local buffer
+
+ u64 tmp[8];
+
+ tmp[0] = digest[0];
+ tmp[1] = digest[1];
+ tmp[2] = digest[2];
+ tmp[3] = digest[3];
+ tmp[4] = digest[4];
+ tmp[5] = digest[5];
+ tmp[6] = digest[6];
+ tmp[7] = digest[7];
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ tmp[0] += SHA512M_A;
+ tmp[1] += SHA512M_B;
+ tmp[2] += SHA512M_C;
+ tmp[3] += SHA512M_D;
+ tmp[4] += SHA512M_E;
+ tmp[5] += SHA512M_F;
+ tmp[6] += SHA512M_G;
+ tmp[7] += SHA512M_H;
+ }
+
+ tmp[0] = byte_swap_64 (tmp[0]);
+ tmp[1] = byte_swap_64 (tmp[1]);
+ tmp[2] = byte_swap_64 (tmp[2]);
+ tmp[3] = byte_swap_64 (tmp[3]);
+ tmp[4] = byte_swap_64 (tmp[4]);
+ tmp[5] = byte_swap_64 (tmp[5]);
+ tmp[6] = byte_swap_64 (tmp[6]);
+ tmp[7] = byte_swap_64 (tmp[7]);
+
+
+ u8 *out_buf = (u8 *) line_buf;
+
+ u64_to_hex (tmp[0], out_buf + 0);
+ u64_to_hex (tmp[1], out_buf + 16);
+ u64_to_hex (tmp[2], out_buf + 32);
+ u64_to_hex (tmp[3], out_buf + 48);
+ u64_to_hex (tmp[4], out_buf + 64);
+ u64_to_hex (tmp[5], out_buf + 80);
+ u64_to_hex (tmp[6], out_buf + 96);
+ u64_to_hex (tmp[7], out_buf + 112);
+
+ const int out_len = 128;
+
+ return out_len;
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+ module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
+ module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
+
+ module_ctx->module_attack_exec = module_attack_exec;
+ module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_mask = MODULE_DEFAULT;
+ module_ctx->module_benchmark_salt = MODULE_DEFAULT;
+ module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
+ module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
+ module_ctx->module_dgst_pos0 = module_dgst_pos0;
+ module_ctx->module_dgst_pos1 = module_dgst_pos1;
+ module_ctx->module_dgst_pos2 = module_dgst_pos2;
+ module_ctx->module_dgst_pos3 = module_dgst_pos3;
+ module_ctx->module_dgst_size = module_dgst_size;
+ module_ctx->module_dictstat_disable = MODULE_DEFAULT;
+ module_ctx->module_esalt_size = MODULE_DEFAULT;
+ module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
+ module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_count = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_save = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
+ module_ctx->module_hash_decode = module_hash_decode;
+ module_ctx->module_hash_encode_status = MODULE_DEFAULT;
+ module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_encode = module_hash_encode;
+ module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
+ module_ctx->module_hash_mode = MODULE_DEFAULT;
+ module_ctx->module_hash_category = module_hash_category;
+ module_ctx->module_hash_name = module_hash_name;
+ module_ctx->module_hashes_count_min = MODULE_DEFAULT;
+ module_ctx->module_hashes_count_max = MODULE_DEFAULT;
+ module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
+ module_ctx->module_hook12 = MODULE_DEFAULT;
+ module_ctx->module_hook23 = MODULE_DEFAULT;
+ module_ctx->module_hook_salt_size = MODULE_DEFAULT;
+ module_ctx->module_hook_size = MODULE_DEFAULT;
+ module_ctx->module_jit_build_options = MODULE_DEFAULT;
+ module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
+ module_ctx->module_kern_type = module_kern_type;
+ module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
+ module_ctx->module_opti_type = module_opti_type;
+ module_ctx->module_opts_type = module_opts_type;
+ module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
+ module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
+ module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
+ module_ctx->module_potfile_disable = MODULE_DEFAULT;
+ module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
+ module_ctx->module_pwdump_column = MODULE_DEFAULT;
+ module_ctx->module_pw_max = MODULE_DEFAULT;
+ module_ctx->module_pw_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = MODULE_DEFAULT;
+ module_ctx->module_salt_min = MODULE_DEFAULT;
+ module_ctx->module_salt_type = module_salt_type;
+ module_ctx->module_separator = MODULE_DEFAULT;
+ module_ctx->module_st_hash = module_st_hash;
+ module_ctx->module_st_pass = module_st_pass;
+ module_ctx->module_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_unstable_warning = MODULE_DEFAULT;
+ module_ctx->module_warmup_disable = MODULE_DEFAULT;
+}
diff --git a/tools/test_modules/m01770.pm b/tools/test_modules/m01770.pm
new file mode 100644
index 000000000..f3d4d7778
--- /dev/null
+++ b/tools/test_modules/m01770.pm
@@ -0,0 +1,43 @@
+#!/usr/bin/env perl
+
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use Digest::SHA qw (sha512);
+use Digest::SHA qw (sha512_hex);
+
+sub module_constraints { [[0, 256], [-1, -1], [0, 55], [-1, -1], [-1, -1]] }
+
+sub module_generate_hash
+{
+ my $word = shift;
+
+ my $digest = sha512_hex (sha512 ($word));
+
+ my $hash = sprintf ("%s", $digest);
+
+ return $hash;
+}
+
+sub module_verify_hash
+{
+ my $line = shift;
+
+ my ($hash, $word) = split (':', $line);
+
+ return unless defined $hash;
+ return unless defined $word;
+
+ my $word_packed = pack_if_HEX_notation ($word);
+
+ my $new_hash = module_generate_hash ($word_packed);
+
+ return ($new_hash, $word);
+}
+
+1;
From ff93d218ee35ed9e0432bfcb47c460099a2c84bc Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 27 Jul 2019 00:01:10 +0200
Subject: [PATCH 030/113] fix code style
---
OpenCL/m01470_a0-pure.cl | 60 ++++++++++++++++++++++++++++++----------
OpenCL/m01470_a1-pure.cl | 60 ++++++++++++++++++++++++++++++----------
OpenCL/m01470_a3-pure.cl | 60 +++++++++++++++++++++++++++++-----------
3 files changed, 136 insertions(+), 44 deletions(-)
diff --git a/OpenCL/m01470_a0-pure.cl b/OpenCL/m01470_a0-pure.cl
index e9926a7b8..46f2c892f 100644
--- a/OpenCL/m01470_a0-pure.cl
+++ b/OpenCL/m01470_a0-pure.cl
@@ -37,6 +37,11 @@ KERNEL_FQ void m01470_mxx (KERN_ATTR_RULES ())
* loop
*/
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
{
pw_t tmp = PASTE_PW;
@@ -55,14 +60,25 @@ KERNEL_FQ void m01470_mxx (KERN_ATTR_RULES ())
sha256_init (&ctx);
- u32 _w0[4];
- _w0[0] = ctx0.h[0]; _w0[1] = ctx0.h[1]; _w0[2] = ctx0.h[2]; _w0[3] = ctx0.h[3];
- u32 _w1[4];
- _w1[0] = ctx0.h[4]; _w1[1] = ctx0.h[5]; _w1[2] = ctx0.h[6]; _w1[3] = ctx0.h[7];
- u32 _w2[4] = { 0, 0, 0, 0 };
- u32 _w3[4] = { 0, 0, 0, 0 };
+ w0[0] = ctx0.h[0];
+ w0[1] = ctx0.h[1];
+ w0[2] = ctx0.h[2];
+ w0[3] = ctx0.h[3];
+ w1[0] = ctx0.h[4];
+ w1[1] = ctx0.h[5];
+ w1[2] = ctx0.h[6];
+ w1[3] = ctx0.h[7];
- sha256_update_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha256_update_64 (&ctx, w0, w1, w2, w3, 32);
sha256_final (&ctx);
@@ -108,6 +124,11 @@ KERNEL_FQ void m01470_sxx (KERN_ATTR_RULES ())
* loop
*/
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
{
pw_t tmp = PASTE_PW;
@@ -126,14 +147,25 @@ KERNEL_FQ void m01470_sxx (KERN_ATTR_RULES ())
sha256_init (&ctx);
- u32 _w0[4];
- _w0[0] = ctx0.h[0]; _w0[1] = ctx0.h[1]; _w0[2] = ctx0.h[2]; _w0[3] = ctx0.h[3];
- u32 _w1[4];
- _w1[0] = ctx0.h[4]; _w1[1] = ctx0.h[5]; _w1[2] = ctx0.h[6]; _w1[3] = ctx0.h[7];
- u32 _w2[4] = { 0, 0, 0, 0 };
- u32 _w3[4] = { 0, 0, 0, 0 };
+ w0[0] = ctx0.h[0];
+ w0[1] = ctx0.h[1];
+ w0[2] = ctx0.h[2];
+ w0[3] = ctx0.h[3];
+ w1[0] = ctx0.h[4];
+ w1[1] = ctx0.h[5];
+ w1[2] = ctx0.h[6];
+ w1[3] = ctx0.h[7];
- sha256_update_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha256_update_64 (&ctx, w0, w1, w2, w3, 32);
sha256_final (&ctx);
diff --git a/OpenCL/m01470_a1-pure.cl b/OpenCL/m01470_a1-pure.cl
index eae6a32e8..2ba848069 100644
--- a/OpenCL/m01470_a1-pure.cl
+++ b/OpenCL/m01470_a1-pure.cl
@@ -39,6 +39,11 @@ KERNEL_FQ void m01470_mxx (KERN_ATTR_BASIC ())
* loop
*/
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
{
sha256_ctx_t ctx0 = ctx1;
@@ -51,14 +56,25 @@ KERNEL_FQ void m01470_mxx (KERN_ATTR_BASIC ())
sha256_init (&ctx);
- u32 _w0[4];
- _w0[0] = ctx0.h[0]; _w0[1] = ctx0.h[1]; _w0[2] = ctx0.h[2]; _w0[3] = ctx0.h[3];
- u32 _w1[4];
- _w1[0] = ctx0.h[4]; _w1[1] = ctx0.h[5]; _w1[2] = ctx0.h[6]; _w1[3] = ctx0.h[7];
- u32 _w2[4] = { 0, 0, 0, 0 };
- u32 _w3[4] = { 0, 0, 0, 0 };
+ w0[0] = ctx0.h[0];
+ w0[1] = ctx0.h[1];
+ w0[2] = ctx0.h[2];
+ w0[3] = ctx0.h[3];
+ w1[0] = ctx0.h[4];
+ w1[1] = ctx0.h[5];
+ w1[2] = ctx0.h[6];
+ w1[3] = ctx0.h[7];
- sha256_update_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha256_update_64 (&ctx, w0, w1, w2, w3, 32);
sha256_final (&ctx);
@@ -108,6 +124,11 @@ KERNEL_FQ void m01470_sxx (KERN_ATTR_BASIC ())
* loop
*/
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
{
sha256_ctx_t ctx0 = ctx1;
@@ -120,14 +141,25 @@ KERNEL_FQ void m01470_sxx (KERN_ATTR_BASIC ())
sha256_init (&ctx);
- u32 _w0[4];
- _w0[0] = ctx0.h[0]; _w0[1] = ctx0.h[1]; _w0[2] = ctx0.h[2]; _w0[3] = ctx0.h[3];
- u32 _w1[4];
- _w1[0] = ctx0.h[4]; _w1[1] = ctx0.h[5]; _w1[2] = ctx0.h[6]; _w1[3] = ctx0.h[7];
- u32 _w2[4] = { 0, 0, 0, 0 };
- u32 _w3[4] = { 0, 0, 0, 0 };
+ w0[0] = ctx0.h[0];
+ w0[1] = ctx0.h[1];
+ w0[2] = ctx0.h[2];
+ w0[3] = ctx0.h[3];
+ w1[0] = ctx0.h[4];
+ w1[1] = ctx0.h[5];
+ w1[2] = ctx0.h[6];
+ w1[3] = ctx0.h[7];
- sha256_update_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha256_update_64 (&ctx, w0, w1, w2, w3, 32);
sha256_final (&ctx);
diff --git a/OpenCL/m01470_a3-pure.cl b/OpenCL/m01470_a3-pure.cl
index 18071aae9..da1f34954 100644
--- a/OpenCL/m01470_a3-pure.cl
+++ b/OpenCL/m01470_a3-pure.cl
@@ -42,6 +42,11 @@ KERNEL_FQ void m01470_mxx (KERN_ATTR_VECTOR ())
* loop
*/
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
u32x w0l = w[0];
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
@@ -64,14 +69,23 @@ KERNEL_FQ void m01470_mxx (KERN_ATTR_VECTOR ())
sha256_init_vector (&ctx);
- u32x _w0[4];
- _w0[0] = ctx0.h[0]; _w0[1] = ctx0.h[1]; _w0[2] = ctx0.h[2]; _w0[3] = ctx0.h[3];
- u32x _w1[4];
- _w1[0] = ctx0.h[4]; _w1[1] = ctx0.h[5]; _w1[2] = ctx0.h[6]; _w1[3] = ctx0.h[7];
- u32x _w2[4];
- _w2[0] = 0; _w2[1] = 0; _w2[2] = 0; _w2[3] = 0;
- u32x _w3[4];
- _w3[0] = 0; _w3[1] = 0; _w3[2] = 0; _w3[3] = 0;
+ _w0[0] = ctx0.h[0];
+ _w0[1] = ctx0.h[1];
+ _w0[2] = ctx0.h[2];
+ _w0[3] = ctx0.h[3];
+ _w1[0] = ctx0.h[4];
+ _w1[1] = ctx0.h[5];
+ _w1[2] = ctx0.h[6];
+ _w1[3] = ctx0.h[7];
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
sha256_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 32);
@@ -126,6 +140,11 @@ KERNEL_FQ void m01470_sxx (KERN_ATTR_VECTOR ())
* loop
*/
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
u32x w0l = w[0];
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
@@ -148,14 +167,23 @@ KERNEL_FQ void m01470_sxx (KERN_ATTR_VECTOR ())
sha256_init_vector (&ctx);
- u32x _w0[4];
- _w0[0] = ctx0.h[0]; _w0[1] = ctx0.h[1]; _w0[2] = ctx0.h[2]; _w0[3] = ctx0.h[3];
- u32x _w1[4];
- _w1[0] = ctx0.h[4]; _w1[1] = ctx0.h[5]; _w1[2] = ctx0.h[6]; _w1[3] = ctx0.h[7];
- u32x _w2[4];
- _w2[0] = 0; _w2[1] = 0; _w2[2] = 0; _w2[3] = 0;
- u32x _w3[4];
- _w3[0] = 0; _w3[1] = 0; _w3[2] = 0; _w3[3] = 0;
+ _w0[0] = ctx0.h[0];
+ _w0[1] = ctx0.h[1];
+ _w0[2] = ctx0.h[2];
+ _w0[3] = ctx0.h[3];
+ _w1[0] = ctx0.h[4];
+ _w1[1] = ctx0.h[5];
+ _w1[2] = ctx0.h[6];
+ _w1[3] = ctx0.h[7];
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
sha256_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 32);
From e766cf0dc785cd6b08a57d2ed406bade63bb424d Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 27 Jul 2019 02:03:23 +0200
Subject: [PATCH 031/113] Added hash-mode: sha1(md5(.))
---
OpenCL/m04720_a0-pure.cl | 276 ++++++++++++++++++++++++++++++++
OpenCL/m04720_a1-pure.cl | 270 ++++++++++++++++++++++++++++++++
OpenCL/m04720_a3-pure.cl | 296 +++++++++++++++++++++++++++++++++++
docs/changes.txt | 1 +
docs/credits.txt | 1 +
docs/readme.txt | 1 +
src/modules/module_04720.c | 233 +++++++++++++++++++++++++++
tools/test_modules/m04720.pm | 45 ++++++
8 files changed, 1123 insertions(+)
create mode 100644 OpenCL/m04720_a0-pure.cl
create mode 100644 OpenCL/m04720_a1-pure.cl
create mode 100644 OpenCL/m04720_a3-pure.cl
create mode 100644 src/modules/module_04720.c
create mode 100644 tools/test_modules/m04720.pm
diff --git a/OpenCL/m04720_a0-pure.cl b/OpenCL/m04720_a0-pure.cl
new file mode 100644
index 000000000..4a1c615fd
--- /dev/null
+++ b/OpenCL/m04720_a0-pure.cl
@@ -0,0 +1,276 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp.h"
+#include "inc_rp.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04720_mxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = salt_bufs[salt_pos].salt_buf[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ md5_ctx_t ctx0;
+
+ md5_init (&ctx0);
+
+ md5_update (&ctx0, tmp.i, tmp.pw_len);
+
+ md5_update (&ctx0, s, salt_len);
+
+ md5_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+
+ sha1_ctx_t ctx;
+
+ sha1_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha1_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ sha1_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04720_sxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = salt_bufs[salt_pos].salt_buf[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ md5_ctx_t ctx0;
+
+ md5_init (&ctx0);
+
+ md5_update (&ctx0, tmp.i, tmp.pw_len);
+
+ md5_update (&ctx0, s, salt_len);
+
+ md5_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+
+ sha1_ctx_t ctx;
+
+ sha1_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha1_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ sha1_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m04720_a1-pure.cl b/OpenCL/m04720_a1-pure.cl
new file mode 100644
index 000000000..5ed4f4d9f
--- /dev/null
+++ b/OpenCL/m04720_a1-pure.cl
@@ -0,0 +1,270 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04720_mxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = salt_bufs[salt_pos].salt_buf[idx];
+ }
+
+ md5_ctx_t ctx0;
+
+ md5_init (&ctx0);
+
+ md5_update_global (&ctx0, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ md5_ctx_t ctx1 = ctx0;
+
+ md5_update_global (&ctx1, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ md5_update (&ctx1, s, salt_len);
+
+ md5_final (&ctx1);
+
+ const u32 a = ctx1.h[0];
+ const u32 b = ctx1.h[1];
+ const u32 c = ctx1.h[2];
+ const u32 d = ctx1.h[3];
+
+ sha1_ctx_t ctx;
+
+ sha1_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha1_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ sha1_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04720_sxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = salt_bufs[salt_pos].salt_buf[idx];
+ }
+
+ md5_ctx_t ctx0;
+
+ md5_init (&ctx0);
+
+ md5_update_global (&ctx0, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ md5_ctx_t ctx1 = ctx0;
+
+ md5_update_global (&ctx1, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ md5_update (&ctx1, s, salt_len);
+
+ md5_final (&ctx1);
+
+ const u32 a = ctx1.h[0];
+ const u32 b = ctx1.h[1];
+ const u32 c = ctx1.h[2];
+ const u32 d = ctx1.h[3];
+
+ sha1_ctx_t ctx;
+
+ sha1_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha1_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ sha1_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m04720_a3-pure.cl b/OpenCL/m04720_a3-pure.cl
new file mode 100644
index 000000000..4554e4604
--- /dev/null
+++ b/OpenCL/m04720_a3-pure.cl
@@ -0,0 +1,296 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04720_mxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = salt_bufs[salt_pos].salt_buf[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ md5_ctx_vector_t ctx0;
+
+ md5_init_vector (&ctx0);
+
+ md5_update_vector (&ctx0, w, pw_len);
+
+ md5_update_vector (&ctx0, s, salt_len);
+
+ md5_final_vector (&ctx0);
+
+ const u32x a = ctx0.h[0];
+ const u32x b = ctx0.h[1];
+ const u32x c = ctx0.h[2];
+ const u32x d = ctx0.h[3];
+
+ sha1_ctx_vector_t ctx;
+
+ sha1_init_vector (&ctx);
+
+ _w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ sha1_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ sha1_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04720_sxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = salt_bufs[salt_pos].salt_buf[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ md5_ctx_vector_t ctx0;
+
+ md5_init_vector (&ctx0);
+
+ md5_update_vector (&ctx0, w, pw_len);
+
+ md5_update_vector (&ctx0, s, salt_len);
+
+ md5_final_vector (&ctx0);
+
+ const u32x a = ctx0.h[0];
+ const u32x b = ctx0.h[1];
+ const u32x c = ctx0.h[2];
+ const u32x d = ctx0.h[3];
+
+ sha1_ctx_vector_t ctx;
+
+ sha1_init_vector (&ctx);
+
+ _w0[0] = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ sha1_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ sha1_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SIMD (r0, r1, r2, r3);
+ }
+}
diff --git a/docs/changes.txt b/docs/changes.txt
index 0bb228187..22b1b4572 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,6 +35,7 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
+- Added hash-mode: sha1(md5($pass.$salt))
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index bd21d35d7..7b6534226 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,6 +18,7 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
+* sha1(md5($pass.$salt)) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
diff --git a/docs/readme.txt b/docs/readme.txt
index 9e36b73ce..4f71181fc 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -81,6 +81,7 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- sha1(sha1($pass))
- sha1($salt.sha1($pass))
- sha1(md5($pass))
+- sha1(md5($pass.$salt))
- sha1(md5(md5($pass)))
- sha1($salt.$pass.$salt)
- sha1(CX)
diff --git a/src/modules/module_04720.c b/src/modules/module_04720.c
new file mode 100644
index 000000000..a414a4a84
--- /dev/null
+++ b/src/modules/module_04720.c
@@ -0,0 +1,233 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+
+static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL;
+static const u32 DGST_POS0 = 3;
+static const u32 DGST_POS1 = 4;
+static const u32 DGST_POS2 = 2;
+static const u32 DGST_POS3 = 1;
+static const u32 DGST_SIZE = DGST_SIZE_4_5;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
+static const char *HASH_NAME = "sha1(md5($pass.$salt))";
+static const u64 KERN_TYPE = 4720;
+static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
+ | OPTI_TYPE_PRECOMPUTE_INIT
+ | OPTI_TYPE_EARLY_SKIP
+ | OPTI_TYPE_NOT_ITERATED
+ | OPTI_TYPE_APPENDED_SALT
+ | OPTI_TYPE_RAW_HASH;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE
+ | OPTS_TYPE_PT_ADD80
+ | OPTS_TYPE_PT_ADDBITS14;
+static const u32 SALT_TYPE = SALT_TYPE_EMBEDDED;
+static const char *ST_PASS = "hashcat";
+static const char *ST_HASH = "aade80a61c6e3cd3cac614f47c1991e0a87dd028:6";
+
+u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
+u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
+u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
+u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
+u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
+u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
+u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
+const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
+u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
+u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
+u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
+u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
+const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
+const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+ u32 *digest = (u32 *) digest_buf;
+
+ token_t token;
+
+ token.token_cnt = 2;
+
+ token.sep[0] = hashconfig->separator;
+ token.len_min[0] = 40;
+ token.len_max[0] = 40;
+ token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_HEX;
+
+ token.len_min[1] = SALT_MIN;
+ token.len_max[1] = SALT_MAX;
+ token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH;
+
+ if (hashconfig->opts_type & OPTS_TYPE_ST_HEX)
+ {
+ token.len_min[1] *= 2;
+ token.len_max[1] *= 2;
+
+ token.attr[1] |= TOKEN_ATTR_VERIFY_HEX;
+ }
+
+ const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+ if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+ const u8 *hash_pos = token.buf[0];
+
+ digest[0] = hex_to_u32 (hash_pos + 0);
+ digest[1] = hex_to_u32 (hash_pos + 8);
+ digest[2] = hex_to_u32 (hash_pos + 16);
+ digest[3] = hex_to_u32 (hash_pos + 24);
+ digest[4] = hex_to_u32 (hash_pos + 32);
+
+ digest[0] = byte_swap_32 (digest[0]);
+ digest[1] = byte_swap_32 (digest[1]);
+ digest[2] = byte_swap_32 (digest[2]);
+ digest[3] = byte_swap_32 (digest[3]);
+ digest[4] = byte_swap_32 (digest[4]);
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ digest[0] -= SHA1M_A;
+ digest[1] -= SHA1M_B;
+ digest[2] -= SHA1M_C;
+ digest[3] -= SHA1M_D;
+ digest[4] -= SHA1M_E;
+ }
+
+ const u8 *salt_pos = token.buf[1];
+ const int salt_len = token.len[1];
+
+ const bool parse_rc = generic_salt_decode (hashconfig, salt_pos, salt_len, (u8 *) salt->salt_buf, (int *) &salt->salt_len);
+
+ if (parse_rc == false) return (PARSER_SALT_LENGTH);
+
+ return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+ const u32 *digest = (const u32 *) digest_buf;
+
+ // we can not change anything in the original buffer, otherwise destroying sorting
+ // therefore create some local buffer
+
+ u32 tmp[5];
+
+ tmp[0] = digest[0];
+ tmp[1] = digest[1];
+ tmp[2] = digest[2];
+ tmp[3] = digest[3];
+ tmp[4] = digest[4];
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ tmp[0] += SHA1M_A;
+ tmp[1] += SHA1M_B;
+ tmp[2] += SHA1M_C;
+ tmp[3] += SHA1M_D;
+ tmp[4] += SHA1M_E;
+ }
+
+ tmp[0] = byte_swap_32 (tmp[0]);
+ tmp[1] = byte_swap_32 (tmp[1]);
+ tmp[2] = byte_swap_32 (tmp[2]);
+ tmp[3] = byte_swap_32 (tmp[3]);
+ tmp[4] = byte_swap_32 (tmp[4]);
+
+ u8 *out_buf = (u8 *) line_buf;
+
+ int out_len = 0;
+
+ u32_to_hex (tmp[0], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[1], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[2], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[3], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[4], out_buf + out_len); out_len += 8;
+
+ out_buf[out_len] = hashconfig->separator;
+
+ out_len += 1;
+
+ out_len += generic_salt_encode (hashconfig, (const u8 *) salt->salt_buf, (const int) salt->salt_len, out_buf + out_len);
+
+ return out_len;
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+ module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
+ module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
+
+ module_ctx->module_attack_exec = module_attack_exec;
+ module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_mask = MODULE_DEFAULT;
+ module_ctx->module_benchmark_salt = MODULE_DEFAULT;
+ module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
+ module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
+ module_ctx->module_dgst_pos0 = module_dgst_pos0;
+ module_ctx->module_dgst_pos1 = module_dgst_pos1;
+ module_ctx->module_dgst_pos2 = module_dgst_pos2;
+ module_ctx->module_dgst_pos3 = module_dgst_pos3;
+ module_ctx->module_dgst_size = module_dgst_size;
+ module_ctx->module_dictstat_disable = MODULE_DEFAULT;
+ module_ctx->module_esalt_size = MODULE_DEFAULT;
+ module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
+ module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_count = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_save = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
+ module_ctx->module_hash_decode = module_hash_decode;
+ module_ctx->module_hash_encode_status = MODULE_DEFAULT;
+ module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_encode = module_hash_encode;
+ module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
+ module_ctx->module_hash_mode = MODULE_DEFAULT;
+ module_ctx->module_hash_category = module_hash_category;
+ module_ctx->module_hash_name = module_hash_name;
+ module_ctx->module_hashes_count_min = MODULE_DEFAULT;
+ module_ctx->module_hashes_count_max = MODULE_DEFAULT;
+ module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
+ module_ctx->module_hook12 = MODULE_DEFAULT;
+ module_ctx->module_hook23 = MODULE_DEFAULT;
+ module_ctx->module_hook_salt_size = MODULE_DEFAULT;
+ module_ctx->module_hook_size = MODULE_DEFAULT;
+ module_ctx->module_jit_build_options = MODULE_DEFAULT;
+ module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
+ module_ctx->module_kern_type = module_kern_type;
+ module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
+ module_ctx->module_opti_type = module_opti_type;
+ module_ctx->module_opts_type = module_opts_type;
+ module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
+ module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
+ module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
+ module_ctx->module_potfile_disable = MODULE_DEFAULT;
+ module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
+ module_ctx->module_pwdump_column = MODULE_DEFAULT;
+ module_ctx->module_pw_max = MODULE_DEFAULT;
+ module_ctx->module_pw_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = MODULE_DEFAULT;
+ module_ctx->module_salt_min = MODULE_DEFAULT;
+ module_ctx->module_salt_type = module_salt_type;
+ module_ctx->module_separator = MODULE_DEFAULT;
+ module_ctx->module_st_hash = module_st_hash;
+ module_ctx->module_st_pass = module_st_pass;
+ module_ctx->module_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_unstable_warning = MODULE_DEFAULT;
+ module_ctx->module_warmup_disable = MODULE_DEFAULT;
+}
diff --git a/tools/test_modules/m04720.pm b/tools/test_modules/m04720.pm
new file mode 100644
index 000000000..3bbd15b93
--- /dev/null
+++ b/tools/test_modules/m04720.pm
@@ -0,0 +1,45 @@
+#!/usr/bin/env perl
+
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use Digest::MD5 qw (md5_hex);
+use Digest::SHA qw (sha1_hex);
+
+sub module_constraints { [[0, 256], [0, 256], [0, 55], [0, 55], [0, 55]] }
+
+sub module_generate_hash
+{
+ my $word = shift;
+ my $salt = random_hex_string (1, 256);
+
+ my $digest = sha1_hex (md5_hex ($word . $salt));
+
+ my $hash = sprintf ("%s:%s", $digest, $salt);
+
+ return $hash;
+}
+
+sub module_verify_hash
+{
+ my $line = shift;
+
+ my ($hash, $salt, $word) = split (':', $line);
+
+ return unless defined $hash;
+ return unless defined $salt;
+ return unless defined $word;
+
+ my $word_packed = pack_if_HEX_notation ($word);
+
+ my $new_hash = module_generate_hash ($word_packed, $salt);
+
+ return ($new_hash, $word);
+}
+
+1;
From 370a5524595175c3f1845b54148b535bc3aa4dda Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 27 Jul 2019 14:16:30 +0200
Subject: [PATCH 032/113] Added hash-mode: md5(sha1().md5())
---
OpenCL/m04420_a0-pure.cl | 360 +++++++++++++++++++++++++++++++++
OpenCL/m04420_a1-pure.cl | 354 ++++++++++++++++++++++++++++++++
OpenCL/m04420_a3-pure.cl | 380 +++++++++++++++++++++++++++++++++++
docs/changes.txt | 1 +
docs/credits.txt | 1 +
docs/readme.txt | 1 +
src/modules/module_04420.c | 215 ++++++++++++++++++++
tools/test_modules/m04420.pm | 45 +++++
8 files changed, 1357 insertions(+)
create mode 100644 OpenCL/m04420_a0-pure.cl
create mode 100644 OpenCL/m04420_a1-pure.cl
create mode 100644 OpenCL/m04420_a3-pure.cl
create mode 100644 src/modules/module_04420.c
create mode 100644 tools/test_modules/m04420.pm
diff --git a/OpenCL/m04420_a0-pure.cl b/OpenCL/m04420_a0-pure.cl
new file mode 100644
index 000000000..6503d8781
--- /dev/null
+++ b/OpenCL/m04420_a0-pure.cl
@@ -0,0 +1,360 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp.h"
+#include "inc_rp.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04420_mxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = salt_bufs[salt_pos].salt_buf[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ sha1_ctx_t ctx0;
+
+ sha1_init (&ctx0);
+
+ sha1_update_swap (&ctx0, s, salt_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a0 = ctx0.h[0];
+ const u32 b0 = ctx0.h[1];
+ const u32 c0 = ctx0.h[2];
+ const u32 d0 = ctx0.h[3];
+ const u32 e0 = ctx0.h[4];
+
+ md5_ctx_t ctx1;
+
+ md5_init (&ctx1);
+
+ md5_update (&ctx1, tmp.i, tmp.pw_len);
+
+ md5_final (&ctx1);
+
+ const u32 a1 = hc_swap32 (ctx1.h[0]);
+ const u32 b1 = hc_swap32 (ctx1.h[1]);
+ const u32 c1 = hc_swap32 (ctx1.h[2]);
+ const u32 d1 = hc_swap32 (ctx1.h[3]);
+
+ md5_ctx_t ctx;
+
+ md5_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ md5_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04420_sxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = salt_bufs[salt_pos].salt_buf[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ sha1_ctx_t ctx0;
+
+ sha1_init (&ctx0);
+
+ sha1_update_swap (&ctx0, s, salt_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a0 = ctx0.h[0];
+ const u32 b0 = ctx0.h[1];
+ const u32 c0 = ctx0.h[2];
+ const u32 d0 = ctx0.h[3];
+ const u32 e0 = ctx0.h[4];
+
+ md5_ctx_t ctx1;
+
+ md5_init (&ctx1);
+
+ md5_update (&ctx1, tmp.i, tmp.pw_len);
+
+ md5_final (&ctx1);
+
+ const u32 a1 = hc_swap32 (ctx1.h[0]);
+ const u32 b1 = hc_swap32 (ctx1.h[1]);
+ const u32 c1 = hc_swap32 (ctx1.h[2]);
+ const u32 d1 = hc_swap32 (ctx1.h[3]);
+
+ md5_ctx_t ctx;
+
+ md5_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ md5_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m04420_a1-pure.cl b/OpenCL/m04420_a1-pure.cl
new file mode 100644
index 000000000..05e845560
--- /dev/null
+++ b/OpenCL/m04420_a1-pure.cl
@@ -0,0 +1,354 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04420_mxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = salt_bufs[salt_pos].salt_buf[idx];
+ }
+
+ md5_ctx_t ctx11;
+
+ md5_init (&ctx11);
+
+ md5_update_global (&ctx11, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ sha1_ctx_t ctx0;
+
+ sha1_init (&ctx0);
+
+ sha1_update_swap (&ctx0, s, salt_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a0 = ctx0.h[0];
+ const u32 b0 = ctx0.h[1];
+ const u32 c0 = ctx0.h[2];
+ const u32 d0 = ctx0.h[3];
+ const u32 e0 = ctx0.h[4];
+
+ md5_ctx_t ctx1 = ctx11;
+
+ md5_update_global (&ctx1, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ md5_final (&ctx1);
+
+ const u32 a1 = hc_swap32 (ctx1.h[0]);
+ const u32 b1 = hc_swap32 (ctx1.h[1]);
+ const u32 c1 = hc_swap32 (ctx1.h[2]);
+ const u32 d1 = hc_swap32 (ctx1.h[3]);
+
+ md5_ctx_t ctx;
+
+ md5_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ md5_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04420_sxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = salt_bufs[salt_pos].salt_buf[idx];
+ }
+
+ md5_ctx_t ctx11;
+
+ md5_init (&ctx11);
+
+ md5_update_global (&ctx11, pws[gid].i, pws[gid].pw_len);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ sha1_ctx_t ctx0;
+
+ sha1_init (&ctx0);
+
+ sha1_update_swap (&ctx0, s, salt_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a0 = ctx0.h[0];
+ const u32 b0 = ctx0.h[1];
+ const u32 c0 = ctx0.h[2];
+ const u32 d0 = ctx0.h[3];
+ const u32 e0 = ctx0.h[4];
+
+ md5_ctx_t ctx1 = ctx11;
+
+ md5_update_global (&ctx1, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ md5_final (&ctx1);
+
+ const u32 a1 = hc_swap32 (ctx1.h[0]);
+ const u32 b1 = hc_swap32 (ctx1.h[1]);
+ const u32 c1 = hc_swap32 (ctx1.h[2]);
+ const u32 d1 = hc_swap32 (ctx1.h[3]);
+
+ md5_ctx_t ctx;
+
+ md5_init (&ctx);
+
+ w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 32);
+
+ md5_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m04420_a3-pure.cl b/OpenCL/m04420_a3-pure.cl
new file mode 100644
index 000000000..58c351b25
--- /dev/null
+++ b/OpenCL/m04420_a3-pure.cl
@@ -0,0 +1,380 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04420_mxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = salt_bufs[salt_pos].salt_buf[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ sha1_ctx_vector_t ctx0;
+
+ sha1_init_vector (&ctx0);
+
+ sha1_update_vector_swap (&ctx0, s, salt_len);
+
+ sha1_final_vector (&ctx0);
+
+ const u32x a0 = ctx0.h[0];
+ const u32x b0 = ctx0.h[1];
+ const u32x c0 = ctx0.h[2];
+ const u32x d0 = ctx0.h[3];
+ const u32x e0 = ctx0.h[4];
+
+ md5_ctx_vector_t ctx1;
+
+ md5_init_vector (&ctx1);
+
+ md5_update_vector (&ctx1, w, pw_len);
+
+ md5_final_vector (&ctx1);
+
+ const u32x a1 = hc_swap32 (ctx1.h[0]);
+ const u32x b1 = hc_swap32 (ctx1.h[1]);
+ const u32x c1 = hc_swap32 (ctx1.h[2]);
+ const u32x d1 = hc_swap32 (ctx1.h[3]);
+
+ md5_ctx_vector_t ctx;
+
+ md5_init_vector (&ctx);
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ md5_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 40);
+
+ _w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ md5_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ md5_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04420_sxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ u32 s[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
+ {
+ s[idx] = salt_bufs[salt_pos].salt_buf[idx];
+ }
+
+ /**
+ * loop
+ */
+
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ sha1_ctx_vector_t ctx0;
+
+ sha1_init_vector (&ctx0);
+
+ sha1_update_vector_swap (&ctx0, s, salt_len);
+
+ sha1_final_vector (&ctx0);
+
+ const u32x a0 = ctx0.h[0];
+ const u32x b0 = ctx0.h[1];
+ const u32x c0 = ctx0.h[2];
+ const u32x d0 = ctx0.h[3];
+ const u32x e0 = ctx0.h[4];
+
+ md5_ctx_vector_t ctx1;
+
+ md5_init_vector (&ctx1);
+
+ md5_update_vector (&ctx1, w, pw_len);
+
+ md5_final_vector (&ctx1);
+
+ const u32x a1 = hc_swap32 (ctx1.h[0]);
+ const u32x b1 = hc_swap32 (ctx1.h[1]);
+ const u32x c1 = hc_swap32 (ctx1.h[2]);
+ const u32x d1 = hc_swap32 (ctx1.h[3]);
+
+ md5_ctx_vector_t ctx;
+
+ md5_init_vector (&ctx);
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ md5_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 40);
+
+ _w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ md5_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 32);
+
+ md5_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SIMD (r0, r1, r2, r3);
+ }
+}
diff --git a/docs/changes.txt b/docs/changes.txt
index 0bb228187..bab9f5bdf 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,6 +35,7 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
+- Added hash-mode: md5(sha1($salt).md5($pass))
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index bd21d35d7..474f29925 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,6 +18,7 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
+* md5(sha1($salt).md5($pass)) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
diff --git a/docs/readme.txt b/docs/readme.txt
index 9e36b73ce..b4d01990c 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -74,6 +74,7 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- md5(md5($pass).md5($salt))
- md5(strtoupper(md5($pass)))
- md5(sha1($pass))
+- md5(sha1($salt).md5($pass))
- sha1($pass.$salt)
- sha1($salt.$pass)
- sha1(utf16le($pass).$salt)
diff --git a/src/modules/module_04420.c b/src/modules/module_04420.c
new file mode 100644
index 000000000..6e736d05a
--- /dev/null
+++ b/src/modules/module_04420.c
@@ -0,0 +1,215 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+
+static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL;
+static const u32 DGST_POS0 = 0;
+static const u32 DGST_POS1 = 3;
+static const u32 DGST_POS2 = 2;
+static const u32 DGST_POS3 = 1;
+static const u32 DGST_SIZE = DGST_SIZE_4_4;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
+static const char *HASH_NAME = "md5(sha1($salt).md5($pass))";
+static const u64 KERN_TYPE = 4420;
+static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
+ | OPTI_TYPE_PRECOMPUTE_INIT
+ | OPTI_TYPE_EARLY_SKIP
+ | OPTI_TYPE_NOT_ITERATED
+ | OPTI_TYPE_RAW_HASH;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE
+ | OPTS_TYPE_PT_ADD80
+ | OPTS_TYPE_PT_ADDBITS14;
+static const u32 SALT_TYPE = SALT_TYPE_EMBEDDED;
+static const char *ST_PASS = "hashcat";
+static const char *ST_HASH = "e69b7a7fe1bf2ad9ef116f79551ee919:baa038987e582431a6d";
+
+u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
+u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
+u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
+u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
+u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
+u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
+u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
+const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
+u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
+u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
+u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
+u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
+const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
+const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+ u32 *digest = (u32 *) digest_buf;
+
+ token_t token;
+
+ token.token_cnt = 2;
+
+ token.sep[0] = hashconfig->separator;
+ token.len_min[0] = 32;
+ token.len_max[0] = 32;
+ token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_HEX;
+
+ token.len_min[1] = 19;
+ token.len_max[1] = 19;
+ token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH;
+
+ if (hashconfig->opts_type & OPTS_TYPE_ST_HEX)
+ {
+ token.len_min[1] *= 2;
+ token.len_max[1] *= 2;
+
+ token.attr[1] |= TOKEN_ATTR_VERIFY_HEX;
+ }
+
+ const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+ if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+ const u8 *hash_pos = token.buf[0];
+
+ digest[0] = hex_to_u32 (hash_pos + 0);
+ digest[1] = hex_to_u32 (hash_pos + 8);
+ digest[2] = hex_to_u32 (hash_pos + 16);
+ digest[3] = hex_to_u32 (hash_pos + 24);
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ digest[0] -= MD5M_A;
+ digest[1] -= MD5M_B;
+ digest[2] -= MD5M_C;
+ digest[3] -= MD5M_D;
+ }
+
+ const u8 *salt_pos = token.buf[1];
+ const int salt_len = token.len[1];
+
+ const bool parse_rc = generic_salt_decode (hashconfig, salt_pos, salt_len, (u8 *) salt->salt_buf, (int *) &salt->salt_len);
+
+ if (parse_rc == false) return (PARSER_SALT_LENGTH);
+
+ return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+ const u32 *digest = (const u32 *) digest_buf;
+
+ // we can not change anything in the original buffer, otherwise destroying sorting
+ // therefore create some local buffer
+
+ u32 tmp[4];
+
+ tmp[0] = digest[0];
+ tmp[1] = digest[1];
+ tmp[2] = digest[2];
+ tmp[3] = digest[3];
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ tmp[0] += MD5M_A;
+ tmp[1] += MD5M_B;
+ tmp[2] += MD5M_C;
+ tmp[3] += MD5M_D;
+ }
+
+ u8 *out_buf = (u8 *) line_buf;
+
+ int out_len = 0;
+
+ u32_to_hex (tmp[0], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[1], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[2], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[3], out_buf + out_len); out_len += 8;
+
+ out_buf[out_len] = hashconfig->separator;
+
+ out_len += 1;
+
+ out_len += generic_salt_encode (hashconfig, (const u8 *) salt->salt_buf, (const int) salt->salt_len, out_buf + out_len);
+
+ return out_len;
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+ module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
+ module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
+
+ module_ctx->module_attack_exec = module_attack_exec;
+ module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_mask = MODULE_DEFAULT;
+ module_ctx->module_benchmark_salt = MODULE_DEFAULT;
+ module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
+ module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
+ module_ctx->module_dgst_pos0 = module_dgst_pos0;
+ module_ctx->module_dgst_pos1 = module_dgst_pos1;
+ module_ctx->module_dgst_pos2 = module_dgst_pos2;
+ module_ctx->module_dgst_pos3 = module_dgst_pos3;
+ module_ctx->module_dgst_size = module_dgst_size;
+ module_ctx->module_dictstat_disable = MODULE_DEFAULT;
+ module_ctx->module_esalt_size = MODULE_DEFAULT;
+ module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
+ module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_count = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_save = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
+ module_ctx->module_hash_decode = module_hash_decode;
+ module_ctx->module_hash_encode_status = MODULE_DEFAULT;
+ module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_encode = module_hash_encode;
+ module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
+ module_ctx->module_hash_mode = MODULE_DEFAULT;
+ module_ctx->module_hash_category = module_hash_category;
+ module_ctx->module_hash_name = module_hash_name;
+ module_ctx->module_hashes_count_min = MODULE_DEFAULT;
+ module_ctx->module_hashes_count_max = MODULE_DEFAULT;
+ module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
+ module_ctx->module_hook12 = MODULE_DEFAULT;
+ module_ctx->module_hook23 = MODULE_DEFAULT;
+ module_ctx->module_hook_salt_size = MODULE_DEFAULT;
+ module_ctx->module_hook_size = MODULE_DEFAULT;
+ module_ctx->module_jit_build_options = MODULE_DEFAULT;
+ module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
+ module_ctx->module_kern_type = module_kern_type;
+ module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
+ module_ctx->module_opti_type = module_opti_type;
+ module_ctx->module_opts_type = module_opts_type;
+ module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
+ module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
+ module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
+ module_ctx->module_potfile_disable = MODULE_DEFAULT;
+ module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
+ module_ctx->module_pwdump_column = MODULE_DEFAULT;
+ module_ctx->module_pw_max = MODULE_DEFAULT;
+ module_ctx->module_pw_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = MODULE_DEFAULT;
+ module_ctx->module_salt_min = MODULE_DEFAULT;
+ module_ctx->module_salt_type = module_salt_type;
+ module_ctx->module_separator = MODULE_DEFAULT;
+ module_ctx->module_st_hash = module_st_hash;
+ module_ctx->module_st_pass = module_st_pass;
+ module_ctx->module_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_unstable_warning = MODULE_DEFAULT;
+ module_ctx->module_warmup_disable = MODULE_DEFAULT;
+}
diff --git a/tools/test_modules/m04420.pm b/tools/test_modules/m04420.pm
new file mode 100644
index 000000000..400afd6cb
--- /dev/null
+++ b/tools/test_modules/m04420.pm
@@ -0,0 +1,45 @@
+#!/usr/bin/env perl
+
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use Digest::MD5 qw (md5_hex);
+use Digest::SHA qw (sha1_hex);
+
+sub module_constraints { [[0, 256], [19, 19], [0, 55], [-1, -1], [-1, -1]] }
+
+sub module_generate_hash
+{
+ my $word = shift;
+ my $salt = random_hex_string (19, 19);
+
+ my $digest = md5_hex (sha1_hex ($salt) . md5_hex ($word));
+
+ my $hash = sprintf ("%s:%s", $digest, $salt);
+
+ return $hash;
+}
+
+sub module_verify_hash
+{
+ my $line = shift;
+
+ my ($hash, $salt, $word) = split (':', $line);
+
+ return unless defined $hash;
+ return unless defined $salt;
+ return unless defined $word;
+
+ my $word_packed = pack_if_HEX_notation ($word);
+
+ my $new_hash = module_generate_hash ($word_packed, $salt);
+
+ return ($new_hash, $word);
+}
+
+1;
From d824d1943e8b235cea1c3946503ceb39f8ee5d50 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 27 Jul 2019 17:03:19 +0200
Subject: [PATCH 033/113] Added hash-mode: md5(salt.sha1(salt.pass))
---
OpenCL/m04430_a0-pure.cl | 276 +++++++++++++++++++++++++++++++
OpenCL/m04430_a1-pure.cl | 266 ++++++++++++++++++++++++++++++
OpenCL/m04430_a3-pure.cl | 304 +++++++++++++++++++++++++++++++++++
docs/changes.txt | 1 +
docs/credits.txt | 1 +
docs/readme.txt | 1 +
src/modules/module_04430.c | 215 +++++++++++++++++++++++++
tools/test_modules/m04430.pm | 50 ++++++
8 files changed, 1114 insertions(+)
create mode 100644 OpenCL/m04430_a0-pure.cl
create mode 100644 OpenCL/m04430_a1-pure.cl
create mode 100644 OpenCL/m04430_a3-pure.cl
create mode 100644 src/modules/module_04430.c
create mode 100644 tools/test_modules/m04430.pm
diff --git a/OpenCL/m04430_a0-pure.cl b/OpenCL/m04430_a0-pure.cl
new file mode 100644
index 000000000..8c25b929e
--- /dev/null
+++ b/OpenCL/m04430_a0-pure.cl
@@ -0,0 +1,276 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp.h"
+#include "inc_rp.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04430_mxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ sha1_ctx_t ctx00;
+
+ sha1_init(&ctx00);
+
+ sha1_update_global_swap (&ctx00, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ md5_ctx_t ctx11;
+
+ md5_init (&ctx11);
+
+ md5_update_global (&ctx11, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ sha1_ctx_t ctx0 = ctx00;
+
+ sha1_update_swap (&ctx0, tmp.i, tmp.pw_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+ const u32 e = ctx0.h[4];
+
+ md5_ctx_t ctx = ctx11;
+
+ w0[0] = uint_to_hex_lower8 ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ md5_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04430_sxx (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ COPY_PW (pws[gid]);
+
+ sha1_ctx_t ctx00;
+
+ sha1_init(&ctx00);
+
+ sha1_update_global_swap (&ctx00, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ md5_ctx_t ctx11;
+
+ md5_init (&ctx11);
+
+ md5_update_global (&ctx11, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ pw_t tmp = PASTE_PW;
+
+ tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
+
+ sha1_ctx_t ctx0 = ctx00;
+
+ sha1_update_swap (&ctx0, tmp.i, tmp.pw_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+ const u32 e = ctx0.h[4];
+
+ md5_ctx_t ctx = ctx11;
+
+ w0[0] = uint_to_hex_lower8 ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ md5_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m04430_a1-pure.cl b/OpenCL/m04430_a1-pure.cl
new file mode 100644
index 000000000..5871f7d7e
--- /dev/null
+++ b/OpenCL/m04430_a1-pure.cl
@@ -0,0 +1,266 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+//#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_scalar.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04430_mxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ sha1_ctx_t ctx00;
+
+ sha1_init (&ctx00);
+
+ sha1_update_global_swap (&ctx00, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ sha1_update_global_swap (&ctx00, pws[gid].i, pws[gid].pw_len);
+
+ md5_ctx_t ctx11;
+
+ md5_init (&ctx11);
+
+ md5_update_global (&ctx11, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ sha1_ctx_t ctx0 = ctx00;
+
+ sha1_update_global_swap (&ctx0, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+ const u32 e = ctx0.h[4];
+
+ md5_ctx_t ctx = ctx11;
+
+ w0[0] = uint_to_hex_lower8 ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ md5_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SCALAR (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04430_sxx (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ sha1_ctx_t ctx00;
+
+ sha1_init (&ctx00);
+
+ sha1_update_global_swap (&ctx00, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ sha1_update_global_swap (&ctx00, pws[gid].i, pws[gid].pw_len);
+
+ md5_ctx_t ctx11;
+
+ md5_init (&ctx11);
+
+ md5_update_global (&ctx11, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ /**
+ * loop
+ */
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ {
+ sha1_ctx_t ctx0 = ctx00;
+
+ sha1_update_global_swap (&ctx0, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a = ctx0.h[0];
+ const u32 b = ctx0.h[1];
+ const u32 c = ctx0.h[2];
+ const u32 d = ctx0.h[3];
+ const u32 e = ctx0.h[4];
+
+ md5_ctx_t ctx = ctx11;
+
+ w0[0] = uint_to_hex_lower8 ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 0) & 255) << 16;
+ w2[0] = uint_to_hex_lower8 ((e >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e >> 16) & 255) << 16;
+ w2[1] = uint_to_hex_lower8 ((e >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e >> 0) & 255) << 16;
+
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ md5_update_64 (&ctx, w0, w1, w2, w3, 40);
+
+ md5_final (&ctx);
+
+ const u32 r0 = ctx.h[DGST_R0];
+ const u32 r1 = ctx.h[DGST_R1];
+ const u32 r2 = ctx.h[DGST_R2];
+ const u32 r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SCALAR (r0, r1, r2, r3);
+ }
+}
diff --git a/OpenCL/m04430_a3-pure.cl b/OpenCL/m04430_a3-pure.cl
new file mode 100644
index 000000000..3f22a77a2
--- /dev/null
+++ b/OpenCL/m04430_a3-pure.cl
@@ -0,0 +1,304 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04430_mxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ sha1_ctx_t ctx00;
+
+ sha1_init (&ctx00);
+
+ sha1_update_global_swap (&ctx00, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ md5_ctx_t ctx11;
+
+ md5_init (&ctx11);
+
+ md5_update_global (&ctx11, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ /**
+ * loop
+ */
+
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ sha1_ctx_vector_t ctx0;
+
+ sha1_init_vector_from_scalar (&ctx0, &ctx00);
+
+ sha1_update_vector_swap (&ctx0, w, pw_len);
+
+ sha1_final_vector (&ctx0);
+
+ const u32x a = ctx0.h[0];
+ const u32x b = ctx0.h[1];
+ const u32x c = ctx0.h[2];
+ const u32x d = ctx0.h[3];
+ const u32x e = ctx0.h[4];
+
+ md5_ctx_vector_t ctx;
+
+ sha1_init_vector_from_scalar (&ctx, &ctx11);
+
+ _w0[0] = uint_to_hex_lower8 ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ md5_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 40);
+
+ md5_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_M_SIMD (r0, r1, r2, r3);
+ }
+}
+
+KERNEL_FQ void m04430_sxx (KERN_ATTR_VECTOR ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * base
+ */
+
+ const u32 pw_len = pws[gid].pw_len;
+
+ u32x w[64] = { 0 };
+
+ for (u32 i = 0, idx = 0; i < pw_len; i += 4, idx += 1)
+ {
+ w[idx] = pws[gid].i[idx];
+ }
+
+ sha1_ctx_t ctx00;
+
+ sha1_init (&ctx00);
+
+ sha1_update_global_swap (&ctx00, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ md5_ctx_t ctx11;
+
+ md5_init (&ctx11);
+
+ md5_update_global (&ctx11, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ /**
+ * loop
+ */
+
+ u32x _w0[4];
+ u32x _w1[4];
+ u32x _w2[4];
+ u32x _w3[4];
+
+ u32x w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ w[0] = w0;
+
+ sha1_ctx_vector_t ctx0;
+
+ sha1_init_vector_from_scalar (&ctx0, &ctx00);
+
+ sha1_update_vector_swap (&ctx0, w, pw_len);
+
+ sha1_final_vector (&ctx0);
+
+ const u32x a = ctx0.h[0];
+ const u32x b = ctx0.h[1];
+ const u32x c = ctx0.h[2];
+ const u32x d = ctx0.h[3];
+ const u32x e = ctx0.h[4];
+
+ md5_ctx_vector_t ctx;
+
+ sha1_init_vector_from_scalar (&ctx, &ctx11);
+
+ _w0[0] = uint_to_hex_lower8 ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ md5_update_vector_64 (&ctx, _w0, _w1, _w2, _w3, 40);
+
+ md5_final_vector (&ctx);
+
+ const u32x r0 = ctx.h[DGST_R0];
+ const u32x r1 = ctx.h[DGST_R1];
+ const u32x r2 = ctx.h[DGST_R2];
+ const u32x r3 = ctx.h[DGST_R3];
+
+ COMPARE_S_SIMD (r0, r1, r2, r3);
+ }
+}
diff --git a/docs/changes.txt b/docs/changes.txt
index 0bb228187..a60aa03f3 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,6 +35,7 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
+- Added hash-mode: md5($salt.sha1($salt.$pass))
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index bd21d35d7..55864e185 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,6 +18,7 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
+* md5($salt.sha1($salt.$pass)) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
diff --git a/docs/readme.txt b/docs/readme.txt
index 9e36b73ce..d403bf936 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -70,6 +70,7 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- md5($salt.md5($pass))
- md5($salt.md5($salt.$pass))
- md5($salt.md5($pass.$salt))
+- md5($salt.sha1($salt.$pass))
- md5(md5($pass))
- md5(md5($pass).md5($salt))
- md5(strtoupper(md5($pass)))
diff --git a/src/modules/module_04430.c b/src/modules/module_04430.c
new file mode 100644
index 000000000..acb878d6d
--- /dev/null
+++ b/src/modules/module_04430.c
@@ -0,0 +1,215 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+
+static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL;
+static const u32 DGST_POS0 = 0;
+static const u32 DGST_POS1 = 3;
+static const u32 DGST_POS2 = 2;
+static const u32 DGST_POS3 = 1;
+static const u32 DGST_SIZE = DGST_SIZE_4_4;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
+static const char *HASH_NAME = "md5($salt.sha1($salt.$pass))";
+static const u64 KERN_TYPE = 4430;
+static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
+ | OPTI_TYPE_PRECOMPUTE_INIT
+ | OPTI_TYPE_EARLY_SKIP
+ | OPTI_TYPE_NOT_ITERATED
+ | OPTI_TYPE_RAW_HASH;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE
+ | OPTS_TYPE_PT_ADD80
+ | OPTS_TYPE_PT_ADDBITS14;
+static const u32 SALT_TYPE = SALT_TYPE_EMBEDDED;
+static const char *ST_PASS = "hashcat";
+static const char *ST_HASH = "799dc7d9aa4d3f404cc21a4936dbdcde:68617368636174"; //6d455b6e8945bebfd0a5878eaa201523:hashcat"; //c8f4f1202e7aaebb14e49903ca973d39:943038186";
+
+u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
+u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
+u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
+u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
+u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
+u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
+u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
+const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
+u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
+u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
+u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
+u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
+const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
+const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+ u32 *digest = (u32 *) digest_buf;
+
+ token_t token;
+
+ token.token_cnt = 2;
+
+ token.sep[0] = hashconfig->separator;
+ token.len_min[0] = 32;
+ token.len_max[0] = 32;
+ token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_HEX;
+
+ token.len_min[1] = SALT_MIN;
+ token.len_max[1] = SALT_MAX;
+ token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH;
+
+ if (hashconfig->opts_type & OPTS_TYPE_ST_HEX)
+ {
+ token.len_min[1] *= 2;
+ token.len_max[1] *= 2;
+
+ token.attr[1] |= TOKEN_ATTR_VERIFY_HEX;
+ }
+
+ const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+ if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+ const u8 *hash_pos = token.buf[0];
+
+ digest[0] = hex_to_u32 (hash_pos + 0);
+ digest[1] = hex_to_u32 (hash_pos + 8);
+ digest[2] = hex_to_u32 (hash_pos + 16);
+ digest[3] = hex_to_u32 (hash_pos + 24);
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ digest[0] -= MD5M_A;
+ digest[1] -= MD5M_B;
+ digest[2] -= MD5M_C;
+ digest[3] -= MD5M_D;
+ }
+
+ const u8 *salt_pos = token.buf[1];
+ const int salt_len = token.len[1];
+
+ const bool parse_rc = generic_salt_decode (hashconfig, salt_pos, salt_len, (u8 *) salt->salt_buf, (int *) &salt->salt_len);
+
+ if (parse_rc == false) return (PARSER_SALT_LENGTH);
+
+ return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+ const u32 *digest = (const u32 *) digest_buf;
+
+ // we can not change anything in the original buffer, otherwise destroying sorting
+ // therefore create some local buffer
+
+ u32 tmp[4];
+
+ tmp[0] = digest[0];
+ tmp[1] = digest[1];
+ tmp[2] = digest[2];
+ tmp[3] = digest[3];
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ tmp[0] += MD5M_A;
+ tmp[1] += MD5M_B;
+ tmp[2] += MD5M_C;
+ tmp[3] += MD5M_D;
+ }
+
+ u8 *out_buf = (u8 *) line_buf;
+
+ int out_len = 0;
+
+ u32_to_hex (tmp[0], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[1], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[2], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[3], out_buf + out_len); out_len += 8;
+
+ out_buf[out_len] = hashconfig->separator;
+
+ out_len += 1;
+
+ out_len += generic_salt_encode (hashconfig, (const u8 *) salt->salt_buf, (const int) salt->salt_len, out_buf + out_len);
+
+ return out_len;
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+ module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
+ module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
+
+ module_ctx->module_attack_exec = module_attack_exec;
+ module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_mask = MODULE_DEFAULT;
+ module_ctx->module_benchmark_salt = MODULE_DEFAULT;
+ module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
+ module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
+ module_ctx->module_dgst_pos0 = module_dgst_pos0;
+ module_ctx->module_dgst_pos1 = module_dgst_pos1;
+ module_ctx->module_dgst_pos2 = module_dgst_pos2;
+ module_ctx->module_dgst_pos3 = module_dgst_pos3;
+ module_ctx->module_dgst_size = module_dgst_size;
+ module_ctx->module_dictstat_disable = MODULE_DEFAULT;
+ module_ctx->module_esalt_size = MODULE_DEFAULT;
+ module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
+ module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_count = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_save = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
+ module_ctx->module_hash_decode = module_hash_decode;
+ module_ctx->module_hash_encode_status = MODULE_DEFAULT;
+ module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_encode = module_hash_encode;
+ module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
+ module_ctx->module_hash_mode = MODULE_DEFAULT;
+ module_ctx->module_hash_category = module_hash_category;
+ module_ctx->module_hash_name = module_hash_name;
+ module_ctx->module_hashes_count_min = MODULE_DEFAULT;
+ module_ctx->module_hashes_count_max = MODULE_DEFAULT;
+ module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
+ module_ctx->module_hook12 = MODULE_DEFAULT;
+ module_ctx->module_hook23 = MODULE_DEFAULT;
+ module_ctx->module_hook_salt_size = MODULE_DEFAULT;
+ module_ctx->module_hook_size = MODULE_DEFAULT;
+ module_ctx->module_jit_build_options = MODULE_DEFAULT;
+ module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
+ module_ctx->module_kern_type = module_kern_type;
+ module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
+ module_ctx->module_opti_type = module_opti_type;
+ module_ctx->module_opts_type = module_opts_type;
+ module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
+ module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
+ module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
+ module_ctx->module_potfile_disable = MODULE_DEFAULT;
+ module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
+ module_ctx->module_pwdump_column = MODULE_DEFAULT;
+ module_ctx->module_pw_max = MODULE_DEFAULT;
+ module_ctx->module_pw_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = MODULE_DEFAULT;
+ module_ctx->module_salt_min = MODULE_DEFAULT;
+ module_ctx->module_salt_type = module_salt_type;
+ module_ctx->module_separator = MODULE_DEFAULT;
+ module_ctx->module_st_hash = module_st_hash;
+ module_ctx->module_st_pass = module_st_pass;
+ module_ctx->module_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_unstable_warning = MODULE_DEFAULT;
+ module_ctx->module_warmup_disable = MODULE_DEFAULT;
+}
diff --git a/tools/test_modules/m04430.pm b/tools/test_modules/m04430.pm
new file mode 100644
index 000000000..6973f8946
--- /dev/null
+++ b/tools/test_modules/m04430.pm
@@ -0,0 +1,50 @@
+#!/usr/bin/env perl
+
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use Digest::MD5 qw (md5_hex);
+use Digest::SHA qw (sha1_hex);
+
+sub module_constraints { [[0, 256], [1, 256], [0, 55], [-1, -1], [-1, -1]] }
+
+sub module_generate_hash
+{
+ my $word = shift;
+ my $salt = shift;
+
+ if (length $salt == 0)
+ {
+ $salt = random_hex_string (1, 256);
+ }
+
+ my $digest = md5_hex ($salt . sha1_hex ($salt . $word));
+
+ my $hash = sprintf ("%s:%s", $digest, $salt);
+
+ return $hash;
+}
+
+sub module_verify_hash
+{
+ my $line = shift;
+
+ my ($hash, $salt, $word) = split (':', $line);
+
+ return unless defined $hash;
+ return unless defined $salt;
+ return unless defined $word;
+
+ my $word_packed = pack_if_HEX_notation ($word);
+
+ my $new_hash = module_generate_hash ($word_packed, $salt);
+
+ return ($new_hash, $word);
+}
+
+1;
From a5af1392f45797ea2103b159238a20a694d4e1c0 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sun, 28 Jul 2019 05:23:06 +0200
Subject: [PATCH 034/113] Added optimized kernels
---
OpenCL/m04410_a1-optimized.cl | 1579 +++++++++++++++++++++++++++++
OpenCL/m04410_a3-optimized.cl | 1785 +++++++++++++++++++++++++++++++++
OpenCL/m04710_a0-optimized.cl | 707 +++++++++++++
3 files changed, 4071 insertions(+)
create mode 100644 OpenCL/m04410_a1-optimized.cl
create mode 100644 OpenCL/m04410_a3-optimized.cl
create mode 100644 OpenCL/m04710_a0-optimized.cl
diff --git a/OpenCL/m04410_a1-optimized.cl b/OpenCL/m04410_a1-optimized.cl
new file mode 100644
index 000000000..f2b73e562
--- /dev/null
+++ b/OpenCL/m04410_a1-optimized.cl
@@ -0,0 +1,1579 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04410_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = wordl3[2] | wordr3[2];
+ w3[3] = wordl3[3] | wordr3[3];
+
+ /**
+ * sha1(pass)
+ */
+
+ u32x w0_t = hc_swap32 (w0[0]);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = pw_len * 8;
+
+ u32x a = SHA1M_A;
+ u32x b = SHA1M_B;
+ u32x c = SHA1M_C;
+ u32x d = SHA1M_D;
+ u32x e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += SHA1M_A;
+ b += SHA1M_B;
+ c += SHA1M_C;
+ d += SHA1M_D;
+ e += SHA1M_E;
+
+ const u32x a0 = a;
+ const u32x b0 = b;
+ const u32x c0 = c;
+ const u32x d0 = d;
+ const u32x e0 = e;
+
+ /**
+ * md5(pass)
+ */
+
+ w0_t = w0[0];
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = pw_len * 8;
+ wf_t = 0;
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ const u32x a1 = hc_swap32 (a);
+ const u32x b1 = hc_swap32 (b);
+ const u32x c1 = hc_swap32 (c);
+ const u32x d1 = hc_swap32 (d);
+
+ /**
+ * final md5
+ */
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ u32x digest[4];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+
+ u32x _d0[4] = { 0 };
+ u32x _d1[4] = { 0 };
+ u32x _d2[4] = { 0 };
+ u32x _d3[4] = { 0 };
+
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ // append sha1(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ // md5_update_64, len 40, pos 0
+
+ _d0[0] = _w0[0];
+ _d0[1] = _w0[1];
+ _d0[2] = _w0[2];
+ _d0[3] = _w0[3];
+ _d1[0] = _w1[0];
+ _d1[1] = _w1[1];
+ _d1[2] = _w1[2];
+ _d1[3] = _w1[3];
+ _d2[0] = _w2[0];
+ _d2[1] = _w2[1];
+ _d2[2] = _w2[2];
+ _d2[3] = _w2[3];
+ _d3[0] = _w3[0];
+ _d3[1] = _w3[1];
+ _d3[2] = _w3[2];
+ _d3[3] = _w3[3];
+
+ // append md5(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ // md5_update_64, len 32, pos 40
+
+ u32x _t0[4] = { 0 };
+ u32x _t1[4] = { 0 };
+ u32x _t2[4] = { 0 };
+ u32x _t3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_le (_w0, _w1, _w2, _w3, _t0, _t1, _t2, _t3, 40);
+
+ _d0[0] |= _w0[0];
+ _d0[1] |= _w0[1];
+ _d0[2] |= _w0[2];
+ _d0[3] |= _w0[3];
+ _d1[0] |= _w1[0];
+ _d1[1] |= _w1[1];
+ _d1[2] |= _w1[2];
+ _d1[3] |= _w1[3];
+ _d2[0] |= _w2[0];
+ _d2[1] |= _w2[1];
+ _d2[2] |= _w2[2];
+ _d2[3] |= _w2[3];
+ _d3[0] |= _w3[0];
+ _d3[1] |= _w3[1];
+ _d3[2] |= _w3[2];
+ _d3[3] |= _w3[3];
+
+ // md5 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _d0[0];
+ w1_t = _d0[1];
+ w2_t = _d0[2];
+ w3_t = _d0[3];
+ w4_t = _d1[0];
+ w5_t = _d1[1];
+ w6_t = _d1[2];
+ w7_t = _d1[3];
+ w8_t = _d2[0];
+ w9_t = _d2[1];
+ wa_t = _d2[2];
+ wb_t = _d2[3];
+ wc_t = _d3[0];
+ wd_t = _d3[1];
+ we_t = _d3[2];
+ wf_t = _d3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ // u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+
+ _d0[0] = _t0[0];
+ _d0[1] = _t0[1];
+ _d0[2] = _t0[2];
+ _d0[3] = _t0[3];
+ _d1[0] = _t1[0];
+ _d1[1] = _t1[1];
+ _d1[2] = _t1[2];
+ _d1[3] = _t1[3];
+ _d2[0] = _t2[0];
+ _d2[1] = _t2[1];
+ _d2[2] = _t2[2];
+ _d2[3] = _t2[3];
+ _d3[0] = _t3[0];
+ _d3[1] = _t3[1];
+ _d3[2] = _t3[2];
+ _d3[3] = _t3[3];
+
+ // append sha1(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ // md5_update_64, len 40, pos 8
+
+ switch_buffer_by_offset_le (_w0, _w1, _w2, _w3, 8);
+
+ _d0[0] |= _w0[0];
+ _d0[1] |= _w0[1];
+ _d0[2] |= _w0[2];
+ _d0[3] |= _w0[3];
+ _d1[0] |= _w1[0];
+ _d1[1] |= _w1[1];
+ _d1[2] |= _w1[2];
+ _d1[3] |= _w1[3];
+ _d2[0] |= _w2[0];
+ _d2[1] |= _w2[1];
+ _d2[2] |= _w2[2];
+ _d2[3] |= _w2[3];
+ _d3[0] |= _w3[0];
+ _d3[1] |= _w3[1];
+ _d3[2] |= _w3[2];
+ _d3[3] |= _w3[3];
+
+ // md5 final, len 112, pos 48
+
+ append_0x80_4x4 (_d0, _d1, _d2, _d3, 48);
+
+ _d3[2] = 112 * 8;
+ _d3[3] = 0;
+
+ // md5 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _d0[0];
+ w1_t = _d0[1];
+ w2_t = _d0[2];
+ w3_t = _d0[3];
+ w4_t = _d1[0];
+ w5_t = _d1[1];
+ w6_t = _d1[2];
+ w7_t = _d1[3];
+ w8_t = _d2[0];
+ w9_t = _d2[1];
+ wa_t = _d2[2];
+ wb_t = _d2[3];
+ wc_t = _d3[0];
+ wd_t = _d3[1];
+ we_t = _d3[2];
+ wf_t = _d3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ // u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += digest[0] - MD5M_A;
+ b += digest[1] - MD5M_B;
+ c += digest[2] - MD5M_C;
+ d += digest[3] - MD5M_D;
+
+ COMPARE_M_SIMD (a, d, c, b);
+ }
+}
+
+KERNEL_FQ void m04410_m08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m04410_m16 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m04410_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = wordl3[2] | wordr3[2];
+ w3[3] = wordl3[3] | wordr3[3];
+
+ /**
+ * sha1(pass)
+ */
+
+ u32x w0_t = hc_swap32 (w0[0]);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = pw_len * 8;
+
+ u32x a = SHA1M_A;
+ u32x b = SHA1M_B;
+ u32x c = SHA1M_C;
+ u32x d = SHA1M_D;
+ u32x e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += SHA1M_A;
+ b += SHA1M_B;
+ c += SHA1M_C;
+ d += SHA1M_D;
+ e += SHA1M_E;
+
+ const u32x a0 = a;
+ const u32x b0 = b;
+ const u32x c0 = c;
+ const u32x d0 = d;
+ const u32x e0 = e;
+
+ /**
+ * md5(pass)
+ */
+
+ w0_t = w0[0];
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = pw_len * 8;
+ wf_t = 0;
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ const u32x a1 = hc_swap32 (a);
+ const u32x b1 = hc_swap32 (b);
+ const u32x c1 = hc_swap32 (c);
+ const u32x d1 = hc_swap32 (d);
+
+ /**
+ * final md5
+ */
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ u32x digest[4];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+
+ u32x _d0[4] = { 0 };
+ u32x _d1[4] = { 0 };
+ u32x _d2[4] = { 0 };
+ u32x _d3[4] = { 0 };
+
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ // append sha1(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ // md5_update_64, len 40, pos 0
+
+ _d0[0] = _w0[0];
+ _d0[1] = _w0[1];
+ _d0[2] = _w0[2];
+ _d0[3] = _w0[3];
+ _d1[0] = _w1[0];
+ _d1[1] = _w1[1];
+ _d1[2] = _w1[2];
+ _d1[3] = _w1[3];
+ _d2[0] = _w2[0];
+ _d2[1] = _w2[1];
+ _d2[2] = _w2[2];
+ _d2[3] = _w2[3];
+ _d3[0] = _w3[0];
+ _d3[1] = _w3[1];
+ _d3[2] = _w3[2];
+ _d3[3] = _w3[3];
+
+ // append md5(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ // md5_update_64, len 32, pos 40
+
+ u32x _t0[4] = { 0 };
+ u32x _t1[4] = { 0 };
+ u32x _t2[4] = { 0 };
+ u32x _t3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_le (_w0, _w1, _w2, _w3, _t0, _t1, _t2, _t3, 40);
+
+ _d0[0] |= _w0[0];
+ _d0[1] |= _w0[1];
+ _d0[2] |= _w0[2];
+ _d0[3] |= _w0[3];
+ _d1[0] |= _w1[0];
+ _d1[1] |= _w1[1];
+ _d1[2] |= _w1[2];
+ _d1[3] |= _w1[3];
+ _d2[0] |= _w2[0];
+ _d2[1] |= _w2[1];
+ _d2[2] |= _w2[2];
+ _d2[3] |= _w2[3];
+ _d3[0] |= _w3[0];
+ _d3[1] |= _w3[1];
+ _d3[2] |= _w3[2];
+ _d3[3] |= _w3[3];
+
+ // md5 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _d0[0];
+ w1_t = _d0[1];
+ w2_t = _d0[2];
+ w3_t = _d0[3];
+ w4_t = _d1[0];
+ w5_t = _d1[1];
+ w6_t = _d1[2];
+ w7_t = _d1[3];
+ w8_t = _d2[0];
+ w9_t = _d2[1];
+ wa_t = _d2[2];
+ wb_t = _d2[3];
+ wc_t = _d3[0];
+ wd_t = _d3[1];
+ we_t = _d3[2];
+ wf_t = _d3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ // u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+
+ _d0[0] = _t0[0];
+ _d0[1] = _t0[1];
+ _d0[2] = _t0[2];
+ _d0[3] = _t0[3];
+ _d1[0] = _t1[0];
+ _d1[1] = _t1[1];
+ _d1[2] = _t1[2];
+ _d1[3] = _t1[3];
+ _d2[0] = _t2[0];
+ _d2[1] = _t2[1];
+ _d2[2] = _t2[2];
+ _d2[3] = _t2[3];
+ _d3[0] = _t3[0];
+ _d3[1] = _t3[1];
+ _d3[2] = _t3[2];
+ _d3[3] = _t3[3];
+
+ // append sha1(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ // md5_update_64, len 40, pos 8
+
+ switch_buffer_by_offset_le (_w0, _w1, _w2, _w3, 8);
+
+ _d0[0] |= _w0[0];
+ _d0[1] |= _w0[1];
+ _d0[2] |= _w0[2];
+ _d0[3] |= _w0[3];
+ _d1[0] |= _w1[0];
+ _d1[1] |= _w1[1];
+ _d1[2] |= _w1[2];
+ _d1[3] |= _w1[3];
+ _d2[0] |= _w2[0];
+ _d2[1] |= _w2[1];
+ _d2[2] |= _w2[2];
+ _d2[3] |= _w2[3];
+ _d3[0] |= _w3[0];
+ _d3[1] |= _w3[1];
+ _d3[2] |= _w3[2];
+ _d3[3] |= _w3[3];
+
+ // md5 final, len 112, pos 48
+
+ append_0x80_4x4 (_d0, _d1, _d2, _d3, 48);
+
+ _d3[2] = 112 * 8;
+ _d3[3] = 0;
+
+ // md5 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _d0[0];
+ w1_t = _d0[1];
+ w2_t = _d0[2];
+ w3_t = _d0[3];
+ w4_t = _d1[0];
+ w5_t = _d1[1];
+ w6_t = _d1[2];
+ w7_t = _d1[3];
+ w8_t = _d2[0];
+ w9_t = _d2[1];
+ wa_t = _d2[2];
+ wb_t = _d2[3];
+ wc_t = _d3[0];
+ wd_t = _d3[1];
+ we_t = _d3[2];
+ wf_t = _d3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ // u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+
+ if (MATCHES_NONE_VS ((a+digest[0]-MD5M_A), search[0])) continue;
+
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += digest[0] - MD5M_A;
+ b += digest[1] - MD5M_B;
+ c += digest[2] - MD5M_C;
+ d += digest[3] - MD5M_D;
+
+ COMPARE_S_SIMD (a, d, c, b);
+ }
+}
+
+KERNEL_FQ void m04410_s08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m04410_s16 (KERN_ATTR_BASIC ())
+{
+}
diff --git a/OpenCL/m04410_a3-optimized.cl b/OpenCL/m04410_a3-optimized.cl
new file mode 100644
index 000000000..569dab215
--- /dev/null
+++ b/OpenCL/m04410_a3-optimized.cl
@@ -0,0 +1,1785 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+DECLSPEC void m04410m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ /**
+ * sha1(pass)
+ */
+
+ u32x w0_t = hc_swap32 (w0lr);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = pw_len * 8;
+
+ u32x a = SHA1M_A;
+ u32x b = SHA1M_B;
+ u32x c = SHA1M_C;
+ u32x d = SHA1M_D;
+ u32x e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += SHA1M_A;
+ b += SHA1M_B;
+ c += SHA1M_C;
+ d += SHA1M_D;
+ e += SHA1M_E;
+
+ const u32x a0 = a;
+ const u32x b0 = b;
+ const u32x c0 = c;
+ const u32x d0 = d;
+ const u32x e0 = e;
+
+ /**
+ * md5(pass)
+ */
+
+ w0_t = w0lr;
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = pw_len * 8;
+ wf_t = 0;
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ const u32x a1 = hc_swap32 (a);
+ const u32x b1 = hc_swap32 (b);
+ const u32x c1 = hc_swap32 (c);
+ const u32x d1 = hc_swap32 (d);
+
+ /**
+ * final md5
+ */
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ u32x digest[4];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+
+ u32x _d0[4] = { 0 };
+ u32x _d1[4] = { 0 };
+ u32x _d2[4] = { 0 };
+ u32x _d3[4] = { 0 };
+
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ // append sha1(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ // md5_update_64, len 40, pos 0
+
+ _d0[0] = _w0[0];
+ _d0[1] = _w0[1];
+ _d0[2] = _w0[2];
+ _d0[3] = _w0[3];
+ _d1[0] = _w1[0];
+ _d1[1] = _w1[1];
+ _d1[2] = _w1[2];
+ _d1[3] = _w1[3];
+ _d2[0] = _w2[0];
+ _d2[1] = _w2[1];
+ _d2[2] = _w2[2];
+ _d2[3] = _w2[3];
+ _d3[0] = _w3[0];
+ _d3[1] = _w3[1];
+ _d3[2] = _w3[2];
+ _d3[3] = _w3[3];
+
+ // append md5(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ // md5_update_64, len 32, pos 40
+
+ u32x _t0[4] = { 0 };
+ u32x _t1[4] = { 0 };
+ u32x _t2[4] = { 0 };
+ u32x _t3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_le (_w0, _w1, _w2, _w3, _t0, _t1, _t2, _t3, 40);
+
+ _d0[0] |= _w0[0];
+ _d0[1] |= _w0[1];
+ _d0[2] |= _w0[2];
+ _d0[3] |= _w0[3];
+ _d1[0] |= _w1[0];
+ _d1[1] |= _w1[1];
+ _d1[2] |= _w1[2];
+ _d1[3] |= _w1[3];
+ _d2[0] |= _w2[0];
+ _d2[1] |= _w2[1];
+ _d2[2] |= _w2[2];
+ _d2[3] |= _w2[3];
+ _d3[0] |= _w3[0];
+ _d3[1] |= _w3[1];
+ _d3[2] |= _w3[2];
+ _d3[3] |= _w3[3];
+
+ // md5 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _d0[0];
+ w1_t = _d0[1];
+ w2_t = _d0[2];
+ w3_t = _d0[3];
+ w4_t = _d1[0];
+ w5_t = _d1[1];
+ w6_t = _d1[2];
+ w7_t = _d1[3];
+ w8_t = _d2[0];
+ w9_t = _d2[1];
+ wa_t = _d2[2];
+ wb_t = _d2[3];
+ wc_t = _d3[0];
+ wd_t = _d3[1];
+ we_t = _d3[2];
+ wf_t = _d3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ // u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+
+ _d0[0] = _t0[0];
+ _d0[1] = _t0[1];
+ _d0[2] = _t0[2];
+ _d0[3] = _t0[3];
+ _d1[0] = _t1[0];
+ _d1[1] = _t1[1];
+ _d1[2] = _t1[2];
+ _d1[3] = _t1[3];
+ _d2[0] = _t2[0];
+ _d2[1] = _t2[1];
+ _d2[2] = _t2[2];
+ _d2[3] = _t2[3];
+ _d3[0] = _t3[0];
+ _d3[1] = _t3[1];
+ _d3[2] = _t3[2];
+ _d3[3] = _t3[3];
+
+ // append sha1(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ // md5_update_64, len 40, pos 8
+
+ switch_buffer_by_offset_le (_w0, _w1, _w2, _w3, 8);
+
+ _d0[0] |= _w0[0];
+ _d0[1] |= _w0[1];
+ _d0[2] |= _w0[2];
+ _d0[3] |= _w0[3];
+ _d1[0] |= _w1[0];
+ _d1[1] |= _w1[1];
+ _d1[2] |= _w1[2];
+ _d1[3] |= _w1[3];
+ _d2[0] |= _w2[0];
+ _d2[1] |= _w2[1];
+ _d2[2] |= _w2[2];
+ _d2[3] |= _w2[3];
+ _d3[0] |= _w3[0];
+ _d3[1] |= _w3[1];
+ _d3[2] |= _w3[2];
+ _d3[3] |= _w3[3];
+
+ // md5 final, len 112, pos 48
+
+ append_0x80_4x4 (_d0, _d1, _d2, _d3, 48);
+
+ _d3[2] = 112 * 8;
+ _d3[3] = 0;
+
+ // md5 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _d0[0];
+ w1_t = _d0[1];
+ w2_t = _d0[2];
+ w3_t = _d0[3];
+ w4_t = _d1[0];
+ w5_t = _d1[1];
+ w6_t = _d1[2];
+ w7_t = _d1[3];
+ w8_t = _d2[0];
+ w9_t = _d2[1];
+ wa_t = _d2[2];
+ wb_t = _d2[3];
+ wc_t = _d3[0];
+ wd_t = _d3[1];
+ we_t = _d3[2];
+ wf_t = _d3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ // u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += digest[0] - MD5M_A;
+ b += digest[1] - MD5M_B;
+ c += digest[2] - MD5M_C;
+ d += digest[3] - MD5M_D;
+
+ COMPARE_M_SIMD (a, d, c, b);
+ }
+}
+
+DECLSPEC void m04410s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ /**
+ * sha1(pass)
+ */
+
+ u32x w0_t = hc_swap32 (w0lr);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = pw_len * 8;
+
+ u32x a = SHA1M_A;
+ u32x b = SHA1M_B;
+ u32x c = SHA1M_C;
+ u32x d = SHA1M_D;
+ u32x e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += SHA1M_A;
+ b += SHA1M_B;
+ c += SHA1M_C;
+ d += SHA1M_D;
+ e += SHA1M_E;
+
+ const u32x a0 = a;
+ const u32x b0 = b;
+ const u32x c0 = c;
+ const u32x d0 = d;
+ const u32x e0 = e;
+
+ /**
+ * md5(pass)
+ */
+
+ w0_t = w0lr;
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = pw_len * 8;
+ wf_t = 0;
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ const u32x a1 = hc_swap32 (a);
+ const u32x b1 = hc_swap32 (b);
+ const u32x c1 = hc_swap32 (c);
+ const u32x d1 = hc_swap32 (d);
+
+ /**
+ * final md5
+ */
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ u32x digest[4];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+
+ u32x _d0[4] = { 0 };
+ u32x _d1[4] = { 0 };
+ u32x _d2[4] = { 0 };
+ u32x _d3[4] = { 0 };
+
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ // append sha1(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ // md5_update_64, len 40, pos 0
+
+ _d0[0] = _w0[0];
+ _d0[1] = _w0[1];
+ _d0[2] = _w0[2];
+ _d0[3] = _w0[3];
+ _d1[0] = _w1[0];
+ _d1[1] = _w1[1];
+ _d1[2] = _w1[2];
+ _d1[3] = _w1[3];
+ _d2[0] = _w2[0];
+ _d2[1] = _w2[1];
+ _d2[2] = _w2[2];
+ _d2[3] = _w2[3];
+ _d3[0] = _w3[0];
+ _d3[1] = _w3[1];
+ _d3[2] = _w3[2];
+ _d3[3] = _w3[3];
+
+ // append md5(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ // md5_update_64, len 32, pos 40
+
+ u32x _t0[4] = { 0 };
+ u32x _t1[4] = { 0 };
+ u32x _t2[4] = { 0 };
+ u32x _t3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_le (_w0, _w1, _w2, _w3, _t0, _t1, _t2, _t3, 40);
+
+ _d0[0] |= _w0[0];
+ _d0[1] |= _w0[1];
+ _d0[2] |= _w0[2];
+ _d0[3] |= _w0[3];
+ _d1[0] |= _w1[0];
+ _d1[1] |= _w1[1];
+ _d1[2] |= _w1[2];
+ _d1[3] |= _w1[3];
+ _d2[0] |= _w2[0];
+ _d2[1] |= _w2[1];
+ _d2[2] |= _w2[2];
+ _d2[3] |= _w2[3];
+ _d3[0] |= _w3[0];
+ _d3[1] |= _w3[1];
+ _d3[2] |= _w3[2];
+ _d3[3] |= _w3[3];
+
+ // md5 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _d0[0];
+ w1_t = _d0[1];
+ w2_t = _d0[2];
+ w3_t = _d0[3];
+ w4_t = _d1[0];
+ w5_t = _d1[1];
+ w6_t = _d1[2];
+ w7_t = _d1[3];
+ w8_t = _d2[0];
+ w9_t = _d2[1];
+ wa_t = _d2[2];
+ wb_t = _d2[3];
+ wc_t = _d3[0];
+ wd_t = _d3[1];
+ we_t = _d3[2];
+ wf_t = _d3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ // u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+
+ _d0[0] = _t0[0];
+ _d0[1] = _t0[1];
+ _d0[2] = _t0[2];
+ _d0[3] = _t0[3];
+ _d1[0] = _t1[0];
+ _d1[1] = _t1[1];
+ _d1[2] = _t1[2];
+ _d1[3] = _t1[3];
+ _d2[0] = _t2[0];
+ _d2[1] = _t2[1];
+ _d2[2] = _t2[2];
+ _d2[3] = _t2[3];
+ _d3[0] = _t3[0];
+ _d3[1] = _t3[1];
+ _d3[2] = _t3[2];
+ _d3[3] = _t3[3];
+
+ // append sha1(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ // md5_update_64, len 40, pos 8
+
+ switch_buffer_by_offset_le (_w0, _w1, _w2, _w3, 8);
+
+ _d0[0] |= _w0[0];
+ _d0[1] |= _w0[1];
+ _d0[2] |= _w0[2];
+ _d0[3] |= _w0[3];
+ _d1[0] |= _w1[0];
+ _d1[1] |= _w1[1];
+ _d1[2] |= _w1[2];
+ _d1[3] |= _w1[3];
+ _d2[0] |= _w2[0];
+ _d2[1] |= _w2[1];
+ _d2[2] |= _w2[2];
+ _d2[3] |= _w2[3];
+ _d3[0] |= _w3[0];
+ _d3[1] |= _w3[1];
+ _d3[2] |= _w3[2];
+ _d3[3] |= _w3[3];
+
+ // md5 final, len 112, pos 48
+
+ append_0x80_4x4 (_d0, _d1, _d2, _d3, 48);
+
+ _d3[2] = 112 * 8;
+ _d3[3] = 0;
+
+ // md5 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _d0[0];
+ w1_t = _d0[1];
+ w2_t = _d0[2];
+ w3_t = _d0[3];
+ w4_t = _d1[0];
+ w5_t = _d1[1];
+ w6_t = _d1[2];
+ w7_t = _d1[3];
+ w8_t = _d2[0];
+ w9_t = _d2[1];
+ wa_t = _d2[2];
+ wb_t = _d2[3];
+ wc_t = _d3[0];
+ wd_t = _d3[1];
+ we_t = _d3[2];
+ wf_t = _d3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ // u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+
+ if (MATCHES_NONE_VS ((a+digest[0]-MD5M_A), search[0])) continue;
+
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += digest[0] - MD5M_A;
+ b += digest[1] - MD5M_B;
+ c += digest[2] - MD5M_C;
+ d += digest[3] - MD5M_D;
+
+ COMPARE_S_SIMD (a, d, c, b);
+ }
+}
+
+KERNEL_FQ void m04410_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04410m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04410_m08 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04410m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04410_m16 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = pws[gid].i[14];
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04410m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04410_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04410s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04410_s08 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04410s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04410_s16 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = pws[gid].i[14];
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04410s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
diff --git a/OpenCL/m04710_a0-optimized.cl b/OpenCL/m04710_a0-optimized.cl
new file mode 100644
index 000000000..488d15da3
--- /dev/null
+++ b/OpenCL/m04710_a0-optimized.cl
@@ -0,0 +1,707 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04710_m04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ w3[2] = out_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha1
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0x80000000;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 32 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_M_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m04710_m08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04710_m16 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04710_s04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+ salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+ salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+ salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+ salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+ salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
+ salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
+ salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
+ salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
+ salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
+ salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
+ salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
+ salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
+ salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
+ salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
+ salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ w3[2] = out_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha1
+ */
+
+ /**
+ * append salt
+ */
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = salt_buf1[0];
+ s1[1] = salt_buf1[1];
+ s1[2] = salt_buf1[2];
+ s1[3] = salt_buf1[3];
+ s2[0] = salt_buf2[0];
+ s2[1] = salt_buf2[1];
+ s2[2] = salt_buf2[2];
+ s2[3] = salt_buf2[3];
+ s3[0] = salt_buf3[0];
+ s3[1] = salt_buf3[1];
+ s3[2] = salt_buf3[2];
+ s3[3] = salt_buf3[3];
+
+ switch_buffer_by_offset_le_VV (s0, s1, s2, s3, 32);
+
+ const u32x pw_salt_len = out_len + salt_len;
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0x80000000;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 0; //32 * 8;
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+
+ we_t = 0;
+ wf_t = pw_salt_len * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+ if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_S_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m04710_s08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04710_s16 (KERN_ATTR_RULES ())
+{
+}
From ebb83bee410d2d6d61aeca1510f3d7a1d4095adf Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sun, 28 Jul 2019 18:22:41 +0200
Subject: [PATCH 035/113] Add the right one a0 optimized kernel
---
OpenCL/m04410_a0-optimized.cl | 1465 +++++++++++++++++++++++++++++++++
OpenCL/m04710_a0-optimized.cl | 707 ----------------
2 files changed, 1465 insertions(+), 707 deletions(-)
create mode 100644 OpenCL/m04410_a0-optimized.cl
delete mode 100644 OpenCL/m04710_a0-optimized.cl
diff --git a/OpenCL/m04410_a0-optimized.cl b/OpenCL/m04410_a0-optimized.cl
new file mode 100644
index 000000000..a44f6eb7c
--- /dev/null
+++ b/OpenCL/m04410_a0-optimized.cl
@@ -0,0 +1,1465 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04410_m04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ /**
+ * sha1(pass)
+ */
+
+ u32x w0_t = hc_swap32 (w0[0]);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = out_len * 8;
+
+ u32x a = SHA1M_A;
+ u32x b = SHA1M_B;
+ u32x c = SHA1M_C;
+ u32x d = SHA1M_D;
+ u32x e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += SHA1M_A;
+ b += SHA1M_B;
+ c += SHA1M_C;
+ d += SHA1M_D;
+ e += SHA1M_E;
+
+ const u32x a0 = a;
+ const u32x b0 = b;
+ const u32x c0 = c;
+ const u32x d0 = d;
+ const u32x e0 = e;
+
+ /**
+ * md5(pass)
+ */
+
+ w0_t = w0[0];
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = out_len * 8;
+ wf_t = 0;
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ const u32x a1 = hc_swap32 (a);
+ const u32x b1 = hc_swap32 (b);
+ const u32x c1 = hc_swap32 (c);
+ const u32x d1 = hc_swap32 (d);
+
+ /**
+ * final md5
+ */
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ u32x digest[4];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+
+ u32x _d0[4] = { 0 };
+ u32x _d1[4] = { 0 };
+ u32x _d2[4] = { 0 };
+ u32x _d3[4] = { 0 };
+
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ // append sha1(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ // md5_update_64, len 40, pos 0
+
+ _d0[0] = _w0[0];
+ _d0[1] = _w0[1];
+ _d0[2] = _w0[2];
+ _d0[3] = _w0[3];
+ _d1[0] = _w1[0];
+ _d1[1] = _w1[1];
+ _d1[2] = _w1[2];
+ _d1[3] = _w1[3];
+ _d2[0] = _w2[0];
+ _d2[1] = _w2[1];
+ _d2[2] = _w2[2];
+ _d2[3] = _w2[3];
+ _d3[0] = _w3[0];
+ _d3[1] = _w3[1];
+ _d3[2] = _w3[2];
+ _d3[3] = _w3[3];
+
+ // append md5(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ // md5_update_64, len 32, pos 40
+
+ u32x _t0[4] = { 0 };
+ u32x _t1[4] = { 0 };
+ u32x _t2[4] = { 0 };
+ u32x _t3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_le (_w0, _w1, _w2, _w3, _t0, _t1, _t2, _t3, 40);
+
+ _d0[0] |= _w0[0];
+ _d0[1] |= _w0[1];
+ _d0[2] |= _w0[2];
+ _d0[3] |= _w0[3];
+ _d1[0] |= _w1[0];
+ _d1[1] |= _w1[1];
+ _d1[2] |= _w1[2];
+ _d1[3] |= _w1[3];
+ _d2[0] |= _w2[0];
+ _d2[1] |= _w2[1];
+ _d2[2] |= _w2[2];
+ _d2[3] |= _w2[3];
+ _d3[0] |= _w3[0];
+ _d3[1] |= _w3[1];
+ _d3[2] |= _w3[2];
+ _d3[3] |= _w3[3];
+
+ // md5 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _d0[0];
+ w1_t = _d0[1];
+ w2_t = _d0[2];
+ w3_t = _d0[3];
+ w4_t = _d1[0];
+ w5_t = _d1[1];
+ w6_t = _d1[2];
+ w7_t = _d1[3];
+ w8_t = _d2[0];
+ w9_t = _d2[1];
+ wa_t = _d2[2];
+ wb_t = _d2[3];
+ wc_t = _d3[0];
+ wd_t = _d3[1];
+ we_t = _d3[2];
+ wf_t = _d3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ // u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+
+ _d0[0] = _t0[0];
+ _d0[1] = _t0[1];
+ _d0[2] = _t0[2];
+ _d0[3] = _t0[3];
+ _d1[0] = _t1[0];
+ _d1[1] = _t1[1];
+ _d1[2] = _t1[2];
+ _d1[3] = _t1[3];
+ _d2[0] = _t2[0];
+ _d2[1] = _t2[1];
+ _d2[2] = _t2[2];
+ _d2[3] = _t2[3];
+ _d3[0] = _t3[0];
+ _d3[1] = _t3[1];
+ _d3[2] = _t3[2];
+ _d3[3] = _t3[3];
+
+ // append sha1(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ // md5_update_64, len 40, pos 8
+
+ switch_buffer_by_offset_le (_w0, _w1, _w2, _w3, 8);
+
+ _d0[0] |= _w0[0];
+ _d0[1] |= _w0[1];
+ _d0[2] |= _w0[2];
+ _d0[3] |= _w0[3];
+ _d1[0] |= _w1[0];
+ _d1[1] |= _w1[1];
+ _d1[2] |= _w1[2];
+ _d1[3] |= _w1[3];
+ _d2[0] |= _w2[0];
+ _d2[1] |= _w2[1];
+ _d2[2] |= _w2[2];
+ _d2[3] |= _w2[3];
+ _d3[0] |= _w3[0];
+ _d3[1] |= _w3[1];
+ _d3[2] |= _w3[2];
+ _d3[3] |= _w3[3];
+
+ // md5 final, len 112, pos 48
+
+ append_0x80_4x4 (_d0, _d1, _d2, _d3, 48);
+
+ _d3[2] = 112 * 8;
+ _d3[3] = 0;
+
+ // md5 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _d0[0];
+ w1_t = _d0[1];
+ w2_t = _d0[2];
+ w3_t = _d0[3];
+ w4_t = _d1[0];
+ w5_t = _d1[1];
+ w6_t = _d1[2];
+ w7_t = _d1[3];
+ w8_t = _d2[0];
+ w9_t = _d2[1];
+ wa_t = _d2[2];
+ wb_t = _d2[3];
+ wc_t = _d3[0];
+ wd_t = _d3[1];
+ we_t = _d3[2];
+ wf_t = _d3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ // u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += digest[0] - MD5M_A;
+ b += digest[1] - MD5M_B;
+ c += digest[2] - MD5M_C;
+ d += digest[3] - MD5M_D;
+
+ COMPARE_M_SIMD (a, d, c, b);
+ }
+}
+
+KERNEL_FQ void m04410_m08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04410_m16 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04410_s04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ /**
+ * sha1(pass)
+ */
+
+ u32x w0_t = hc_swap32 (w0[0]);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = out_len * 8;
+
+ u32x a = SHA1M_A;
+ u32x b = SHA1M_B;
+ u32x c = SHA1M_C;
+ u32x d = SHA1M_D;
+ u32x e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += SHA1M_A;
+ b += SHA1M_B;
+ c += SHA1M_C;
+ d += SHA1M_D;
+ e += SHA1M_E;
+
+ const u32x a0 = a;
+ const u32x b0 = b;
+ const u32x c0 = c;
+ const u32x d0 = d;
+ const u32x e0 = e;
+
+ /**
+ * md5(pass)
+ */
+
+ w0_t = w0[0];
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = out_len * 8;
+ wf_t = 0;
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ const u32x a1 = hc_swap32 (a);
+ const u32x b1 = hc_swap32 (b);
+ const u32x c1 = hc_swap32 (c);
+ const u32x d1 = hc_swap32 (d);
+
+ /**
+ * final md5
+ */
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ u32x digest[4];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+
+ u32x _d0[4] = { 0 };
+ u32x _d1[4] = { 0 };
+ u32x _d2[4] = { 0 };
+ u32x _d3[4] = { 0 };
+
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ // append sha1(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ // md5_update_64, len 40, pos 0
+
+ _d0[0] = _w0[0];
+ _d0[1] = _w0[1];
+ _d0[2] = _w0[2];
+ _d0[3] = _w0[3];
+ _d1[0] = _w1[0];
+ _d1[1] = _w1[1];
+ _d1[2] = _w1[2];
+ _d1[3] = _w1[3];
+ _d2[0] = _w2[0];
+ _d2[1] = _w2[1];
+ _d2[2] = _w2[2];
+ _d2[3] = _w2[3];
+ _d3[0] = _w3[0];
+ _d3[1] = _w3[1];
+ _d3[2] = _w3[2];
+ _d3[3] = _w3[3];
+
+ // append md5(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ // md5_update_64, len 32, pos 40
+
+ u32x _t0[4] = { 0 };
+ u32x _t1[4] = { 0 };
+ u32x _t2[4] = { 0 };
+ u32x _t3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_le (_w0, _w1, _w2, _w3, _t0, _t1, _t2, _t3, 40);
+
+ _d0[0] |= _w0[0];
+ _d0[1] |= _w0[1];
+ _d0[2] |= _w0[2];
+ _d0[3] |= _w0[3];
+ _d1[0] |= _w1[0];
+ _d1[1] |= _w1[1];
+ _d1[2] |= _w1[2];
+ _d1[3] |= _w1[3];
+ _d2[0] |= _w2[0];
+ _d2[1] |= _w2[1];
+ _d2[2] |= _w2[2];
+ _d2[3] |= _w2[3];
+ _d3[0] |= _w3[0];
+ _d3[1] |= _w3[1];
+ _d3[2] |= _w3[2];
+ _d3[3] |= _w3[3];
+
+ // md5 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _d0[0];
+ w1_t = _d0[1];
+ w2_t = _d0[2];
+ w3_t = _d0[3];
+ w4_t = _d1[0];
+ w5_t = _d1[1];
+ w6_t = _d1[2];
+ w7_t = _d1[3];
+ w8_t = _d2[0];
+ w9_t = _d2[1];
+ wa_t = _d2[2];
+ wb_t = _d2[3];
+ wc_t = _d3[0];
+ wd_t = _d3[1];
+ we_t = _d3[2];
+ wf_t = _d3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ // u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+
+ _d0[0] = _t0[0];
+ _d0[1] = _t0[1];
+ _d0[2] = _t0[2];
+ _d0[3] = _t0[3];
+ _d1[0] = _t1[0];
+ _d1[1] = _t1[1];
+ _d1[2] = _t1[2];
+ _d1[3] = _t1[3];
+ _d2[0] = _t2[0];
+ _d2[1] = _t2[1];
+ _d2[2] = _t2[2];
+ _d2[3] = _t2[3];
+ _d3[0] = _t3[0];
+ _d3[1] = _t3[1];
+ _d3[2] = _t3[2];
+ _d3[3] = _t3[3];
+
+ // append sha1(pass)
+
+ _w0[0] = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ _w2[0] = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ _w2[1] = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ // md5_update_64, len 40, pos 8
+
+ switch_buffer_by_offset_le (_w0, _w1, _w2, _w3, 8);
+
+ _d0[0] |= _w0[0];
+ _d0[1] |= _w0[1];
+ _d0[2] |= _w0[2];
+ _d0[3] |= _w0[3];
+ _d1[0] |= _w1[0];
+ _d1[1] |= _w1[1];
+ _d1[2] |= _w1[2];
+ _d1[3] |= _w1[3];
+ _d2[0] |= _w2[0];
+ _d2[1] |= _w2[1];
+ _d2[2] |= _w2[2];
+ _d2[3] |= _w2[3];
+ _d3[0] |= _w3[0];
+ _d3[1] |= _w3[1];
+ _d3[2] |= _w3[2];
+ _d3[3] |= _w3[3];
+
+ // md5 final, len 112, pos 48
+
+ append_0x80_4x4 (_d0, _d1, _d2, _d3, 48);
+
+ _d3[2] = 112 * 8;
+ _d3[3] = 0;
+
+ // md5 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _d0[0];
+ w1_t = _d0[1];
+ w2_t = _d0[2];
+ w3_t = _d0[3];
+ w4_t = _d1[0];
+ w5_t = _d1[1];
+ w6_t = _d1[2];
+ w7_t = _d1[3];
+ w8_t = _d2[0];
+ w9_t = _d2[1];
+ wa_t = _d2[2];
+ wb_t = _d2[3];
+ wc_t = _d3[0];
+ wd_t = _d3[1];
+ we_t = _d3[2];
+ wf_t = _d3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ // u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+
+ if (MATCHES_NONE_VS ((a+digest[0]-MD5M_A), search[0])) continue;
+
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += digest[0] - MD5M_A;
+ b += digest[1] - MD5M_B;
+ c += digest[2] - MD5M_C;
+ d += digest[3] - MD5M_D;
+
+ COMPARE_S_SIMD (a, d, c, b);
+ }
+}
+
+KERNEL_FQ void m04410_s08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04410_s16 (KERN_ATTR_RULES ())
+{
+}
diff --git a/OpenCL/m04710_a0-optimized.cl b/OpenCL/m04710_a0-optimized.cl
deleted file mode 100644
index 488d15da3..000000000
--- a/OpenCL/m04710_a0-optimized.cl
+++ /dev/null
@@ -1,707 +0,0 @@
-/**
- * Author......: See docs/credits.txt
- * License.....: MIT
- */
-
-#define NEW_SIMD_CODE
-
-#ifdef KERNEL_STATIC
-#include "inc_vendor.h"
-#include "inc_types.h"
-#include "inc_platform.cl"
-#include "inc_common.cl"
-#include "inc_rp_optimized.h"
-#include "inc_rp_optimized.cl"
-#include "inc_simd.cl"
-#include "inc_hash_md5.cl"
-#include "inc_hash_sha1.cl"
-#endif
-
-#if VECT_SIZE == 1
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
-#elif VECT_SIZE == 2
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
-#elif VECT_SIZE == 4
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
-#elif VECT_SIZE == 8
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
-#elif VECT_SIZE == 16
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
-#endif
-
-KERNEL_FQ void m04710_m04 (KERN_ATTR_RULES ())
-{
- /**
- * modifier
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
- const u64 lsz = get_local_size (0);
-
- /**
- * bin2asc table
- */
-
- LOCAL_VK u32 l_bin2asc[256];
-
- for (u32 i = lid; i < 256; i += lsz)
- {
- const u32 i0 = (i >> 0) & 15;
- const u32 i1 = (i >> 4) & 15;
-
- l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
- | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
- }
-
- SYNC_THREADS ();
-
- if (gid >= gid_max) return;
-
- /**
- * base
- */
-
- u32 pw_buf0[4];
- u32 pw_buf1[4];
-
- pw_buf0[0] = pws[gid].i[0];
- pw_buf0[1] = pws[gid].i[1];
- pw_buf0[2] = pws[gid].i[2];
- pw_buf0[3] = pws[gid].i[3];
- pw_buf1[0] = pws[gid].i[4];
- pw_buf1[1] = pws[gid].i[5];
- pw_buf1[2] = pws[gid].i[6];
- pw_buf1[3] = pws[gid].i[7];
-
- const u32 pw_len = pws[gid].pw_len & 63;
-
- /**
- * loop
- */
-
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
- {
- u32x w0[4] = { 0 };
- u32x w1[4] = { 0 };
- u32x w2[4] = { 0 };
- u32x w3[4] = { 0 };
-
- const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
-
- append_0x80_2x4_VV (w0, w1, out_len);
-
- w3[2] = out_len * 8;
- w3[3] = 0;
-
- /**
- * md5
- */
-
- u32x a = MD5M_A;
- u32x b = MD5M_B;
- u32x c = MD5M_C;
- u32x d = MD5M_D;
- u32x e = 0;
-
- MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
-
- MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
-
- u32x t;
-
- MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
-
- MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
-
- a += MD5M_A;
- b += MD5M_B;
- c += MD5M_C;
- d += MD5M_D;
-
- /*
- * sha1
- */
-
- u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
- u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
- u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
- u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
- u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
- u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
- u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
- u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
- u32x w8_t = 0x80000000;
- u32x w9_t = 0;
- u32x wa_t = 0;
- u32x wb_t = 0;
- u32x wc_t = 0;
- u32x wd_t = 0;
- u32x we_t = 0;
- u32x wf_t = 32 * 8;
-
- a = SHA1M_A;
- b = SHA1M_B;
- c = SHA1M_C;
- d = SHA1M_D;
- e = SHA1M_E;
-
- #undef K
- #define K SHA1C00
-
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
-
- #undef K
- #define K SHA1C01
-
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
-
- #undef K
- #define K SHA1C02
-
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
-
- #undef K
- #define K SHA1C03
-
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
-
- COMPARE_M_SIMD (d, e, c, b);
- }
-}
-
-KERNEL_FQ void m04710_m08 (KERN_ATTR_RULES ())
-{
-}
-
-KERNEL_FQ void m04710_m16 (KERN_ATTR_RULES ())
-{
-}
-
-KERNEL_FQ void m04710_s04 (KERN_ATTR_RULES ())
-{
- /**
- * modifier
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
- const u64 lsz = get_local_size (0);
-
- /**
- * bin2asc table
- */
-
- LOCAL_VK u32 l_bin2asc[256];
-
- for (u32 i = lid; i < 256; i += lsz)
- {
- const u32 i0 = (i >> 0) & 15;
- const u32 i1 = (i >> 4) & 15;
-
- l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
- | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
- }
-
- SYNC_THREADS ();
-
- if (gid >= gid_max) return;
-
- /**
- * base
- */
-
- u32 pw_buf0[4];
- u32 pw_buf1[4];
-
- pw_buf0[0] = pws[gid].i[0];
- pw_buf0[1] = pws[gid].i[1];
- pw_buf0[2] = pws[gid].i[2];
- pw_buf0[3] = pws[gid].i[3];
- pw_buf1[0] = pws[gid].i[4];
- pw_buf1[1] = pws[gid].i[5];
- pw_buf1[2] = pws[gid].i[6];
- pw_buf1[3] = pws[gid].i[7];
-
- const u32 pw_len = pws[gid].pw_len & 63;
-
- /**
- * salt
- */
-
- u32 salt_buf0[4];
- u32 salt_buf1[4];
- u32 salt_buf2[4];
- u32 salt_buf3[4];
-
- salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
- salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
- salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
- salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
- salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
- salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
- salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
- salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
- salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
- salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
- salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
- salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
- salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
- salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
- salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
- salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
-
- const u32 salt_len = salt_bufs[salt_pos].salt_len;
-
- /**
- * digest
- */
-
- const u32 search[4] =
- {
- digests_buf[digests_offset].digest_buf[DGST_R0],
- digests_buf[digests_offset].digest_buf[DGST_R1],
- digests_buf[digests_offset].digest_buf[DGST_R2],
- digests_buf[digests_offset].digest_buf[DGST_R3]
- };
-
- /**
- * reverse
- */
-
- const u32 e_rev = hc_rotl32_S (search[1], 2u);
-
- /**
- * loop
- */
-
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
- {
- u32x w0[4] = { 0 };
- u32x w1[4] = { 0 };
- u32x w2[4] = { 0 };
- u32x w3[4] = { 0 };
-
- const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
-
- append_0x80_2x4_VV (w0, w1, out_len);
-
- w3[2] = out_len * 8;
- w3[3] = 0;
-
- /**
- * md5
- */
-
- u32x a = MD5M_A;
- u32x b = MD5M_B;
- u32x c = MD5M_C;
- u32x d = MD5M_D;
- u32x e = 0;
-
- MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
-
- MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
-
- u32x t;
-
- MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
-
- MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
-
- a += MD5M_A;
- b += MD5M_B;
- c += MD5M_C;
- d += MD5M_D;
-
- /*
- * sha1
- */
-
- /**
- * append salt
- */
-
- u32x s0[4];
- u32x s1[4];
- u32x s2[4];
- u32x s3[4];
-
- s0[0] = salt_buf0[0];
- s0[1] = salt_buf0[1];
- s0[2] = salt_buf0[2];
- s0[3] = salt_buf0[3];
- s1[0] = salt_buf1[0];
- s1[1] = salt_buf1[1];
- s1[2] = salt_buf1[2];
- s1[3] = salt_buf1[3];
- s2[0] = salt_buf2[0];
- s2[1] = salt_buf2[1];
- s2[2] = salt_buf2[2];
- s2[3] = salt_buf2[3];
- s3[0] = salt_buf3[0];
- s3[1] = salt_buf3[1];
- s3[2] = salt_buf3[2];
- s3[3] = salt_buf3[3];
-
- switch_buffer_by_offset_le_VV (s0, s1, s2, s3, 32);
-
- const u32x pw_salt_len = out_len + salt_len;
-
- u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
- u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
- u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
- u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
- u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
- u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
- u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
- u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
- u32x w8_t = 0x80000000;
- u32x w9_t = 0;
- u32x wa_t = 0;
- u32x wb_t = 0;
- u32x wc_t = 0;
- u32x wd_t = 0;
- u32x we_t = 0;
- u32x wf_t = 0; //32 * 8;
-
- w0_t |= s0[0];
- w1_t |= s0[1];
- w2_t |= s0[2];
- w3_t |= s0[3];
- w4_t |= s1[0];
- w5_t |= s1[1];
- w6_t |= s1[2];
- w7_t |= s1[3];
-
- we_t = 0;
- wf_t = pw_salt_len * 8;
-
- a = SHA1M_A;
- b = SHA1M_B;
- c = SHA1M_C;
- d = SHA1M_D;
- e = SHA1M_E;
-
- #undef K
- #define K SHA1C00
-
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
-
- #undef K
- #define K SHA1C01
-
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
-
- #undef K
- #define K SHA1C02
-
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
-
- #undef K
- #define K SHA1C03
-
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
-
- if (MATCHES_NONE_VS (e, e_rev)) continue;
-
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
-
- COMPARE_S_SIMD (d, e, c, b);
- }
-}
-
-KERNEL_FQ void m04710_s08 (KERN_ATTR_RULES ())
-{
-}
-
-KERNEL_FQ void m04710_s16 (KERN_ATTR_RULES ())
-{
-}
From 973a972324138b69383e0164f93d0d58ddd39c6a Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Mon, 29 Jul 2019 00:31:51 +0200
Subject: [PATCH 036/113] Added optimized kernels, fix test
---
OpenCL/m19400_a0-optimized.cl | 970 +++++++++++++++++++++++++
OpenCL/m19400_a1-optimized.cl | 1084 ++++++++++++++++++++++++++++
OpenCL/m19400_a3-optimized.cl | 1242 +++++++++++++++++++++++++++++++++
tools/test_modules/m19400.pm | 2 +-
4 files changed, 3297 insertions(+), 1 deletion(-)
create mode 100644 OpenCL/m19400_a0-optimized.cl
create mode 100644 OpenCL/m19400_a1-optimized.cl
create mode 100644 OpenCL/m19400_a3-optimized.cl
diff --git a/OpenCL/m19400_a0-optimized.cl b/OpenCL/m19400_a0-optimized.cl
new file mode 100644
index 000000000..de343f7fa
--- /dev/null
+++ b/OpenCL/m19400_a0-optimized.cl
@@ -0,0 +1,970 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+#define SHA256_STEP_REV(a,b,c,d,e,f,g,h) \
+{ \
+ u32 t2 = SHA256_S2_S(b) + SHA256_F0o(b,c,d); \
+ u32 t1 = a - t2; \
+ a = b; \
+ b = c; \
+ c = d; \
+ d = e - t1; \
+ e = f; \
+ f = g; \
+ g = h; \
+ h = 0; \
+}
+
+KERNEL_FQ void m19400_m04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ /**
+ * sha256(pass)
+ */
+
+ u32x w0_t = hc_swap32 (w0[0]);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = out_len * 8;
+
+ u32x a = SHA256M_A;
+ u32x b = SHA256M_B;
+ u32x c = SHA256M_C;
+ u32x d = SHA256M_D;
+ u32x e = SHA256M_E;
+ u32x f = SHA256M_F;
+ u32x g = SHA256M_G;
+ u32x h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ a += SHA256M_A;
+ b += SHA256M_B;
+ c += SHA256M_C;
+ d += SHA256M_D;
+ e += SHA256M_E;
+ f += SHA256M_F;
+ g += SHA256M_G;
+ h += SHA256M_H;
+
+ // final sha256
+
+ // sha256_update_64, len 64, pos 0
+
+ w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
+ w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+ w9_t = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
+ wa_t = uint_to_hex_lower8_le ((f >> 16) & 255) << 0 | uint_to_hex_lower8_le ((f >> 24) & 255) << 16;
+ wb_t = uint_to_hex_lower8_le ((f >> 0) & 255) << 0 | uint_to_hex_lower8_le ((f >> 8) & 255) << 16;
+ wc_t = uint_to_hex_lower8_le ((g >> 16) & 255) << 0 | uint_to_hex_lower8_le ((g >> 24) & 255) << 16;
+ wd_t = uint_to_hex_lower8_le ((g >> 0) & 255) << 0 | uint_to_hex_lower8_le ((g >> 8) & 255) << 16;
+ we_t = uint_to_hex_lower8_le ((h >> 16) & 255) << 0 | uint_to_hex_lower8_le ((h >> 24) & 255) << 16;
+ wf_t = uint_to_hex_lower8_le ((h >> 0) & 255) << 0 | uint_to_hex_lower8_le ((h >> 8) & 255) << 16;
+
+ // sha256 transform
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ u32x digest[8];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+ f = digest[5];
+ g = digest[6];
+ h = digest[7];
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ // add salt
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = 0;
+ s1[1] = 0;
+ s1[2] = 0;
+ s1[3] = 0;
+ s2[0] = 0;
+ s2[1] = 0;
+ s2[2] = 0;
+ s2[3] = 0;
+ s3[0] = 0;
+ s3[1] = 0;
+ s3[2] = 0;
+ s3[3] = 0;
+
+ // ctx_len 80, pos 16
+
+ append_0x80_4x4 (s0, s1, s2, s3, 16 ^ 3);
+
+ s3[2] = 0;
+ s3[3] = (64 + 16) * 8;
+
+ w0_t = s0[0];
+ w1_t = s0[1];
+ w2_t = s0[2];
+ w3_t = s0[3];
+ w4_t = s1[0];
+ w5_t = s1[1];
+ w6_t = s1[2];
+ w7_t = s1[3];
+ w8_t = s2[0];
+ w9_t = s2[1];
+ wa_t = s2[2];
+ wb_t = s2[3];
+ wc_t = s3[0];
+ wd_t = s3[1];
+ we_t = s3[2];
+ wf_t = s3[3];
+
+ // sha256 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+ f = digest[5];
+ g = digest[6];
+ h = digest[7];
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+// a += digest[0] - SHA256M_A;
+// b += digest[1] - SHA256M_B;
+ c += digest[2] - SHA256M_C;
+ d += digest[3] - SHA256M_D;
+// e += digest[4] - SHA256M_E;
+// f += digest[5] - SHA256M_F;
+ g += digest[6] - SHA256M_G;
+ h += digest[7] - SHA256M_H;
+
+ COMPARE_M_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m19400_m08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m19400_m16 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m19400_s04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ /**
+ * sha256(pass)
+ */
+
+ u32x w0_t = hc_swap32 (w0[0]);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = out_len * 8;
+
+ u32x a = SHA256M_A;
+ u32x b = SHA256M_B;
+ u32x c = SHA256M_C;
+ u32x d = SHA256M_D;
+ u32x e = SHA256M_E;
+ u32x f = SHA256M_F;
+ u32x g = SHA256M_G;
+ u32x h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ a += SHA256M_A;
+ b += SHA256M_B;
+ c += SHA256M_C;
+ d += SHA256M_D;
+ e += SHA256M_E;
+ f += SHA256M_F;
+ g += SHA256M_G;
+ h += SHA256M_H;
+
+ // final sha256
+
+ // sha256_update_64, len 64, pos 0
+
+ w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
+ w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+ w9_t = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
+ wa_t = uint_to_hex_lower8_le ((f >> 16) & 255) << 0 | uint_to_hex_lower8_le ((f >> 24) & 255) << 16;
+ wb_t = uint_to_hex_lower8_le ((f >> 0) & 255) << 0 | uint_to_hex_lower8_le ((f >> 8) & 255) << 16;
+ wc_t = uint_to_hex_lower8_le ((g >> 16) & 255) << 0 | uint_to_hex_lower8_le ((g >> 24) & 255) << 16;
+ wd_t = uint_to_hex_lower8_le ((g >> 0) & 255) << 0 | uint_to_hex_lower8_le ((g >> 8) & 255) << 16;
+ we_t = uint_to_hex_lower8_le ((h >> 16) & 255) << 0 | uint_to_hex_lower8_le ((h >> 24) & 255) << 16;
+ wf_t = uint_to_hex_lower8_le ((h >> 0) & 255) << 0 | uint_to_hex_lower8_le ((h >> 8) & 255) << 16;
+
+ // sha256 transform
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ u32x digest[8];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ // add salt
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = 0;
+ s1[1] = 0;
+ s1[2] = 0;
+ s1[3] = 0;
+ s2[0] = 0;
+ s2[1] = 0;
+ s2[2] = 0;
+ s2[3] = 0;
+ s3[0] = 0;
+ s3[1] = 0;
+ s3[2] = 0;
+ s3[3] = 0;
+
+ // ctx_len 80, pos 16
+
+ append_0x80_4x4 (s0, s1, s2, s3, 16 ^ 3);
+
+ s3[2] = 0;
+ s3[3] = (64 + 16) * 8;
+
+ w0_t = s0[0];
+ w1_t = s0[1];
+ w2_t = s0[2];
+ w3_t = s0[3];
+ w4_t = s1[0];
+ w5_t = s1[1];
+ w6_t = s1[2];
+ w7_t = s1[3];
+ w8_t = s2[0];
+ w9_t = s2[1];
+ wa_t = s2[2];
+ wb_t = s2[3];
+ wc_t = s3[0];
+ wd_t = s3[1];
+ we_t = s3[2];
+ wf_t = s3[3];
+
+ // sha256 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+ f = digest[5];
+ g = digest[6];
+ h = digest[7];
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+
+ // if (MATCHES_NONE_VS (h+digest[7]-SHA256M_H, d_rev)) continue;
+
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+
+ if (MATCHES_NONE_VS (h+digest[7]-SHA256M_H, search[1])) continue;
+
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+// a += digest[0] - SHA256M_A;
+// b += digest[1] - SHA256M_B;
+ c += digest[2] - SHA256M_C;
+ d += digest[3] - SHA256M_D;
+// e += digest[4] - SHA256M_E;
+// f += digest[5] - SHA256M_F;
+ g += digest[6] - SHA256M_G;
+ h += digest[7] - SHA256M_H;
+
+ COMPARE_S_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m19400_s08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m19400_s16 (KERN_ATTR_RULES ())
+{
+}
diff --git a/OpenCL/m19400_a1-optimized.cl b/OpenCL/m19400_a1-optimized.cl
new file mode 100644
index 000000000..679d8479f
--- /dev/null
+++ b/OpenCL/m19400_a1-optimized.cl
@@ -0,0 +1,1084 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+#define SHA256_STEP_REV(a,b,c,d,e,f,g,h) \
+{ \
+ u32 t2 = SHA256_S2_S(b) + SHA256_F0o(b,c,d); \
+ u32 t1 = a - t2; \
+ a = b; \
+ b = c; \
+ c = d; \
+ d = e - t1; \
+ e = f; \
+ f = g; \
+ g = h; \
+ h = 0; \
+}
+
+KERNEL_FQ void m19400_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = wordl3[2] | wordr3[2];
+ w3[3] = wordl3[3] | wordr3[3];
+
+ /**
+ * sha256(pass)
+ */
+
+ u32x w0_t = hc_swap32 (w0[0]);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = pw_len * 8;
+
+ u32x a = SHA256M_A;
+ u32x b = SHA256M_B;
+ u32x c = SHA256M_C;
+ u32x d = SHA256M_D;
+ u32x e = SHA256M_E;
+ u32x f = SHA256M_F;
+ u32x g = SHA256M_G;
+ u32x h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ a += SHA256M_A;
+ b += SHA256M_B;
+ c += SHA256M_C;
+ d += SHA256M_D;
+ e += SHA256M_E;
+ f += SHA256M_F;
+ g += SHA256M_G;
+ h += SHA256M_H;
+
+ // final sha256
+
+ // sha256_update_64, len 64, pos 0
+
+ w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
+ w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+ w9_t = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
+ wa_t = uint_to_hex_lower8_le ((f >> 16) & 255) << 0 | uint_to_hex_lower8_le ((f >> 24) & 255) << 16;
+ wb_t = uint_to_hex_lower8_le ((f >> 0) & 255) << 0 | uint_to_hex_lower8_le ((f >> 8) & 255) << 16;
+ wc_t = uint_to_hex_lower8_le ((g >> 16) & 255) << 0 | uint_to_hex_lower8_le ((g >> 24) & 255) << 16;
+ wd_t = uint_to_hex_lower8_le ((g >> 0) & 255) << 0 | uint_to_hex_lower8_le ((g >> 8) & 255) << 16;
+ we_t = uint_to_hex_lower8_le ((h >> 16) & 255) << 0 | uint_to_hex_lower8_le ((h >> 24) & 255) << 16;
+ wf_t = uint_to_hex_lower8_le ((h >> 0) & 255) << 0 | uint_to_hex_lower8_le ((h >> 8) & 255) << 16;
+
+ // sha256 transform
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ u32x digest[8];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+ f = digest[5];
+ g = digest[6];
+ h = digest[7];
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ // add salt
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = 0;
+ s1[1] = 0;
+ s1[2] = 0;
+ s1[3] = 0;
+ s2[0] = 0;
+ s2[1] = 0;
+ s2[2] = 0;
+ s2[3] = 0;
+ s3[0] = 0;
+ s3[1] = 0;
+ s3[2] = 0;
+ s3[3] = 0;
+
+ // ctx_len 80, pos 16
+
+ append_0x80_4x4 (s0, s1, s2, s3, 16 ^ 3);
+
+ s3[2] = 0;
+ s3[3] = (64 + 16) * 8;
+
+ w0_t = s0[0];
+ w1_t = s0[1];
+ w2_t = s0[2];
+ w3_t = s0[3];
+ w4_t = s1[0];
+ w5_t = s1[1];
+ w6_t = s1[2];
+ w7_t = s1[3];
+ w8_t = s2[0];
+ w9_t = s2[1];
+ wa_t = s2[2];
+ wb_t = s2[3];
+ wc_t = s3[0];
+ wd_t = s3[1];
+ we_t = s3[2];
+ wf_t = s3[3];
+
+ // sha256 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+ f = digest[5];
+ g = digest[6];
+ h = digest[7];
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+// a += digest[0] - SHA256M_A;
+// b += digest[1] - SHA256M_B;
+ c += digest[2] - SHA256M_C;
+ d += digest[3] - SHA256M_D;
+// e += digest[4] - SHA256M_E;
+// f += digest[5] - SHA256M_F;
+ g += digest[6] - SHA256M_G;
+ h += digest[7] - SHA256M_H;
+
+ COMPARE_M_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m19400_m08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m19400_m16 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m19400_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = wordl3[2] | wordr3[2];
+ w3[3] = wordl3[3] | wordr3[3];
+
+ /**
+ * sha256(pass)
+ */
+
+ u32x w0_t = hc_swap32 (w0[0]);
+ u32x w1_t = hc_swap32 (w0[1]);
+ u32x w2_t = hc_swap32 (w0[2]);
+ u32x w3_t = hc_swap32 (w0[3]);
+ u32x w4_t = hc_swap32 (w1[0]);
+ u32x w5_t = hc_swap32 (w1[1]);
+ u32x w6_t = hc_swap32 (w1[2]);
+ u32x w7_t = hc_swap32 (w1[3]);
+ u32x w8_t = hc_swap32 (w2[0]);
+ u32x w9_t = hc_swap32 (w2[1]);
+ u32x wa_t = hc_swap32 (w2[2]);
+ u32x wb_t = hc_swap32 (w2[3]);
+ u32x wc_t = hc_swap32 (w3[0]);
+ u32x wd_t = hc_swap32 (w3[1]);
+ u32x we_t = 0;
+ u32x wf_t = pw_len * 8;
+
+ u32x a = SHA256M_A;
+ u32x b = SHA256M_B;
+ u32x c = SHA256M_C;
+ u32x d = SHA256M_D;
+ u32x e = SHA256M_E;
+ u32x f = SHA256M_F;
+ u32x g = SHA256M_G;
+ u32x h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ a += SHA256M_A;
+ b += SHA256M_B;
+ c += SHA256M_C;
+ d += SHA256M_D;
+ e += SHA256M_E;
+ f += SHA256M_F;
+ g += SHA256M_G;
+ h += SHA256M_H;
+
+ // final sha256
+
+ // sha256_update_64, len 64, pos 0
+
+ w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
+ w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+ w9_t = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
+ wa_t = uint_to_hex_lower8_le ((f >> 16) & 255) << 0 | uint_to_hex_lower8_le ((f >> 24) & 255) << 16;
+ wb_t = uint_to_hex_lower8_le ((f >> 0) & 255) << 0 | uint_to_hex_lower8_le ((f >> 8) & 255) << 16;
+ wc_t = uint_to_hex_lower8_le ((g >> 16) & 255) << 0 | uint_to_hex_lower8_le ((g >> 24) & 255) << 16;
+ wd_t = uint_to_hex_lower8_le ((g >> 0) & 255) << 0 | uint_to_hex_lower8_le ((g >> 8) & 255) << 16;
+ we_t = uint_to_hex_lower8_le ((h >> 16) & 255) << 0 | uint_to_hex_lower8_le ((h >> 24) & 255) << 16;
+ wf_t = uint_to_hex_lower8_le ((h >> 0) & 255) << 0 | uint_to_hex_lower8_le ((h >> 8) & 255) << 16;
+
+ // sha256 transform
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ u32x digest[8];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ // add salt
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = 0;
+ s1[1] = 0;
+ s1[2] = 0;
+ s1[3] = 0;
+ s2[0] = 0;
+ s2[1] = 0;
+ s2[2] = 0;
+ s2[3] = 0;
+ s3[0] = 0;
+ s3[1] = 0;
+ s3[2] = 0;
+ s3[3] = 0;
+
+ // ctx_len 80, pos 16
+
+ append_0x80_4x4 (s0, s1, s2, s3, 16 ^ 3);
+
+ s3[2] = 0;
+ s3[3] = (64 + 16) * 8;
+
+ w0_t = s0[0];
+ w1_t = s0[1];
+ w2_t = s0[2];
+ w3_t = s0[3];
+ w4_t = s1[0];
+ w5_t = s1[1];
+ w6_t = s1[2];
+ w7_t = s1[3];
+ w8_t = s2[0];
+ w9_t = s2[1];
+ wa_t = s2[2];
+ wb_t = s2[3];
+ wc_t = s3[0];
+ wd_t = s3[1];
+ we_t = s3[2];
+ wf_t = s3[3];
+
+ // sha256 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+ f = digest[5];
+ g = digest[6];
+ h = digest[7];
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+
+ // if (MATCHES_NONE_VS (h+digest[7]-SHA256M_H, d_rev)) continue;
+
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+
+ if (MATCHES_NONE_VS (h+digest[7]-SHA256M_H, search[1])) continue;
+
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+// a += digest[0] - SHA256M_A;
+// b += digest[1] - SHA256M_B;
+ c += digest[2] - SHA256M_C;
+ d += digest[3] - SHA256M_D;
+// e += digest[4] - SHA256M_E;
+// f += digest[5] - SHA256M_F;
+ g += digest[6] - SHA256M_G;
+ h += digest[7] - SHA256M_H;
+
+ COMPARE_S_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m19400_s08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m19400_s16 (KERN_ATTR_BASIC ())
+{
+}
diff --git a/OpenCL/m19400_a3-optimized.cl b/OpenCL/m19400_a3-optimized.cl
new file mode 100644
index 000000000..e6892950b
--- /dev/null
+++ b/OpenCL/m19400_a3-optimized.cl
@@ -0,0 +1,1242 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha256.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+#define SHA256_STEP_REV(a,b,c,d,e,f,g,h) \
+{ \
+ u32 t2 = SHA256_S2_S(b) + SHA256_F0o(b,c,d); \
+ u32 t1 = a - t2; \
+ a = b; \
+ b = c; \
+ c = d; \
+ d = e - t1; \
+ e = f; \
+ f = g; \
+ g = h; \
+ h = 0; \
+}
+
+DECLSPEC void m19400m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ /**
+ * sha256(pass)
+ */
+
+ u32x w0_t = w0;
+ u32x w1_t = w[ 1];
+ u32x w2_t = w[ 2];
+ u32x w3_t = w[ 3];
+ u32x w4_t = w[ 4];
+ u32x w5_t = w[ 5];
+ u32x w6_t = w[ 6];
+ u32x w7_t = w[ 7];
+ u32x w8_t = w[ 8];
+ u32x w9_t = w[ 9];
+ u32x wa_t = w[10];
+ u32x wb_t = w[11];
+ u32x wc_t = w[12];
+ u32x wd_t = w[13];
+ u32x we_t = w[14];
+ u32x wf_t = w[15];
+
+ u32x a = SHA256M_A;
+ u32x b = SHA256M_B;
+ u32x c = SHA256M_C;
+ u32x d = SHA256M_D;
+ u32x e = SHA256M_E;
+ u32x f = SHA256M_F;
+ u32x g = SHA256M_G;
+ u32x h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ a += SHA256M_A;
+ b += SHA256M_B;
+ c += SHA256M_C;
+ d += SHA256M_D;
+ e += SHA256M_E;
+ f += SHA256M_F;
+ g += SHA256M_G;
+ h += SHA256M_H;
+
+ // final sha256
+
+ // sha256_update_64, len 64, pos 0
+
+ w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
+ w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+ w9_t = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
+ wa_t = uint_to_hex_lower8_le ((f >> 16) & 255) << 0 | uint_to_hex_lower8_le ((f >> 24) & 255) << 16;
+ wb_t = uint_to_hex_lower8_le ((f >> 0) & 255) << 0 | uint_to_hex_lower8_le ((f >> 8) & 255) << 16;
+ wc_t = uint_to_hex_lower8_le ((g >> 16) & 255) << 0 | uint_to_hex_lower8_le ((g >> 24) & 255) << 16;
+ wd_t = uint_to_hex_lower8_le ((g >> 0) & 255) << 0 | uint_to_hex_lower8_le ((g >> 8) & 255) << 16;
+ we_t = uint_to_hex_lower8_le ((h >> 16) & 255) << 0 | uint_to_hex_lower8_le ((h >> 24) & 255) << 16;
+ wf_t = uint_to_hex_lower8_le ((h >> 0) & 255) << 0 | uint_to_hex_lower8_le ((h >> 8) & 255) << 16;
+
+ // sha256 transform
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ u32x digest[8];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+ f = digest[5];
+ g = digest[6];
+ h = digest[7];
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ // add salt
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = 0;
+ s1[1] = 0;
+ s1[2] = 0;
+ s1[3] = 0;
+ s2[0] = 0;
+ s2[1] = 0;
+ s2[2] = 0;
+ s2[3] = 0;
+ s3[0] = 0;
+ s3[1] = 0;
+ s3[2] = 0;
+ s3[3] = 0;
+
+ // ctx_len 80, pos 16
+
+ append_0x80_4x4 (s0, s1, s2, s3, 16 ^ 3);
+
+ s3[2] = 0;
+ s3[3] = (64 + 16) * 8;
+
+ w0_t = s0[0];
+ w1_t = s0[1];
+ w2_t = s0[2];
+ w3_t = s0[3];
+ w4_t = s1[0];
+ w5_t = s1[1];
+ w6_t = s1[2];
+ w7_t = s1[3];
+ w8_t = s2[0];
+ w9_t = s2[1];
+ wa_t = s2[2];
+ wb_t = s2[3];
+ wc_t = s3[0];
+ wd_t = s3[1];
+ we_t = s3[2];
+ wf_t = s3[3];
+
+ // sha256 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+ f = digest[5];
+ g = digest[6];
+ h = digest[7];
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+// a += digest[0] - SHA256M_A;
+// b += digest[1] - SHA256M_B;
+ c += digest[2] - SHA256M_C;
+ d += digest[3] - SHA256M_D;
+// e += digest[4] - SHA256M_E;
+// f += digest[5] - SHA256M_F;
+ g += digest[6] - SHA256M_G;
+ h += digest[7] - SHA256M_H;
+
+ COMPARE_M_SIMD (d, h, c, g);
+ }
+}
+
+DECLSPEC void m19400s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
+
+ const u32x w0 = w0l | w0r;
+
+ /**
+ * sha256(pass)
+ */
+
+ u32x w0_t = w0;
+ u32x w1_t = w[ 1];
+ u32x w2_t = w[ 2];
+ u32x w3_t = w[ 3];
+ u32x w4_t = w[ 4];
+ u32x w5_t = w[ 5];
+ u32x w6_t = w[ 6];
+ u32x w7_t = w[ 7];
+ u32x w8_t = w[ 8];
+ u32x w9_t = w[ 9];
+ u32x wa_t = w[10];
+ u32x wb_t = w[11];
+ u32x wc_t = w[12];
+ u32x wd_t = w[13];
+ u32x we_t = w[14];
+ u32x wf_t = w[15];
+
+ u32x a = SHA256M_A;
+ u32x b = SHA256M_B;
+ u32x c = SHA256M_C;
+ u32x d = SHA256M_D;
+ u32x e = SHA256M_E;
+ u32x f = SHA256M_F;
+ u32x g = SHA256M_G;
+ u32x h = SHA256M_H;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ a += SHA256M_A;
+ b += SHA256M_B;
+ c += SHA256M_C;
+ d += SHA256M_D;
+ e += SHA256M_E;
+ f += SHA256M_F;
+ g += SHA256M_G;
+ h += SHA256M_H;
+
+ // final sha256
+
+ // sha256_update_64, len 64, pos 0
+
+ w0_t = uint_to_hex_lower8_le ((a >> 16) & 255) << 0 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 0) & 255) << 0 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 16) & 255) << 0 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 0) & 255) << 0 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 16) & 255) << 0 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 0) & 255) << 0 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 16) & 255) << 0 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 0) & 255) << 0 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
+ w8_t = uint_to_hex_lower8_le ((e >> 16) & 255) << 0 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
+ w9_t = uint_to_hex_lower8_le ((e >> 0) & 255) << 0 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
+ wa_t = uint_to_hex_lower8_le ((f >> 16) & 255) << 0 | uint_to_hex_lower8_le ((f >> 24) & 255) << 16;
+ wb_t = uint_to_hex_lower8_le ((f >> 0) & 255) << 0 | uint_to_hex_lower8_le ((f >> 8) & 255) << 16;
+ wc_t = uint_to_hex_lower8_le ((g >> 16) & 255) << 0 | uint_to_hex_lower8_le ((g >> 24) & 255) << 16;
+ wd_t = uint_to_hex_lower8_le ((g >> 0) & 255) << 0 | uint_to_hex_lower8_le ((g >> 8) & 255) << 16;
+ we_t = uint_to_hex_lower8_le ((h >> 16) & 255) << 0 | uint_to_hex_lower8_le ((h >> 24) & 255) << 16;
+ wf_t = uint_to_hex_lower8_le ((h >> 0) & 255) << 0 | uint_to_hex_lower8_le ((h >> 8) & 255) << 16;
+
+ // sha256 transform
+
+ a = SHA256M_A;
+ b = SHA256M_B;
+ c = SHA256M_C;
+ d = SHA256M_D;
+ e = SHA256M_E;
+ f = SHA256M_F;
+ g = SHA256M_G;
+ h = SHA256M_H;
+
+ u32x digest[8];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+ f = digest[5];
+ g = digest[6];
+ h = digest[7];
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ // add salt
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = 0;
+ s1[1] = 0;
+ s1[2] = 0;
+ s1[3] = 0;
+ s2[0] = 0;
+ s2[1] = 0;
+ s2[2] = 0;
+ s2[3] = 0;
+ s3[0] = 0;
+ s3[1] = 0;
+ s3[2] = 0;
+ s3[3] = 0;
+
+ // ctx_len 80, pos 16
+
+ append_0x80_4x4 (s0, s1, s2, s3, 16 ^ 3);
+
+ s3[2] = 0;
+ s3[3] = (64 + 16) * 8;
+
+ w0_t = s0[0];
+ w1_t = s0[1];
+ w2_t = s0[2];
+ w3_t = s0[3];
+ w4_t = s1[0];
+ w5_t = s1[1];
+ w6_t = s1[2];
+ w7_t = s1[3];
+ w8_t = s2[0];
+ w9_t = s2[1];
+ wa_t = s2[2];
+ wb_t = s2[3];
+ wc_t = s3[0];
+ wd_t = s3[1];
+ we_t = s3[2];
+ wf_t = s3[3];
+
+ // sha256 transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+ f = digest[5];
+ g = digest[6];
+ h = digest[7];
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+
+ if (MATCHES_NONE_VS (h+digest[7]-SHA256M_H, search[1])) continue;
+
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+// a += digest[0] - SHA256M_A;
+// b += digest[1] - SHA256M_B;
+ c += digest[2] - SHA256M_C;
+ d += digest[3] - SHA256M_D;
+// e += digest[4] - SHA256M_E;
+// f += digest[5] - SHA256M_F;
+ g += digest[6] - SHA256M_G;
+ h += digest[7] - SHA256M_H;
+
+ COMPARE_S_SIMD (d, h, c, g);
+ }
+}
+
+KERNEL_FQ void m19400_m04 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = 0;
+ w[ 5] = 0;
+ w[ 6] = 0;
+ w[ 7] = 0;
+ w[ 8] = 0;
+ w[ 9] = 0;
+ w[10] = 0;
+ w[11] = 0;
+ w[12] = 0;
+ w[13] = 0;
+ w[14] = 0;
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m19400m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m19400_m08 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = pws[gid].i[ 4];
+ w[ 5] = pws[gid].i[ 5];
+ w[ 6] = pws[gid].i[ 6];
+ w[ 7] = pws[gid].i[ 7];
+ w[ 8] = 0;
+ w[ 9] = 0;
+ w[10] = 0;
+ w[11] = 0;
+ w[12] = 0;
+ w[13] = 0;
+ w[14] = 0;
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m19400m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m19400_m16 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = pws[gid].i[ 4];
+ w[ 5] = pws[gid].i[ 5];
+ w[ 6] = pws[gid].i[ 6];
+ w[ 7] = pws[gid].i[ 7];
+ w[ 8] = pws[gid].i[ 8];
+ w[ 9] = pws[gid].i[ 9];
+ w[10] = pws[gid].i[10];
+ w[11] = pws[gid].i[11];
+ w[12] = pws[gid].i[12];
+ w[13] = pws[gid].i[13];
+ w[14] = pws[gid].i[14];
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m19400m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m19400_s04 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = 0;
+ w[ 5] = 0;
+ w[ 6] = 0;
+ w[ 7] = 0;
+ w[ 8] = 0;
+ w[ 9] = 0;
+ w[10] = 0;
+ w[11] = 0;
+ w[12] = 0;
+ w[13] = 0;
+ w[14] = 0;
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m19400s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m19400_s08 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = pws[gid].i[ 4];
+ w[ 5] = pws[gid].i[ 5];
+ w[ 6] = pws[gid].i[ 6];
+ w[ 7] = pws[gid].i[ 7];
+ w[ 8] = 0;
+ w[ 9] = 0;
+ w[10] = 0;
+ w[11] = 0;
+ w[12] = 0;
+ w[13] = 0;
+ w[14] = 0;
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m19400s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m19400_s16 (KERN_ATTR_VECTOR ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w[16];
+
+ w[ 0] = pws[gid].i[ 0];
+ w[ 1] = pws[gid].i[ 1];
+ w[ 2] = pws[gid].i[ 2];
+ w[ 3] = pws[gid].i[ 3];
+ w[ 4] = pws[gid].i[ 4];
+ w[ 5] = pws[gid].i[ 5];
+ w[ 6] = pws[gid].i[ 6];
+ w[ 7] = pws[gid].i[ 7];
+ w[ 8] = pws[gid].i[ 8];
+ w[ 9] = pws[gid].i[ 9];
+ w[10] = pws[gid].i[10];
+ w[11] = pws[gid].i[11];
+ w[12] = pws[gid].i[12];
+ w[13] = pws[gid].i[13];
+ w[14] = pws[gid].i[14];
+ w[15] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m19400s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
diff --git a/tools/test_modules/m19400.pm b/tools/test_modules/m19400.pm
index f2fddb511..292604cc0 100644
--- a/tools/test_modules/m19400.pm
+++ b/tools/test_modules/m19400.pm
@@ -10,7 +10,7 @@ use warnings;
use Digest::SHA qw (sha256_hex);
-sub module_constraints { [[1, 32], [16, 16], [-1, -1], [-1, -1], [-1, -1]] }
+sub module_constraints { [[1, 31], [16, 16], [-1, -1], [-1, -1], [-1, -1]] }
sub module_generate_hash
{
From 85b16ef844bc80816441de976b0826e1b59713d5 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Mon, 29 Jul 2019 14:29:43 +0200
Subject: [PATCH 037/113] do not call mp_css_utf16le_expand() in case this is a
slow_candidate session
---
src/interface.c | 2 +-
src/mpsp.c | 15 +++++++++------
2 files changed, 10 insertions(+), 7 deletions(-)
diff --git a/src/interface.c b/src/interface.c
index c908d9c0c..442076317 100644
--- a/src/interface.c
+++ b/src/interface.c
@@ -353,7 +353,7 @@ int hashconfig_init (hashcat_ctx_t *hashcat_ctx)
{
if (user_options->quiet == false) event_log_warning (hashcat_ctx, "%s: Optimized OpenCL kernel requested but not needed - falling back to pure OpenCL kernel", source_file);
}
- else if (user_options->slow_candidates == false)
+ else
{
hashconfig->opti_type |= OPTI_TYPE_OPTIMIZED_KERNEL;
}
diff --git a/src/mpsp.c b/src/mpsp.c
index 0fce4d5fb..2ebf72d72 100644
--- a/src/mpsp.c
+++ b/src/mpsp.c
@@ -1297,13 +1297,16 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
return -1;
}
- if (hashconfig->opts_type & OPTS_TYPE_PT_UTF16LE)
+ if (user_options->slow_candidates == false)
{
- if (mp_css_utf16le_expand (hashcat_ctx) == -1) return -1;
- }
- else if (hashconfig->opts_type & OPTS_TYPE_PT_UTF16BE)
- {
- if (mp_css_utf16be_expand (hashcat_ctx) == -1) return -1;
+ if (hashconfig->opts_type & OPTS_TYPE_PT_UTF16LE)
+ {
+ if (mp_css_utf16le_expand (hashcat_ctx) == -1) return -1;
+ }
+ else if (hashconfig->opts_type & OPTS_TYPE_PT_UTF16BE)
+ {
+ if (mp_css_utf16be_expand (hashcat_ctx) == -1) return -1;
+ }
}
u32 css_cnt_orig = mask_ctx->css_cnt;
From e76c3de86a063b9ca46bf521c42caac571ae5b10 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Mon, 29 Jul 2019 16:11:50 +0200
Subject: [PATCH 038/113] Fix invalid password truncation in -a 1 mode
---
src/outfile.c | 36 +++++++++++++++++++++++++++++-------
1 file changed, 29 insertions(+), 7 deletions(-)
diff --git a/src/outfile.c b/src/outfile.c
index ecb5a7d36..8dc949b50 100644
--- a/src/outfile.c
+++ b/src/outfile.c
@@ -18,12 +18,13 @@
int build_plain (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param, plain_t *plain, u32 *plain_buf, int *out_len)
{
- const combinator_ctx_t *combinator_ctx = hashcat_ctx->combinator_ctx;
- const hashconfig_t *hashconfig = hashcat_ctx->hashconfig;
- const hashes_t *hashes = hashcat_ctx->hashes;
- const mask_ctx_t *mask_ctx = hashcat_ctx->mask_ctx;
- const straight_ctx_t *straight_ctx = hashcat_ctx->straight_ctx;
- const user_options_t *user_options = hashcat_ctx->user_options;
+ const combinator_ctx_t *combinator_ctx = hashcat_ctx->combinator_ctx;
+ const hashconfig_t *hashconfig = hashcat_ctx->hashconfig;
+ const hashes_t *hashes = hashcat_ctx->hashes;
+ const mask_ctx_t *mask_ctx = hashcat_ctx->mask_ctx;
+ const straight_ctx_t *straight_ctx = hashcat_ctx->straight_ctx;
+ const user_options_t *user_options = hashcat_ctx->user_options;
+ const user_options_extra_t *user_options_extra = hashcat_ctx->user_options_extra;
const u64 gidvid = plain->gidvid;
const u32 il_pos = plain->il_pos;
@@ -234,7 +235,28 @@ int build_plain (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param, pl
}
}
- const int pw_max = (const int) hashconfig->pw_max;
+ int pw_max = (const int) hashconfig->pw_max;
+
+ // pw_max is per pw_t element but in combinator we have two pw_t elements.
+ // therefore we can support up to 64 in combinator in optimized mode (but limited by general hash limit 55)
+ // or full 512 in pure mode (but limited by hashcat buffer size limit 256).
+ // some algorithms do not support general default pw_max = 31,
+ // therefore we need to use pw_max as a base and not hardcode it.
+
+ if (plain_len > pw_max)
+ {
+ if (user_options_extra->attack_kern == ATTACK_KERN_COMBI)
+ {
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ pw_max = MIN ((pw_max * 2), 55);
+ }
+ else
+ {
+ pw_max = MIN ((pw_max * 2), 256);
+ }
+ }
+ }
if (plain_len > pw_max) plain_len = MIN (plain_len, pw_max);
From c1d15d613b833c3134a5b52cf7a92bbdde374a7b Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Mon, 29 Jul 2019 17:16:53 +0200
Subject: [PATCH 039/113] switch hash-mode from 19400 to 20700
---
...a0-optimized.cl => m20700_a0-optimized.cl} | 12 ++++----
.../{m19400_a0-pure.cl => m20700_a0-pure.cl} | 4 +--
...a1-optimized.cl => m20700_a1-optimized.cl} | 12 ++++----
.../{m19400_a1-pure.cl => m20700_a1-pure.cl} | 4 +--
...a3-optimized.cl => m20700_a3-optimized.cl} | 28 +++++++++----------
.../{m19400_a3-pure.cl => m20700_a3-pure.cl} | 4 +--
.../{module_19400.c => module_20700.c} | 2 +-
tools/test_modules/{m19400.pm => m20700.pm} | 0
8 files changed, 33 insertions(+), 33 deletions(-)
rename OpenCL/{m19400_a0-optimized.cl => m20700_a0-optimized.cl} (99%)
rename OpenCL/{m19400_a0-pure.cl => m20700_a0-pure.cl} (98%)
rename OpenCL/{m19400_a1-optimized.cl => m20700_a1-optimized.cl} (99%)
rename OpenCL/{m19400_a1-pure.cl => m20700_a1-pure.cl} (98%)
rename OpenCL/{m19400_a3-optimized.cl => m20700_a3-optimized.cl} (98%)
rename OpenCL/{m19400_a3-pure.cl => m20700_a3-pure.cl} (98%)
rename src/modules/{module_19400.c => module_20700.c} (99%)
rename tools/test_modules/{m19400.pm => m20700.pm} (100%)
diff --git a/OpenCL/m19400_a0-optimized.cl b/OpenCL/m20700_a0-optimized.cl
similarity index 99%
rename from OpenCL/m19400_a0-optimized.cl
rename to OpenCL/m20700_a0-optimized.cl
index de343f7fa..c4d263fb2 100644
--- a/OpenCL/m19400_a0-optimized.cl
+++ b/OpenCL/m20700_a0-optimized.cl
@@ -42,7 +42,7 @@
h = 0; \
}
-KERNEL_FQ void m19400_m04 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20700_m04 (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -493,15 +493,15 @@ KERNEL_FQ void m19400_m04 (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m19400_m08 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20700_m08 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m19400_m16 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20700_m16 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m19400_s04 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20700_s04 (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -961,10 +961,10 @@ KERNEL_FQ void m19400_s04 (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m19400_s08 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20700_s08 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m19400_s16 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20700_s16 (KERN_ATTR_RULES ())
{
}
diff --git a/OpenCL/m19400_a0-pure.cl b/OpenCL/m20700_a0-pure.cl
similarity index 98%
rename from OpenCL/m19400_a0-pure.cl
rename to OpenCL/m20700_a0-pure.cl
index f35929826..f3f6d6308 100644
--- a/OpenCL/m19400_a0-pure.cl
+++ b/OpenCL/m20700_a0-pure.cl
@@ -28,7 +28,7 @@
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m19400_mxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m20700_mxx (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -140,7 +140,7 @@ KERNEL_FQ void m19400_mxx (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m19400_sxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m20700_sxx (KERN_ATTR_RULES ())
{
/**
* modifier
diff --git a/OpenCL/m19400_a1-optimized.cl b/OpenCL/m20700_a1-optimized.cl
similarity index 99%
rename from OpenCL/m19400_a1-optimized.cl
rename to OpenCL/m20700_a1-optimized.cl
index 679d8479f..447e6cd36 100644
--- a/OpenCL/m19400_a1-optimized.cl
+++ b/OpenCL/m20700_a1-optimized.cl
@@ -40,7 +40,7 @@
h = 0; \
}
-KERNEL_FQ void m19400_m04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20700_m04 (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -549,15 +549,15 @@ KERNEL_FQ void m19400_m04 (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m19400_m08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20700_m08 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m19400_m16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20700_m16 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m19400_s04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20700_s04 (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -1075,10 +1075,10 @@ KERNEL_FQ void m19400_s04 (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m19400_s08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20700_s08 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m19400_s16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20700_s16 (KERN_ATTR_BASIC ())
{
}
diff --git a/OpenCL/m19400_a1-pure.cl b/OpenCL/m20700_a1-pure.cl
similarity index 98%
rename from OpenCL/m19400_a1-pure.cl
rename to OpenCL/m20700_a1-pure.cl
index 9b4a2b346..fd8a312ad 100644
--- a/OpenCL/m19400_a1-pure.cl
+++ b/OpenCL/m20700_a1-pure.cl
@@ -26,7 +26,7 @@
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m19400_mxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20700_mxx (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -136,7 +136,7 @@ KERNEL_FQ void m19400_mxx (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m19400_sxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20700_sxx (KERN_ATTR_BASIC ())
{
/**
* modifier
diff --git a/OpenCL/m19400_a3-optimized.cl b/OpenCL/m20700_a3-optimized.cl
similarity index 98%
rename from OpenCL/m19400_a3-optimized.cl
rename to OpenCL/m20700_a3-optimized.cl
index e6892950b..a08dce4c4 100644
--- a/OpenCL/m19400_a3-optimized.cl
+++ b/OpenCL/m20700_a3-optimized.cl
@@ -40,7 +40,7 @@
h = 0; \
}
-DECLSPEC void m19400m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u32 *l_bin2asc)
+DECLSPEC void m20700m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u32 *l_bin2asc)
{
/**
* modifier
@@ -450,7 +450,7 @@ DECLSPEC void m19400m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u
}
}
-DECLSPEC void m19400s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u32 *l_bin2asc)
+DECLSPEC void m20700s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u32 *l_bin2asc)
{
/**
* modifier
@@ -875,7 +875,7 @@ DECLSPEC void m19400s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u
}
}
-KERNEL_FQ void m19400_m04 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20700_m04 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -933,10 +933,10 @@ KERNEL_FQ void m19400_m04 (KERN_ATTR_VECTOR ())
* main
*/
- m19400m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20700m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m19400_m08 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20700_m08 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -994,10 +994,10 @@ KERNEL_FQ void m19400_m08 (KERN_ATTR_VECTOR ())
* main
*/
- m19400m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20700m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m19400_m16 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20700_m16 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -1055,10 +1055,10 @@ KERNEL_FQ void m19400_m16 (KERN_ATTR_VECTOR ())
* main
*/
- m19400m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20700m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m19400_s04 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20700_s04 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -1116,10 +1116,10 @@ KERNEL_FQ void m19400_s04 (KERN_ATTR_VECTOR ())
* main
*/
- m19400s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20700s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m19400_s08 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20700_s08 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -1177,10 +1177,10 @@ KERNEL_FQ void m19400_s08 (KERN_ATTR_VECTOR ())
* main
*/
- m19400s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20700s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m19400_s16 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20700_s16 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -1238,5 +1238,5 @@ KERNEL_FQ void m19400_s16 (KERN_ATTR_VECTOR ())
* main
*/
- m19400s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20700s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
diff --git a/OpenCL/m19400_a3-pure.cl b/OpenCL/m20700_a3-pure.cl
similarity index 98%
rename from OpenCL/m19400_a3-pure.cl
rename to OpenCL/m20700_a3-pure.cl
index 7798664b6..09155b33d 100644
--- a/OpenCL/m19400_a3-pure.cl
+++ b/OpenCL/m20700_a3-pure.cl
@@ -26,7 +26,7 @@
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m19400_mxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20700_mxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -149,7 +149,7 @@ KERNEL_FQ void m19400_mxx (KERN_ATTR_VECTOR ())
}
}
-KERNEL_FQ void m19400_sxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20700_sxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
diff --git a/src/modules/module_19400.c b/src/modules/module_20700.c
similarity index 99%
rename from src/modules/module_19400.c
rename to src/modules/module_20700.c
index 35adb27b2..7473c661c 100644
--- a/src/modules/module_19400.c
+++ b/src/modules/module_20700.c
@@ -19,7 +19,7 @@ static const u32 DGST_POS3 = 6;
static const u32 DGST_SIZE = DGST_SIZE_4_8;
static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
static const char *HASH_NAME = "AuthMe - sha256(sha256($pass).$salt)";
-static const u64 KERN_TYPE = 19400;
+static const u64 KERN_TYPE = 20700;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
| OPTI_TYPE_EARLY_SKIP
diff --git a/tools/test_modules/m19400.pm b/tools/test_modules/m20700.pm
similarity index 100%
rename from tools/test_modules/m19400.pm
rename to tools/test_modules/m20700.pm
From b54ad7981f0ae29a6927b05c4307b43ac603182c Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Mon, 29 Jul 2019 18:42:50 +0200
Subject: [PATCH 040/113] update repo and re-apply zip patch
---
.gitignore | 1 +
docs/changes.txt | 1 +
docs/credits.txt | 2 +-
include/ext_lzma.h | 4 ++-
include/types.h | 21 +++++++++--
src/Makefile | 5 ++-
src/filehandling.c | 87 +++++++++++++++++++++++++++++++++++++++++++---
src/shared.c | 1 +
8 files changed, 112 insertions(+), 10 deletions(-)
diff --git a/.gitignore b/.gitignore
index 1565b6a31..dc0c997d3 100644
--- a/.gitignore
+++ b/.gitignore
@@ -18,6 +18,7 @@ kernels/**
lib/*.a
modules/*.dll
modules/*.so
+obj/*/*/*.o
obj/*.o
obj/*.a
include/CL
diff --git a/docs/changes.txt b/docs/changes.txt
index 0bb228187..a4f07f4a0 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -7,6 +7,7 @@
- Fully modularized hash-mode integration via plugin interface and converted all existing hash-modes
- Support for inline VeraCrypt PIM Brute-Force
- Support Deflate decompression for the 7-Zip hash type using zlib
+- Compressed wordlists, gzip and zip format, using zlib
##
## Algorithms
diff --git a/docs/credits.txt b/docs/credits.txt
index bd21d35d7..ae8d03881 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,7 +18,7 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
-* gzip wordlists feature
+* Compressed wordlists feature (gzip/zip)
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
* OpenCL Info feature
diff --git a/include/ext_lzma.h b/include/ext_lzma.h
index 96560b94d..feaa5d908 100644
--- a/include/ext_lzma.h
+++ b/include/ext_lzma.h
@@ -5,10 +5,12 @@
#ifndef _EXT_LZMA_H
-#include <Alloc.h>
#include <LzmaDec.h>
#include <Lzma2Dec.h>
+#include "contrib/minizip/ioapi.h"
+#include "contrib/minizip/unzip.h"
+
int hc_lzma1_decompress (const unsigned char *in, SizeT *in_len, unsigned char *out, SizeT *out_len, const char *props);
int hc_lzma2_decompress (const unsigned char *in, SizeT *in_len, unsigned char *out, SizeT *out_len, const char *props);
diff --git a/include/types.h b/include/types.h
index 6452f859f..08e3f88c0 100644
--- a/include/types.h
+++ b/include/types.h
@@ -17,7 +17,18 @@
#include <sys/time.h>
#include <unistd.h>
#include <math.h>
+
+// workaround to get the rid of "redefinition of typedef 'Byte'" build warning
+#if !defined (__APPLE__)
#include "zlib.h"
+#endif
+
+#if !defined(__MACTYPES__)
+#define __MACTYPES__
+#include "ext_lzma.h"
+#undef __MACTYPES__
+#endif
+// end of workaround
#if defined (_WIN)
#define WINICONV_CONST
@@ -989,15 +1000,19 @@ typedef struct link_speed
} link_speed_t;
-// handling gzip files
+// file handling
typedef struct hc_fp
{
int fd;
- FILE *pfp;
- gzFile gfp;
+
+ FILE *pfp; // plain fp
+ gzFile gfp; // gzip fp
+ unzFile ufp; // zip fp
bool is_gzip;
+ bool is_zip;
+
char *mode;
const char *path;
} HCFILE;
diff --git a/src/Makefile b/src/Makefile
index 89a16dbda..c61078a4a 100644
--- a/src/Makefile
+++ b/src/Makefile
@@ -180,6 +180,8 @@ endif
ifeq ($(USE_SYSTEM_ZLIB),0)
CFLAGS_ZLIB += -Wno-implicit-fallthrough
CFLAGS_ZLIB += -Wno-implicit-function-declaration
+CFLAGS_ZLIB += -Wno-unused-parameter
+CFLAGS_ZLIB += -DIOAPI_NO_64
endif
ifeq ($(DEBUG),0)
@@ -319,7 +321,7 @@ WIN_OBJS += $(foreach OBJ,$(OBJS_LZMA),obj/$(OBJ).WIN.o)
endif
ifeq ($(USE_SYSTEM_ZLIB),0)
-OBJS_ZLIB := adler32 crc32 deflate inflate inffast inftrees trees gzread gzwrite gzclose zutil gzlib
+OBJS_ZLIB := adler32 crc32 deflate inflate inffast inftrees trees gzread gzwrite gzclose zutil gzlib contrib/minizip/unzip contrib/minizip/ioapi
NATIVE_OBJS += $(foreach OBJ,$(OBJS_ZLIB),obj/$(OBJ).NATIVE.o)
LINUX_OBJS += $(foreach OBJ,$(OBJS_ZLIB),obj/$(OBJ).LINUX.o)
@@ -348,6 +350,7 @@ clean:
$(RM) -rf modules/*.dSYM
$(RM) -f modules/*.dll
$(RM) -f modules/*.so
+ $(RM) -f obj/*/*/*.o
$(RM) -f obj/*.o
$(RM) -f obj/*.a
$(RM) -f *.bin *.exe
diff --git a/src/filehandling.c b/src/filehandling.c
index 22d3deda4..55cfc1f6a 100644
--- a/src/filehandling.c
+++ b/src/filehandling.c
@@ -11,7 +11,7 @@
#if defined (__CYGWIN__)
// workaround for zlib with cygwin build
-int _wopen(const char *path, int oflag, ...)
+int _wopen (const char *path, int oflag, ...)
{
va_list ap;
va_start (ap, oflag);
@@ -62,8 +62,9 @@ bool hc_fopen (HCFILE *fp, const char *path, char *mode)
fp->pfp = NULL;
fp->is_gzip = false;
+ fp->is_zip = false;
- unsigned char check[3] = { 0 };
+ unsigned char check[4] = { 0 };
int fd_tmp = open (path, O_RDONLY);
@@ -73,7 +74,8 @@ bool hc_fopen (HCFILE *fp, const char *path, char *mode)
if (read (fd_tmp, check, sizeof(check)) > 0)
{
- if (check[0] == 0x1f && check[1] == 0x8b && check[2] == 0x08) fp->is_gzip = true;
+ if (check[0] == 0x1f && check[1] == 0x8b && check[2] == 0x08 && check[3] == 0x08) fp->is_gzip = true;
+ if (check[0] == 0x50 && check[1] == 0x4b && check[2] == 0x03 && check[3] == 0x04) fp->is_zip = true;
}
close (fd_tmp);
@@ -88,12 +90,18 @@ bool hc_fopen (HCFILE *fp, const char *path, char *mode)
fp->fd = open (path, oflag, fmode);
}
- if (fp->fd == -1) return false;
+ if (fp->fd == -1 && fp->is_zip == false) return false;
if (fp->is_gzip)
{
if ((fp->gfp = gzdopen (fp->fd, mode)) == NULL) return false;
}
+ else if (fp->is_zip)
+ {
+ if ((fp->ufp = unzOpen64 (path)) == NULL) return false;
+
+ if (unzOpenCurrentFile (fp->ufp) != UNZ_OK) return false;
+ }
else
{
if ((fp->pfp = fdopen (fp->fd, mode)) == NULL) return false;
@@ -115,6 +123,12 @@ size_t hc_fread (void *ptr, size_t size, size_t nmemb, HCFILE *fp)
{
n = gzfread (ptr, size, nmemb, fp->gfp);
}
+ else if (fp->is_zip)
+ {
+ unsigned s = size * nmemb;
+
+ n = unzReadCurrentFile (fp->ufp, ptr, s);
+ }
else
{
n = fread (ptr, size, nmemb, fp->pfp);
@@ -133,6 +147,9 @@ size_t hc_fwrite (void *ptr, size_t size, size_t nmemb, HCFILE *fp)
{
n = gzfwrite (ptr, size, nmemb, fp->gfp);
}
+ else if (fp->is_zip)
+ {
+ }
else
{
n = fwrite (ptr, size, nmemb, fp->pfp);
@@ -153,6 +170,27 @@ int hc_fseek (HCFILE *fp, off_t offset, int whence)
{
r = gzseek (fp->gfp, (z_off_t) offset, whence);
}
+ else if (fp->is_zip)
+ {
+ /*
+ // untested and not used in wordlist engine
+ zlib_filefunc64_32_def *d = NULL;
+ if (whence == SEEK_SET)
+ {
+ r = ZSEEK64(*d, fp->ufp, offset, ZLIB_FILEFUNC_SEEK_SET);
+ }
+ else if (whence == SEEK_CUR)
+ {
+ r = ZSEEK64(*d, fp->ufp, offset, ZLIB_FILEFUNC_SEEK_CUR);
+ }
+ else if (whence == SEEK_END)
+ {
+ r = ZSEEK64(*d, fp->ufp, offset, ZLIB_FILEFUNC_SEEK_END);
+ }
+ // or
+ // r = unzSetOffset (fp->ufp, offset);
+ */
+ }
else
{
r = fseeko (fp->pfp, offset, whence);
@@ -169,6 +207,10 @@ void hc_rewind (HCFILE *fp)
{
gzrewind (fp->gfp);
}
+ else if (fp->is_zip)
+ {
+ unzGoToFirstFile (fp->ufp);
+ }
else
{
rewind (fp->pfp);
@@ -185,6 +227,10 @@ off_t hc_ftell (HCFILE *fp)
{
n = (off_t) gztell (fp->gfp);
}
+ else if (fp->is_zip)
+ {
+ n = unztell (fp->ufp);
+ }
else
{
n = ftello (fp->pfp);
@@ -203,6 +249,9 @@ int hc_fputc (int c, HCFILE *fp)
{
r = gzputc (fp->gfp, c);
}
+ else if (fp->is_zip)
+ {
+ }
else
{
r = fputc (c, fp->pfp);
@@ -221,6 +270,12 @@ int hc_fgetc (HCFILE *fp)
{
r = gzgetc (fp->gfp);
}
+ else if (fp->is_zip)
+ {
+ unsigned char c = 0;
+
+ if (unzReadCurrentFile (fp->ufp, &c, 1) == 1) r = (int) c;
+ }
else
{
r = fgetc (fp->pfp);
@@ -239,6 +294,10 @@ char *hc_fgets (char *buf, int len, HCFILE *fp)
{
r = gzgets (fp->gfp, buf, len);
}
+ else if (fp->is_zip)
+ {
+ if (unzReadCurrentFile (fp->ufp, buf, len) > 0) r = buf;
+ }
else
{
r = fgets (buf, len, fp->pfp);
@@ -257,6 +316,9 @@ int hc_vfprintf (HCFILE *fp, const char *format, va_list ap)
{
r = gzvprintf (fp->gfp, format, ap);
}
+ else if (fp->is_zip)
+ {
+ }
else
{
r = vfprintf (fp->pfp, format, ap);
@@ -279,6 +341,9 @@ int hc_fprintf (HCFILE *fp, const char *format, ...)
{
r = gzvprintf (fp->gfp, format, ap);
}
+ else if (fp->is_zip)
+ {
+ }
else
{
r = vfprintf (fp->pfp, format, ap);
@@ -330,6 +395,10 @@ int hc_feof (HCFILE *fp)
{
r = gzeof (fp->gfp);
}
+ else if (fp->is_zip)
+ {
+ r = unzeof (fp->ufp);
+ }
else
{
r = feof (fp->pfp);
@@ -346,6 +415,9 @@ void hc_fflush (HCFILE *fp)
{
gzflush (fp->gfp, Z_SYNC_FLUSH);
}
+ else if (fp->is_zip)
+ {
+ }
else
{
fflush (fp->pfp);
@@ -360,6 +432,12 @@ void hc_fclose (HCFILE *fp)
{
gzclose (fp->gfp);
}
+ else if (fp->is_zip)
+ {
+ unzCloseCurrentFile (fp->ufp);
+
+ unzClose (fp->ufp);
+ }
else
{
fclose (fp->pfp);
@@ -370,6 +448,7 @@ void hc_fclose (HCFILE *fp)
fp->fd = -1;
fp->pfp = NULL;
fp->is_gzip = false;
+ fp->is_zip = false;
fp->path = NULL;
fp->mode = NULL;
diff --git a/src/shared.c b/src/shared.c
index fff7192b6..b27dbdba1 100644
--- a/src/shared.c
+++ b/src/shared.c
@@ -8,6 +8,7 @@
#include "convert.h"
#include "shared.h"
#include "memory.h"
+#include "ext_lzma.h"
#include <errno.h>
#if defined (__CYGWIN__)
From 7f38c824c8396dd1ad906fff16f26c3410894e22 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Mon, 29 Jul 2019 18:46:12 +0200
Subject: [PATCH 041/113] add missing lock file
---
obj/contrib/minizip/.lock | 0
1 file changed, 0 insertions(+), 0 deletions(-)
create mode 100644 obj/contrib/minizip/.lock
diff --git a/obj/contrib/minizip/.lock b/obj/contrib/minizip/.lock
new file mode 100644
index 000000000..e69de29bb
From 19d14f67c2730d80b2cd407ca1eb569ab2db880a Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 30 Jul 2019 14:07:57 +0200
Subject: [PATCH 042/113] cleanup credits.txt
---
docs/credits.txt | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/docs/credits.txt b/docs/credits.txt
index ae8d03881..bd21d35d7 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,7 +18,7 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
-* Compressed wordlists feature (gzip/zip)
+* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
* OpenCL Info feature
From f90222dab001315e38362119d30b513904d4de70 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 30 Jul 2019 14:11:29 +0200
Subject: [PATCH 043/113] cleanup credits.txt and changes.txt
---
docs/changes.txt | 1 -
docs/credits.txt | 1 -
2 files changed, 2 deletions(-)
diff --git a/docs/changes.txt b/docs/changes.txt
index ca110004f..0bb228187 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,7 +35,6 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
-- Added hash-mode: AuthMe - sha256(sha256($pass).$salt)
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index bd08200cc..bd21d35d7 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,7 +18,6 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
-* AuthMe - sha256(sha256($pass).$salt) kernel module (thanks to @0xbsec)
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
From 1a110b4f7119f0c87455ea3abe81f26baf450348 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 30 Jul 2019 14:12:42 +0200
Subject: [PATCH 044/113] cleanup credits.txt and changes.txt
---
docs/changes.txt | 1 -
docs/credits.txt | 1 -
2 files changed, 2 deletions(-)
diff --git a/docs/changes.txt b/docs/changes.txt
index 809c29c3b..0bb228187 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,7 +35,6 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
-- Added hash-mode: BitShares v0.x - sha512(sha512(pass))
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index a70e4506e..bd21d35d7 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,7 +18,6 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
-* BitShares v0.x - sha512(sha512(pass)) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
From 9502705c034b2a0ac813d29309a33dda9faa6fbd Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 30 Jul 2019 14:14:15 +0200
Subject: [PATCH 045/113] cleanup credits.txt, changes.txt and readme.txt
---
docs/changes.txt | 1 -
docs/credits.txt | 1 -
docs/readme.txt | 1 -
3 files changed, 3 deletions(-)
diff --git a/docs/changes.txt b/docs/changes.txt
index 22b1b4572..0bb228187 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,7 +35,6 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
-- Added hash-mode: sha1(md5($pass.$salt))
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index 7b6534226..bd21d35d7 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,7 +18,6 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
-* sha1(md5($pass.$salt)) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
diff --git a/docs/readme.txt b/docs/readme.txt
index 4f71181fc..9e36b73ce 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -81,7 +81,6 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- sha1(sha1($pass))
- sha1($salt.sha1($pass))
- sha1(md5($pass))
-- sha1(md5($pass.$salt))
- sha1(md5(md5($pass)))
- sha1($salt.$pass.$salt)
- sha1(CX)
From 6a6c393bc52906c2d2785bab8c01867c86467d04 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 30 Jul 2019 14:15:30 +0200
Subject: [PATCH 046/113] cleanup credits.txt and changes.txt
---
docs/changes.txt | 1 -
docs/credits.txt | 1 -
2 files changed, 2 deletions(-)
diff --git a/docs/changes.txt b/docs/changes.txt
index bab9f5bdf..0bb228187 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,7 +35,6 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
-- Added hash-mode: md5(sha1($salt).md5($pass))
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index 474f29925..bd21d35d7 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,7 +18,6 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
-* md5(sha1($salt).md5($pass)) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
From 2bd78e5ea15354abb605b0da26b03df42e592008 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 30 Jul 2019 14:16:12 +0200
Subject: [PATCH 047/113] cleanup credits.txt and changes.txt
---
docs/changes.txt | 1 -
docs/credits.txt | 1 -
2 files changed, 2 deletions(-)
diff --git a/docs/changes.txt b/docs/changes.txt
index a60aa03f3..0bb228187 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,7 +35,6 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
-- Added hash-mode: md5($salt.sha1($salt.$pass))
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index 55864e185..bd21d35d7 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,7 +18,6 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
-* md5($salt.sha1($salt.$pass)) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
From f2d92d8aec11d8af5e4bf6eedd4cfae342da82d5 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 30 Jul 2019 14:44:17 +0200
Subject: [PATCH 048/113] switch hash-mode from 4710 to 20800
---
...a0-optimized.cl => m20800_a0-optimized.cl} | 12 ++++----
.../{m04710_a0-pure.cl => m20800_a0-pure.cl} | 4 +--
...a1-optimized.cl => m20800_a1-optimized.cl} | 12 ++++----
.../{m04710_a1-pure.cl => m20800_a1-pure.cl} | 4 +--
...a3-optimized.cl => m20800_a3-optimized.cl} | 28 +++++++++----------
.../{m04710_a3-pure.cl => m20800_a3-pure.cl} | 4 +--
docs/changes.txt | 1 -
docs/credits.txt | 1 -
.../{module_04710.c => module_20800.c} | 2 +-
tools/test_modules/{m04710.pm => m20800.pm} | 0
10 files changed, 33 insertions(+), 35 deletions(-)
rename OpenCL/{m04710_a0-optimized.cl => m20800_a0-optimized.cl} (99%)
rename OpenCL/{m04710_a0-pure.cl => m20800_a0-pure.cl} (98%)
rename OpenCL/{m04710_a1-optimized.cl => m20800_a1-optimized.cl} (99%)
rename OpenCL/{m04710_a1-pure.cl => m20800_a1-pure.cl} (98%)
rename OpenCL/{m04710_a3-optimized.cl => m20800_a3-optimized.cl} (97%)
rename OpenCL/{m04710_a3-pure.cl => m20800_a3-pure.cl} (98%)
rename src/modules/{module_04710.c => module_20800.c} (99%)
rename tools/test_modules/{m04710.pm => m20800.pm} (100%)
diff --git a/OpenCL/m04710_a0-optimized.cl b/OpenCL/m20800_a0-optimized.cl
similarity index 99%
rename from OpenCL/m04710_a0-optimized.cl
rename to OpenCL/m20800_a0-optimized.cl
index d2f365c25..d428df4f0 100644
--- a/OpenCL/m04710_a0-optimized.cl
+++ b/OpenCL/m20800_a0-optimized.cl
@@ -43,7 +43,7 @@
h = 0; \
}
-KERNEL_FQ void m04710_m04 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20800_m04 (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -306,15 +306,15 @@ KERNEL_FQ void m04710_m04 (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m04710_m08 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20800_m08 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m04710_m16 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20800_m16 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m04710_s04 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20800_s04 (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -610,10 +610,10 @@ KERNEL_FQ void m04710_s04 (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m04710_s08 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20800_s08 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m04710_s16 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20800_s16 (KERN_ATTR_RULES ())
{
}
diff --git a/OpenCL/m04710_a0-pure.cl b/OpenCL/m20800_a0-pure.cl
similarity index 98%
rename from OpenCL/m04710_a0-pure.cl
rename to OpenCL/m20800_a0-pure.cl
index 966463126..01ce1a6ad 100644
--- a/OpenCL/m04710_a0-pure.cl
+++ b/OpenCL/m20800_a0-pure.cl
@@ -29,7 +29,7 @@
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04710_mxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m20800_mxx (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -130,7 +130,7 @@ KERNEL_FQ void m04710_mxx (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m04710_sxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m20800_sxx (KERN_ATTR_RULES ())
{
/**
* modifier
diff --git a/OpenCL/m04710_a1-optimized.cl b/OpenCL/m20800_a1-optimized.cl
similarity index 99%
rename from OpenCL/m04710_a1-optimized.cl
rename to OpenCL/m20800_a1-optimized.cl
index e510b235b..6ec1be3da 100644
--- a/OpenCL/m04710_a1-optimized.cl
+++ b/OpenCL/m20800_a1-optimized.cl
@@ -41,7 +41,7 @@
h = 0; \
}
-KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_m04 (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -359,15 +359,15 @@ KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m04710_m08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_m08 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m04710_m16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_m16 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_s04 (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -718,10 +718,10 @@ KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m04710_s08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_s08 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m04710_s16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_s16 (KERN_ATTR_BASIC ())
{
}
diff --git a/OpenCL/m04710_a1-pure.cl b/OpenCL/m20800_a1-pure.cl
similarity index 98%
rename from OpenCL/m04710_a1-pure.cl
rename to OpenCL/m20800_a1-pure.cl
index 044b07058..1bce6143a 100644
--- a/OpenCL/m04710_a1-pure.cl
+++ b/OpenCL/m20800_a1-pure.cl
@@ -27,7 +27,7 @@
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04710_mxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_mxx (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -126,7 +126,7 @@ KERNEL_FQ void m04710_mxx (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m04710_sxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_sxx (KERN_ATTR_BASIC ())
{
/**
* modifier
diff --git a/OpenCL/m04710_a3-optimized.cl b/OpenCL/m20800_a3-optimized.cl
similarity index 97%
rename from OpenCL/m04710_a3-optimized.cl
rename to OpenCL/m20800_a3-optimized.cl
index 4651c8d43..8ddfcc703 100644
--- a/OpenCL/m04710_a3-optimized.cl
+++ b/OpenCL/m20800_a3-optimized.cl
@@ -41,7 +41,7 @@
h = 0; \
}
-DECLSPEC void m04710m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+DECLSPEC void m20800m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
{
/**
* modifier
@@ -277,7 +277,7 @@ DECLSPEC void m04710m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
}
}
-DECLSPEC void m04710s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+DECLSPEC void m20800s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
{
/**
* modifier
@@ -546,7 +546,7 @@ DECLSPEC void m04710s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
}
}
-KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_m04 (KERN_ATTR_BASIC ())
{
/**
* base
@@ -613,10 +613,10 @@ KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
* main
*/
- m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20800m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m04710_m08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_m08 (KERN_ATTR_BASIC ())
{
/**
* base
@@ -683,10 +683,10 @@ KERNEL_FQ void m04710_m08 (KERN_ATTR_BASIC ())
* main
*/
- m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20800m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m04710_m16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_m16 (KERN_ATTR_BASIC ())
{
/**
* base
@@ -753,10 +753,10 @@ KERNEL_FQ void m04710_m16 (KERN_ATTR_BASIC ())
* main
*/
- m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20800m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_s04 (KERN_ATTR_BASIC ())
{
/**
* base
@@ -823,10 +823,10 @@ KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
* main
*/
- m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20800s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m04710_s08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_s08 (KERN_ATTR_BASIC ())
{
/**
* base
@@ -893,10 +893,10 @@ KERNEL_FQ void m04710_s08 (KERN_ATTR_BASIC ())
* main
*/
- m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20800s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m04710_s16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20800_s16 (KERN_ATTR_BASIC ())
{
/**
* base
@@ -963,5 +963,5 @@ KERNEL_FQ void m04710_s16 (KERN_ATTR_BASIC ())
* main
*/
- m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20800s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
diff --git a/OpenCL/m04710_a3-pure.cl b/OpenCL/m20800_a3-pure.cl
similarity index 98%
rename from OpenCL/m04710_a3-pure.cl
rename to OpenCL/m20800_a3-pure.cl
index 449da471d..9cb333ba1 100644
--- a/OpenCL/m04710_a3-pure.cl
+++ b/OpenCL/m20800_a3-pure.cl
@@ -27,7 +27,7 @@
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04710_mxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20800_mxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -139,7 +139,7 @@ KERNEL_FQ void m04710_mxx (KERN_ATTR_VECTOR ())
}
}
-KERNEL_FQ void m04710_sxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20800_sxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
diff --git a/docs/changes.txt b/docs/changes.txt
index 7062e62af..0bb228187 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,7 +35,6 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
-- Added hash-mode: sha256(md5($pass))
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index c89524dab..bd21d35d7 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,7 +18,6 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
-* sha256(md5(pass)) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
diff --git a/src/modules/module_04710.c b/src/modules/module_20800.c
similarity index 99%
rename from src/modules/module_04710.c
rename to src/modules/module_20800.c
index 95fbdffbb..1613d607f 100644
--- a/src/modules/module_04710.c
+++ b/src/modules/module_20800.c
@@ -18,7 +18,7 @@ static const u32 DGST_POS3 = 6;
static const u32 DGST_SIZE = DGST_SIZE_4_8;
static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
static const char *HASH_NAME = "sha256(md5($pass))";
-static const u64 KERN_TYPE = 4710;
+static const u64 KERN_TYPE = 20800;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
| OPTI_TYPE_EARLY_SKIP
diff --git a/tools/test_modules/m04710.pm b/tools/test_modules/m20800.pm
similarity index 100%
rename from tools/test_modules/m04710.pm
rename to tools/test_modules/m20800.pm
From 1b5168b95a2ab17c6795a26bbcd32609de48a4dc Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 30 Jul 2019 15:08:55 +0200
Subject: [PATCH 049/113] switch hash-mode from 4410 to 20900
---
...a0-optimized.cl => m20900_a0-optimized.cl} | 12 ++++----
.../{m04410_a0-pure.cl => m20900_a0-pure.cl} | 4 +--
...a1-optimized.cl => m20900_a1-optimized.cl} | 12 ++++----
.../{m04410_a1-pure.cl => m20900_a1-pure.cl} | 4 +--
...a3-optimized.cl => m20900_a3-optimized.cl} | 28 +++++++++----------
.../{m04410_a3-pure.cl => m20900_a3-pure.cl} | 4 +--
docs/changes.txt | 1 -
docs/credits.txt | 1 -
docs/readme.txt | 1 -
.../{module_04410.c => module_20900.c} | 2 +-
tools/test_modules/{m04410.pm => m20900.pm} | 0
11 files changed, 33 insertions(+), 36 deletions(-)
rename OpenCL/{m04410_a0-optimized.cl => m20900_a0-optimized.cl} (99%)
rename OpenCL/{m04410_a0-pure.cl => m20900_a0-pure.cl} (99%)
rename OpenCL/{m04410_a1-optimized.cl => m20900_a1-optimized.cl} (99%)
rename OpenCL/{m04410_a1-pure.cl => m20900_a1-pure.cl} (99%)
rename OpenCL/{m04410_a3-optimized.cl => m20900_a3-optimized.cl} (98%)
rename OpenCL/{m04410_a3-pure.cl => m20900_a3-pure.cl} (99%)
rename src/modules/{module_04410.c => module_20900.c} (99%)
rename tools/test_modules/{m04410.pm => m20900.pm} (100%)
diff --git a/OpenCL/m04410_a0-optimized.cl b/OpenCL/m20900_a0-optimized.cl
similarity index 99%
rename from OpenCL/m04410_a0-optimized.cl
rename to OpenCL/m20900_a0-optimized.cl
index a44f6eb7c..1b9c24e0c 100644
--- a/OpenCL/m04410_a0-optimized.cl
+++ b/OpenCL/m20900_a0-optimized.cl
@@ -29,7 +29,7 @@
#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04410_m04 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20900_m04 (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -731,15 +731,15 @@ KERNEL_FQ void m04410_m04 (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m04410_m08 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20900_m08 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m04410_m16 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20900_m16 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m04410_s04 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20900_s04 (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -1456,10 +1456,10 @@ KERNEL_FQ void m04410_s04 (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m04410_s08 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20900_s08 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m04410_s16 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20900_s16 (KERN_ATTR_RULES ())
{
}
diff --git a/OpenCL/m04410_a0-pure.cl b/OpenCL/m20900_a0-pure.cl
similarity index 99%
rename from OpenCL/m04410_a0-pure.cl
rename to OpenCL/m20900_a0-pure.cl
index bd4c96415..773a6249e 100644
--- a/OpenCL/m04410_a0-pure.cl
+++ b/OpenCL/m20900_a0-pure.cl
@@ -29,7 +29,7 @@
#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04410_mxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m20900_mxx (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -209,7 +209,7 @@ KERNEL_FQ void m04410_mxx (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m04410_sxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m20900_sxx (KERN_ATTR_RULES ())
{
/**
* modifier
diff --git a/OpenCL/m04410_a1-optimized.cl b/OpenCL/m20900_a1-optimized.cl
similarity index 99%
rename from OpenCL/m04410_a1-optimized.cl
rename to OpenCL/m20900_a1-optimized.cl
index f2b73e562..89b25c3b0 100644
--- a/OpenCL/m04410_a1-optimized.cl
+++ b/OpenCL/m20900_a1-optimized.cl
@@ -27,7 +27,7 @@
#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04410_m04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_m04 (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -787,15 +787,15 @@ KERNEL_FQ void m04410_m04 (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m04410_m08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_m08 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m04410_m16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_m16 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m04410_s04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_s04 (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -1570,10 +1570,10 @@ KERNEL_FQ void m04410_s04 (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m04410_s08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_s08 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m04410_s16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_s16 (KERN_ATTR_BASIC ())
{
}
diff --git a/OpenCL/m04410_a1-pure.cl b/OpenCL/m20900_a1-pure.cl
similarity index 99%
rename from OpenCL/m04410_a1-pure.cl
rename to OpenCL/m20900_a1-pure.cl
index 45953c61b..7c8474c56 100644
--- a/OpenCL/m04410_a1-pure.cl
+++ b/OpenCL/m20900_a1-pure.cl
@@ -27,7 +27,7 @@
#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04410_mxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_mxx (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -209,7 +209,7 @@ KERNEL_FQ void m04410_mxx (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m04410_sxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_sxx (KERN_ATTR_BASIC ())
{
/**
* modifier
diff --git a/OpenCL/m04410_a3-optimized.cl b/OpenCL/m20900_a3-optimized.cl
similarity index 98%
rename from OpenCL/m04410_a3-optimized.cl
rename to OpenCL/m20900_a3-optimized.cl
index 569dab215..ec8b4c3ab 100644
--- a/OpenCL/m04410_a3-optimized.cl
+++ b/OpenCL/m20900_a3-optimized.cl
@@ -27,7 +27,7 @@
#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-DECLSPEC void m04410m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+DECLSPEC void m20900m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
{
/**
* modifier
@@ -688,7 +688,7 @@ DECLSPEC void m04410m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
}
}
-DECLSPEC void m04410s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+DECLSPEC void m20900s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
{
/**
* modifier
@@ -1364,7 +1364,7 @@ DECLSPEC void m04410s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
}
}
-KERNEL_FQ void m04410_m04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_m04 (KERN_ATTR_BASIC ())
{
/**
* base
@@ -1431,10 +1431,10 @@ KERNEL_FQ void m04410_m04 (KERN_ATTR_BASIC ())
* main
*/
- m04410m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20900m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m04410_m08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_m08 (KERN_ATTR_BASIC ())
{
/**
* base
@@ -1501,10 +1501,10 @@ KERNEL_FQ void m04410_m08 (KERN_ATTR_BASIC ())
* main
*/
- m04410m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20900m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m04410_m16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_m16 (KERN_ATTR_BASIC ())
{
/**
* base
@@ -1571,10 +1571,10 @@ KERNEL_FQ void m04410_m16 (KERN_ATTR_BASIC ())
* main
*/
- m04410m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20900m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m04410_s04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_s04 (KERN_ATTR_BASIC ())
{
/**
* base
@@ -1641,10 +1641,10 @@ KERNEL_FQ void m04410_s04 (KERN_ATTR_BASIC ())
* main
*/
- m04410s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20900s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m04410_s08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_s08 (KERN_ATTR_BASIC ())
{
/**
* base
@@ -1711,10 +1711,10 @@ KERNEL_FQ void m04410_s08 (KERN_ATTR_BASIC ())
* main
*/
- m04410s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20900s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m04410_s16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20900_s16 (KERN_ATTR_BASIC ())
{
/**
* base
@@ -1781,5 +1781,5 @@ KERNEL_FQ void m04410_s16 (KERN_ATTR_BASIC ())
* main
*/
- m04410s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20900s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
diff --git a/OpenCL/m04410_a3-pure.cl b/OpenCL/m20900_a3-pure.cl
similarity index 99%
rename from OpenCL/m04410_a3-pure.cl
rename to OpenCL/m20900_a3-pure.cl
index c93d52b70..ad6eb3071 100644
--- a/OpenCL/m04410_a3-pure.cl
+++ b/OpenCL/m20900_a3-pure.cl
@@ -27,7 +27,7 @@
#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04410_mxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20900_mxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -218,7 +218,7 @@ KERNEL_FQ void m04410_mxx (KERN_ATTR_VECTOR ())
}
}
-KERNEL_FQ void m04410_sxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20900_sxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
diff --git a/docs/changes.txt b/docs/changes.txt
index 76388fccc..0bb228187 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,7 +35,6 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
-- Added hash-mode: md5(sha1($pass).md5($pass).sha1($pass))
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index 73e07221c..bd21d35d7 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,7 +18,6 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
-* md5(sha1($pass).md5($pass).sha1($pass)) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
diff --git a/docs/readme.txt b/docs/readme.txt
index 7eac7a963..9e36b73ce 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -74,7 +74,6 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- md5(md5($pass).md5($salt))
- md5(strtoupper(md5($pass)))
- md5(sha1($pass))
-- md5(sha1($pass).md5($pass).sha1($pass))
- sha1($pass.$salt)
- sha1($salt.$pass)
- sha1(utf16le($pass).$salt)
diff --git a/src/modules/module_04410.c b/src/modules/module_20900.c
similarity index 99%
rename from src/modules/module_04410.c
rename to src/modules/module_20900.c
index 36ca3de20..defcc93cf 100644
--- a/src/modules/module_04410.c
+++ b/src/modules/module_20900.c
@@ -18,7 +18,7 @@ static const u32 DGST_POS3 = 1;
static const u32 DGST_SIZE = DGST_SIZE_4_4;
static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
static const char *HASH_NAME = "md5(sha1($pass).md5($pass).sha1($pass))";
-static const u64 KERN_TYPE = 4410;
+static const u64 KERN_TYPE = 20900;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
| OPTI_TYPE_EARLY_SKIP
diff --git a/tools/test_modules/m04410.pm b/tools/test_modules/m20900.pm
similarity index 100%
rename from tools/test_modules/m04410.pm
rename to tools/test_modules/m20900.pm
From bba2ee65a2b7f20b5e2b31ec13710d2ae10e9ee2 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 30 Jul 2019 15:15:49 +0200
Subject: [PATCH 050/113] switch hash-mode from 1770 to 21000
---
...a0-optimized.cl => m21000_a0-optimized.cl} | 12 ++++----
.../{m01770_a0-pure.cl => m21000_a0-pure.cl} | 4 +--
...a1-optimized.cl => m21000_a1-optimized.cl} | 12 ++++----
.../{m01770_a1-pure.cl => m21000_a1-pure.cl} | 4 +--
...a3-optimized.cl => m21000_a3-optimized.cl} | 28 +++++++++----------
.../{m01770_a3-pure.cl => m21000_a3-pure.cl} | 4 +--
docs/readme.txt | 1 -
.../{module_01770.c => module_21000.c} | 2 +-
tools/test_modules/{m01770.pm => m21000.pm} | 0
9 files changed, 33 insertions(+), 34 deletions(-)
rename OpenCL/{m01770_a0-optimized.cl => m21000_a0-optimized.cl} (97%)
rename OpenCL/{m01770_a0-pure.cl => m21000_a0-pure.cl} (97%)
rename OpenCL/{m01770_a1-optimized.cl => m21000_a1-optimized.cl} (98%)
rename OpenCL/{m01770_a1-pure.cl => m21000_a1-pure.cl} (97%)
rename OpenCL/{m01770_a3-optimized.cl => m21000_a3-optimized.cl} (95%)
rename OpenCL/{m01770_a3-pure.cl => m21000_a3-pure.cl} (97%)
rename src/modules/{module_01770.c => module_21000.c} (99%)
rename tools/test_modules/{m01770.pm => m21000.pm} (100%)
diff --git a/OpenCL/m01770_a0-optimized.cl b/OpenCL/m21000_a0-optimized.cl
similarity index 97%
rename from OpenCL/m01770_a0-optimized.cl
rename to OpenCL/m21000_a0-optimized.cl
index ebca7fe35..c7cfa5b8d 100644
--- a/OpenCL/m01770_a0-optimized.cl
+++ b/OpenCL/m21000_a0-optimized.cl
@@ -125,7 +125,7 @@ DECLSPEC void sha512_transform_opt (const u32x *w0, const u32x *w1, const u32x *
digest[7] = h;
}
-KERNEL_FQ void m01770_m04 (KERN_ATTR_RULES ())
+KERNEL_FQ void m21000_m04 (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -266,15 +266,15 @@ KERNEL_FQ void m01770_m04 (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m01770_m08 (KERN_ATTR_RULES ())
+KERNEL_FQ void m21000_m08 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m01770_m16 (KERN_ATTR_RULES ())
+KERNEL_FQ void m21000_m16 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m01770_s04 (KERN_ATTR_RULES ())
+KERNEL_FQ void m21000_s04 (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -427,10 +427,10 @@ KERNEL_FQ void m01770_s04 (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m01770_s08 (KERN_ATTR_RULES ())
+KERNEL_FQ void m21000_s08 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m01770_s16 (KERN_ATTR_RULES ())
+KERNEL_FQ void m21000_s16 (KERN_ATTR_RULES ())
{
}
diff --git a/OpenCL/m01770_a0-pure.cl b/OpenCL/m21000_a0-pure.cl
similarity index 97%
rename from OpenCL/m01770_a0-pure.cl
rename to OpenCL/m21000_a0-pure.cl
index b69f9528c..247fc3b3d 100644
--- a/OpenCL/m01770_a0-pure.cl
+++ b/OpenCL/m21000_a0-pure.cl
@@ -16,7 +16,7 @@
#include "inc_hash_sha512.cl"
#endif
-KERNEL_FQ void m01770_mxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m21000_mxx (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -87,7 +87,7 @@ KERNEL_FQ void m01770_mxx (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m01770_sxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m21000_sxx (KERN_ATTR_RULES ())
{
/**
* modifier
diff --git a/OpenCL/m01770_a1-optimized.cl b/OpenCL/m21000_a1-optimized.cl
similarity index 98%
rename from OpenCL/m01770_a1-optimized.cl
rename to OpenCL/m21000_a1-optimized.cl
index 346be147f..7ff4577f7 100644
--- a/OpenCL/m01770_a1-optimized.cl
+++ b/OpenCL/m21000_a1-optimized.cl
@@ -218,7 +218,7 @@ DECLSPEC void sha512_transform_opt (const u32x *w0, const u32x *w1, const u32x *
digest[7] = h;
}
-KERNEL_FQ void m01770_m04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21000_m04 (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -397,15 +397,15 @@ KERNEL_FQ void m01770_m04 (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m01770_m08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21000_m08 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m01770_m16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21000_m16 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m01770_s04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21000_s04 (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -596,10 +596,10 @@ KERNEL_FQ void m01770_s04 (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m01770_s08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21000_s08 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m01770_s16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21000_s16 (KERN_ATTR_BASIC ())
{
}
diff --git a/OpenCL/m01770_a1-pure.cl b/OpenCL/m21000_a1-pure.cl
similarity index 97%
rename from OpenCL/m01770_a1-pure.cl
rename to OpenCL/m21000_a1-pure.cl
index 3c57255d6..f5782bbd4 100644
--- a/OpenCL/m01770_a1-pure.cl
+++ b/OpenCL/m21000_a1-pure.cl
@@ -14,7 +14,7 @@
#include "inc_hash_sha512.cl"
#endif
-KERNEL_FQ void m01770_mxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21000_mxx (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -83,7 +83,7 @@ KERNEL_FQ void m01770_mxx (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m01770_sxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21000_sxx (KERN_ATTR_BASIC ())
{
/**
* modifier
diff --git a/OpenCL/m01770_a3-optimized.cl b/OpenCL/m21000_a3-optimized.cl
similarity index 95%
rename from OpenCL/m01770_a3-optimized.cl
rename to OpenCL/m21000_a3-optimized.cl
index 541110eab..768ba9e02 100644
--- a/OpenCL/m01770_a3-optimized.cl
+++ b/OpenCL/m21000_a3-optimized.cl
@@ -218,7 +218,7 @@ DECLSPEC void sha512_transform_opt (const u32x *w0, const u32x *w1, const u32x *
digest[7] = h;
}
-DECLSPEC void m01770m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
+DECLSPEC void m21000m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -311,7 +311,7 @@ DECLSPEC void m01770m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
}
}
-DECLSPEC void m01770s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
+DECLSPEC void m21000s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -416,7 +416,7 @@ DECLSPEC void m01770s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
}
}
-KERNEL_FQ void m01770_m04 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21000_m04 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -451,10 +451,10 @@ KERNEL_FQ void m01770_m04 (KERN_ATTR_VECTOR ())
* main
*/
- m01770m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+ m21000m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
-KERNEL_FQ void m01770_m08 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21000_m08 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -489,10 +489,10 @@ KERNEL_FQ void m01770_m08 (KERN_ATTR_VECTOR ())
* main
*/
- m01770m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+ m21000m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
-KERNEL_FQ void m01770_m16 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21000_m16 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -527,10 +527,10 @@ KERNEL_FQ void m01770_m16 (KERN_ATTR_VECTOR ())
* main
*/
- m01770m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+ m21000m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
-KERNEL_FQ void m01770_s04 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21000_s04 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -565,10 +565,10 @@ KERNEL_FQ void m01770_s04 (KERN_ATTR_VECTOR ())
* main
*/
- m01770s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+ m21000s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
-KERNEL_FQ void m01770_s08 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21000_s08 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -603,10 +603,10 @@ KERNEL_FQ void m01770_s08 (KERN_ATTR_VECTOR ())
* main
*/
- m01770s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+ m21000s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
-KERNEL_FQ void m01770_s16 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21000_s16 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -641,5 +641,5 @@ KERNEL_FQ void m01770_s16 (KERN_ATTR_VECTOR ())
* main
*/
- m01770s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+ m21000s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
diff --git a/OpenCL/m01770_a3-pure.cl b/OpenCL/m21000_a3-pure.cl
similarity index 97%
rename from OpenCL/m01770_a3-pure.cl
rename to OpenCL/m21000_a3-pure.cl
index 3a4a27c14..7ff68d9cb 100644
--- a/OpenCL/m01770_a3-pure.cl
+++ b/OpenCL/m21000_a3-pure.cl
@@ -14,7 +14,7 @@
#include "inc_hash_sha512.cl"
#endif
-KERNEL_FQ void m01770_mxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21000_mxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -96,7 +96,7 @@ KERNEL_FQ void m01770_mxx (KERN_ATTR_VECTOR ())
}
}
-KERNEL_FQ void m01770_sxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21000_sxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
diff --git a/docs/readme.txt b/docs/readme.txt
index 6ab191951..9e36b73ce 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -92,7 +92,6 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- sha512($salt.$pass)
- sha512(utf16le($pass).$salt)
- sha512($salt.utf16le($pass))
-- BitShares v0.x - sha512(sha512(pass))
- HMAC-MD5 (key = $pass)
- HMAC-MD5 (key = $salt)
- HMAC-SHA1 (key = $pass)
diff --git a/src/modules/module_01770.c b/src/modules/module_21000.c
similarity index 99%
rename from src/modules/module_01770.c
rename to src/modules/module_21000.c
index a12c4b53f..f3a631193 100644
--- a/src/modules/module_01770.c
+++ b/src/modules/module_21000.c
@@ -18,7 +18,7 @@ static const u32 DGST_POS3 = 7;
static const u32 DGST_SIZE = DGST_SIZE_8_8;
static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH;
static const char *HASH_NAME = "BitShares v0.x - sha512(sha512(pass))";
-static const u64 KERN_TYPE = 1770;
+static const u64 KERN_TYPE = 21000;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
| OPTI_TYPE_EARLY_SKIP
diff --git a/tools/test_modules/m01770.pm b/tools/test_modules/m21000.pm
similarity index 100%
rename from tools/test_modules/m01770.pm
rename to tools/test_modules/m21000.pm
From 8f236f960990e10af18431788fd72b0fc4352e6e Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 30 Jul 2019 15:19:22 +0200
Subject: [PATCH 051/113] switch hash-mode from 4720 to 21100
---
OpenCL/{m04720_a0-pure.cl => m21100_a0-pure.cl} | 4 ++--
OpenCL/{m04720_a1-pure.cl => m21100_a1-pure.cl} | 4 ++--
OpenCL/{m04720_a3-pure.cl => m21100_a3-pure.cl} | 4 ++--
src/modules/{module_04720.c => module_21100.c} | 2 +-
tools/test_modules/{m04720.pm => m21100.pm} | 0
5 files changed, 7 insertions(+), 7 deletions(-)
rename OpenCL/{m04720_a0-pure.cl => m21100_a0-pure.cl} (98%)
rename OpenCL/{m04720_a1-pure.cl => m21100_a1-pure.cl} (98%)
rename OpenCL/{m04720_a3-pure.cl => m21100_a3-pure.cl} (98%)
rename src/modules/{module_04720.c => module_21100.c} (99%)
rename tools/test_modules/{m04720.pm => m21100.pm} (100%)
diff --git a/OpenCL/m04720_a0-pure.cl b/OpenCL/m21100_a0-pure.cl
similarity index 98%
rename from OpenCL/m04720_a0-pure.cl
rename to OpenCL/m21100_a0-pure.cl
index 4a1c615fd..18ccf6823 100644
--- a/OpenCL/m04720_a0-pure.cl
+++ b/OpenCL/m21100_a0-pure.cl
@@ -29,7 +29,7 @@
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04720_mxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m21100_mxx (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -146,7 +146,7 @@ KERNEL_FQ void m04720_mxx (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m04720_sxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m21100_sxx (KERN_ATTR_RULES ())
{
/**
* modifier
diff --git a/OpenCL/m04720_a1-pure.cl b/OpenCL/m21100_a1-pure.cl
similarity index 98%
rename from OpenCL/m04720_a1-pure.cl
rename to OpenCL/m21100_a1-pure.cl
index 5ed4f4d9f..783632dcd 100644
--- a/OpenCL/m04720_a1-pure.cl
+++ b/OpenCL/m21100_a1-pure.cl
@@ -27,7 +27,7 @@
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04720_mxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21100_mxx (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -142,7 +142,7 @@ KERNEL_FQ void m04720_mxx (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m04720_sxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21100_sxx (KERN_ATTR_BASIC ())
{
/**
* modifier
diff --git a/OpenCL/m04720_a3-pure.cl b/OpenCL/m21100_a3-pure.cl
similarity index 98%
rename from OpenCL/m04720_a3-pure.cl
rename to OpenCL/m21100_a3-pure.cl
index 4554e4604..c38d7cae5 100644
--- a/OpenCL/m04720_a3-pure.cl
+++ b/OpenCL/m21100_a3-pure.cl
@@ -27,7 +27,7 @@
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04720_mxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21100_mxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -155,7 +155,7 @@ KERNEL_FQ void m04720_mxx (KERN_ATTR_VECTOR ())
}
}
-KERNEL_FQ void m04720_sxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21100_sxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
diff --git a/src/modules/module_04720.c b/src/modules/module_21100.c
similarity index 99%
rename from src/modules/module_04720.c
rename to src/modules/module_21100.c
index a414a4a84..b03986550 100644
--- a/src/modules/module_04720.c
+++ b/src/modules/module_21100.c
@@ -18,7 +18,7 @@ static const u32 DGST_POS3 = 1;
static const u32 DGST_SIZE = DGST_SIZE_4_5;
static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
static const char *HASH_NAME = "sha1(md5($pass.$salt))";
-static const u64 KERN_TYPE = 4720;
+static const u64 KERN_TYPE = 21100;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
| OPTI_TYPE_EARLY_SKIP
diff --git a/tools/test_modules/m04720.pm b/tools/test_modules/m21100.pm
similarity index 100%
rename from tools/test_modules/m04720.pm
rename to tools/test_modules/m21100.pm
From 16b4f745af9a79fa19ec41c923f862da3b2fe70c Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 30 Jul 2019 15:23:04 +0200
Subject: [PATCH 052/113] switch hash-mode from 4420 to 21200
---
OpenCL/{m04420_a0-pure.cl => m21200_a0-pure.cl} | 4 ++--
OpenCL/{m04420_a1-pure.cl => m21200_a1-pure.cl} | 4 ++--
OpenCL/{m04420_a3-pure.cl => m21200_a3-pure.cl} | 4 ++--
docs/readme.txt | 1 -
src/modules/{module_04420.c => module_21200.c} | 2 +-
tools/test_modules/{m04420.pm => m21200.pm} | 0
6 files changed, 7 insertions(+), 8 deletions(-)
rename OpenCL/{m04420_a0-pure.cl => m21200_a0-pure.cl} (99%)
rename OpenCL/{m04420_a1-pure.cl => m21200_a1-pure.cl} (99%)
rename OpenCL/{m04420_a3-pure.cl => m21200_a3-pure.cl} (99%)
rename src/modules/{module_04420.c => module_21200.c} (99%)
rename tools/test_modules/{m04420.pm => m21200.pm} (100%)
diff --git a/OpenCL/m04420_a0-pure.cl b/OpenCL/m21200_a0-pure.cl
similarity index 99%
rename from OpenCL/m04420_a0-pure.cl
rename to OpenCL/m21200_a0-pure.cl
index 6503d8781..2ebe15969 100644
--- a/OpenCL/m04420_a0-pure.cl
+++ b/OpenCL/m21200_a0-pure.cl
@@ -29,7 +29,7 @@
#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04420_mxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m21200_mxx (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -188,7 +188,7 @@ KERNEL_FQ void m04420_mxx (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m04420_sxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m21200_sxx (KERN_ATTR_RULES ())
{
/**
* modifier
diff --git a/OpenCL/m04420_a1-pure.cl b/OpenCL/m21200_a1-pure.cl
similarity index 99%
rename from OpenCL/m04420_a1-pure.cl
rename to OpenCL/m21200_a1-pure.cl
index 05e845560..574cc528b 100644
--- a/OpenCL/m04420_a1-pure.cl
+++ b/OpenCL/m21200_a1-pure.cl
@@ -27,7 +27,7 @@
#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04420_mxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21200_mxx (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -184,7 +184,7 @@ KERNEL_FQ void m04420_mxx (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m04420_sxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21200_sxx (KERN_ATTR_BASIC ())
{
/**
* modifier
diff --git a/OpenCL/m04420_a3-pure.cl b/OpenCL/m21200_a3-pure.cl
similarity index 99%
rename from OpenCL/m04420_a3-pure.cl
rename to OpenCL/m21200_a3-pure.cl
index 58c351b25..1b097b9af 100644
--- a/OpenCL/m04420_a3-pure.cl
+++ b/OpenCL/m21200_a3-pure.cl
@@ -27,7 +27,7 @@
#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04420_mxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21200_mxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -197,7 +197,7 @@ KERNEL_FQ void m04420_mxx (KERN_ATTR_VECTOR ())
}
}
-KERNEL_FQ void m04420_sxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21200_sxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
diff --git a/docs/readme.txt b/docs/readme.txt
index b4d01990c..9e36b73ce 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -74,7 +74,6 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- md5(md5($pass).md5($salt))
- md5(strtoupper(md5($pass)))
- md5(sha1($pass))
-- md5(sha1($salt).md5($pass))
- sha1($pass.$salt)
- sha1($salt.$pass)
- sha1(utf16le($pass).$salt)
diff --git a/src/modules/module_04420.c b/src/modules/module_21200.c
similarity index 99%
rename from src/modules/module_04420.c
rename to src/modules/module_21200.c
index 6e736d05a..6c9ea1daf 100644
--- a/src/modules/module_04420.c
+++ b/src/modules/module_21200.c
@@ -18,7 +18,7 @@ static const u32 DGST_POS3 = 1;
static const u32 DGST_SIZE = DGST_SIZE_4_4;
static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
static const char *HASH_NAME = "md5(sha1($salt).md5($pass))";
-static const u64 KERN_TYPE = 4420;
+static const u64 KERN_TYPE = 21200;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
| OPTI_TYPE_EARLY_SKIP
diff --git a/tools/test_modules/m04420.pm b/tools/test_modules/m21200.pm
similarity index 100%
rename from tools/test_modules/m04420.pm
rename to tools/test_modules/m21200.pm
From 16b06f51fca07e7974b7fee49b44efd7ab2f45b8 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 30 Jul 2019 15:26:07 +0200
Subject: [PATCH 053/113] switch hash-mode from 4430 to 21300
---
OpenCL/{m04430_a0-pure.cl => m21300_a0-pure.cl} | 4 ++--
OpenCL/{m04430_a1-pure.cl => m21300_a1-pure.cl} | 4 ++--
OpenCL/{m04430_a3-pure.cl => m21300_a3-pure.cl} | 4 ++--
docs/readme.txt | 1 -
src/modules/{module_04430.c => module_21300.c} | 2 +-
tools/test_modules/{m04430.pm => m21300.pm} | 0
6 files changed, 7 insertions(+), 8 deletions(-)
rename OpenCL/{m04430_a0-pure.cl => m21300_a0-pure.cl} (98%)
rename OpenCL/{m04430_a1-pure.cl => m21300_a1-pure.cl} (98%)
rename OpenCL/{m04430_a3-pure.cl => m21300_a3-pure.cl} (98%)
rename src/modules/{module_04430.c => module_21300.c} (99%)
rename tools/test_modules/{m04430.pm => m21300.pm} (100%)
diff --git a/OpenCL/m04430_a0-pure.cl b/OpenCL/m21300_a0-pure.cl
similarity index 98%
rename from OpenCL/m04430_a0-pure.cl
rename to OpenCL/m21300_a0-pure.cl
index 8c25b929e..04c76d812 100644
--- a/OpenCL/m04430_a0-pure.cl
+++ b/OpenCL/m21300_a0-pure.cl
@@ -29,7 +29,7 @@
#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04430_mxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m21300_mxx (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -146,7 +146,7 @@ KERNEL_FQ void m04430_mxx (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m04430_sxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m21300_sxx (KERN_ATTR_RULES ())
{
/**
* modifier
diff --git a/OpenCL/m04430_a1-pure.cl b/OpenCL/m21300_a1-pure.cl
similarity index 98%
rename from OpenCL/m04430_a1-pure.cl
rename to OpenCL/m21300_a1-pure.cl
index 5871f7d7e..9b231e6f2 100644
--- a/OpenCL/m04430_a1-pure.cl
+++ b/OpenCL/m21300_a1-pure.cl
@@ -27,7 +27,7 @@
#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04430_mxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21300_mxx (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -140,7 +140,7 @@ KERNEL_FQ void m04430_mxx (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m04430_sxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21300_sxx (KERN_ATTR_BASIC ())
{
/**
* modifier
diff --git a/OpenCL/m04430_a3-pure.cl b/OpenCL/m21300_a3-pure.cl
similarity index 98%
rename from OpenCL/m04430_a3-pure.cl
rename to OpenCL/m21300_a3-pure.cl
index 3f22a77a2..f659497c8 100644
--- a/OpenCL/m04430_a3-pure.cl
+++ b/OpenCL/m21300_a3-pure.cl
@@ -27,7 +27,7 @@
#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m04430_mxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21300_mxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -159,7 +159,7 @@ KERNEL_FQ void m04430_mxx (KERN_ATTR_VECTOR ())
}
}
-KERNEL_FQ void m04430_sxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21300_sxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
diff --git a/docs/readme.txt b/docs/readme.txt
index d403bf936..9e36b73ce 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -70,7 +70,6 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- md5($salt.md5($pass))
- md5($salt.md5($salt.$pass))
- md5($salt.md5($pass.$salt))
-- md5($salt.sha1($salt.$pass))
- md5(md5($pass))
- md5(md5($pass).md5($salt))
- md5(strtoupper(md5($pass)))
diff --git a/src/modules/module_04430.c b/src/modules/module_21300.c
similarity index 99%
rename from src/modules/module_04430.c
rename to src/modules/module_21300.c
index acb878d6d..6c4522dc2 100644
--- a/src/modules/module_04430.c
+++ b/src/modules/module_21300.c
@@ -18,7 +18,7 @@ static const u32 DGST_POS3 = 1;
static const u32 DGST_SIZE = DGST_SIZE_4_4;
static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
static const char *HASH_NAME = "md5($salt.sha1($salt.$pass))";
-static const u64 KERN_TYPE = 4430;
+static const u64 KERN_TYPE = 21300;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
| OPTI_TYPE_EARLY_SKIP
diff --git a/tools/test_modules/m04430.pm b/tools/test_modules/m21300.pm
similarity index 100%
rename from tools/test_modules/m04430.pm
rename to tools/test_modules/m21300.pm
From 9ad46c5d818ca195cd7fe538022ea59adfeaa3b6 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Wed, 31 Jul 2019 14:34:18 +0200
Subject: [PATCH 054/113] fix bug in 21300 a3 kernel
---
OpenCL/m21300_a3-pure.cl | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/OpenCL/m21300_a3-pure.cl b/OpenCL/m21300_a3-pure.cl
index f659497c8..d517eb0a0 100644
--- a/OpenCL/m21300_a3-pure.cl
+++ b/OpenCL/m21300_a3-pure.cl
@@ -116,7 +116,7 @@ KERNEL_FQ void m21300_mxx (KERN_ATTR_VECTOR ())
md5_ctx_vector_t ctx;
- sha1_init_vector_from_scalar (&ctx, &ctx11);
+ md5_init_vector_from_scalar (&ctx, &ctx11);
_w0[0] = uint_to_hex_lower8 ((a >> 24) & 255) << 0
| uint_to_hex_lower8 ((a >> 16) & 255) << 16;
@@ -260,7 +260,7 @@ KERNEL_FQ void m21300_sxx (KERN_ATTR_VECTOR ())
md5_ctx_vector_t ctx;
- sha1_init_vector_from_scalar (&ctx, &ctx11);
+ md5_init_vector_from_scalar (&ctx, &ctx11);
_w0[0] = uint_to_hex_lower8 ((a >> 24) & 255) << 0
| uint_to_hex_lower8 ((a >> 16) & 255) << 16;
From d045c0f62a837bd741cf47d4ee6d6f0f72cfab72 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Wed, 31 Jul 2019 15:21:03 +0200
Subject: [PATCH 055/113] fix bug in 21000 a3 kernel
---
OpenCL/m21000_a3-pure.cl | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/OpenCL/m21000_a3-pure.cl b/OpenCL/m21000_a3-pure.cl
index 7ff68d9cb..87c56c54f 100644
--- a/OpenCL/m21000_a3-pure.cl
+++ b/OpenCL/m21000_a3-pure.cl
@@ -60,7 +60,7 @@ KERNEL_FQ void m21000_mxx (KERN_ATTR_VECTOR ())
sha512_final_vector (&ctx0);
- sha512_ctx_t ctx;
+ sha512_ctx_vector_t ctx;
sha512_init_vector (&ctx);
@@ -154,7 +154,7 @@ KERNEL_FQ void m21000_sxx (KERN_ATTR_VECTOR ())
sha512_final_vector (&ctx0);
- sha512_ctx_t ctx;
+ sha512_ctx_vector_t ctx;
sha512_init_vector (&ctx);
From ca0ef1b70eeea84e504a93ed71589e73d3bf1e1f Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Wed, 31 Jul 2019 15:30:39 +0200
Subject: [PATCH 056/113] update hash-name
---
src/modules/module_21000.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/modules/module_21000.c b/src/modules/module_21000.c
index f3a631193..41e32c006 100644
--- a/src/modules/module_21000.c
+++ b/src/modules/module_21000.c
@@ -17,7 +17,7 @@ static const u32 DGST_POS2 = 6;
static const u32 DGST_POS3 = 7;
static const u32 DGST_SIZE = DGST_SIZE_8_8;
static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH;
-static const char *HASH_NAME = "BitShares v0.x - sha512(sha512(pass))";
+static const char *HASH_NAME = "BitShares v0.x - sha512(sha512_bin(pass))";
static const u64 KERN_TYPE = 21000;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
From cc689caa42ad281870e21aaeffb3bb638b1debfa Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Wed, 31 Jul 2019 15:39:16 +0200
Subject: [PATCH 057/113] switch hash-mode from 1470 to 21400, cleanup
credits/readme/changes txt
---
...a0-optimized.cl => m21400_a0-optimized.cl} | 12 ++++----
.../{m01470_a0-pure.cl => m21400_a0-pure.cl} | 4 +--
...a1-optimized.cl => m21400_a1-optimized.cl} | 12 ++++----
.../{m01470_a1-pure.cl => m21400_a1-pure.cl} | 4 +--
...a3-optimized.cl => m21400_a3-optimized.cl} | 28 +++++++++----------
.../{m01470_a3-pure.cl => m21400_a3-pure.cl} | 4 +--
docs/changes.txt | 1 -
docs/credits.txt | 1 -
docs/readme.txt | 1 -
.../{module_01470.c => module_21400.c} | 4 +--
tools/test_modules/{m01470.pm => m21400.pm} | 0
11 files changed, 34 insertions(+), 37 deletions(-)
rename OpenCL/{m01470_a0-optimized.cl => m21400_a0-optimized.cl} (99%)
rename OpenCL/{m01470_a0-pure.cl => m21400_a0-pure.cl} (96%)
rename OpenCL/{m01470_a1-optimized.cl => m21400_a1-optimized.cl} (99%)
rename OpenCL/{m01470_a1-pure.cl => m21400_a1-pure.cl} (96%)
rename OpenCL/{m01470_a3-optimized.cl => m21400_a3-optimized.cl} (98%)
rename OpenCL/{m01470_a3-pure.cl => m21400_a3-pure.cl} (97%)
rename src/modules/{module_01470.c => module_21400.c} (99%)
rename tools/test_modules/{m01470.pm => m21400.pm} (100%)
diff --git a/OpenCL/m01470_a0-optimized.cl b/OpenCL/m21400_a0-optimized.cl
similarity index 99%
rename from OpenCL/m01470_a0-optimized.cl
rename to OpenCL/m21400_a0-optimized.cl
index 5acf8ae17..0de1171c0 100644
--- a/OpenCL/m01470_a0-optimized.cl
+++ b/OpenCL/m21400_a0-optimized.cl
@@ -30,7 +30,7 @@
h = 0; \
}
-KERNEL_FQ void m01470_m04 (KERN_ATTR_RULES ())
+KERNEL_FQ void m21400_m04 (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -277,15 +277,15 @@ KERNEL_FQ void m01470_m04 (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m01470_m08 (KERN_ATTR_RULES ())
+KERNEL_FQ void m21400_m08 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m01470_m16 (KERN_ATTR_RULES ())
+KERNEL_FQ void m21400_m16 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m01470_s04 (KERN_ATTR_RULES ())
+KERNEL_FQ void m21400_s04 (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -565,10 +565,10 @@ KERNEL_FQ void m01470_s04 (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m01470_s08 (KERN_ATTR_RULES ())
+KERNEL_FQ void m21400_s08 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m01470_s16 (KERN_ATTR_RULES ())
+KERNEL_FQ void m21400_s16 (KERN_ATTR_RULES ())
{
}
diff --git a/OpenCL/m01470_a0-pure.cl b/OpenCL/m21400_a0-pure.cl
similarity index 96%
rename from OpenCL/m01470_a0-pure.cl
rename to OpenCL/m21400_a0-pure.cl
index 46f2c892f..1937d53e9 100644
--- a/OpenCL/m01470_a0-pure.cl
+++ b/OpenCL/m21400_a0-pure.cl
@@ -16,7 +16,7 @@
#include "inc_hash_sha256.cl"
#endif
-KERNEL_FQ void m01470_mxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m21400_mxx (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -91,7 +91,7 @@ KERNEL_FQ void m01470_mxx (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m01470_sxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m21400_sxx (KERN_ATTR_RULES ())
{
/**
* modifier
diff --git a/OpenCL/m01470_a1-optimized.cl b/OpenCL/m21400_a1-optimized.cl
similarity index 99%
rename from OpenCL/m01470_a1-optimized.cl
rename to OpenCL/m21400_a1-optimized.cl
index cfe607622..49e39d78e 100644
--- a/OpenCL/m01470_a1-optimized.cl
+++ b/OpenCL/m21400_a1-optimized.cl
@@ -28,7 +28,7 @@
h = 0; \
}
-KERNEL_FQ void m01470_m04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21400_m04 (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -333,15 +333,15 @@ KERNEL_FQ void m01470_m04 (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m01470_m08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21400_m08 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m01470_m16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21400_m16 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m01470_s04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21400_s04 (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -679,10 +679,10 @@ KERNEL_FQ void m01470_s04 (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m01470_s08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21400_s08 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m01470_s16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21400_s16 (KERN_ATTR_BASIC ())
{
}
diff --git a/OpenCL/m01470_a1-pure.cl b/OpenCL/m21400_a1-pure.cl
similarity index 96%
rename from OpenCL/m01470_a1-pure.cl
rename to OpenCL/m21400_a1-pure.cl
index 2ba848069..3336bf6ee 100644
--- a/OpenCL/m01470_a1-pure.cl
+++ b/OpenCL/m21400_a1-pure.cl
@@ -14,7 +14,7 @@
#include "inc_hash_sha256.cl"
#endif
-KERNEL_FQ void m01470_mxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21400_mxx (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -87,7 +87,7 @@ KERNEL_FQ void m01470_mxx (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m01470_sxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m21400_sxx (KERN_ATTR_BASIC ())
{
/**
* modifier
diff --git a/OpenCL/m01470_a3-optimized.cl b/OpenCL/m21400_a3-optimized.cl
similarity index 98%
rename from OpenCL/m01470_a3-optimized.cl
rename to OpenCL/m21400_a3-optimized.cl
index 4df35b766..82cc7448b 100644
--- a/OpenCL/m01470_a3-optimized.cl
+++ b/OpenCL/m21400_a3-optimized.cl
@@ -28,7 +28,7 @@
h = 0; \
}
-DECLSPEC void m01470m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
+DECLSPEC void m21400m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -247,7 +247,7 @@ DECLSPEC void m01470m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
}
}
-DECLSPEC void m01470s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
+DECLSPEC void m21400s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -499,7 +499,7 @@ DECLSPEC void m01470s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR ())
}
}
-KERNEL_FQ void m01470_m04 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21400_m04 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -534,10 +534,10 @@ KERNEL_FQ void m01470_m04 (KERN_ATTR_VECTOR ())
* main
*/
- m01470m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+ m21400m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
-KERNEL_FQ void m01470_m08 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21400_m08 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -572,10 +572,10 @@ KERNEL_FQ void m01470_m08 (KERN_ATTR_VECTOR ())
* main
*/
- m01470m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+ m21400m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
-KERNEL_FQ void m01470_m16 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21400_m16 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -610,10 +610,10 @@ KERNEL_FQ void m01470_m16 (KERN_ATTR_VECTOR ())
* main
*/
- m01470m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+ m21400m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
-KERNEL_FQ void m01470_s04 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21400_s04 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -648,10 +648,10 @@ KERNEL_FQ void m01470_s04 (KERN_ATTR_VECTOR ())
* main
*/
- m01470s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+ m21400s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
-KERNEL_FQ void m01470_s08 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21400_s08 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -686,10 +686,10 @@ KERNEL_FQ void m01470_s08 (KERN_ATTR_VECTOR ())
* main
*/
- m01470s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+ m21400s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
-KERNEL_FQ void m01470_s16 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21400_s16 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -724,5 +724,5 @@ KERNEL_FQ void m01470_s16 (KERN_ATTR_VECTOR ())
* main
*/
- m01470s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
+ m21400s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
diff --git a/OpenCL/m01470_a3-pure.cl b/OpenCL/m21400_a3-pure.cl
similarity index 97%
rename from OpenCL/m01470_a3-pure.cl
rename to OpenCL/m21400_a3-pure.cl
index da1f34954..ed44f3b5a 100644
--- a/OpenCL/m01470_a3-pure.cl
+++ b/OpenCL/m21400_a3-pure.cl
@@ -14,7 +14,7 @@
#include "inc_hash_sha256.cl"
#endif
-KERNEL_FQ void m01470_mxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21400_mxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -100,7 +100,7 @@ KERNEL_FQ void m01470_mxx (KERN_ATTR_VECTOR ())
}
}
-KERNEL_FQ void m01470_sxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m21400_sxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
diff --git a/docs/changes.txt b/docs/changes.txt
index 07dc343c9..0bb228187 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -35,7 +35,6 @@
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
-- Added hash-mode: Double sha256
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index 02f4b0873..bd21d35d7 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,7 +18,6 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
-* Double sha256 kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
* Some AES OpenCL kernel module optimizations
diff --git a/docs/readme.txt b/docs/readme.txt
index 4afef8d2c..9e36b73ce 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -84,7 +84,6 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- sha1(md5(md5($pass)))
- sha1($salt.$pass.$salt)
- sha1(CX)
-- Double sha256
- sha256($pass.$salt)
- sha256($salt.$pass)
- sha256(utf16le($pass).$salt)
diff --git a/src/modules/module_01470.c b/src/modules/module_21400.c
similarity index 99%
rename from src/modules/module_01470.c
rename to src/modules/module_21400.c
index 100407a2d..dc92ef5c8 100644
--- a/src/modules/module_01470.c
+++ b/src/modules/module_21400.c
@@ -17,8 +17,8 @@ static const u32 DGST_POS2 = 2;
static const u32 DGST_POS3 = 6;
static const u32 DGST_SIZE = DGST_SIZE_4_8;
static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH;
-static const char *HASH_NAME = "Double sha256";
-static const u64 KERN_TYPE = 1470;
+static const char *HASH_NAME = "sha256(sha256_bin(pass))";
+static const u64 KERN_TYPE = 21400;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
| OPTI_TYPE_EARLY_SKIP
diff --git a/tools/test_modules/m01470.pm b/tools/test_modules/m21400.pm
similarity index 100%
rename from tools/test_modules/m01470.pm
rename to tools/test_modules/m21400.pm
From 468bf2f19a4d4bf513bba600d81b682bac221b38 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Wed, 31 Jul 2019 17:36:31 +0200
Subject: [PATCH 058/113] update AuthMe patch (1)
---
...a0-optimized.cl => m20710_a0-optimized.cl} | 12 +-
.../{m20700_a0-pure.cl => m20710_a0-pure.cl} | 4 +-
...a1-optimized.cl => m20710_a1-optimized.cl} | 12 +-
.../{m20700_a1-pure.cl => m20710_a1-pure.cl} | 4 +-
...a3-optimized.cl => m20710_a3-optimized.cl} | 28 +-
.../{m20700_a3-pure.cl => m20710_a3-pure.cl} | 4 +-
src/modules/module_20710.c | 279 ++++++++++++++++++
.../{module_20700.c => module_20711.c} | 4 +-
8 files changed, 313 insertions(+), 34 deletions(-)
rename OpenCL/{m20700_a0-optimized.cl => m20710_a0-optimized.cl} (99%)
rename OpenCL/{m20700_a0-pure.cl => m20710_a0-pure.cl} (98%)
rename OpenCL/{m20700_a1-optimized.cl => m20710_a1-optimized.cl} (99%)
rename OpenCL/{m20700_a1-pure.cl => m20710_a1-pure.cl} (98%)
rename OpenCL/{m20700_a3-optimized.cl => m20710_a3-optimized.cl} (98%)
rename OpenCL/{m20700_a3-pure.cl => m20710_a3-pure.cl} (98%)
create mode 100644 src/modules/module_20710.c
rename src/modules/{module_20700.c => module_20711.c} (99%)
diff --git a/OpenCL/m20700_a0-optimized.cl b/OpenCL/m20710_a0-optimized.cl
similarity index 99%
rename from OpenCL/m20700_a0-optimized.cl
rename to OpenCL/m20710_a0-optimized.cl
index c4d263fb2..db63864d2 100644
--- a/OpenCL/m20700_a0-optimized.cl
+++ b/OpenCL/m20710_a0-optimized.cl
@@ -42,7 +42,7 @@
h = 0; \
}
-KERNEL_FQ void m20700_m04 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20710_m04 (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -493,15 +493,15 @@ KERNEL_FQ void m20700_m04 (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m20700_m08 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20710_m08 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m20700_m16 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20710_m16 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m20700_s04 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20710_s04 (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -961,10 +961,10 @@ KERNEL_FQ void m20700_s04 (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m20700_s08 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20710_s08 (KERN_ATTR_RULES ())
{
}
-KERNEL_FQ void m20700_s16 (KERN_ATTR_RULES ())
+KERNEL_FQ void m20710_s16 (KERN_ATTR_RULES ())
{
}
diff --git a/OpenCL/m20700_a0-pure.cl b/OpenCL/m20710_a0-pure.cl
similarity index 98%
rename from OpenCL/m20700_a0-pure.cl
rename to OpenCL/m20710_a0-pure.cl
index f3f6d6308..0c150aa03 100644
--- a/OpenCL/m20700_a0-pure.cl
+++ b/OpenCL/m20710_a0-pure.cl
@@ -28,7 +28,7 @@
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m20700_mxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m20710_mxx (KERN_ATTR_RULES ())
{
/**
* modifier
@@ -140,7 +140,7 @@ KERNEL_FQ void m20700_mxx (KERN_ATTR_RULES ())
}
}
-KERNEL_FQ void m20700_sxx (KERN_ATTR_RULES ())
+KERNEL_FQ void m20710_sxx (KERN_ATTR_RULES ())
{
/**
* modifier
diff --git a/OpenCL/m20700_a1-optimized.cl b/OpenCL/m20710_a1-optimized.cl
similarity index 99%
rename from OpenCL/m20700_a1-optimized.cl
rename to OpenCL/m20710_a1-optimized.cl
index 447e6cd36..360fc61b1 100644
--- a/OpenCL/m20700_a1-optimized.cl
+++ b/OpenCL/m20710_a1-optimized.cl
@@ -40,7 +40,7 @@
h = 0; \
}
-KERNEL_FQ void m20700_m04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20710_m04 (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -549,15 +549,15 @@ KERNEL_FQ void m20700_m04 (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m20700_m08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20710_m08 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m20700_m16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20710_m16 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m20700_s04 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20710_s04 (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -1075,10 +1075,10 @@ KERNEL_FQ void m20700_s04 (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m20700_s08 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20710_s08 (KERN_ATTR_BASIC ())
{
}
-KERNEL_FQ void m20700_s16 (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20710_s16 (KERN_ATTR_BASIC ())
{
}
diff --git a/OpenCL/m20700_a1-pure.cl b/OpenCL/m20710_a1-pure.cl
similarity index 98%
rename from OpenCL/m20700_a1-pure.cl
rename to OpenCL/m20710_a1-pure.cl
index fd8a312ad..ae7b05d41 100644
--- a/OpenCL/m20700_a1-pure.cl
+++ b/OpenCL/m20710_a1-pure.cl
@@ -26,7 +26,7 @@
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m20700_mxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20710_mxx (KERN_ATTR_BASIC ())
{
/**
* modifier
@@ -136,7 +136,7 @@ KERNEL_FQ void m20700_mxx (KERN_ATTR_BASIC ())
}
}
-KERNEL_FQ void m20700_sxx (KERN_ATTR_BASIC ())
+KERNEL_FQ void m20710_sxx (KERN_ATTR_BASIC ())
{
/**
* modifier
diff --git a/OpenCL/m20700_a3-optimized.cl b/OpenCL/m20710_a3-optimized.cl
similarity index 98%
rename from OpenCL/m20700_a3-optimized.cl
rename to OpenCL/m20710_a3-optimized.cl
index a08dce4c4..409133f89 100644
--- a/OpenCL/m20700_a3-optimized.cl
+++ b/OpenCL/m20710_a3-optimized.cl
@@ -40,7 +40,7 @@
h = 0; \
}
-DECLSPEC void m20700m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u32 *l_bin2asc)
+DECLSPEC void m20710m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u32 *l_bin2asc)
{
/**
* modifier
@@ -450,7 +450,7 @@ DECLSPEC void m20700m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u
}
}
-DECLSPEC void m20700s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u32 *l_bin2asc)
+DECLSPEC void m20710s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u32 *l_bin2asc)
{
/**
* modifier
@@ -875,7 +875,7 @@ DECLSPEC void m20700s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u
}
}
-KERNEL_FQ void m20700_m04 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20710_m04 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -933,10 +933,10 @@ KERNEL_FQ void m20700_m04 (KERN_ATTR_VECTOR ())
* main
*/
- m20700m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20710m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m20700_m08 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20710_m08 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -994,10 +994,10 @@ KERNEL_FQ void m20700_m08 (KERN_ATTR_VECTOR ())
* main
*/
- m20700m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20710m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m20700_m16 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20710_m16 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -1055,10 +1055,10 @@ KERNEL_FQ void m20700_m16 (KERN_ATTR_VECTOR ())
* main
*/
- m20700m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20710m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m20700_s04 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20710_s04 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -1116,10 +1116,10 @@ KERNEL_FQ void m20700_s04 (KERN_ATTR_VECTOR ())
* main
*/
- m20700s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20710s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m20700_s08 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20710_s08 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -1177,10 +1177,10 @@ KERNEL_FQ void m20700_s08 (KERN_ATTR_VECTOR ())
* main
*/
- m20700s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20710s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
-KERNEL_FQ void m20700_s16 (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20710_s16 (KERN_ATTR_VECTOR ())
{
/**
* base
@@ -1238,5 +1238,5 @@ KERNEL_FQ void m20700_s16 (KERN_ATTR_VECTOR ())
* main
*/
- m20700s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+ m20710s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
}
diff --git a/OpenCL/m20700_a3-pure.cl b/OpenCL/m20710_a3-pure.cl
similarity index 98%
rename from OpenCL/m20700_a3-pure.cl
rename to OpenCL/m20710_a3-pure.cl
index 09155b33d..ede8e076a 100644
--- a/OpenCL/m20700_a3-pure.cl
+++ b/OpenCL/m20710_a3-pure.cl
@@ -26,7 +26,7 @@
#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
#endif
-KERNEL_FQ void m20700_mxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20710_mxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
@@ -149,7 +149,7 @@ KERNEL_FQ void m20700_mxx (KERN_ATTR_VECTOR ())
}
}
-KERNEL_FQ void m20700_sxx (KERN_ATTR_VECTOR ())
+KERNEL_FQ void m20710_sxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
diff --git a/src/modules/module_20710.c b/src/modules/module_20710.c
new file mode 100644
index 000000000..ea0ac2e6a
--- /dev/null
+++ b/src/modules/module_20710.c
@@ -0,0 +1,279 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+#include "memory.h"
+
+static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL;
+static const u32 DGST_POS0 = 3;
+static const u32 DGST_POS1 = 7;
+static const u32 DGST_POS2 = 2;
+static const u32 DGST_POS3 = 6;
+static const u32 DGST_SIZE = DGST_SIZE_4_8;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_EAS;
+static const char *HASH_NAME = "AuthMe - sha256(sha256($pass).$salt)";
+static const u64 KERN_TYPE = 20710;
+static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
+ | OPTI_TYPE_PRECOMPUTE_INIT
+ | OPTI_TYPE_EARLY_SKIP
+ | OPTI_TYPE_NOT_ITERATED
+ | OPTI_TYPE_RAW_HASH;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_BE
+ | OPTS_TYPE_PT_ADD80
+ | OPTS_TYPE_PT_ADDBITS15;
+static const u32 SALT_TYPE = SALT_TYPE_EMBEDDED;
+static const char *ST_PASS = "hashcat";
+static const char *ST_HASH = "$SHA$7218532375810603$bfede293ecf6539211a7305ea218b9f3f608953130405cda9eaba6fb6250f824";
+
+u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
+u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
+u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
+u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
+u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
+u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
+u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
+const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
+u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
+u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
+u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
+u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
+const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
+const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+
+u32 module_pw_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+ const u32 pw_max = 32;
+
+ return pw_max;
+}
+
+static const char *SIGNATURE_AUTHME = "$SHA$";
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+ u32 *digest = (u32 *) digest_buf;
+
+ token_t token;
+
+ token.token_cnt = 3;
+
+ token.signatures_cnt = 1;
+ token.signatures_buf[0] = SIGNATURE_AUTHME;
+
+ token.len[0] = 5;
+ token.attr[0] = TOKEN_ATTR_FIXED_LENGTH
+ | TOKEN_ATTR_VERIFY_SIGNATURE;
+
+ token.sep[1] = '$';
+ token.len_min[1] = 16;
+ token.len_max[1] = 16;
+ token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_DIGIT;
+
+ token.sep[2] = '$';
+ token.len_min[2] = 64;
+ token.len_max[2] = 64;
+ token.attr[2] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_HEX;
+
+ const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+ if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+ // salt
+
+ const u8 *salt_pos = token.buf[1];
+ const int salt_len = token.len[1];
+
+ memcpy ((u8 *) salt->salt_buf, salt_pos, salt_len);
+
+ salt->salt_len = salt_len;
+
+ // hash
+
+ const u8 *hash_pos = token.buf[2];
+
+ digest[0] = hex_to_u32 (hash_pos + 0);
+ digest[1] = hex_to_u32 (hash_pos + 8);
+ digest[2] = hex_to_u32 (hash_pos + 16);
+ digest[3] = hex_to_u32 (hash_pos + 24);
+ digest[4] = hex_to_u32 (hash_pos + 32);
+ digest[5] = hex_to_u32 (hash_pos + 40);
+ digest[6] = hex_to_u32 (hash_pos + 48);
+ digest[7] = hex_to_u32 (hash_pos + 56);
+
+ digest[0] = byte_swap_32 (digest[0]);
+ digest[1] = byte_swap_32 (digest[1]);
+ digest[2] = byte_swap_32 (digest[2]);
+ digest[3] = byte_swap_32 (digest[3]);
+ digest[4] = byte_swap_32 (digest[4]);
+ digest[5] = byte_swap_32 (digest[5]);
+ digest[6] = byte_swap_32 (digest[6]);
+ digest[7] = byte_swap_32 (digest[7]);
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ digest[0] -= SHA256M_A;
+ digest[1] -= SHA256M_B;
+ digest[2] -= SHA256M_C;
+ digest[3] -= SHA256M_D;
+ digest[4] -= SHA256M_E;
+ digest[5] -= SHA256M_F;
+ digest[6] -= SHA256M_G;
+ digest[7] -= SHA256M_H;
+ }
+
+ return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+ const u32 *digest = (const u32 *) digest_buf;
+
+ int line_len = 0;
+
+ // signature
+
+ line_buf[line_len++] = '$';
+ line_buf[line_len++] = 'S';
+ line_buf[line_len++] = 'H';
+ line_buf[line_len++] = 'A';
+ line_buf[line_len++] = '$';
+
+ // salt
+
+ memcpy (line_buf + line_len, salt->salt_buf, salt->salt_len);
+
+ line_len += salt->salt_len;
+
+ line_buf[line_len++] = '$';
+
+ // digest
+
+ u32 tmp[8];
+
+ tmp[0] = digest[0];
+ tmp[1] = digest[1];
+ tmp[2] = digest[2];
+ tmp[3] = digest[3];
+ tmp[4] = digest[4];
+ tmp[5] = digest[5];
+ tmp[6] = digest[6];
+ tmp[7] = digest[7];
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ tmp[0] += SHA256M_A;
+ tmp[1] += SHA256M_B;
+ tmp[2] += SHA256M_C;
+ tmp[3] += SHA256M_D;
+ tmp[4] += SHA256M_E;
+ tmp[5] += SHA256M_F;
+ tmp[6] += SHA256M_G;
+ tmp[7] += SHA256M_H;
+ }
+
+ tmp[0] = byte_swap_32 (tmp[0]);
+ tmp[1] = byte_swap_32 (tmp[1]);
+ tmp[2] = byte_swap_32 (tmp[2]);
+ tmp[3] = byte_swap_32 (tmp[3]);
+ tmp[4] = byte_swap_32 (tmp[4]);
+ tmp[5] = byte_swap_32 (tmp[5]);
+ tmp[6] = byte_swap_32 (tmp[6]);
+ tmp[7] = byte_swap_32 (tmp[7]);
+
+ u8 *out_buf = (u8 *) line_buf;
+
+ u32_to_hex (tmp[0], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[1], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[2], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[3], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[4], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[5], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[6], out_buf + line_len); line_len += 8;
+ u32_to_hex (tmp[7], out_buf + line_len); line_len += 8;
+
+ line_buf[line_len] = 0;
+
+ return line_len;
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+ module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
+ module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
+
+ module_ctx->module_attack_exec = module_attack_exec;
+ module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_mask = MODULE_DEFAULT;
+ module_ctx->module_benchmark_salt = MODULE_DEFAULT;
+ module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
+ module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
+ module_ctx->module_dgst_pos0 = module_dgst_pos0;
+ module_ctx->module_dgst_pos1 = module_dgst_pos1;
+ module_ctx->module_dgst_pos2 = module_dgst_pos2;
+ module_ctx->module_dgst_pos3 = module_dgst_pos3;
+ module_ctx->module_dgst_size = module_dgst_size;
+ module_ctx->module_dictstat_disable = MODULE_DEFAULT;
+ module_ctx->module_esalt_size = MODULE_DEFAULT;
+ module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
+ module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_count = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_save = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
+ module_ctx->module_hash_decode = module_hash_decode;
+ module_ctx->module_hash_encode_status = MODULE_DEFAULT;
+ module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_encode = module_hash_encode;
+ module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
+ module_ctx->module_hash_mode = MODULE_DEFAULT;
+ module_ctx->module_hash_category = module_hash_category;
+ module_ctx->module_hash_name = module_hash_name;
+ module_ctx->module_hashes_count_min = MODULE_DEFAULT;
+ module_ctx->module_hashes_count_max = MODULE_DEFAULT;
+ module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
+ module_ctx->module_hook12 = MODULE_DEFAULT;
+ module_ctx->module_hook23 = MODULE_DEFAULT;
+ module_ctx->module_hook_salt_size = MODULE_DEFAULT;
+ module_ctx->module_hook_size = MODULE_DEFAULT;
+ module_ctx->module_jit_build_options = MODULE_DEFAULT;
+ module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
+ module_ctx->module_kern_type = module_kern_type;
+ module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
+ module_ctx->module_opti_type = module_opti_type;
+ module_ctx->module_opts_type = module_opts_type;
+ module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
+ module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
+ module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
+ module_ctx->module_potfile_disable = MODULE_DEFAULT;
+ module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
+ module_ctx->module_pwdump_column = MODULE_DEFAULT;
+ module_ctx->module_pw_max = module_pw_max;
+ module_ctx->module_pw_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = MODULE_DEFAULT;
+ module_ctx->module_salt_min = MODULE_DEFAULT;
+ module_ctx->module_salt_type = module_salt_type;
+ module_ctx->module_separator = MODULE_DEFAULT;
+ module_ctx->module_st_hash = module_st_hash;
+ module_ctx->module_st_pass = module_st_pass;
+ module_ctx->module_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_unstable_warning = MODULE_DEFAULT;
+ module_ctx->module_warmup_disable = MODULE_DEFAULT;
+}
diff --git a/src/modules/module_20700.c b/src/modules/module_20711.c
similarity index 99%
rename from src/modules/module_20700.c
rename to src/modules/module_20711.c
index 7473c661c..ac8269cdb 100644
--- a/src/modules/module_20700.c
+++ b/src/modules/module_20711.c
@@ -17,9 +17,9 @@ static const u32 DGST_POS1 = 7;
static const u32 DGST_POS2 = 2;
static const u32 DGST_POS3 = 6;
static const u32 DGST_SIZE = DGST_SIZE_4_8;
-static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_EAS;
static const char *HASH_NAME = "AuthMe - sha256(sha256($pass).$salt)";
-static const u64 KERN_TYPE = 20700;
+static const u64 KERN_TYPE = 20710;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
| OPTI_TYPE_EARLY_SKIP
From 94d901e411ce5852b83f3985225569cd54ba8951 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Wed, 31 Jul 2019 19:04:40 +0200
Subject: [PATCH 059/113] fix bug in 4710 a3 kernel
---
OpenCL/m04710_a3-pure.cl | 4 ++--
src/modules/module_04710.c | 18 ++++++++++++++++--
2 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/OpenCL/m04710_a3-pure.cl b/OpenCL/m04710_a3-pure.cl
index 23d62d71e..9db9ed1ef 100644
--- a/OpenCL/m04710_a3-pure.cl
+++ b/OpenCL/m04710_a3-pure.cl
@@ -71,7 +71,7 @@ KERNEL_FQ void m04710_mxx (KERN_ATTR_VECTOR ())
const u32 salt_len = salt_bufs[salt_pos].salt_len;
- u32 s[64] = { 0 };
+ u32x s[8] = { 0 };
for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
{
@@ -211,7 +211,7 @@ KERNEL_FQ void m04710_sxx (KERN_ATTR_VECTOR ())
const u32 salt_len = salt_bufs[salt_pos].salt_len;
- u32 s[64] = { 0 };
+ u32x s[8] = { 0 };
for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
{
diff --git a/src/modules/module_04710.c b/src/modules/module_04710.c
index a229e280a..14ff2aee8 100644
--- a/src/modules/module_04710.c
+++ b/src/modules/module_04710.c
@@ -46,6 +46,20 @@ u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig,
const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+u32 module_salt_min (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+ const u32 salt_min = 8;
+
+ return salt_min;
+}
+
+u32 module_salt_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+ const u32 salt_max = 8;
+
+ return salt_max;
+}
+
int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
{
u32 *digest = (u32 *) digest_buf;
@@ -212,8 +226,8 @@ void module_init (module_ctx_t *module_ctx)
module_ctx->module_pwdump_column = MODULE_DEFAULT;
module_ctx->module_pw_max = MODULE_DEFAULT;
module_ctx->module_pw_min = MODULE_DEFAULT;
- module_ctx->module_salt_max = MODULE_DEFAULT;
- module_ctx->module_salt_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = module_salt_max;
+ module_ctx->module_salt_min = module_salt_min;
module_ctx->module_salt_type = module_salt_type;
module_ctx->module_separator = MODULE_DEFAULT;
module_ctx->module_st_hash = module_st_hash;
From ff8c3ed8abef195fcae3d9b3ffd737d4bb621a8f Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Wed, 31 Jul 2019 20:52:10 +0200
Subject: [PATCH 060/113] Added hash-mode 4710 optimized kernels
---
OpenCL/m04710_a0-optimized.cl | 651 ++++++++++++++++++++++
OpenCL/m04710_a1-optimized.cl | 759 ++++++++++++++++++++++++++
OpenCL/m04710_a3-optimized.cl | 999 ++++++++++++++++++++++++++++++++++
3 files changed, 2409 insertions(+)
create mode 100644 OpenCL/m04710_a0-optimized.cl
create mode 100644 OpenCL/m04710_a1-optimized.cl
create mode 100644 OpenCL/m04710_a3-optimized.cl
diff --git a/OpenCL/m04710_a0-optimized.cl b/OpenCL/m04710_a0-optimized.cl
new file mode 100644
index 000000000..ab2657798
--- /dev/null
+++ b/OpenCL/m04710_a0-optimized.cl
@@ -0,0 +1,651 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04710_m04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ u32 salt_buf0[2];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ w3[2] = out_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5(pass)
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * append salt + sha1
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = salt_buf0[0];
+ u32x w9_t = salt_buf0[1];
+ u32x wa_t = 0x80000000;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 40 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_M_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m04710_m08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04710_m16 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04710_s04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ u32 salt_buf0[2];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ w3[2] = out_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5(pass)
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * append salt + sha1
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = salt_buf0[0];
+ u32x w9_t = salt_buf0[1];
+ u32x wa_t = 0x80000000;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 40 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+ if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_S_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m04710_s08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04710_s16 (KERN_ATTR_RULES ())
+{
+}
diff --git a/OpenCL/m04710_a1-optimized.cl b/OpenCL/m04710_a1-optimized.cl
new file mode 100644
index 000000000..38ab761ee
--- /dev/null
+++ b/OpenCL/m04710_a1-optimized.cl
@@ -0,0 +1,759 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ u32 salt_buf0[2];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = pw_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5(pass)
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * append salt + sha1
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = salt_buf0[0];
+ u32x w9_t = salt_buf0[1];
+ u32x wa_t = 0x80000000;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 40 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_M_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m04710_m08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m04710_m16 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ u32 salt_buf0[2];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = pw_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5(pass)
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * append salt + sha1
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = salt_buf0[0];
+ u32x w9_t = salt_buf0[1];
+ u32x wa_t = 0x80000000;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 40 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+ if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_S_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m04710_s08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m04710_s16 (KERN_ATTR_BASIC ())
+{
+}
diff --git a/OpenCL/m04710_a3-optimized.cl b/OpenCL/m04710_a3-optimized.cl
new file mode 100644
index 000000000..cd5ad074b
--- /dev/null
+++ b/OpenCL/m04710_a3-optimized.cl
@@ -0,0 +1,999 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+DECLSPEC void m04710m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ u32 salt_buf0[2];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ u32x w0_t = w0lr;
+ u32x w1_t = w0[1];
+ u32x w2_t = w0[2];
+ u32x w3_t = w0[3];
+ u32x w4_t = w1[0];
+ u32x w5_t = w1[1];
+ u32x w6_t = w1[2];
+ u32x w7_t = w1[3];
+ u32x w8_t = w2[0];
+ u32x w9_t = w2[1];
+ u32x wa_t = w2[2];
+ u32x wb_t = w2[3];
+ u32x wc_t = w3[0];
+ u32x wd_t = w3[1];
+ u32x we_t = w3[2];
+ u32x wf_t = w3[3];
+
+ /**
+ * md5(pass)
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * append salt + sha1
+ */
+
+ w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ w8_t = salt_buf0[0];
+ w9_t = salt_buf0[1];
+ wa_t = 0x80000000;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 40 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_M_SIMD (d, e, c, b);
+ }
+}
+
+DECLSPEC void m04710s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ u32 salt_buf0[2];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ u32x w0_t = w0lr;
+ u32x w1_t = w0[1];
+ u32x w2_t = w0[2];
+ u32x w3_t = w0[3];
+ u32x w4_t = w1[0];
+ u32x w5_t = w1[1];
+ u32x w6_t = w1[2];
+ u32x w7_t = w1[3];
+ u32x w8_t = w2[0];
+ u32x w9_t = w2[1];
+ u32x wa_t = w2[2];
+ u32x wb_t = w2[3];
+ u32x wc_t = w3[0];
+ u32x wd_t = w3[1];
+ u32x we_t = w3[2];
+ u32x wf_t = w3[3];
+
+ /**
+ * md5(pass)
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * append salt + sha1
+ */
+
+ w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ w8_t = salt_buf0[0];
+ w9_t = salt_buf0[1];
+ wa_t = 0x80000000;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 40 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+ if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_S_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_m08 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_m16 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = pws[gid].i[14];
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_s08 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_s16 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = pws[gid].i[14];
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
From d794d662c6ee811f6ad22d44c274ef2e29a65c90 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Thu, 1 Aug 2019 02:38:43 +0200
Subject: [PATCH 061/113] Added hash-mode 21100 optimized kernels
---
OpenCL/m21100_a0-optimized.cl | 781 ++++++++++++++++++++++++
OpenCL/m21100_a1-optimized.cl | 895 +++++++++++++++++++++++++++
OpenCL/m21100_a3-optimized.cl | 1061 +++++++++++++++++++++++++++++++++
src/modules/module_21100.c | 6 +-
4 files changed, 2740 insertions(+), 3 deletions(-)
create mode 100644 OpenCL/m21100_a0-optimized.cl
create mode 100644 OpenCL/m21100_a1-optimized.cl
create mode 100644 OpenCL/m21100_a3-optimized.cl
diff --git a/OpenCL/m21100_a0-optimized.cl b/OpenCL/m21100_a0-optimized.cl
new file mode 100644
index 000000000..810899b66
--- /dev/null
+++ b/OpenCL/m21100_a0-optimized.cl
@@ -0,0 +1,781 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m21100_m04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+ salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+ salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+ salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+ salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+ salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
+ salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
+ salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
+ salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
+ salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
+ salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
+ salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
+ salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
+ salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
+ salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
+ salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ append_0x80_4x4_S (salt_buf0, salt_buf1, salt_buf2, salt_buf3, salt_len);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ /**
+ * append salt
+ */
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = salt_buf1[0];
+ s1[1] = salt_buf1[1];
+ s1[2] = salt_buf1[2];
+ s1[3] = salt_buf1[3];
+ s2[0] = salt_buf2[0];
+ s2[1] = salt_buf2[1];
+ s2[2] = salt_buf2[2];
+ s2[3] = salt_buf2[3];
+ s3[0] = salt_buf3[0];
+ s3[1] = salt_buf3[1];
+ s3[2] = salt_buf3[2];
+ s3[3] = salt_buf3[3];
+
+ switch_buffer_by_offset_le_VV (s0, s1, s2, s3, out_len);
+
+ const u32x pw_salt_len = out_len + salt_len;
+
+ w0[0] |= s0[0];
+ w0[1] |= s0[1];
+ w0[2] |= s0[2];
+ w0[3] |= s0[3];
+ w1[0] |= s1[0];
+ w1[1] |= s1[1];
+ w1[2] |= s1[2];
+ w1[3] |= s1[3];
+ w2[0] |= s2[0];
+ w2[1] |= s2[1];
+ w2[2] |= s2[2];
+ w2[3] |= s2[3];
+ w3[0] |= s3[0];
+ w3[1] |= s3[1];
+ w3[2] = pw_salt_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha1
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0x80000000;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 32 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_M_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m21100_m08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m21100_m16 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m21100_s04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+ salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+ salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+ salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+ salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+ salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
+ salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
+ salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
+ salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
+ salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
+ salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
+ salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
+ salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
+ salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
+ salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
+ salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ append_0x80_4x4_S (salt_buf0, salt_buf1, salt_buf2, salt_buf3, salt_len);
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ /**
+ * append salt
+ */
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = salt_buf1[0];
+ s1[1] = salt_buf1[1];
+ s1[2] = salt_buf1[2];
+ s1[3] = salt_buf1[3];
+ s2[0] = salt_buf2[0];
+ s2[1] = salt_buf2[1];
+ s2[2] = salt_buf2[2];
+ s2[3] = salt_buf2[3];
+ s3[0] = salt_buf3[0];
+ s3[1] = salt_buf3[1];
+ s3[2] = salt_buf3[2];
+ s3[3] = salt_buf3[3];
+
+ switch_buffer_by_offset_le_VV (s0, s1, s2, s3, out_len);
+
+ const u32x pw_salt_len = out_len + salt_len;
+
+ w0[0] |= s0[0];
+ w0[1] |= s0[1];
+ w0[2] |= s0[2];
+ w0[3] |= s0[3];
+ w1[0] |= s1[0];
+ w1[1] |= s1[1];
+ w1[2] |= s1[2];
+ w1[3] |= s1[3];
+ w2[0] |= s2[0];
+ w2[1] |= s2[1];
+ w2[2] |= s2[2];
+ w2[3] |= s2[3];
+ w3[0] |= s3[0];
+ w3[1] |= s3[1];
+ w3[2] = pw_salt_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha1
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0x80000000;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 32 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+ if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_S_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m21100_s08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m21100_s16 (KERN_ATTR_RULES ())
+{
+}
diff --git a/OpenCL/m21100_a1-optimized.cl b/OpenCL/m21100_a1-optimized.cl
new file mode 100644
index 000000000..815bb508f
--- /dev/null
+++ b/OpenCL/m21100_a1-optimized.cl
@@ -0,0 +1,895 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m21100_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+ salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+ salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+ salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+ salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+ salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
+ salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
+ salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
+ salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
+ salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
+ salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
+ salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
+ salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
+ salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
+ salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
+ salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = wordl3[2] | wordr3[2];
+ w3[3] = wordl3[3] | wordr3[3];
+
+ /**
+ * append salt
+ */
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = salt_buf1[0];
+ s1[1] = salt_buf1[1];
+ s1[2] = salt_buf1[2];
+ s1[3] = salt_buf1[3];
+ s2[0] = salt_buf2[0];
+ s2[1] = salt_buf2[1];
+ s2[2] = salt_buf2[2];
+ s2[3] = salt_buf2[3];
+ s3[0] = salt_buf3[0];
+ s3[1] = salt_buf3[1];
+ s3[2] = salt_buf3[2];
+ s3[3] = salt_buf3[3];
+
+ switch_buffer_by_offset_le_VV (s0, s1, s2, s3, pw_len);
+
+ const u32x pw_salt_len = pw_len + salt_len;
+
+ w0[0] |= s0[0];
+ w0[1] |= s0[1];
+ w0[2] |= s0[2];
+ w0[3] |= s0[3];
+ w1[0] |= s1[0];
+ w1[1] |= s1[1];
+ w1[2] |= s1[2];
+ w1[3] |= s1[3];
+ w2[0] |= s2[0];
+ w2[1] |= s2[1];
+ w2[2] |= s2[2];
+ w2[3] |= s2[3];
+ w3[0] |= s3[0];
+ w3[1] |= s3[1];
+ w3[2] = pw_salt_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha1
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0x80000000;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 32 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_M_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m21100_m08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m21100_m16 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m21100_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+ salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+ salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+ salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+ salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+ salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
+ salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
+ salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
+ salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
+ salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
+ salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
+ salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
+ salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
+ salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
+ salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
+ salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = wordl3[2] | wordr3[2];
+ w3[3] = wordl3[3] | wordr3[3];
+
+ /**
+ * append salt
+ */
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = salt_buf1[0];
+ s1[1] = salt_buf1[1];
+ s1[2] = salt_buf1[2];
+ s1[3] = salt_buf1[3];
+ s2[0] = salt_buf2[0];
+ s2[1] = salt_buf2[1];
+ s2[2] = salt_buf2[2];
+ s2[3] = salt_buf2[3];
+ s3[0] = salt_buf3[0];
+ s3[1] = salt_buf3[1];
+ s3[2] = salt_buf3[2];
+ s3[3] = salt_buf3[3];
+
+ switch_buffer_by_offset_le_VV (s0, s1, s2, s3, pw_len);
+
+ const u32x pw_salt_len = pw_len + salt_len;
+
+ w0[0] |= s0[0];
+ w0[1] |= s0[1];
+ w0[2] |= s0[2];
+ w0[3] |= s0[3];
+ w1[0] |= s1[0];
+ w1[1] |= s1[1];
+ w1[2] |= s1[2];
+ w1[3] |= s1[3];
+ w2[0] |= s2[0];
+ w2[1] |= s2[1];
+ w2[2] |= s2[2];
+ w2[3] |= s2[3];
+ w3[0] |= s3[0];
+ w3[1] |= s3[1];
+ w3[2] = pw_salt_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha1
+ */
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0x80000000;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 32 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+ if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_S_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m21100_s08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m21100_s16 (KERN_ATTR_BASIC ())
+{
+}
diff --git a/OpenCL/m21100_a3-optimized.cl b/OpenCL/m21100_a3-optimized.cl
new file mode 100644
index 000000000..4d83834cf
--- /dev/null
+++ b/OpenCL/m21100_a3-optimized.cl
@@ -0,0 +1,1061 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+DECLSPEC void m21100m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+ salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+ salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+ salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+ salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+ salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
+ salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
+ salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
+ salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
+ salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
+ salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
+ salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
+ salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
+ salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
+ salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
+ salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+ const u32 pw_salt_len = pw_len + salt_len;
+
+ /**
+ * append salt
+ */
+
+ u32 salt_buf0_t[4];
+ u32 salt_buf1_t[4];
+ u32 salt_buf2_t[4];
+ u32 salt_buf3_t[4];
+
+ salt_buf0_t[0] = salt_buf0[0];
+ salt_buf0_t[1] = salt_buf0[1];
+ salt_buf0_t[2] = salt_buf0[2];
+ salt_buf0_t[3] = salt_buf0[3];
+ salt_buf1_t[0] = salt_buf1[0];
+ salt_buf1_t[1] = salt_buf1[1];
+ salt_buf1_t[2] = salt_buf1[2];
+ salt_buf1_t[3] = salt_buf1[3];
+ salt_buf2_t[0] = salt_buf2[0];
+ salt_buf2_t[1] = salt_buf2[1];
+ salt_buf2_t[2] = salt_buf2[2];
+ salt_buf2_t[3] = salt_buf2[3];
+ salt_buf3_t[0] = salt_buf3[0];
+ salt_buf3_t[1] = salt_buf3[1];
+ salt_buf3_t[2] = salt_buf3[2];
+ salt_buf3_t[3] = salt_buf3[3];
+
+ append_0x80_4x4_S (salt_buf0_t, salt_buf1_t, salt_buf2_t, salt_buf3_t, salt_len);
+
+ switch_buffer_by_offset_le_S (salt_buf0_t, salt_buf1_t, salt_buf2_t, salt_buf3_t, pw_len);
+
+ w0[0] |= salt_buf0_t[0];
+ w0[1] |= salt_buf0_t[1];
+ w0[2] |= salt_buf0_t[2];
+ w0[3] |= salt_buf0_t[3];
+ w1[0] |= salt_buf1_t[0];
+ w1[1] |= salt_buf1_t[1];
+ w1[2] |= salt_buf1_t[2];
+ w1[3] |= salt_buf1_t[3];
+ w2[0] |= salt_buf2_t[0];
+ w2[1] |= salt_buf2_t[1];
+ w2[2] |= salt_buf2_t[2];
+ w2[3] |= salt_buf2_t[3];
+ w3[0] |= salt_buf3_t[0];
+ w3[1] |= salt_buf3_t[1];
+ w3[2] = pw_salt_len * 8;
+ w3[3] = 0;
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ u32x w0_t = w0lr;
+ u32x w1_t = w0[1];
+ u32x w2_t = w0[2];
+ u32x w3_t = w0[3];
+ u32x w4_t = w1[0];
+ u32x w5_t = w1[1];
+ u32x w6_t = w1[2];
+ u32x w7_t = w1[3];
+ u32x w8_t = w2[0];
+ u32x w9_t = w2[1];
+ u32x wa_t = w2[2];
+ u32x wb_t = w2[3];
+ u32x wc_t = w3[0];
+ u32x wd_t = w3[1];
+ u32x we_t = w3[2];
+ u32x wf_t = w3[3];
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha1
+ */
+
+ w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ w8_t = 0x80000000;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 32 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_M_SIMD (d, e, c, b);
+ }
+}
+
+DECLSPEC void m21100s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ u32x w0_t = w0lr;
+ u32x w1_t = w0[1];
+ u32x w2_t = w0[2];
+ u32x w3_t = w0[3];
+ u32x w4_t = w1[0];
+ u32x w5_t = w1[1];
+ u32x w6_t = w1[2];
+ u32x w7_t = w1[3];
+ u32x w8_t = w2[0];
+ u32x w9_t = w2[1];
+ u32x wa_t = w2[2];
+ u32x wb_t = w2[3];
+ u32x wc_t = w3[0];
+ u32x wd_t = w3[1];
+ u32x we_t = w3[2];
+ u32x wf_t = w3[3];
+
+ /**
+ * md5
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ /*
+ * sha1
+ */
+
+ w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ w8_t = 0x80000000;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 32 * 8;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+ if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_S_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m21100_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m21100m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m21100_m08 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m21100m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m21100_m16 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = pws[gid].i[14];
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m21100m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m21100_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m21100s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m21100_s08 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m21100s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m21100_s16 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = pws[gid].i[14];
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m21100s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
diff --git a/src/modules/module_21100.c b/src/modules/module_21100.c
index b03986550..34ed11ea1 100644
--- a/src/modules/module_21100.c
+++ b/src/modules/module_21100.c
@@ -26,9 +26,9 @@ static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_APPENDED_SALT
| OPTI_TYPE_RAW_HASH;
static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE
- | OPTS_TYPE_PT_ADD80
- | OPTS_TYPE_PT_ADDBITS14;
-static const u32 SALT_TYPE = SALT_TYPE_EMBEDDED;
+ | OPTS_TYPE_ST_ADD80
+ | OPTS_TYPE_ST_ADDBITS14;
+static const u32 SALT_TYPE = SALT_TYPE_GENERIC;
static const char *ST_PASS = "hashcat";
static const char *ST_HASH = "aade80a61c6e3cd3cac614f47c1991e0a87dd028:6";
From 7c08184ea59858083763c366aa67a29217754f4d Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Thu, 1 Aug 2019 03:10:47 +0200
Subject: [PATCH 062/113] optimizing 21200 pure kernels: move sha1(salt)
outside the loop
---
OpenCL/m21200_a0-pure.cl | 56 ++++++++++++++++++++--------------------
OpenCL/m21200_a1-pure.cl | 56 ++++++++++++++++++++--------------------
OpenCL/m21200_a3-pure.cl | 56 ++++++++++++++++++++--------------------
3 files changed, 84 insertions(+), 84 deletions(-)
diff --git a/OpenCL/m21200_a0-pure.cl b/OpenCL/m21200_a0-pure.cl
index 2ebe15969..c06536b58 100644
--- a/OpenCL/m21200_a0-pure.cl
+++ b/OpenCL/m21200_a0-pure.cl
@@ -73,6 +73,20 @@ KERNEL_FQ void m21200_mxx (KERN_ATTR_RULES ())
s[idx] = salt_bufs[salt_pos].salt_buf[idx];
}
+ sha1_ctx_t ctx0;
+
+ sha1_init (&ctx0);
+
+ sha1_update_swap (&ctx0, s, salt_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a0 = ctx0.h[0];
+ const u32 b0 = ctx0.h[1];
+ const u32 c0 = ctx0.h[2];
+ const u32 d0 = ctx0.h[3];
+ const u32 e0 = ctx0.h[4];
+
/**
* loop
*/
@@ -88,20 +102,6 @@ KERNEL_FQ void m21200_mxx (KERN_ATTR_RULES ())
tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
- sha1_ctx_t ctx0;
-
- sha1_init (&ctx0);
-
- sha1_update_swap (&ctx0, s, salt_len);
-
- sha1_final (&ctx0);
-
- const u32 a0 = ctx0.h[0];
- const u32 b0 = ctx0.h[1];
- const u32 c0 = ctx0.h[2];
- const u32 d0 = ctx0.h[3];
- const u32 e0 = ctx0.h[4];
-
md5_ctx_t ctx1;
md5_init (&ctx1);
@@ -244,6 +244,20 @@ KERNEL_FQ void m21200_sxx (KERN_ATTR_RULES ())
s[idx] = salt_bufs[salt_pos].salt_buf[idx];
}
+ sha1_ctx_t ctx0;
+
+ sha1_init (&ctx0);
+
+ sha1_update_swap (&ctx0, s, salt_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a0 = ctx0.h[0];
+ const u32 b0 = ctx0.h[1];
+ const u32 c0 = ctx0.h[2];
+ const u32 d0 = ctx0.h[3];
+ const u32 e0 = ctx0.h[4];
+
/**
* loop
*/
@@ -259,20 +273,6 @@ KERNEL_FQ void m21200_sxx (KERN_ATTR_RULES ())
tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
- sha1_ctx_t ctx0;
-
- sha1_init (&ctx0);
-
- sha1_update_swap (&ctx0, s, salt_len);
-
- sha1_final (&ctx0);
-
- const u32 a0 = ctx0.h[0];
- const u32 b0 = ctx0.h[1];
- const u32 c0 = ctx0.h[2];
- const u32 d0 = ctx0.h[3];
- const u32 e0 = ctx0.h[4];
-
md5_ctx_t ctx1;
md5_init (&ctx1);
diff --git a/OpenCL/m21200_a1-pure.cl b/OpenCL/m21200_a1-pure.cl
index 574cc528b..c06f0d633 100644
--- a/OpenCL/m21200_a1-pure.cl
+++ b/OpenCL/m21200_a1-pure.cl
@@ -69,6 +69,20 @@ KERNEL_FQ void m21200_mxx (KERN_ATTR_BASIC ())
s[idx] = salt_bufs[salt_pos].salt_buf[idx];
}
+ sha1_ctx_t ctx0;
+
+ sha1_init (&ctx0);
+
+ sha1_update_swap (&ctx0, s, salt_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a0 = ctx0.h[0];
+ const u32 b0 = ctx0.h[1];
+ const u32 c0 = ctx0.h[2];
+ const u32 d0 = ctx0.h[3];
+ const u32 e0 = ctx0.h[4];
+
md5_ctx_t ctx11;
md5_init (&ctx11);
@@ -86,20 +100,6 @@ KERNEL_FQ void m21200_mxx (KERN_ATTR_BASIC ())
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
{
- sha1_ctx_t ctx0;
-
- sha1_init (&ctx0);
-
- sha1_update_swap (&ctx0, s, salt_len);
-
- sha1_final (&ctx0);
-
- const u32 a0 = ctx0.h[0];
- const u32 b0 = ctx0.h[1];
- const u32 c0 = ctx0.h[2];
- const u32 d0 = ctx0.h[3];
- const u32 e0 = ctx0.h[4];
-
md5_ctx_t ctx1 = ctx11;
md5_update_global (&ctx1, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
@@ -238,6 +238,20 @@ KERNEL_FQ void m21200_sxx (KERN_ATTR_BASIC ())
s[idx] = salt_bufs[salt_pos].salt_buf[idx];
}
+ sha1_ctx_t ctx0;
+
+ sha1_init (&ctx0);
+
+ sha1_update_swap (&ctx0, s, salt_len);
+
+ sha1_final (&ctx0);
+
+ const u32 a0 = ctx0.h[0];
+ const u32 b0 = ctx0.h[1];
+ const u32 c0 = ctx0.h[2];
+ const u32 d0 = ctx0.h[3];
+ const u32 e0 = ctx0.h[4];
+
md5_ctx_t ctx11;
md5_init (&ctx11);
@@ -255,20 +269,6 @@ KERNEL_FQ void m21200_sxx (KERN_ATTR_BASIC ())
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
{
- sha1_ctx_t ctx0;
-
- sha1_init (&ctx0);
-
- sha1_update_swap (&ctx0, s, salt_len);
-
- sha1_final (&ctx0);
-
- const u32 a0 = ctx0.h[0];
- const u32 b0 = ctx0.h[1];
- const u32 c0 = ctx0.h[2];
- const u32 d0 = ctx0.h[3];
- const u32 e0 = ctx0.h[4];
-
md5_ctx_t ctx1 = ctx11;
md5_update_global (&ctx1, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
diff --git a/OpenCL/m21200_a3-pure.cl b/OpenCL/m21200_a3-pure.cl
index 1b097b9af..a2206dcc8 100644
--- a/OpenCL/m21200_a3-pure.cl
+++ b/OpenCL/m21200_a3-pure.cl
@@ -78,6 +78,20 @@ KERNEL_FQ void m21200_mxx (KERN_ATTR_VECTOR ())
s[idx] = salt_bufs[salt_pos].salt_buf[idx];
}
+ sha1_ctx_t ctx0;
+
+ sha1_init (&ctx0);
+
+ sha1_update_swap (&ctx0, s, salt_len);
+
+ sha1_final (&ctx0);
+
+ const u32x a0 = ctx0.h[0];
+ const u32x b0 = ctx0.h[1];
+ const u32x c0 = ctx0.h[2];
+ const u32x d0 = ctx0.h[3];
+ const u32x e0 = ctx0.h[4];
+
/**
* loop
*/
@@ -97,20 +111,6 @@ KERNEL_FQ void m21200_mxx (KERN_ATTR_VECTOR ())
w[0] = w0;
- sha1_ctx_vector_t ctx0;
-
- sha1_init_vector (&ctx0);
-
- sha1_update_vector_swap (&ctx0, s, salt_len);
-
- sha1_final_vector (&ctx0);
-
- const u32x a0 = ctx0.h[0];
- const u32x b0 = ctx0.h[1];
- const u32x c0 = ctx0.h[2];
- const u32x d0 = ctx0.h[3];
- const u32x e0 = ctx0.h[4];
-
md5_ctx_vector_t ctx1;
md5_init_vector (&ctx1);
@@ -260,6 +260,20 @@ KERNEL_FQ void m21200_sxx (KERN_ATTR_VECTOR ())
s[idx] = salt_bufs[salt_pos].salt_buf[idx];
}
+ sha1_ctx_t ctx0;
+
+ sha1_init (&ctx0);
+
+ sha1_update_swap (&ctx0, s, salt_len);
+
+ sha1_final (&ctx0);
+
+ const u32x a0 = ctx0.h[0];
+ const u32x b0 = ctx0.h[1];
+ const u32x c0 = ctx0.h[2];
+ const u32x d0 = ctx0.h[3];
+ const u32x e0 = ctx0.h[4];
+
/**
* loop
*/
@@ -279,20 +293,6 @@ KERNEL_FQ void m21200_sxx (KERN_ATTR_VECTOR ())
w[0] = w0;
- sha1_ctx_vector_t ctx0;
-
- sha1_init_vector (&ctx0);
-
- sha1_update_vector_swap (&ctx0, s, salt_len);
-
- sha1_final_vector (&ctx0);
-
- const u32x a0 = ctx0.h[0];
- const u32x b0 = ctx0.h[1];
- const u32x c0 = ctx0.h[2];
- const u32x d0 = ctx0.h[3];
- const u32x e0 = ctx0.h[4];
-
md5_ctx_vector_t ctx1;
md5_init_vector (&ctx1);
From 7e91bff5af82db685e22cda14f6101a2e6b7df42 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Thu, 1 Aug 2019 05:17:11 +0200
Subject: [PATCH 063/113] Added hash-mode 21200 optimized kernels
---
OpenCL/m21200_a0-optimized.cl | 1297 ++++++++++++++++++++++++++
OpenCL/m21200_a1-optimized.cl | 1411 ++++++++++++++++++++++++++++
OpenCL/m21200_a3-optimized.cl | 1629 +++++++++++++++++++++++++++++++++
3 files changed, 4337 insertions(+)
create mode 100644 OpenCL/m21200_a0-optimized.cl
create mode 100644 OpenCL/m21200_a1-optimized.cl
create mode 100644 OpenCL/m21200_a3-optimized.cl
diff --git a/OpenCL/m21200_a0-optimized.cl b/OpenCL/m21200_a0-optimized.cl
new file mode 100644
index 000000000..fe2cb311b
--- /dev/null
+++ b/OpenCL/m21200_a0-optimized.cl
@@ -0,0 +1,1297 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m21200_m04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+
+ salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+ salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+ salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+ salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+ salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+ salt_buf1[1] = 0;
+ salt_buf1[2] = 0;
+ salt_buf1[3] = 0;
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ append_0x80_2x4_S (salt_buf0, salt_buf1, salt_len);
+
+ /**
+ * sha1(salt)
+ */
+
+ u32x w0_t = hc_swap32 (salt_buf0[0]);
+ u32x w1_t = hc_swap32 (salt_buf0[1]);
+ u32x w2_t = hc_swap32 (salt_buf0[2]);
+ u32x w3_t = hc_swap32 (salt_buf0[3]);
+ u32x w4_t = hc_swap32 (salt_buf1[0]);
+ u32x w5_t = 0;
+ u32x w6_t = 0;
+ u32x w7_t = 0;
+ u32x w8_t = 0;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = salt_len * 8;
+
+ u32x a = SHA1M_A;
+ u32x b = SHA1M_B;
+ u32x c = SHA1M_C;
+ u32x d = SHA1M_D;
+ u32x e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += SHA1M_A;
+ b += SHA1M_B;
+ c += SHA1M_C;
+ d += SHA1M_D;
+ e += SHA1M_E;
+
+ const u32x a0 = a;
+ const u32x b0 = b;
+ const u32x c0 = c;
+ const u32x d0 = d;
+ const u32x e0 = e;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ /**
+ * md5
+ */
+
+ w0_t = w0[0];
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = out_len * 8;
+ wf_t = 0;
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ const u32x a1 = hc_swap32 (a);
+ const u32x b1 = hc_swap32 (b);
+ const u32x c1 = hc_swap32 (c);
+ const u32x d1 = hc_swap32 (d);
+
+ /**
+ * md5
+ */
+
+ w0_t = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w1_t = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w2_t = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w3_t = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w4_t = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w5_t = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w6_t = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w7_t = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w8_t = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w9_t = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+
+ // ctx len 40, pos 40
+
+ w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_le (w0, w1, w2, w3, _w0, _w1, _w2, _w3, 40);
+
+ w0_t |= w0[0];
+ w1_t |= w0[1];
+ w2_t |= w0[2];
+ w3_t |= w0[3];
+ w4_t |= w1[0];
+ w5_t |= w1[1];
+ w6_t |= w1[2];
+ w7_t |= w1[3];
+ w8_t |= w2[0];
+ w9_t |= w2[1];
+ wa_t |= w2[2];
+ wb_t |= w2[3];
+ wc_t |= w3[0];
+ wd_t |= w3[1];
+ we_t |= w3[2];
+ wf_t |= w3[3];
+
+ // md5 transform
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ u32x digest[4];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+
+ w0[0] = _w0[0];
+ w0[1] = _w0[1];
+ w0[2] = _w0[2];
+ w0[3] = _w0[3];
+ w1[0] = _w1[0];
+ w1[1] = _w1[1];
+ w1[2] = _w1[2];
+ w1[3] = _w1[3];
+ w2[0] = _w2[0];
+ w2[1] = _w2[1];
+ w2[2] = _w2[2];
+ w2[3] = _w2[3];
+ w3[0] = _w3[0];
+ w3[1] = _w3[1];
+ w3[2] = _w3[2];
+ w3[3] = _w3[3];
+
+ // ctx len 72, pos 8
+
+ append_0x80_4x4 (w0, w1, w2, w3, 8);
+
+ w3[2] = 72 * 8;
+ w3[3] = 0;
+
+ // md5 final transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = w0[0];
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = w3[2];
+ wf_t = w3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += digest[0] - MD5M_A;
+ b += digest[1] - MD5M_B;
+ c += digest[2] - MD5M_C;
+ d += digest[3] - MD5M_D;
+
+ COMPARE_M_SIMD (a, d, c, b);
+ }
+}
+
+KERNEL_FQ void m21200_m08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m21200_m16 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m21200_s04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+
+ salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+ salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+ salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+ salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+ salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+ salt_buf1[1] = 0;
+ salt_buf1[2] = 0;
+ salt_buf1[3] = 0;
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ append_0x80_2x4_S (salt_buf0, salt_buf1, salt_len);
+
+ /**
+ * sha1(salt)
+ */
+
+ u32x w0_t = hc_swap32 (salt_buf0[0]);
+ u32x w1_t = hc_swap32 (salt_buf0[1]);
+ u32x w2_t = hc_swap32 (salt_buf0[2]);
+ u32x w3_t = hc_swap32 (salt_buf0[3]);
+ u32x w4_t = hc_swap32 (salt_buf1[0]);
+ u32x w5_t = 0;
+ u32x w6_t = 0;
+ u32x w7_t = 0;
+ u32x w8_t = 0;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = salt_len * 8;
+
+ u32x a = SHA1M_A;
+ u32x b = SHA1M_B;
+ u32x c = SHA1M_C;
+ u32x d = SHA1M_D;
+ u32x e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += SHA1M_A;
+ b += SHA1M_B;
+ c += SHA1M_C;
+ d += SHA1M_D;
+ e += SHA1M_E;
+
+ const u32x a0 = a;
+ const u32x b0 = b;
+ const u32x c0 = c;
+ const u32x d0 = d;
+ const u32x e0 = e;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ /**
+ * md5
+ */
+
+ w0_t = w0[0];
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = out_len * 8;
+ wf_t = 0;
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ const u32x a1 = hc_swap32 (a);
+ const u32x b1 = hc_swap32 (b);
+ const u32x c1 = hc_swap32 (c);
+ const u32x d1 = hc_swap32 (d);
+
+ /**
+ * md5
+ */
+
+ w0_t = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w1_t = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w2_t = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w3_t = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w4_t = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w5_t = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w6_t = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w7_t = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w8_t = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w9_t = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+
+ // ctx len 40, pos 40
+
+ w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_le (w0, w1, w2, w3, _w0, _w1, _w2, _w3, 40);
+
+ w0_t |= w0[0];
+ w1_t |= w0[1];
+ w2_t |= w0[2];
+ w3_t |= w0[3];
+ w4_t |= w1[0];
+ w5_t |= w1[1];
+ w6_t |= w1[2];
+ w7_t |= w1[3];
+ w8_t |= w2[0];
+ w9_t |= w2[1];
+ wa_t |= w2[2];
+ wb_t |= w2[3];
+ wc_t |= w3[0];
+ wd_t |= w3[1];
+ we_t |= w3[2];
+ wf_t |= w3[3];
+
+ // md5 transform
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ u32x digest[4];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+
+ w0[0] = _w0[0];
+ w0[1] = _w0[1];
+ w0[2] = _w0[2];
+ w0[3] = _w0[3];
+ w1[0] = _w1[0];
+ w1[1] = _w1[1];
+ w1[2] = _w1[2];
+ w1[3] = _w1[3];
+ w2[0] = _w2[0];
+ w2[1] = _w2[1];
+ w2[2] = _w2[2];
+ w2[3] = _w2[3];
+ w3[0] = _w3[0];
+ w3[1] = _w3[1];
+ w3[2] = _w3[2];
+ w3[3] = _w3[3];
+
+ // ctx len 72, pos 8
+
+ append_0x80_4x4 (w0, w1, w2, w3, 8);
+
+ w3[2] = 72 * 8;
+ w3[3] = 0;
+
+ // md5 final transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = w0[0];
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = w3[2];
+ wf_t = w3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+
+ if (MATCHES_NONE_VS ((a+digest[0]-MD5M_A), search[0])) continue;
+
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += digest[0] - MD5M_A;
+ b += digest[1] - MD5M_B;
+ c += digest[2] - MD5M_C;
+ d += digest[3] - MD5M_D;
+
+ COMPARE_S_SIMD (a, d, c, b);
+ }
+}
+
+KERNEL_FQ void m21200_s08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m21200_s16 (KERN_ATTR_RULES ())
+{
+}
diff --git a/OpenCL/m21200_a1-optimized.cl b/OpenCL/m21200_a1-optimized.cl
new file mode 100644
index 000000000..4f835c979
--- /dev/null
+++ b/OpenCL/m21200_a1-optimized.cl
@@ -0,0 +1,1411 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m21200_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+
+ salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+ salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+ salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+ salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+ salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+ salt_buf1[1] = 0;
+ salt_buf1[2] = 0;
+ salt_buf1[3] = 0;
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ append_0x80_2x4_S (salt_buf0, salt_buf1, salt_len);
+
+ /**
+ * sha1(salt)
+ */
+
+ u32x w0_t = hc_swap32 (salt_buf0[0]);
+ u32x w1_t = hc_swap32 (salt_buf0[1]);
+ u32x w2_t = hc_swap32 (salt_buf0[2]);
+ u32x w3_t = hc_swap32 (salt_buf0[3]);
+ u32x w4_t = hc_swap32 (salt_buf1[0]);
+ u32x w5_t = 0;
+ u32x w6_t = 0;
+ u32x w7_t = 0;
+ u32x w8_t = 0;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = salt_len * 8;
+
+ u32x a = SHA1M_A;
+ u32x b = SHA1M_B;
+ u32x c = SHA1M_C;
+ u32x d = SHA1M_D;
+ u32x e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += SHA1M_A;
+ b += SHA1M_B;
+ c += SHA1M_C;
+ d += SHA1M_D;
+ e += SHA1M_E;
+
+ const u32x a0 = a;
+ const u32x b0 = b;
+ const u32x c0 = c;
+ const u32x d0 = d;
+ const u32x e0 = e;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = wordl3[2] | wordr3[2];
+ w3[3] = wordl3[3] | wordr3[3];
+
+ /**
+ * md5
+ */
+
+ w0_t = w0[0];
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = pw_len * 8;
+ wf_t = 0;
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ const u32x a1 = hc_swap32 (a);
+ const u32x b1 = hc_swap32 (b);
+ const u32x c1 = hc_swap32 (c);
+ const u32x d1 = hc_swap32 (d);
+
+ /**
+ * md5
+ */
+
+ w0_t = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w1_t = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w2_t = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w3_t = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w4_t = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w5_t = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w6_t = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w7_t = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w8_t = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w9_t = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+
+ // ctx len 40, pos 40
+
+ w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_le (w0, w1, w2, w3, _w0, _w1, _w2, _w3, 40);
+
+ w0_t |= w0[0];
+ w1_t |= w0[1];
+ w2_t |= w0[2];
+ w3_t |= w0[3];
+ w4_t |= w1[0];
+ w5_t |= w1[1];
+ w6_t |= w1[2];
+ w7_t |= w1[3];
+ w8_t |= w2[0];
+ w9_t |= w2[1];
+ wa_t |= w2[2];
+ wb_t |= w2[3];
+ wc_t |= w3[0];
+ wd_t |= w3[1];
+ we_t |= w3[2];
+ wf_t |= w3[3];
+
+ // md5 transform
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ u32x digest[4];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+
+ w0[0] = _w0[0];
+ w0[1] = _w0[1];
+ w0[2] = _w0[2];
+ w0[3] = _w0[3];
+ w1[0] = _w1[0];
+ w1[1] = _w1[1];
+ w1[2] = _w1[2];
+ w1[3] = _w1[3];
+ w2[0] = _w2[0];
+ w2[1] = _w2[1];
+ w2[2] = _w2[2];
+ w2[3] = _w2[3];
+ w3[0] = _w3[0];
+ w3[1] = _w3[1];
+ w3[2] = _w3[2];
+ w3[3] = _w3[3];
+
+ // ctx len 72, pos 8
+
+ append_0x80_4x4 (w0, w1, w2, w3, 8);
+
+ w3[2] = 72 * 8;
+ w3[3] = 0;
+
+ // md5 final transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = w0[0];
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = w3[2];
+ wf_t = w3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += digest[0] - MD5M_A;
+ b += digest[1] - MD5M_B;
+ c += digest[2] - MD5M_C;
+ d += digest[3] - MD5M_D;
+
+ COMPARE_M_SIMD (a, d, c, b);
+ }
+}
+
+KERNEL_FQ void m21200_m08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m21200_m16 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m21200_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+
+ salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+ salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+ salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+ salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+ salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+ salt_buf1[1] = 0;
+ salt_buf1[2] = 0;
+ salt_buf1[3] = 0;
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ append_0x80_2x4_S (salt_buf0, salt_buf1, salt_len);
+
+ /**
+ * sha1(salt)
+ */
+
+ u32x w0_t = hc_swap32 (salt_buf0[0]);
+ u32x w1_t = hc_swap32 (salt_buf0[1]);
+ u32x w2_t = hc_swap32 (salt_buf0[2]);
+ u32x w3_t = hc_swap32 (salt_buf0[3]);
+ u32x w4_t = hc_swap32 (salt_buf1[0]);
+ u32x w5_t = 0;
+ u32x w6_t = 0;
+ u32x w7_t = 0;
+ u32x w8_t = 0;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = salt_len * 8;
+
+ u32x a = SHA1M_A;
+ u32x b = SHA1M_B;
+ u32x c = SHA1M_C;
+ u32x d = SHA1M_D;
+ u32x e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += SHA1M_A;
+ b += SHA1M_B;
+ c += SHA1M_C;
+ d += SHA1M_D;
+ e += SHA1M_E;
+
+ const u32x a0 = a;
+ const u32x b0 = b;
+ const u32x c0 = c;
+ const u32x d0 = d;
+ const u32x e0 = e;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = wordl3[2] | wordr3[2];
+ w3[3] = wordl3[3] | wordr3[3];
+
+ /**
+ * md5
+ */
+
+ w0_t = w0[0];
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = pw_len * 8;
+ wf_t = 0;
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ const u32x a1 = hc_swap32 (a);
+ const u32x b1 = hc_swap32 (b);
+ const u32x c1 = hc_swap32 (c);
+ const u32x d1 = hc_swap32 (d);
+
+ /**
+ * md5
+ */
+
+ w0_t = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w1_t = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w2_t = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w3_t = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w4_t = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w5_t = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w6_t = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w7_t = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w8_t = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w9_t = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+
+ // ctx len 40, pos 40
+
+ w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_le (w0, w1, w2, w3, _w0, _w1, _w2, _w3, 40);
+
+ w0_t |= w0[0];
+ w1_t |= w0[1];
+ w2_t |= w0[2];
+ w3_t |= w0[3];
+ w4_t |= w1[0];
+ w5_t |= w1[1];
+ w6_t |= w1[2];
+ w7_t |= w1[3];
+ w8_t |= w2[0];
+ w9_t |= w2[1];
+ wa_t |= w2[2];
+ wb_t |= w2[3];
+ wc_t |= w3[0];
+ wd_t |= w3[1];
+ we_t |= w3[2];
+ wf_t |= w3[3];
+
+ // md5 transform
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ u32x digest[4];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+
+ w0[0] = _w0[0];
+ w0[1] = _w0[1];
+ w0[2] = _w0[2];
+ w0[3] = _w0[3];
+ w1[0] = _w1[0];
+ w1[1] = _w1[1];
+ w1[2] = _w1[2];
+ w1[3] = _w1[3];
+ w2[0] = _w2[0];
+ w2[1] = _w2[1];
+ w2[2] = _w2[2];
+ w2[3] = _w2[3];
+ w3[0] = _w3[0];
+ w3[1] = _w3[1];
+ w3[2] = _w3[2];
+ w3[3] = _w3[3];
+
+ // ctx len 72, pos 8
+
+ append_0x80_4x4 (w0, w1, w2, w3, 8);
+
+ w3[2] = 72 * 8;
+ w3[3] = 0;
+
+ // md5 final transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = w0[0];
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = w3[2];
+ wf_t = w3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+
+ if (MATCHES_NONE_VS ((a+digest[0]-MD5M_A), search[0])) continue;
+
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += digest[0] - MD5M_A;
+ b += digest[1] - MD5M_B;
+ c += digest[2] - MD5M_C;
+ d += digest[3] - MD5M_D;
+
+ COMPARE_S_SIMD (a, d, c, b);
+ }
+}
+
+KERNEL_FQ void m21200_s08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m21200_s16 (KERN_ATTR_BASIC ())
+{
+}
diff --git a/OpenCL/m21200_a3-optimized.cl b/OpenCL/m21200_a3-optimized.cl
new file mode 100644
index 000000000..84f09e7d0
--- /dev/null
+++ b/OpenCL/m21200_a3-optimized.cl
@@ -0,0 +1,1629 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+DECLSPEC void m21200m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+
+ salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+ salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+ salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+ salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+ salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+ salt_buf1[1] = 0;
+ salt_buf1[2] = 0;
+ salt_buf1[3] = 0;
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ append_0x80_2x4_S (salt_buf0, salt_buf1, salt_len);
+
+ /**
+ * sha1(salt)
+ */
+
+ u32x w0_t = hc_swap32 (salt_buf0[0]);
+ u32x w1_t = hc_swap32 (salt_buf0[1]);
+ u32x w2_t = hc_swap32 (salt_buf0[2]);
+ u32x w3_t = hc_swap32 (salt_buf0[3]);
+ u32x w4_t = hc_swap32 (salt_buf1[0]);
+ u32x w5_t = 0;
+ u32x w6_t = 0;
+ u32x w7_t = 0;
+ u32x w8_t = 0;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = salt_len * 8;
+
+ u32x a = SHA1M_A;
+ u32x b = SHA1M_B;
+ u32x c = SHA1M_C;
+ u32x d = SHA1M_D;
+ u32x e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += SHA1M_A;
+ b += SHA1M_B;
+ c += SHA1M_C;
+ d += SHA1M_D;
+ e += SHA1M_E;
+
+ const u32x a0 = a;
+ const u32x b0 = b;
+ const u32x c0 = c;
+ const u32x d0 = d;
+ const u32x e0 = e;
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ /**
+ * md5
+ */
+
+ w0_t = w0lr;
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = pw_len * 8;
+ wf_t = 0;
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ const u32x a1 = hc_swap32 (a);
+ const u32x b1 = hc_swap32 (b);
+ const u32x c1 = hc_swap32 (c);
+ const u32x d1 = hc_swap32 (d);
+
+ /**
+ * md5
+ */
+
+ w0_t = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w1_t = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w2_t = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w3_t = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w4_t = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w5_t = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w6_t = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w7_t = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w8_t = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w9_t = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+
+ // ctx len 40, pos 40
+
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ _w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ u32x _c0[4] = { 0 };
+ u32x _c1[4] = { 0 };
+ u32x _c2[4] = { 0 };
+ u32x _c3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_le (_w0, _w1, _w2, _w3, _c0, _c1, _c2, _c3, 40);
+
+ w0_t |= _w0[0];
+ w1_t |= _w0[1];
+ w2_t |= _w0[2];
+ w3_t |= _w0[3];
+ w4_t |= _w1[0];
+ w5_t |= _w1[1];
+ w6_t |= _w1[2];
+ w7_t |= _w1[3];
+ w8_t |= _w2[0];
+ w9_t |= _w2[1];
+ wa_t |= _w2[2];
+ wb_t |= _w2[3];
+ wc_t |= _w3[0];
+ wd_t |= _w3[1];
+ we_t |= _w3[2];
+ wf_t |= _w3[3];
+
+ // md5 transform
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ u32x digest[4];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+
+ _w0[0] = _c0[0];
+ _w0[1] = _c0[1];
+ _w0[2] = _c0[2];
+ _w0[3] = _c0[3];
+ _w1[0] = _c1[0];
+ _w1[1] = _c1[1];
+ _w1[2] = _c1[2];
+ _w1[3] = _c1[3];
+ _w2[0] = _c2[0];
+ _w2[1] = _c2[1];
+ _w2[2] = _c2[2];
+ _w2[3] = _c2[3];
+ _w3[0] = _c3[0];
+ _w3[1] = _c3[1];
+ _w3[2] = _c3[2];
+ _w3[3] = _c3[3];
+
+ // ctx len 72, pos 8
+
+ append_0x80_4x4 (_w0, _w1, _w2, _w3, 8);
+
+ _w3[2] = 72 * 8;
+ _w3[3] = 0;
+
+ // md5 final transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _w0[0];
+ w1_t = _w0[1];
+ w2_t = _w0[2];
+ w3_t = _w0[3];
+ w4_t = _w1[0];
+ w5_t = _w1[1];
+ w6_t = _w1[2];
+ w7_t = _w1[3];
+ w8_t = _w2[0];
+ w9_t = _w2[1];
+ wa_t = _w2[2];
+ wb_t = _w2[3];
+ wc_t = _w3[0];
+ wd_t = _w3[1];
+ we_t = _w3[2];
+ wf_t = _w3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += digest[0] - MD5M_A;
+ b += digest[1] - MD5M_B;
+ c += digest[2] - MD5M_C;
+ d += digest[3] - MD5M_D;
+
+ COMPARE_M_SIMD (a, d, c, b);
+ }
+}
+
+DECLSPEC void m21200s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+
+ salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
+ salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
+ salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
+ salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
+ salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
+ salt_buf1[1] = 0;
+ salt_buf1[2] = 0;
+ salt_buf1[3] = 0;
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ append_0x80_2x4_S (salt_buf0, salt_buf1, salt_len);
+
+ /**
+ * sha1(salt)
+ */
+
+ u32x w0_t = hc_swap32 (salt_buf0[0]);
+ u32x w1_t = hc_swap32 (salt_buf0[1]);
+ u32x w2_t = hc_swap32 (salt_buf0[2]);
+ u32x w3_t = hc_swap32 (salt_buf0[3]);
+ u32x w4_t = hc_swap32 (salt_buf1[0]);
+ u32x w5_t = 0;
+ u32x w6_t = 0;
+ u32x w7_t = 0;
+ u32x w8_t = 0;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = salt_len * 8;
+
+ u32x a = SHA1M_A;
+ u32x b = SHA1M_B;
+ u32x c = SHA1M_C;
+ u32x d = SHA1M_D;
+ u32x e = SHA1M_E;
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ a += SHA1M_A;
+ b += SHA1M_B;
+ c += SHA1M_C;
+ d += SHA1M_D;
+ e += SHA1M_E;
+
+ const u32x a0 = a;
+ const u32x b0 = b;
+ const u32x c0 = c;
+ const u32x d0 = d;
+ const u32x e0 = e;
+
+if (gid == 0) printf("sha1(salt): %08x %08x %08x %08x %08x\n", a0, b0, c0, d0, e0);
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ /**
+ * md5
+ */
+
+ w0_t = w0lr;
+ w1_t = w0[1];
+ w2_t = w0[2];
+ w3_t = w0[3];
+ w4_t = w1[0];
+ w5_t = w1[1];
+ w6_t = w1[2];
+ w7_t = w1[3];
+ w8_t = w2[0];
+ w9_t = w2[1];
+ wa_t = w2[2];
+ wb_t = w2[3];
+ wc_t = w3[0];
+ wd_t = w3[1];
+ we_t = pw_len * 8;
+ wf_t = 0;
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ const u32x a1 = hc_swap32 (a);
+ const u32x b1 = hc_swap32 (b);
+ const u32x c1 = hc_swap32 (c);
+ const u32x d1 = hc_swap32 (d);
+
+ /**
+ * md5
+ */
+
+ w0_t = uint_to_hex_lower8 ((a0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 16) & 255) << 16;
+ w1_t = uint_to_hex_lower8 ((a0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a0 >> 0) & 255) << 16;
+ w2_t = uint_to_hex_lower8 ((b0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 16) & 255) << 16;
+ w3_t = uint_to_hex_lower8 ((b0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b0 >> 0) & 255) << 16;
+ w4_t = uint_to_hex_lower8 ((c0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 16) & 255) << 16;
+ w5_t = uint_to_hex_lower8 ((c0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c0 >> 0) & 255) << 16;
+ w6_t = uint_to_hex_lower8 ((d0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 16) & 255) << 16;
+ w7_t = uint_to_hex_lower8 ((d0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d0 >> 0) & 255) << 16;
+ w8_t = uint_to_hex_lower8 ((e0 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 16) & 255) << 16;
+ w9_t = uint_to_hex_lower8 ((e0 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((e0 >> 0) & 255) << 16;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+
+ // ctx len 40, pos 40
+
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ _w0[0] = uint_to_hex_lower8 ((a1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 16) & 255) << 16;
+ _w0[1] = uint_to_hex_lower8 ((a1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((a1 >> 0) & 255) << 16;
+ _w0[2] = uint_to_hex_lower8 ((b1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 16) & 255) << 16;
+ _w0[3] = uint_to_hex_lower8 ((b1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((b1 >> 0) & 255) << 16;
+ _w1[0] = uint_to_hex_lower8 ((c1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 16) & 255) << 16;
+ _w1[1] = uint_to_hex_lower8 ((c1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((c1 >> 0) & 255) << 16;
+ _w1[2] = uint_to_hex_lower8 ((d1 >> 24) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 16) & 255) << 16;
+ _w1[3] = uint_to_hex_lower8 ((d1 >> 8) & 255) << 0
+ | uint_to_hex_lower8 ((d1 >> 0) & 255) << 16;
+
+ _w2[0] = 0;
+ _w2[1] = 0;
+ _w2[2] = 0;
+ _w2[3] = 0;
+ _w3[0] = 0;
+ _w3[1] = 0;
+ _w3[2] = 0;
+ _w3[3] = 0;
+
+ u32x _c0[4] = { 0 };
+ u32x _c1[4] = { 0 };
+ u32x _c2[4] = { 0 };
+ u32x _c3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_le (_w0, _w1, _w2, _w3, _c0, _c1, _c2, _c3, 40);
+
+ w0_t |= _w0[0];
+ w1_t |= _w0[1];
+ w2_t |= _w0[2];
+ w3_t |= _w0[3];
+ w4_t |= _w1[0];
+ w5_t |= _w1[1];
+ w6_t |= _w1[2];
+ w7_t |= _w1[3];
+ w8_t |= _w2[0];
+ w9_t |= _w2[1];
+ wa_t |= _w2[2];
+ wb_t |= _w2[3];
+ wc_t |= _w3[0];
+ wd_t |= _w3[1];
+ we_t |= _w3[2];
+ wf_t |= _w3[3];
+
+ // md5 transform
+
+ a = MD5M_A;
+ b = MD5M_B;
+ c = MD5M_C;
+ d = MD5M_D;
+
+ u32x digest[4];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+
+ _w0[0] = _c0[0];
+ _w0[1] = _c0[1];
+ _w0[2] = _c0[2];
+ _w0[3] = _c0[3];
+ _w1[0] = _c1[0];
+ _w1[1] = _c1[1];
+ _w1[2] = _c1[2];
+ _w1[3] = _c1[3];
+ _w2[0] = _c2[0];
+ _w2[1] = _c2[1];
+ _w2[2] = _c2[2];
+ _w2[3] = _c2[3];
+ _w3[0] = _c3[0];
+ _w3[1] = _c3[1];
+ _w3[2] = _c3[2];
+ _w3[3] = _c3[3];
+
+ // ctx len 72, pos 8
+
+ append_0x80_4x4 (_w0, _w1, _w2, _w3, 8);
+
+ _w3[2] = 72 * 8;
+ _w3[3] = 0;
+
+ // md5 final transform
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+
+ w0_t = _w0[0];
+ w1_t = _w0[1];
+ w2_t = _w0[2];
+ w3_t = _w0[3];
+ w4_t = _w1[0];
+ w5_t = _w1[1];
+ w6_t = _w1[2];
+ w7_t = _w1[3];
+ w8_t = _w2[0];
+ w9_t = _w2[1];
+ wa_t = _w2[2];
+ wb_t = _w2[3];
+ wc_t = _w3[0];
+ wd_t = _w3[1];
+ we_t = _w3[2];
+ wf_t = _w3[3];
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+
+ if (MATCHES_NONE_VS ((a+digest[0]-MD5M_A), search[0])) continue;
+
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += digest[0] - MD5M_A;
+ b += digest[1] - MD5M_B;
+ c += digest[2] - MD5M_C;
+ d += digest[3] - MD5M_D;
+
+ COMPARE_S_SIMD (a, d, c, b);
+ }
+}
+
+KERNEL_FQ void m21200_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m21200m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m21200_m08 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m21200m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m21200_m16 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = pws[gid].i[14];
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m21200m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m21200_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m21200s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m21200_s08 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m21200s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m21200_s16 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = pws[gid].i[14];
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m21200s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
From 66337ee8f5625d1eac6a556cd865b9bcb60065fb Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Thu, 1 Aug 2019 15:11:47 +0200
Subject: [PATCH 064/113] update AuthMe patch (2)
---
docs/readme.txt | 3 +-
src/modules/module_20710.c | 107 ++++++++------------
src/modules/module_20711.c | 2 +-
tools/test_modules/m20710.pm | 46 +++++++++
tools/test_modules/{m20700.pm => m20711.pm} | 2 +-
5 files changed, 93 insertions(+), 67 deletions(-)
create mode 100644 tools/test_modules/m20710.pm
rename tools/test_modules/{m20700.pm => m20711.pm} (91%)
diff --git a/docs/readme.txt b/docs/readme.txt
index 71963b378..0b13ca5be 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -92,7 +92,8 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- sha512($salt.$pass)
- sha512(utf16le($pass).$salt)
- sha512($salt.utf16le($pass))
-- AuthMe - sha256(sha256($pass).$salt)
+- sha256(sha256($pass).$salt)
+- AuthMe sha256
- HMAC-MD5 (key = $pass)
- HMAC-MD5 (key = $salt)
- HMAC-SHA1 (key = $pass)
diff --git a/src/modules/module_20710.c b/src/modules/module_20710.c
index ea0ac2e6a..d71160c25 100644
--- a/src/modules/module_20710.c
+++ b/src/modules/module_20710.c
@@ -17,8 +17,8 @@ static const u32 DGST_POS1 = 7;
static const u32 DGST_POS2 = 2;
static const u32 DGST_POS3 = 6;
static const u32 DGST_SIZE = DGST_SIZE_4_8;
-static const u32 HASH_CATEGORY = HASH_CATEGORY_EAS;
-static const char *HASH_NAME = "AuthMe - sha256(sha256($pass).$salt)";
+static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH_SALTED;
+static const char *HASH_NAME = "sha256(sha256($pass).$salt)";
static const u64 KERN_TYPE = 20710;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
@@ -30,7 +30,7 @@ static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_BE
| OPTS_TYPE_PT_ADDBITS15;
static const u32 SALT_TYPE = SALT_TYPE_EMBEDDED;
static const char *ST_PASS = "hashcat";
-static const char *ST_HASH = "$SHA$7218532375810603$bfede293ecf6539211a7305ea218b9f3f608953130405cda9eaba6fb6250f824";
+static const char *ST_HASH = "bfede293ecf6539211a7305ea218b9f3f608953130405cda9eaba6fb6250f824:7218532375810603";
u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
@@ -54,51 +54,37 @@ u32 module_pw_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED con
return pw_max;
}
-static const char *SIGNATURE_AUTHME = "$SHA$";
-
int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
{
u32 *digest = (u32 *) digest_buf;
token_t token;
- token.token_cnt = 3;
+ token.token_cnt = 2;
- token.signatures_cnt = 1;
- token.signatures_buf[0] = SIGNATURE_AUTHME;
-
- token.len[0] = 5;
- token.attr[0] = TOKEN_ATTR_FIXED_LENGTH
- | TOKEN_ATTR_VERIFY_SIGNATURE;
-
- token.sep[1] = '$';
- token.len_min[1] = 16;
- token.len_max[1] = 16;
- token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH
+ token.sep[0] = hashconfig->separator;
+ token.len_min[0] = 64;
+ token.len_max[0] = 64;
+ token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
| TOKEN_ATTR_VERIFY_DIGIT;
- token.sep[2] = '$';
- token.len_min[2] = 64;
- token.len_max[2] = 64;
- token.attr[2] = TOKEN_ATTR_VERIFY_LENGTH
- | TOKEN_ATTR_VERIFY_HEX;
+ token.len_min[1] = SALT_MIN;
+ token.len_max[1] = SALT_MAX;
+ token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH;
+
+ if (hashconfig->opts_type & OPTS_TYPE_ST_HEX)
+ {
+ token.len_min[1] *= 2;
+ token.len_max[1] *= 2;
+
+ token.attr[1] |= TOKEN_ATTR_VERIFY_HEX;
+ }
const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
- // salt
-
- const u8 *salt_pos = token.buf[1];
- const int salt_len = token.len[1];
-
- memcpy ((u8 *) salt->salt_buf, salt_pos, salt_len);
-
- salt->salt_len = salt_len;
-
- // hash
-
- const u8 *hash_pos = token.buf[2];
+ const u8 *hash_pos = token.buf[0];
digest[0] = hex_to_u32 (hash_pos + 0);
digest[1] = hex_to_u32 (hash_pos + 8);
@@ -130,6 +116,13 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
digest[7] -= SHA256M_H;
}
+ const u8 *salt_pos = token.buf[1];
+ const int salt_len = token.len[1];
+
+ const bool parse_rc = generic_salt_decode (hashconfig, salt_pos, salt_len, (u8 *) salt->salt_buf, (int *) &salt->salt_len);
+
+ if (parse_rc == false) return (PARSER_SALT_LENGTH);
+
return (PARSER_OK);
}
@@ -137,26 +130,6 @@ int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
{
const u32 *digest = (const u32 *) digest_buf;
- int line_len = 0;
-
- // signature
-
- line_buf[line_len++] = '$';
- line_buf[line_len++] = 'S';
- line_buf[line_len++] = 'H';
- line_buf[line_len++] = 'A';
- line_buf[line_len++] = '$';
-
- // salt
-
- memcpy (line_buf + line_len, salt->salt_buf, salt->salt_len);
-
- line_len += salt->salt_len;
-
- line_buf[line_len++] = '$';
-
- // digest
-
u32 tmp[8];
tmp[0] = digest[0];
@@ -191,18 +164,24 @@ int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
u8 *out_buf = (u8 *) line_buf;
- u32_to_hex (tmp[0], out_buf + line_len); line_len += 8;
- u32_to_hex (tmp[1], out_buf + line_len); line_len += 8;
- u32_to_hex (tmp[2], out_buf + line_len); line_len += 8;
- u32_to_hex (tmp[3], out_buf + line_len); line_len += 8;
- u32_to_hex (tmp[4], out_buf + line_len); line_len += 8;
- u32_to_hex (tmp[5], out_buf + line_len); line_len += 8;
- u32_to_hex (tmp[6], out_buf + line_len); line_len += 8;
- u32_to_hex (tmp[7], out_buf + line_len); line_len += 8;
+ int out_len = 0;
- line_buf[line_len] = 0;
+ u32_to_hex (tmp[0], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[1], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[2], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[3], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[4], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[5], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[6], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[7], out_buf + out_len); out_len += 8;
- return line_len;
+ out_buf[out_len] = hashconfig->separator;
+
+ out_len += 1;
+
+ out_len += generic_salt_encode (hashconfig, (const u8 *) salt->salt_buf, (const int) salt->salt_len, out_buf + out_len);
+
+ return out_len;
}
void module_init (module_ctx_t *module_ctx)
diff --git a/src/modules/module_20711.c b/src/modules/module_20711.c
index ac8269cdb..0628759be 100644
--- a/src/modules/module_20711.c
+++ b/src/modules/module_20711.c
@@ -18,7 +18,7 @@ static const u32 DGST_POS2 = 2;
static const u32 DGST_POS3 = 6;
static const u32 DGST_SIZE = DGST_SIZE_4_8;
static const u32 HASH_CATEGORY = HASH_CATEGORY_EAS;
-static const char *HASH_NAME = "AuthMe - sha256(sha256($pass).$salt)";
+static const char *HASH_NAME = "AuthMe sha256";
static const u64 KERN_TYPE = 20710;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
diff --git a/tools/test_modules/m20710.pm b/tools/test_modules/m20710.pm
new file mode 100644
index 000000000..191f4a7c7
--- /dev/null
+++ b/tools/test_modules/m20710.pm
@@ -0,0 +1,46 @@
+#!/usr/bin/env perl
+
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use Digest::SHA qw (sha256_hex);
+
+sub module_constraints { [[1, 31], [16, 16], [1, 31], [16, 16], [-1, -1]] }
+
+sub module_generate_hash
+{
+ my $word = shift;
+ my $salt = shift;
+
+ my $digest = sha256_hex (sha256_hex ($word) . $salt);
+
+ my $hash = sprintf ("%s:%s", $digest, $salt);
+
+ return $hash;
+}
+
+sub module_verify_hash
+{
+ my $line = shift;
+
+ my ($digest, $salt, $word) = split (':', $line);
+
+ return unless defined $digest;
+ return unless defined $salt;
+ return unless defined $word;
+
+ return unless length ($salt) == 16;
+
+ my $word_packed = pack_if_HEX_notation ($word);
+
+ my $new_hash = module_generate_hash ($word_packed, $salt);
+
+ return ($new_hash, $word);
+}
+
+1;
diff --git a/tools/test_modules/m20700.pm b/tools/test_modules/m20711.pm
similarity index 91%
rename from tools/test_modules/m20700.pm
rename to tools/test_modules/m20711.pm
index 292604cc0..334c20b10 100644
--- a/tools/test_modules/m20700.pm
+++ b/tools/test_modules/m20711.pm
@@ -10,7 +10,7 @@ use warnings;
use Digest::SHA qw (sha256_hex);
-sub module_constraints { [[1, 31], [16, 16], [-1, -1], [-1, -1], [-1, -1]] }
+sub module_constraints { [[1, 31], [16, 16], [1, 31], [16, 16], [-1, -1]] }
sub module_generate_hash
{
From c40473416a20d0485210f413fa1fb221035d0256 Mon Sep 17 00:00:00 2001
From: Awais Chishti <chishtiawais511@gmail.com>
Date: Thu, 1 Aug 2019 21:28:48 +0500
Subject: [PATCH 065/113] Avoid -Waddress-of-packed-member warnings
---
src/modules/module_17200.c | 10 ++++------
src/modules/module_17210.c | 10 ++++------
src/modules/module_17220.c | 4 +---
src/modules/module_17225.c | 4 +---
src/modules/module_17230.c | 4 +---
5 files changed, 11 insertions(+), 21 deletions(-)
diff --git a/src/modules/module_17200.c b/src/modules/module_17200.c
index e42081643..a94a30ec7 100644
--- a/src/modules/module_17200.c
+++ b/src/modules/module_17200.c
@@ -284,12 +284,10 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
hex_to_binary (p, strlen (p), (char *) &(pkzip->hash.data));
// fake salt
- u32 *ptr = (u32 *) pkzip->hash.data;
-
- salt->salt_buf[0] = ptr[0];
- salt->salt_buf[1] = ptr[1];
- salt->salt_buf[2] = ptr[2];
- salt->salt_buf[3] = ptr[3];
+ salt->salt_buf[0] = pkzip->hash.data[0];
+ salt->salt_buf[1] = pkzip->hash.data[1];
+ salt->salt_buf[2] = pkzip->hash.data[2];
+ salt->salt_buf[3] = pkzip->hash.data[3];
salt->salt_len = 16;
diff --git a/src/modules/module_17210.c b/src/modules/module_17210.c
index 6025921f6..c1f405f2e 100644
--- a/src/modules/module_17210.c
+++ b/src/modules/module_17210.c
@@ -283,12 +283,10 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
hex_to_binary (p, strlen (p), (char *) &(pkzip->hash.data));
// fake salt
- u32 *ptr = (u32 *) pkzip->hash.data;
-
- salt->salt_buf[0] = ptr[0];
- salt->salt_buf[1] = ptr[1];
- salt->salt_buf[2] = ptr[2];
- salt->salt_buf[3] = ptr[3];
+ salt->salt_buf[0] = pkzip->hash.data[0];
+ salt->salt_buf[1] = pkzip->hash.data[1];
+ salt->salt_buf[2] = pkzip->hash.data[2];
+ salt->salt_buf[3] = pkzip->hash.data[3];
salt->salt_len = 16;
diff --git a/src/modules/module_17220.c b/src/modules/module_17220.c
index fa737ecbf..403640d94 100644
--- a/src/modules/module_17220.c
+++ b/src/modules/module_17220.c
@@ -285,9 +285,7 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
hex_to_binary (p, strlen (p), (char *) &(pkzip->hashes[i].data));
// fake salt
- u32 *ptr = (u32 *) pkzip->hashes[i].data;
-
- salt->salt_buf[i] = ptr[0];
+ salt->salt_buf[i] = pkzip->hashes[i].data[0];
if (i == 0) digest[i] = pkzip->hashes[i].checksum_from_crc;
}
diff --git a/src/modules/module_17225.c b/src/modules/module_17225.c
index 9cf725cf0..66907159f 100644
--- a/src/modules/module_17225.c
+++ b/src/modules/module_17225.c
@@ -285,9 +285,7 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
hex_to_binary (p, strlen (p), (char *) &(pkzip->hashes[i].data));
// fake salt
- u32 *ptr = (u32 *) pkzip->hashes[i].data;
-
- salt->salt_buf[i] = ptr[0];
+ salt->salt_buf[i] = pkzip->hashes[i].data[0];
if (i == 0) digest[i] = pkzip->hashes[i].checksum_from_crc;
}
diff --git a/src/modules/module_17230.c b/src/modules/module_17230.c
index 26cbb1b5c..2b65dd65e 100644
--- a/src/modules/module_17230.c
+++ b/src/modules/module_17230.c
@@ -286,9 +286,7 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
hex_to_binary (p, strlen (p), (char *) &(pkzip->hashes[i].data));
// fake salt
- u32 *ptr = (u32 *) pkzip->hashes[i].data;
-
- salt->salt_buf[i] = ptr[0];
+ salt->salt_buf[i] = pkzip->hashes[i].data[0];
if (i == 0) digest[i] = pkzip->hashes[i].checksum_from_crc;
}
From c845d1460173276d96c51fe2c3d65dd547113cfd Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Fri, 2 Aug 2019 10:40:32 +0200
Subject: [PATCH 066/113] Make -m 4710 more generic
---
OpenCL/m04710_a0-optimized.cl | 651 ----------------------
OpenCL/m04710_a1-optimized.cl | 759 --------------------------
OpenCL/m04710_a3-optimized.cl | 999 ----------------------------------
OpenCL/m04710_a3-pure.cl | 2 +-
src/modules/module_04710.c | 30 +-
tools/test_modules/m04710.pm | 4 +-
6 files changed, 15 insertions(+), 2430 deletions(-)
delete mode 100644 OpenCL/m04710_a0-optimized.cl
delete mode 100644 OpenCL/m04710_a1-optimized.cl
delete mode 100644 OpenCL/m04710_a3-optimized.cl
diff --git a/OpenCL/m04710_a0-optimized.cl b/OpenCL/m04710_a0-optimized.cl
deleted file mode 100644
index ab2657798..000000000
--- a/OpenCL/m04710_a0-optimized.cl
+++ /dev/null
@@ -1,651 +0,0 @@
-/**
- * Author......: See docs/credits.txt
- * License.....: MIT
- */
-
-#define NEW_SIMD_CODE
-
-#ifdef KERNEL_STATIC
-#include "inc_vendor.h"
-#include "inc_types.h"
-#include "inc_platform.cl"
-#include "inc_common.cl"
-#include "inc_rp_optimized.h"
-#include "inc_rp_optimized.cl"
-#include "inc_simd.cl"
-#include "inc_hash_md5.cl"
-#include "inc_hash_sha1.cl"
-#endif
-
-#if VECT_SIZE == 1
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
-#elif VECT_SIZE == 2
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
-#elif VECT_SIZE == 4
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
-#elif VECT_SIZE == 8
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
-#elif VECT_SIZE == 16
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
-#endif
-
-KERNEL_FQ void m04710_m04 (KERN_ATTR_RULES ())
-{
- /**
- * modifier
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
- const u64 lsz = get_local_size (0);
-
- /**
- * bin2asc table
- */
-
- LOCAL_VK u32 l_bin2asc[256];
-
- for (u32 i = lid; i < 256; i += lsz)
- {
- const u32 i0 = (i >> 0) & 15;
- const u32 i1 = (i >> 4) & 15;
-
- l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
- | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
- }
-
- SYNC_THREADS ();
-
- if (gid >= gid_max) return;
-
- /**
- * base
- */
-
- u32 pw_buf0[4];
- u32 pw_buf1[4];
-
- pw_buf0[0] = pws[gid].i[0];
- pw_buf0[1] = pws[gid].i[1];
- pw_buf0[2] = pws[gid].i[2];
- pw_buf0[3] = pws[gid].i[3];
- pw_buf1[0] = pws[gid].i[4];
- pw_buf1[1] = pws[gid].i[5];
- pw_buf1[2] = pws[gid].i[6];
- pw_buf1[3] = pws[gid].i[7];
-
- const u32 pw_len = pws[gid].pw_len & 63;
-
- u32 salt_buf0[2];
-
- salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
- salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
-
- const u32 salt_len = salt_bufs[salt_pos].salt_len;
-
- /**
- * loop
- */
-
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
- {
- u32x w0[4] = { 0 };
- u32x w1[4] = { 0 };
- u32x w2[4] = { 0 };
- u32x w3[4] = { 0 };
-
- const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
-
- append_0x80_2x4_VV (w0, w1, out_len);
-
- w3[2] = out_len * 8;
- w3[3] = 0;
-
- /**
- * md5(pass)
- */
-
- u32x a = MD5M_A;
- u32x b = MD5M_B;
- u32x c = MD5M_C;
- u32x d = MD5M_D;
- u32x e = 0;
-
- MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
-
- MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
-
- u32x t;
-
- MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
-
- MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
-
- a += MD5M_A;
- b += MD5M_B;
- c += MD5M_C;
- d += MD5M_D;
-
- /*
- * append salt + sha1
- */
-
- u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
- u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
- u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
- u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
- u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
- u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
- u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
- u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
- u32x w8_t = salt_buf0[0];
- u32x w9_t = salt_buf0[1];
- u32x wa_t = 0x80000000;
- u32x wb_t = 0;
- u32x wc_t = 0;
- u32x wd_t = 0;
- u32x we_t = 0;
- u32x wf_t = 40 * 8;
-
- a = SHA1M_A;
- b = SHA1M_B;
- c = SHA1M_C;
- d = SHA1M_D;
- e = SHA1M_E;
-
- #undef K
- #define K SHA1C00
-
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
-
- #undef K
- #define K SHA1C01
-
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
-
- #undef K
- #define K SHA1C02
-
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
-
- #undef K
- #define K SHA1C03
-
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
-
- COMPARE_M_SIMD (d, e, c, b);
- }
-}
-
-KERNEL_FQ void m04710_m08 (KERN_ATTR_RULES ())
-{
-}
-
-KERNEL_FQ void m04710_m16 (KERN_ATTR_RULES ())
-{
-}
-
-KERNEL_FQ void m04710_s04 (KERN_ATTR_RULES ())
-{
- /**
- * modifier
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
- const u64 lsz = get_local_size (0);
-
- /**
- * bin2asc table
- */
-
- LOCAL_VK u32 l_bin2asc[256];
-
- for (u32 i = lid; i < 256; i += lsz)
- {
- const u32 i0 = (i >> 0) & 15;
- const u32 i1 = (i >> 4) & 15;
-
- l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
- | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
- }
-
- SYNC_THREADS ();
-
- if (gid >= gid_max) return;
-
- /**
- * base
- */
-
- u32 pw_buf0[4];
- u32 pw_buf1[4];
-
- pw_buf0[0] = pws[gid].i[0];
- pw_buf0[1] = pws[gid].i[1];
- pw_buf0[2] = pws[gid].i[2];
- pw_buf0[3] = pws[gid].i[3];
- pw_buf1[0] = pws[gid].i[4];
- pw_buf1[1] = pws[gid].i[5];
- pw_buf1[2] = pws[gid].i[6];
- pw_buf1[3] = pws[gid].i[7];
-
- const u32 pw_len = pws[gid].pw_len & 63;
-
- u32 salt_buf0[2];
-
- salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
- salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
-
- const u32 salt_len = salt_bufs[salt_pos].salt_len;
-
- /**
- * digest
- */
-
- const u32 search[4] =
- {
- digests_buf[digests_offset].digest_buf[DGST_R0],
- digests_buf[digests_offset].digest_buf[DGST_R1],
- digests_buf[digests_offset].digest_buf[DGST_R2],
- digests_buf[digests_offset].digest_buf[DGST_R3]
- };
-
- /**
- * reverse
- */
-
- const u32 e_rev = hc_rotl32_S (search[1], 2u);
-
- /**
- * loop
- */
-
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
- {
- u32x w0[4] = { 0 };
- u32x w1[4] = { 0 };
- u32x w2[4] = { 0 };
- u32x w3[4] = { 0 };
-
- const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
-
- append_0x80_2x4_VV (w0, w1, out_len);
-
- w3[2] = out_len * 8;
- w3[3] = 0;
-
- /**
- * md5(pass)
- */
-
- u32x a = MD5M_A;
- u32x b = MD5M_B;
- u32x c = MD5M_C;
- u32x d = MD5M_D;
- u32x e = 0;
-
- MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
-
- MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
-
- u32x t;
-
- MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
-
- MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
-
- a += MD5M_A;
- b += MD5M_B;
- c += MD5M_C;
- d += MD5M_D;
-
- /*
- * append salt + sha1
- */
-
- u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
- u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
- u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
- u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
- u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
- u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
- u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
- u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
- u32x w8_t = salt_buf0[0];
- u32x w9_t = salt_buf0[1];
- u32x wa_t = 0x80000000;
- u32x wb_t = 0;
- u32x wc_t = 0;
- u32x wd_t = 0;
- u32x we_t = 0;
- u32x wf_t = 40 * 8;
-
- a = SHA1M_A;
- b = SHA1M_B;
- c = SHA1M_C;
- d = SHA1M_D;
- e = SHA1M_E;
-
- #undef K
- #define K SHA1C00
-
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
-
- #undef K
- #define K SHA1C01
-
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
-
- #undef K
- #define K SHA1C02
-
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
-
- #undef K
- #define K SHA1C03
-
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
-
- if (MATCHES_NONE_VS (e, e_rev)) continue;
-
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
-
- COMPARE_S_SIMD (d, e, c, b);
- }
-}
-
-KERNEL_FQ void m04710_s08 (KERN_ATTR_RULES ())
-{
-}
-
-KERNEL_FQ void m04710_s16 (KERN_ATTR_RULES ())
-{
-}
diff --git a/OpenCL/m04710_a1-optimized.cl b/OpenCL/m04710_a1-optimized.cl
deleted file mode 100644
index 38ab761ee..000000000
--- a/OpenCL/m04710_a1-optimized.cl
+++ /dev/null
@@ -1,759 +0,0 @@
-/**
- * Author......: See docs/credits.txt
- * License.....: MIT
- */
-
-#define NEW_SIMD_CODE
-
-#ifdef KERNEL_STATIC
-#include "inc_vendor.h"
-#include "inc_types.h"
-#include "inc_platform.cl"
-#include "inc_common.cl"
-#include "inc_simd.cl"
-#include "inc_hash_md5.cl"
-#include "inc_hash_sha1.cl"
-#endif
-
-#if VECT_SIZE == 1
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
-#elif VECT_SIZE == 2
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
-#elif VECT_SIZE == 4
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
-#elif VECT_SIZE == 8
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
-#elif VECT_SIZE == 16
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
-#endif
-
-KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
-{
- /**
- * modifier
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
- const u64 lsz = get_local_size (0);
-
- /**
- * bin2asc table
- */
-
- LOCAL_VK u32 l_bin2asc[256];
-
- for (u32 i = lid; i < 256; i += lsz)
- {
- const u32 i0 = (i >> 0) & 15;
- const u32 i1 = (i >> 4) & 15;
-
- l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
- | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
- }
-
- SYNC_THREADS ();
-
- if (gid >= gid_max) return;
-
- /**
- * base
- */
-
- u32 pw_buf0[4];
- u32 pw_buf1[4];
-
- pw_buf0[0] = pws[gid].i[0];
- pw_buf0[1] = pws[gid].i[1];
- pw_buf0[2] = pws[gid].i[2];
- pw_buf0[3] = pws[gid].i[3];
- pw_buf1[0] = pws[gid].i[4];
- pw_buf1[1] = pws[gid].i[5];
- pw_buf1[2] = pws[gid].i[6];
- pw_buf1[3] = pws[gid].i[7];
-
- const u32 pw_l_len = pws[gid].pw_len & 63;
-
- u32 salt_buf0[2];
-
- salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
- salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
-
- const u32 salt_len = salt_bufs[salt_pos].salt_len;
-
- /**
- * loop
- */
-
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
- {
- const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
-
- const u32x pw_len = (pw_l_len + pw_r_len) & 63;
-
- /**
- * concat password candidate
- */
-
- u32x wordl0[4] = { 0 };
- u32x wordl1[4] = { 0 };
- u32x wordl2[4] = { 0 };
- u32x wordl3[4] = { 0 };
-
- wordl0[0] = pw_buf0[0];
- wordl0[1] = pw_buf0[1];
- wordl0[2] = pw_buf0[2];
- wordl0[3] = pw_buf0[3];
- wordl1[0] = pw_buf1[0];
- wordl1[1] = pw_buf1[1];
- wordl1[2] = pw_buf1[2];
- wordl1[3] = pw_buf1[3];
-
- u32x wordr0[4] = { 0 };
- u32x wordr1[4] = { 0 };
- u32x wordr2[4] = { 0 };
- u32x wordr3[4] = { 0 };
-
- wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
- wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
- wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
- wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
- wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
- wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
- wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
- wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
-
- if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
- {
- switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
- }
- else
- {
- switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
- }
-
- u32x w0[4];
- u32x w1[4];
- u32x w2[4];
- u32x w3[4];
-
- w0[0] = wordl0[0] | wordr0[0];
- w0[1] = wordl0[1] | wordr0[1];
- w0[2] = wordl0[2] | wordr0[2];
- w0[3] = wordl0[3] | wordr0[3];
- w1[0] = wordl1[0] | wordr1[0];
- w1[1] = wordl1[1] | wordr1[1];
- w1[2] = wordl1[2] | wordr1[2];
- w1[3] = wordl1[3] | wordr1[3];
- w2[0] = wordl2[0] | wordr2[0];
- w2[1] = wordl2[1] | wordr2[1];
- w2[2] = wordl2[2] | wordr2[2];
- w2[3] = wordl2[3] | wordr2[3];
- w3[0] = wordl3[0] | wordr3[0];
- w3[1] = wordl3[1] | wordr3[1];
- w3[2] = pw_len * 8;
- w3[3] = 0;
-
- /**
- * md5(pass)
- */
-
- u32x a = MD5M_A;
- u32x b = MD5M_B;
- u32x c = MD5M_C;
- u32x d = MD5M_D;
- u32x e = 0;
-
- MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
-
- MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
-
- u32x t;
-
- MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
-
- MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
-
- a += MD5M_A;
- b += MD5M_B;
- c += MD5M_C;
- d += MD5M_D;
-
- /*
- * append salt + sha1
- */
-
- u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
- u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
- u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
- u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
- u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
- u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
- u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
- u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
- u32x w8_t = salt_buf0[0];
- u32x w9_t = salt_buf0[1];
- u32x wa_t = 0x80000000;
- u32x wb_t = 0;
- u32x wc_t = 0;
- u32x wd_t = 0;
- u32x we_t = 0;
- u32x wf_t = 40 * 8;
-
- a = SHA1M_A;
- b = SHA1M_B;
- c = SHA1M_C;
- d = SHA1M_D;
- e = SHA1M_E;
-
- #undef K
- #define K SHA1C00
-
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
-
- #undef K
- #define K SHA1C01
-
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
-
- #undef K
- #define K SHA1C02
-
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
-
- #undef K
- #define K SHA1C03
-
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
-
- COMPARE_M_SIMD (d, e, c, b);
- }
-}
-
-KERNEL_FQ void m04710_m08 (KERN_ATTR_BASIC ())
-{
-}
-
-KERNEL_FQ void m04710_m16 (KERN_ATTR_BASIC ())
-{
-}
-
-KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
-{
- /**
- * modifier
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
- const u64 lsz = get_local_size (0);
-
- /**
- * bin2asc table
- */
-
- LOCAL_VK u32 l_bin2asc[256];
-
- for (u32 i = lid; i < 256; i += lsz)
- {
- const u32 i0 = (i >> 0) & 15;
- const u32 i1 = (i >> 4) & 15;
-
- l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
- | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
- }
-
- SYNC_THREADS ();
-
- if (gid >= gid_max) return;
-
- /**
- * base
- */
-
- u32 pw_buf0[4];
- u32 pw_buf1[4];
-
- pw_buf0[0] = pws[gid].i[0];
- pw_buf0[1] = pws[gid].i[1];
- pw_buf0[2] = pws[gid].i[2];
- pw_buf0[3] = pws[gid].i[3];
- pw_buf1[0] = pws[gid].i[4];
- pw_buf1[1] = pws[gid].i[5];
- pw_buf1[2] = pws[gid].i[6];
- pw_buf1[3] = pws[gid].i[7];
-
- const u32 pw_l_len = pws[gid].pw_len & 63;
-
- u32 salt_buf0[2];
-
- salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
- salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
-
- const u32 salt_len = salt_bufs[salt_pos].salt_len;
-
- /**
- * digest
- */
-
- const u32 search[4] =
- {
- digests_buf[digests_offset].digest_buf[DGST_R0],
- digests_buf[digests_offset].digest_buf[DGST_R1],
- digests_buf[digests_offset].digest_buf[DGST_R2],
- digests_buf[digests_offset].digest_buf[DGST_R3]
- };
-
- /**
- * reverse
- */
-
- const u32 e_rev = hc_rotl32_S (search[1], 2u);
-
- /**
- * loop
- */
-
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
- {
- const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
-
- const u32x pw_len = (pw_l_len + pw_r_len) & 63;
-
- /**
- * concat password candidate
- */
-
- u32x wordl0[4] = { 0 };
- u32x wordl1[4] = { 0 };
- u32x wordl2[4] = { 0 };
- u32x wordl3[4] = { 0 };
-
- wordl0[0] = pw_buf0[0];
- wordl0[1] = pw_buf0[1];
- wordl0[2] = pw_buf0[2];
- wordl0[3] = pw_buf0[3];
- wordl1[0] = pw_buf1[0];
- wordl1[1] = pw_buf1[1];
- wordl1[2] = pw_buf1[2];
- wordl1[3] = pw_buf1[3];
-
- u32x wordr0[4] = { 0 };
- u32x wordr1[4] = { 0 };
- u32x wordr2[4] = { 0 };
- u32x wordr3[4] = { 0 };
-
- wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
- wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
- wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
- wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
- wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
- wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
- wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
- wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
-
- if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
- {
- switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
- }
- else
- {
- switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
- }
-
- u32x w0[4];
- u32x w1[4];
- u32x w2[4];
- u32x w3[4];
-
- w0[0] = wordl0[0] | wordr0[0];
- w0[1] = wordl0[1] | wordr0[1];
- w0[2] = wordl0[2] | wordr0[2];
- w0[3] = wordl0[3] | wordr0[3];
- w1[0] = wordl1[0] | wordr1[0];
- w1[1] = wordl1[1] | wordr1[1];
- w1[2] = wordl1[2] | wordr1[2];
- w1[3] = wordl1[3] | wordr1[3];
- w2[0] = wordl2[0] | wordr2[0];
- w2[1] = wordl2[1] | wordr2[1];
- w2[2] = wordl2[2] | wordr2[2];
- w2[3] = wordl2[3] | wordr2[3];
- w3[0] = wordl3[0] | wordr3[0];
- w3[1] = wordl3[1] | wordr3[1];
- w3[2] = pw_len * 8;
- w3[3] = 0;
-
- /**
- * md5(pass)
- */
-
- u32x a = MD5M_A;
- u32x b = MD5M_B;
- u32x c = MD5M_C;
- u32x d = MD5M_D;
- u32x e = 0;
-
- MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
-
- MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
-
- u32x t;
-
- MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
-
- MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
-
- a += MD5M_A;
- b += MD5M_B;
- c += MD5M_C;
- d += MD5M_D;
-
- /*
- * append salt + sha1
- */
-
- u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
- u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
- u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
- u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
- u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
- u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
- u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
- u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
- u32x w8_t = salt_buf0[0];
- u32x w9_t = salt_buf0[1];
- u32x wa_t = 0x80000000;
- u32x wb_t = 0;
- u32x wc_t = 0;
- u32x wd_t = 0;
- u32x we_t = 0;
- u32x wf_t = 40 * 8;
-
- a = SHA1M_A;
- b = SHA1M_B;
- c = SHA1M_C;
- d = SHA1M_D;
- e = SHA1M_E;
-
- #undef K
- #define K SHA1C00
-
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
-
- #undef K
- #define K SHA1C01
-
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
-
- #undef K
- #define K SHA1C02
-
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
-
- #undef K
- #define K SHA1C03
-
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
-
- if (MATCHES_NONE_VS (e, e_rev)) continue;
-
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
-
- COMPARE_S_SIMD (d, e, c, b);
- }
-}
-
-KERNEL_FQ void m04710_s08 (KERN_ATTR_BASIC ())
-{
-}
-
-KERNEL_FQ void m04710_s16 (KERN_ATTR_BASIC ())
-{
-}
diff --git a/OpenCL/m04710_a3-optimized.cl b/OpenCL/m04710_a3-optimized.cl
deleted file mode 100644
index cd5ad074b..000000000
--- a/OpenCL/m04710_a3-optimized.cl
+++ /dev/null
@@ -1,999 +0,0 @@
-/**
- * Author......: See docs/credits.txt
- * License.....: MIT
- */
-
-#define NEW_SIMD_CODE
-
-#ifdef KERNEL_STATIC
-#include "inc_vendor.h"
-#include "inc_types.h"
-#include "inc_platform.cl"
-#include "inc_common.cl"
-#include "inc_simd.cl"
-#include "inc_hash_md5.cl"
-#include "inc_hash_sha1.cl"
-#endif
-
-#if VECT_SIZE == 1
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
-#elif VECT_SIZE == 2
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
-#elif VECT_SIZE == 4
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
-#elif VECT_SIZE == 8
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
-#elif VECT_SIZE == 16
-#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
-#endif
-
-DECLSPEC void m04710m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
-{
- /**
- * modifier
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
-
- u32 salt_buf0[2];
-
- salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
- salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
-
- const u32 salt_len = salt_bufs[salt_pos].salt_len;
-
- /**
- * loop
- */
-
- u32 w0l = w0[0];
-
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
- {
- const u32x w0r = ix_create_bft (bfs_buf, il_pos);
-
- const u32x w0lr = w0l | w0r;
-
- u32x w0_t = w0lr;
- u32x w1_t = w0[1];
- u32x w2_t = w0[2];
- u32x w3_t = w0[3];
- u32x w4_t = w1[0];
- u32x w5_t = w1[1];
- u32x w6_t = w1[2];
- u32x w7_t = w1[3];
- u32x w8_t = w2[0];
- u32x w9_t = w2[1];
- u32x wa_t = w2[2];
- u32x wb_t = w2[3];
- u32x wc_t = w3[0];
- u32x wd_t = w3[1];
- u32x we_t = w3[2];
- u32x wf_t = w3[3];
-
- /**
- * md5(pass)
- */
-
- u32x a = MD5M_A;
- u32x b = MD5M_B;
- u32x c = MD5M_C;
- u32x d = MD5M_D;
- u32x e = 0;
-
- MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
-
- MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
-
- u32x t;
-
- MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
-
- MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
-
- a += MD5M_A;
- b += MD5M_B;
- c += MD5M_C;
- d += MD5M_D;
-
- /*
- * append salt + sha1
- */
-
- w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
- w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
- w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
- w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
- w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
- w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
- w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
- w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
- w8_t = salt_buf0[0];
- w9_t = salt_buf0[1];
- wa_t = 0x80000000;
- wb_t = 0;
- wc_t = 0;
- wd_t = 0;
- we_t = 0;
- wf_t = 40 * 8;
-
- a = SHA1M_A;
- b = SHA1M_B;
- c = SHA1M_C;
- d = SHA1M_D;
- e = SHA1M_E;
-
- #undef K
- #define K SHA1C00
-
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
-
- #undef K
- #define K SHA1C01
-
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
-
- #undef K
- #define K SHA1C02
-
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
-
- #undef K
- #define K SHA1C03
-
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
-
- COMPARE_M_SIMD (d, e, c, b);
- }
-}
-
-DECLSPEC void m04710s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
-{
- /**
- * modifier
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
-
- u32 salt_buf0[2];
-
- salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
- salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
-
- const u32 salt_len = salt_bufs[salt_pos].salt_len;
-
- /**
- * digest
- */
-
- const u32 search[4] =
- {
- digests_buf[digests_offset].digest_buf[DGST_R0],
- digests_buf[digests_offset].digest_buf[DGST_R1],
- digests_buf[digests_offset].digest_buf[DGST_R2],
- digests_buf[digests_offset].digest_buf[DGST_R3]
- };
-
- /**
- * reverse
- */
-
- const u32 e_rev = hc_rotl32_S (search[1], 2u);
-
- /**
- * loop
- */
-
- u32 w0l = w0[0];
-
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
- {
- const u32x w0r = ix_create_bft (bfs_buf, il_pos);
-
- const u32x w0lr = w0l | w0r;
-
- u32x w0_t = w0lr;
- u32x w1_t = w0[1];
- u32x w2_t = w0[2];
- u32x w3_t = w0[3];
- u32x w4_t = w1[0];
- u32x w5_t = w1[1];
- u32x w6_t = w1[2];
- u32x w7_t = w1[3];
- u32x w8_t = w2[0];
- u32x w9_t = w2[1];
- u32x wa_t = w2[2];
- u32x wb_t = w2[3];
- u32x wc_t = w3[0];
- u32x wd_t = w3[1];
- u32x we_t = w3[2];
- u32x wf_t = w3[3];
-
- /**
- * md5(pass)
- */
-
- u32x a = MD5M_A;
- u32x b = MD5M_B;
- u32x c = MD5M_C;
- u32x d = MD5M_D;
- u32x e = 0;
-
- MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
- MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
- MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
- MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
- MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
-
- MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
- MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
- MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
- MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
- MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
-
- u32x t;
-
- MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
- MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
- MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
- MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
- MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
-
- MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
- MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
- MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
- MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
- MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
-
- a += MD5M_A;
- b += MD5M_B;
- c += MD5M_C;
- d += MD5M_D;
-
- /*
- * append salt + sha1
- */
-
- w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
- w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
- w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
- w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
- w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
- w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
- w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
- w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
- | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
- w8_t = salt_buf0[0];
- w9_t = salt_buf0[1];
- wa_t = 0x80000000;
- wb_t = 0;
- wc_t = 0;
- wd_t = 0;
- we_t = 0;
- wf_t = 40 * 8;
-
- a = SHA1M_A;
- b = SHA1M_B;
- c = SHA1M_C;
- d = SHA1M_D;
- e = SHA1M_E;
-
- #undef K
- #define K SHA1C00
-
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
- SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
- SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
- SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
- SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
- SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
-
- #undef K
- #define K SHA1C01
-
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
-
- #undef K
- #define K SHA1C02
-
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
-
- #undef K
- #define K SHA1C03
-
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
- w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
- w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
- w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
- w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
- w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
- w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
- w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
- w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
- w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
- w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
- wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
- wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
-
- if (MATCHES_NONE_VS (e, e_rev)) continue;
-
- wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
- wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
- we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
- wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
-
- COMPARE_S_SIMD (d, e, c, b);
- }
-}
-
-KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
-{
- /**
- * base
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
- const u64 lsz = get_local_size (0);
-
- /**
- * bin2asc table
- */
-
- LOCAL_VK u32 l_bin2asc[256];
-
- for (u32 i = lid; i < 256; i += lsz)
- {
- const u32 i0 = (i >> 0) & 15;
- const u32 i1 = (i >> 4) & 15;
-
- l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
- | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
- }
-
- SYNC_THREADS ();
-
- if (gid >= gid_max) return;
-
- /**
- * modifier
- */
-
- u32 w0[4];
-
- w0[0] = pws[gid].i[ 0];
- w0[1] = pws[gid].i[ 1];
- w0[2] = pws[gid].i[ 2];
- w0[3] = pws[gid].i[ 3];
-
- u32 w1[4];
-
- w1[0] = 0;
- w1[1] = 0;
- w1[2] = 0;
- w1[3] = 0;
-
- u32 w2[4];
-
- w2[0] = 0;
- w2[1] = 0;
- w2[2] = 0;
- w2[3] = 0;
-
- u32 w3[4];
-
- w3[0] = 0;
- w3[1] = 0;
- w3[2] = pws[gid].i[14];
- w3[3] = 0;
-
- const u32 pw_len = pws[gid].pw_len & 63;
-
- /**
- * main
- */
-
- m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
-}
-
-KERNEL_FQ void m04710_m08 (KERN_ATTR_BASIC ())
-{
- /**
- * base
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
- const u64 lsz = get_local_size (0);
-
- /**
- * bin2asc table
- */
-
- LOCAL_VK u32 l_bin2asc[256];
-
- for (u32 i = lid; i < 256; i += lsz)
- {
- const u32 i0 = (i >> 0) & 15;
- const u32 i1 = (i >> 4) & 15;
-
- l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
- | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
- }
-
- SYNC_THREADS ();
-
- if (gid >= gid_max) return;
-
- /**
- * modifier
- */
-
- u32 w0[4];
-
- w0[0] = pws[gid].i[ 0];
- w0[1] = pws[gid].i[ 1];
- w0[2] = pws[gid].i[ 2];
- w0[3] = pws[gid].i[ 3];
-
- u32 w1[4];
-
- w1[0] = pws[gid].i[ 4];
- w1[1] = pws[gid].i[ 5];
- w1[2] = pws[gid].i[ 6];
- w1[3] = pws[gid].i[ 7];
-
- u32 w2[4];
-
- w2[0] = 0;
- w2[1] = 0;
- w2[2] = 0;
- w2[3] = 0;
-
- u32 w3[4];
-
- w3[0] = 0;
- w3[1] = 0;
- w3[2] = pws[gid].i[14];
- w3[3] = 0;
-
- const u32 pw_len = pws[gid].pw_len & 63;
-
- /**
- * main
- */
-
- m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
-}
-
-KERNEL_FQ void m04710_m16 (KERN_ATTR_BASIC ())
-{
- /**
- * base
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
- const u64 lsz = get_local_size (0);
-
- /**
- * bin2asc table
- */
-
- LOCAL_VK u32 l_bin2asc[256];
-
- for (u32 i = lid; i < 256; i += lsz)
- {
- const u32 i0 = (i >> 0) & 15;
- const u32 i1 = (i >> 4) & 15;
-
- l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
- | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
- }
-
- SYNC_THREADS ();
-
- if (gid >= gid_max) return;
-
- /**
- * modifier
- */
-
- u32 w0[4];
-
- w0[0] = pws[gid].i[ 0];
- w0[1] = pws[gid].i[ 1];
- w0[2] = pws[gid].i[ 2];
- w0[3] = pws[gid].i[ 3];
-
- u32 w1[4];
-
- w1[0] = pws[gid].i[ 4];
- w1[1] = pws[gid].i[ 5];
- w1[2] = pws[gid].i[ 6];
- w1[3] = pws[gid].i[ 7];
-
- u32 w2[4];
-
- w2[0] = pws[gid].i[ 8];
- w2[1] = pws[gid].i[ 9];
- w2[2] = pws[gid].i[10];
- w2[3] = pws[gid].i[11];
-
- u32 w3[4];
-
- w3[0] = pws[gid].i[12];
- w3[1] = pws[gid].i[13];
- w3[2] = pws[gid].i[14];
- w3[3] = pws[gid].i[15];
-
- const u32 pw_len = pws[gid].pw_len & 63;
-
- /**
- * main
- */
-
- m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
-}
-
-KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
-{
- /**
- * base
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
- const u64 lsz = get_local_size (0);
-
- /**
- * bin2asc table
- */
-
- LOCAL_VK u32 l_bin2asc[256];
-
- for (u32 i = lid; i < 256; i += lsz)
- {
- const u32 i0 = (i >> 0) & 15;
- const u32 i1 = (i >> 4) & 15;
-
- l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
- | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
- }
-
- SYNC_THREADS ();
-
- if (gid >= gid_max) return;
-
- /**
- * modifier
- */
-
- u32 w0[4];
-
- w0[0] = pws[gid].i[ 0];
- w0[1] = pws[gid].i[ 1];
- w0[2] = pws[gid].i[ 2];
- w0[3] = pws[gid].i[ 3];
-
- u32 w1[4];
-
- w1[0] = 0;
- w1[1] = 0;
- w1[2] = 0;
- w1[3] = 0;
-
- u32 w2[4];
-
- w2[0] = 0;
- w2[1] = 0;
- w2[2] = 0;
- w2[3] = 0;
-
- u32 w3[4];
-
- w3[0] = 0;
- w3[1] = 0;
- w3[2] = pws[gid].i[14];
- w3[3] = 0;
-
- const u32 pw_len = pws[gid].pw_len & 63;
-
- /**
- * main
- */
-
- m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
-}
-
-KERNEL_FQ void m04710_s08 (KERN_ATTR_BASIC ())
-{
- /**
- * base
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
- const u64 lsz = get_local_size (0);
-
- /**
- * bin2asc table
- */
-
- LOCAL_VK u32 l_bin2asc[256];
-
- for (u32 i = lid; i < 256; i += lsz)
- {
- const u32 i0 = (i >> 0) & 15;
- const u32 i1 = (i >> 4) & 15;
-
- l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
- | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
- }
-
- SYNC_THREADS ();
-
- if (gid >= gid_max) return;
-
- /**
- * modifier
- */
-
- u32 w0[4];
-
- w0[0] = pws[gid].i[ 0];
- w0[1] = pws[gid].i[ 1];
- w0[2] = pws[gid].i[ 2];
- w0[3] = pws[gid].i[ 3];
-
- u32 w1[4];
-
- w1[0] = pws[gid].i[ 4];
- w1[1] = pws[gid].i[ 5];
- w1[2] = pws[gid].i[ 6];
- w1[3] = pws[gid].i[ 7];
-
- u32 w2[4];
-
- w2[0] = 0;
- w2[1] = 0;
- w2[2] = 0;
- w2[3] = 0;
-
- u32 w3[4];
-
- w3[0] = 0;
- w3[1] = 0;
- w3[2] = pws[gid].i[14];
- w3[3] = 0;
-
- const u32 pw_len = pws[gid].pw_len & 63;
-
- /**
- * main
- */
-
- m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
-}
-
-KERNEL_FQ void m04710_s16 (KERN_ATTR_BASIC ())
-{
- /**
- * base
- */
-
- const u64 gid = get_global_id (0);
- const u64 lid = get_local_id (0);
- const u64 lsz = get_local_size (0);
-
- /**
- * bin2asc table
- */
-
- LOCAL_VK u32 l_bin2asc[256];
-
- for (u32 i = lid; i < 256; i += lsz)
- {
- const u32 i0 = (i >> 0) & 15;
- const u32 i1 = (i >> 4) & 15;
-
- l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
- | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
- }
-
- SYNC_THREADS ();
-
- if (gid >= gid_max) return;
-
- /**
- * modifier
- */
-
- u32 w0[4];
-
- w0[0] = pws[gid].i[ 0];
- w0[1] = pws[gid].i[ 1];
- w0[2] = pws[gid].i[ 2];
- w0[3] = pws[gid].i[ 3];
-
- u32 w1[4];
-
- w1[0] = pws[gid].i[ 4];
- w1[1] = pws[gid].i[ 5];
- w1[2] = pws[gid].i[ 6];
- w1[3] = pws[gid].i[ 7];
-
- u32 w2[4];
-
- w2[0] = pws[gid].i[ 8];
- w2[1] = pws[gid].i[ 9];
- w2[2] = pws[gid].i[10];
- w2[3] = pws[gid].i[11];
-
- u32 w3[4];
-
- w3[0] = pws[gid].i[12];
- w3[1] = pws[gid].i[13];
- w3[2] = pws[gid].i[14];
- w3[3] = pws[gid].i[15];
-
- const u32 pw_len = pws[gid].pw_len & 63;
-
- /**
- * main
- */
-
- m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
-}
diff --git a/OpenCL/m04710_a3-pure.cl b/OpenCL/m04710_a3-pure.cl
index 9db9ed1ef..830ac303f 100644
--- a/OpenCL/m04710_a3-pure.cl
+++ b/OpenCL/m04710_a3-pure.cl
@@ -71,7 +71,7 @@ KERNEL_FQ void m04710_mxx (KERN_ATTR_VECTOR ())
const u32 salt_len = salt_bufs[salt_pos].salt_len;
- u32x s[8] = { 0 };
+ u32x s[64] = { 0 };
for (u32 i = 0, idx = 0; i < salt_len; i += 4, idx += 1)
{
diff --git a/src/modules/module_04710.c b/src/modules/module_04710.c
index 14ff2aee8..0921abcbe 100644
--- a/src/modules/module_04710.c
+++ b/src/modules/module_04710.c
@@ -46,20 +46,6 @@ u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig,
const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
-u32 module_salt_min (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
-{
- const u32 salt_min = 8;
-
- return salt_min;
-}
-
-u32 module_salt_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
-{
- const u32 salt_max = 8;
-
- return salt_max;
-}
-
int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
{
u32 *digest = (u32 *) digest_buf;
@@ -74,10 +60,18 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
| TOKEN_ATTR_VERIFY_HEX;
- token.len_min[1] = 8;
- token.len_max[1] = 8;
+ token.len_min[1] = SALT_MIN;
+ token.len_max[1] = SALT_MAX;
token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH;
+ if (hashconfig->opts_type & OPTS_TYPE_ST_HEX)
+ {
+ token.len_min[1] *= 2;
+ token.len_max[1] *= 2;
+
+ token.attr[1] |= TOKEN_ATTR_VERIFY_HEX;
+ }
+
const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
@@ -226,8 +220,8 @@ void module_init (module_ctx_t *module_ctx)
module_ctx->module_pwdump_column = MODULE_DEFAULT;
module_ctx->module_pw_max = MODULE_DEFAULT;
module_ctx->module_pw_min = MODULE_DEFAULT;
- module_ctx->module_salt_max = module_salt_max;
- module_ctx->module_salt_min = module_salt_min;
+ module_ctx->module_salt_max = MODULE_DEFAULT;
+ module_ctx->module_salt_min = MODULE_DEFAULT;
module_ctx->module_salt_type = module_salt_type;
module_ctx->module_separator = MODULE_DEFAULT;
module_ctx->module_st_hash = module_st_hash;
diff --git a/tools/test_modules/m04710.pm b/tools/test_modules/m04710.pm
index e74a1596a..ce760a4b1 100644
--- a/tools/test_modules/m04710.pm
+++ b/tools/test_modules/m04710.pm
@@ -11,12 +11,12 @@ use warnings;
use Digest::MD5 qw (md5_hex);
use Digest::SHA qw (sha1_hex);
-sub module_constraints { [[0, 256], [-1, -1], [0, 55], [-1, -1], [-1, -1]] }
+sub module_constraints { [[0, 256], [0, 223], [-1, -1], [-1, -1], [-1, -1]] }
sub module_generate_hash
{
- my $salt = random_hex_string (8, 8);
my $word = shift;
+ my $salt = shift;
my $digest = sha1_hex (md5_hex ($word) . $salt);
From 358c68abd25574eed7fe154730f4b39b62e1919b Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 3 Aug 2019 02:37:43 +0200
Subject: [PATCH 067/113] update AuthMe patch (3)
---
OpenCL/m20710_a0-optimized.cl | 681 ++++++++++++++++++++++++++++-----
OpenCL/m20710_a1-optimized.cl | 681 ++++++++++++++++++++++++++++-----
OpenCL/m20710_a3-optimized.cl | 690 ++++++++++++++++++++++++++++------
src/modules/module_20710.c | 9 +-
src/modules/module_20711.c | 9 +-
tools/test_modules/m20710.pm | 4 +-
tools/test_modules/m20711.pm | 2 +-
7 files changed, 1744 insertions(+), 332 deletions(-)
diff --git a/OpenCL/m20710_a0-optimized.cl b/OpenCL/m20710_a0-optimized.cl
index db63864d2..311bdf508 100644
--- a/OpenCL/m20710_a0-optimized.cl
+++ b/OpenCL/m20710_a0-optimized.cl
@@ -94,11 +94,26 @@ KERNEL_FQ void m20710_m04 (KERN_ATTR_RULES ())
*/
u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
- salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
- salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
- salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[2]);
- salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
+ salt_buf1[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
+ salt_buf1[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
+ salt_buf1[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
+ salt_buf1[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
+ salt_buf2[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
+ salt_buf2[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
+ salt_buf2[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[10]);
+ salt_buf2[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[11]);
+ salt_buf3[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[12]);
+ salt_buf3[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[13]);
+ salt_buf3[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[14]);
+ salt_buf3[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[15]);
const u32 salt_len = salt_bufs[salt_pos].salt_len;
@@ -267,15 +282,6 @@ KERNEL_FQ void m20710_m04 (KERN_ATTR_RULES ())
digest[6] = g;
digest[7] = h;
- a = digest[0];
- b = digest[1];
- c = digest[2];
- d = digest[3];
- e = digest[4];
- f = digest[5];
- g = digest[6];
- h = digest[7];
-
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
@@ -353,55 +359,284 @@ KERNEL_FQ void m20710_m04 (KERN_ATTR_RULES ())
digest[6] += g;
digest[7] += h;
- // add salt
+ // append salt
- u32x s0[4];
- u32x s1[4];
- u32x s2[4];
- u32x s3[4];
+ // sha256_update: ctx_len 64, pos 0, len = salt_len
- s0[0] = salt_buf0[0];
- s0[1] = salt_buf0[1];
- s0[2] = salt_buf0[2];
- s0[3] = salt_buf0[3];
- s1[0] = 0;
- s1[1] = 0;
- s1[2] = 0;
- s1[3] = 0;
- s2[0] = 0;
- s2[1] = 0;
- s2[2] = 0;
- s2[3] = 0;
- s3[0] = 0;
- s3[1] = 0;
- s3[2] = 0;
- s3[3] = 0;
+ w0_t = salt_buf0[0];
+ w1_t = salt_buf0[1];
+ w2_t = salt_buf0[2];
+ w3_t = salt_buf0[3];
+ w4_t = salt_buf1[0];
+ w5_t = salt_buf1[1];
+ w6_t = salt_buf1[2];
+ w7_t = salt_buf1[3];
+ w8_t = salt_buf2[0];
+ w9_t = salt_buf2[1];
+ wa_t = salt_buf2[2];
+ wb_t = salt_buf2[3];
+ wc_t = salt_buf3[0];
+ wd_t = salt_buf3[1];
+ we_t = salt_buf3[2];
+ wf_t = salt_buf3[3];
- // ctx_len 80, pos 16
+ // sha256_update_64: pos 0
- append_0x80_4x4 (s0, s1, s2, s3, 16 ^ 3);
+ if (salt_len == 64)
+ {
+ // sha256 transform
- s3[2] = 0;
- s3[3] = (64 + 16) * 8;
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
- w0_t = s0[0];
- w1_t = s0[1];
- w2_t = s0[2];
- w3_t = s0[3];
- w4_t = s1[0];
- w5_t = s1[1];
- w6_t = s1[2];
- w7_t = s1[3];
- w8_t = s2[0];
- w9_t = s2[1];
- wa_t = s2[2];
- wb_t = s2[3];
- wc_t = s3[0];
- wd_t = s3[1];
- we_t = s3[2];
- wf_t = s3[3];
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
- // sha256 transform
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ const int ctx_len = 64 + salt_len;
+
+ const int pos = ctx_len & 63;
+
+ // append_0x80_4x4, offset = pos ^ 3
+
+ const u32 off = pos ^ 3;
+
+ const u32 c0 = (off & 15) / 4;
+
+ const u32 r0 = 0xff << ((off & 3) * 8);
+
+ const u32 m0[4] = { ((c0 == 0) ? r0 : 0), ((c0 == 1) ? r0 : 0), ((c0 == 2) ? r0 : 0), ((c0 == 3) ? r0 : 0) };
+
+ const u32 off16 = off / 16;
+
+ const u32 v0[4] = { ((off16 == 0) ? 0x80808080 : 0), ((off16 == 1) ? 0x80808080 : 0), ((off16 == 2) ? 0x80808080 : 0), ((off16 == 3) ? 0x80808080 : 0) };
+
+ w0_t |= v0[0] & m0[0];
+ w1_t |= v0[0] & m0[1];
+ w2_t |= v0[0] & m0[2];
+ w3_t |= v0[0] & m0[3];
+ w4_t |= v0[1] & m0[0];
+ w5_t |= v0[1] & m0[1];
+ w6_t |= v0[1] & m0[2];
+ w7_t |= v0[1] & m0[3];
+ w8_t |= v0[2] & m0[0];
+ w9_t |= v0[2] & m0[1];
+ wa_t |= v0[2] & m0[2];
+ wb_t |= v0[2] & m0[3];
+ wc_t |= v0[3] & m0[0];
+ wd_t |= v0[3] & m0[1];
+ we_t |= v0[3] & m0[2];
+ wf_t |= v0[3] & m0[3];
+
+ if (pos >= 56)
+ {
+ // sha256 transform
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ // last sha256 transform
+
+ we_t = 0;
+ wf_t = ctx_len * 8;
a = digest[0];
b = digest[1];
@@ -553,11 +788,26 @@ KERNEL_FQ void m20710_s04 (KERN_ATTR_RULES ())
*/
u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
- salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
- salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
- salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[2]);
- salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
+ salt_buf1[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
+ salt_buf1[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
+ salt_buf1[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
+ salt_buf1[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
+ salt_buf2[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
+ salt_buf2[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
+ salt_buf2[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[10]);
+ salt_buf2[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[11]);
+ salt_buf3[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[12]);
+ salt_buf3[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[13]);
+ salt_buf3[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[14]);
+ salt_buf3[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[15]);
const u32 salt_len = salt_bufs[salt_pos].salt_len;
@@ -815,55 +1065,284 @@ KERNEL_FQ void m20710_s04 (KERN_ATTR_RULES ())
digest[6] += g;
digest[7] += h;
- // add salt
+ // append salt
- u32x s0[4];
- u32x s1[4];
- u32x s2[4];
- u32x s3[4];
+ // sha256_update: ctx_len 64, pos 0, len = salt_len
- s0[0] = salt_buf0[0];
- s0[1] = salt_buf0[1];
- s0[2] = salt_buf0[2];
- s0[3] = salt_buf0[3];
- s1[0] = 0;
- s1[1] = 0;
- s1[2] = 0;
- s1[3] = 0;
- s2[0] = 0;
- s2[1] = 0;
- s2[2] = 0;
- s2[3] = 0;
- s3[0] = 0;
- s3[1] = 0;
- s3[2] = 0;
- s3[3] = 0;
+ w0_t = salt_buf0[0];
+ w1_t = salt_buf0[1];
+ w2_t = salt_buf0[2];
+ w3_t = salt_buf0[3];
+ w4_t = salt_buf1[0];
+ w5_t = salt_buf1[1];
+ w6_t = salt_buf1[2];
+ w7_t = salt_buf1[3];
+ w8_t = salt_buf2[0];
+ w9_t = salt_buf2[1];
+ wa_t = salt_buf2[2];
+ wb_t = salt_buf2[3];
+ wc_t = salt_buf3[0];
+ wd_t = salt_buf3[1];
+ we_t = salt_buf3[2];
+ wf_t = salt_buf3[3];
- // ctx_len 80, pos 16
+ // sha256_update_64: pos 0
- append_0x80_4x4 (s0, s1, s2, s3, 16 ^ 3);
+ if (salt_len == 64)
+ {
+ // sha256 transform
- s3[2] = 0;
- s3[3] = (64 + 16) * 8;
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
- w0_t = s0[0];
- w1_t = s0[1];
- w2_t = s0[2];
- w3_t = s0[3];
- w4_t = s1[0];
- w5_t = s1[1];
- w6_t = s1[2];
- w7_t = s1[3];
- w8_t = s2[0];
- w9_t = s2[1];
- wa_t = s2[2];
- wb_t = s2[3];
- wc_t = s3[0];
- wd_t = s3[1];
- we_t = s3[2];
- wf_t = s3[3];
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
- // sha256 transform
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ const int ctx_len = 64 + salt_len;
+
+ const int pos = ctx_len & 63;
+
+ // append_0x80_4x4, offset = pos ^ 3
+
+ const u32 off = pos ^ 3;
+
+ const u32 c0 = (off & 15) / 4;
+
+ const u32 r0 = 0xff << ((off & 3) * 8);
+
+ const u32 m0[4] = { ((c0 == 0) ? r0 : 0), ((c0 == 1) ? r0 : 0), ((c0 == 2) ? r0 : 0), ((c0 == 3) ? r0 : 0) };
+
+ const u32 off16 = off / 16;
+
+ const u32 v0[4] = { ((off16 == 0) ? 0x80808080 : 0), ((off16 == 1) ? 0x80808080 : 0), ((off16 == 2) ? 0x80808080 : 0), ((off16 == 3) ? 0x80808080 : 0) };
+
+ w0_t |= v0[0] & m0[0];
+ w1_t |= v0[0] & m0[1];
+ w2_t |= v0[0] & m0[2];
+ w3_t |= v0[0] & m0[3];
+ w4_t |= v0[1] & m0[0];
+ w5_t |= v0[1] & m0[1];
+ w6_t |= v0[1] & m0[2];
+ w7_t |= v0[1] & m0[3];
+ w8_t |= v0[2] & m0[0];
+ w9_t |= v0[2] & m0[1];
+ wa_t |= v0[2] & m0[2];
+ wb_t |= v0[2] & m0[3];
+ wc_t |= v0[3] & m0[0];
+ wd_t |= v0[3] & m0[1];
+ we_t |= v0[3] & m0[2];
+ wf_t |= v0[3] & m0[3];
+
+ if (pos >= 56)
+ {
+ // sha256 transform
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ // last sha256 transform
+
+ we_t = 0;
+ wf_t = ctx_len * 8;
a = digest[0];
b = digest[1];
diff --git a/OpenCL/m20710_a1-optimized.cl b/OpenCL/m20710_a1-optimized.cl
index 360fc61b1..8458348fb 100644
--- a/OpenCL/m20710_a1-optimized.cl
+++ b/OpenCL/m20710_a1-optimized.cl
@@ -92,11 +92,26 @@ KERNEL_FQ void m20710_m04 (KERN_ATTR_BASIC ())
*/
u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
- salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
- salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
- salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[2]);
- salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
+ salt_buf1[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
+ salt_buf1[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
+ salt_buf1[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
+ salt_buf1[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
+ salt_buf2[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
+ salt_buf2[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
+ salt_buf2[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[10]);
+ salt_buf2[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[11]);
+ salt_buf3[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[12]);
+ salt_buf3[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[13]);
+ salt_buf3[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[14]);
+ salt_buf3[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[15]);
const u32 salt_len = salt_bufs[salt_pos].salt_len;
@@ -323,15 +338,6 @@ KERNEL_FQ void m20710_m04 (KERN_ATTR_BASIC ())
digest[6] = g;
digest[7] = h;
- a = digest[0];
- b = digest[1];
- c = digest[2];
- d = digest[3];
- e = digest[4];
- f = digest[5];
- g = digest[6];
- h = digest[7];
-
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
@@ -409,55 +415,284 @@ KERNEL_FQ void m20710_m04 (KERN_ATTR_BASIC ())
digest[6] += g;
digest[7] += h;
- // add salt
+ // append salt
- u32x s0[4];
- u32x s1[4];
- u32x s2[4];
- u32x s3[4];
+ // sha256_update: ctx_len 64, pos 0, len = salt_len
- s0[0] = salt_buf0[0];
- s0[1] = salt_buf0[1];
- s0[2] = salt_buf0[2];
- s0[3] = salt_buf0[3];
- s1[0] = 0;
- s1[1] = 0;
- s1[2] = 0;
- s1[3] = 0;
- s2[0] = 0;
- s2[1] = 0;
- s2[2] = 0;
- s2[3] = 0;
- s3[0] = 0;
- s3[1] = 0;
- s3[2] = 0;
- s3[3] = 0;
+ w0_t = salt_buf0[0];
+ w1_t = salt_buf0[1];
+ w2_t = salt_buf0[2];
+ w3_t = salt_buf0[3];
+ w4_t = salt_buf1[0];
+ w5_t = salt_buf1[1];
+ w6_t = salt_buf1[2];
+ w7_t = salt_buf1[3];
+ w8_t = salt_buf2[0];
+ w9_t = salt_buf2[1];
+ wa_t = salt_buf2[2];
+ wb_t = salt_buf2[3];
+ wc_t = salt_buf3[0];
+ wd_t = salt_buf3[1];
+ we_t = salt_buf3[2];
+ wf_t = salt_buf3[3];
- // ctx_len 80, pos 16
+ // sha256_update_64: pos 0
- append_0x80_4x4 (s0, s1, s2, s3, 16 ^ 3);
+ if (salt_len == 64)
+ {
+ // sha256 transform
- s3[2] = 0;
- s3[3] = (64 + 16) * 8;
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
- w0_t = s0[0];
- w1_t = s0[1];
- w2_t = s0[2];
- w3_t = s0[3];
- w4_t = s1[0];
- w5_t = s1[1];
- w6_t = s1[2];
- w7_t = s1[3];
- w8_t = s2[0];
- w9_t = s2[1];
- wa_t = s2[2];
- wb_t = s2[3];
- wc_t = s3[0];
- wd_t = s3[1];
- we_t = s3[2];
- wf_t = s3[3];
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
- // sha256 transform
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ const int ctx_len = 64 + salt_len;
+
+ const int pos = ctx_len & 63;
+
+ // append_0x80_4x4, offset = pos ^ 3
+
+ const u32 off = pos ^ 3;
+
+ const u32 c0 = (off & 15) / 4;
+
+ const u32 r0 = 0xff << ((off & 3) * 8);
+
+ const u32 m0[4] = { ((c0 == 0) ? r0 : 0), ((c0 == 1) ? r0 : 0), ((c0 == 2) ? r0 : 0), ((c0 == 3) ? r0 : 0) };
+
+ const u32 off16 = off / 16;
+
+ const u32 v0[4] = { ((off16 == 0) ? 0x80808080 : 0), ((off16 == 1) ? 0x80808080 : 0), ((off16 == 2) ? 0x80808080 : 0), ((off16 == 3) ? 0x80808080 : 0) };
+
+ w0_t |= v0[0] & m0[0];
+ w1_t |= v0[0] & m0[1];
+ w2_t |= v0[0] & m0[2];
+ w3_t |= v0[0] & m0[3];
+ w4_t |= v0[1] & m0[0];
+ w5_t |= v0[1] & m0[1];
+ w6_t |= v0[1] & m0[2];
+ w7_t |= v0[1] & m0[3];
+ w8_t |= v0[2] & m0[0];
+ w9_t |= v0[2] & m0[1];
+ wa_t |= v0[2] & m0[2];
+ wb_t |= v0[2] & m0[3];
+ wc_t |= v0[3] & m0[0];
+ wd_t |= v0[3] & m0[1];
+ we_t |= v0[3] & m0[2];
+ wf_t |= v0[3] & m0[3];
+
+ if (pos >= 56)
+ {
+ // sha256 transform
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ // last sha256 transform
+
+ we_t = 0;
+ wf_t = ctx_len * 8;
a = digest[0];
b = digest[1];
@@ -609,11 +844,26 @@ KERNEL_FQ void m20710_s04 (KERN_ATTR_BASIC ())
*/
u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
- salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
- salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
- salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[2]);
- salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
+ salt_buf1[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
+ salt_buf1[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
+ salt_buf1[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
+ salt_buf1[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
+ salt_buf2[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
+ salt_buf2[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
+ salt_buf2[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[10]);
+ salt_buf2[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[11]);
+ salt_buf3[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[12]);
+ salt_buf3[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[13]);
+ salt_buf3[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[14]);
+ salt_buf3[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[15]);
const u32 salt_len = salt_bufs[salt_pos].salt_len;
@@ -929,55 +1179,284 @@ KERNEL_FQ void m20710_s04 (KERN_ATTR_BASIC ())
digest[6] += g;
digest[7] += h;
- // add salt
+ // append salt
- u32x s0[4];
- u32x s1[4];
- u32x s2[4];
- u32x s3[4];
+ // sha256_update: ctx_len 64, pos 0, len = salt_len
- s0[0] = salt_buf0[0];
- s0[1] = salt_buf0[1];
- s0[2] = salt_buf0[2];
- s0[3] = salt_buf0[3];
- s1[0] = 0;
- s1[1] = 0;
- s1[2] = 0;
- s1[3] = 0;
- s2[0] = 0;
- s2[1] = 0;
- s2[2] = 0;
- s2[3] = 0;
- s3[0] = 0;
- s3[1] = 0;
- s3[2] = 0;
- s3[3] = 0;
+ w0_t = salt_buf0[0];
+ w1_t = salt_buf0[1];
+ w2_t = salt_buf0[2];
+ w3_t = salt_buf0[3];
+ w4_t = salt_buf1[0];
+ w5_t = salt_buf1[1];
+ w6_t = salt_buf1[2];
+ w7_t = salt_buf1[3];
+ w8_t = salt_buf2[0];
+ w9_t = salt_buf2[1];
+ wa_t = salt_buf2[2];
+ wb_t = salt_buf2[3];
+ wc_t = salt_buf3[0];
+ wd_t = salt_buf3[1];
+ we_t = salt_buf3[2];
+ wf_t = salt_buf3[3];
- // ctx_len 80, pos 16
+ // sha256_update_64: pos 0
- append_0x80_4x4 (s0, s1, s2, s3, 16 ^ 3);
+ if (salt_len == 64)
+ {
+ // sha256 transform
- s3[2] = 0;
- s3[3] = (64 + 16) * 8;
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
- w0_t = s0[0];
- w1_t = s0[1];
- w2_t = s0[2];
- w3_t = s0[3];
- w4_t = s1[0];
- w5_t = s1[1];
- w6_t = s1[2];
- w7_t = s1[3];
- w8_t = s2[0];
- w9_t = s2[1];
- wa_t = s2[2];
- wb_t = s2[3];
- wc_t = s3[0];
- wd_t = s3[1];
- we_t = s3[2];
- wf_t = s3[3];
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
- // sha256 transform
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ const int ctx_len = 64 + salt_len;
+
+ const int pos = ctx_len & 63;
+
+ // append_0x80_4x4, offset = pos ^ 3
+
+ const u32 off = pos ^ 3;
+
+ const u32 c0 = (off & 15) / 4;
+
+ const u32 r0 = 0xff << ((off & 3) * 8);
+
+ const u32 m0[4] = { ((c0 == 0) ? r0 : 0), ((c0 == 1) ? r0 : 0), ((c0 == 2) ? r0 : 0), ((c0 == 3) ? r0 : 0) };
+
+ const u32 off16 = off / 16;
+
+ const u32 v0[4] = { ((off16 == 0) ? 0x80808080 : 0), ((off16 == 1) ? 0x80808080 : 0), ((off16 == 2) ? 0x80808080 : 0), ((off16 == 3) ? 0x80808080 : 0) };
+
+ w0_t |= v0[0] & m0[0];
+ w1_t |= v0[0] & m0[1];
+ w2_t |= v0[0] & m0[2];
+ w3_t |= v0[0] & m0[3];
+ w4_t |= v0[1] & m0[0];
+ w5_t |= v0[1] & m0[1];
+ w6_t |= v0[1] & m0[2];
+ w7_t |= v0[1] & m0[3];
+ w8_t |= v0[2] & m0[0];
+ w9_t |= v0[2] & m0[1];
+ wa_t |= v0[2] & m0[2];
+ wb_t |= v0[2] & m0[3];
+ wc_t |= v0[3] & m0[0];
+ wd_t |= v0[3] & m0[1];
+ we_t |= v0[3] & m0[2];
+ wf_t |= v0[3] & m0[3];
+
+ if (pos >= 56)
+ {
+ // sha256 transform
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ // last sha256 transform
+
+ we_t = 0;
+ wf_t = ctx_len * 8;
a = digest[0];
b = digest[1];
diff --git a/OpenCL/m20710_a3-optimized.cl b/OpenCL/m20710_a3-optimized.cl
index 409133f89..95f20665d 100644
--- a/OpenCL/m20710_a3-optimized.cl
+++ b/OpenCL/m20710_a3-optimized.cl
@@ -54,11 +54,26 @@ DECLSPEC void m20710m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u
*/
u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
- salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
- salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
- salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[2]);
- salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
+ salt_buf1[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
+ salt_buf1[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
+ salt_buf1[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
+ salt_buf1[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
+ salt_buf2[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
+ salt_buf2[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
+ salt_buf2[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[10]);
+ salt_buf2[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[11]);
+ salt_buf3[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[12]);
+ salt_buf3[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[13]);
+ salt_buf3[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[14]);
+ salt_buf3[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[15]);
const u32 salt_len = salt_bufs[salt_pos].salt_len;
@@ -224,15 +239,6 @@ DECLSPEC void m20710m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u
digest[6] = g;
digest[7] = h;
- a = digest[0];
- b = digest[1];
- c = digest[2];
- d = digest[3];
- e = digest[4];
- f = digest[5];
- g = digest[6];
- h = digest[7];
-
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
@@ -310,55 +316,284 @@ DECLSPEC void m20710m (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u
digest[6] += g;
digest[7] += h;
- // add salt
+ // append salt
- u32x s0[4];
- u32x s1[4];
- u32x s2[4];
- u32x s3[4];
+ // sha256_update: ctx_len 64, pos 0, len = salt_len
- s0[0] = salt_buf0[0];
- s0[1] = salt_buf0[1];
- s0[2] = salt_buf0[2];
- s0[3] = salt_buf0[3];
- s1[0] = 0;
- s1[1] = 0;
- s1[2] = 0;
- s1[3] = 0;
- s2[0] = 0;
- s2[1] = 0;
- s2[2] = 0;
- s2[3] = 0;
- s3[0] = 0;
- s3[1] = 0;
- s3[2] = 0;
- s3[3] = 0;
+ w0_t = salt_buf0[0];
+ w1_t = salt_buf0[1];
+ w2_t = salt_buf0[2];
+ w3_t = salt_buf0[3];
+ w4_t = salt_buf1[0];
+ w5_t = salt_buf1[1];
+ w6_t = salt_buf1[2];
+ w7_t = salt_buf1[3];
+ w8_t = salt_buf2[0];
+ w9_t = salt_buf2[1];
+ wa_t = salt_buf2[2];
+ wb_t = salt_buf2[3];
+ wc_t = salt_buf3[0];
+ wd_t = salt_buf3[1];
+ we_t = salt_buf3[2];
+ wf_t = salt_buf3[3];
- // ctx_len 80, pos 16
+ // sha256_update_64: pos 0
- append_0x80_4x4 (s0, s1, s2, s3, 16 ^ 3);
+ if (salt_len == 64)
+ {
+ // sha256 transform
- s3[2] = 0;
- s3[3] = (64 + 16) * 8;
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
- w0_t = s0[0];
- w1_t = s0[1];
- w2_t = s0[2];
- w3_t = s0[3];
- w4_t = s1[0];
- w5_t = s1[1];
- w6_t = s1[2];
- w7_t = s1[3];
- w8_t = s2[0];
- w9_t = s2[1];
- wa_t = s2[2];
- wb_t = s2[3];
- wc_t = s3[0];
- wd_t = s3[1];
- we_t = s3[2];
- wf_t = s3[3];
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
- // sha256 transform
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ const int ctx_len = 64 + salt_len;
+
+ const int pos = ctx_len & 63;
+
+ // append_0x80_4x4, offset = pos ^ 3
+
+ const u32 off = pos ^ 3;
+
+ const u32 c0 = (off & 15) / 4;
+
+ const u32 r0 = 0xff << ((off & 3) * 8);
+
+ const u32 m0[4] = { ((c0 == 0) ? r0 : 0), ((c0 == 1) ? r0 : 0), ((c0 == 2) ? r0 : 0), ((c0 == 3) ? r0 : 0) };
+
+ const u32 off16 = off / 16;
+
+ const u32 v0[4] = { ((off16 == 0) ? 0x80808080 : 0), ((off16 == 1) ? 0x80808080 : 0), ((off16 == 2) ? 0x80808080 : 0), ((off16 == 3) ? 0x80808080 : 0) };
+
+ w0_t |= v0[0] & m0[0];
+ w1_t |= v0[0] & m0[1];
+ w2_t |= v0[0] & m0[2];
+ w3_t |= v0[0] & m0[3];
+ w4_t |= v0[1] & m0[0];
+ w5_t |= v0[1] & m0[1];
+ w6_t |= v0[1] & m0[2];
+ w7_t |= v0[1] & m0[3];
+ w8_t |= v0[2] & m0[0];
+ w9_t |= v0[2] & m0[1];
+ wa_t |= v0[2] & m0[2];
+ wb_t |= v0[2] & m0[3];
+ wc_t |= v0[3] & m0[0];
+ wd_t |= v0[3] & m0[1];
+ we_t |= v0[3] & m0[2];
+ wf_t |= v0[3] & m0[3];
+
+ if (pos >= 56)
+ {
+ // sha256 transform
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ // last sha256 transform
+
+ we_t = 0;
+ wf_t = ctx_len * 8;
a = digest[0];
b = digest[1];
@@ -476,11 +711,26 @@ DECLSPEC void m20710s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u
*/
u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
- salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[0]);
- salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[1]);
- salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[2]);
- salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[3]);
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
+ salt_buf1[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
+ salt_buf1[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
+ salt_buf1[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
+ salt_buf1[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
+ salt_buf2[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
+ salt_buf2[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
+ salt_buf2[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[10]);
+ salt_buf2[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[11]);
+ salt_buf3[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[12]);
+ salt_buf3[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[13]);
+ salt_buf3[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[14]);
+ salt_buf3[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[15]);
const u32 salt_len = salt_bufs[salt_pos].salt_len;
@@ -646,15 +896,6 @@ DECLSPEC void m20710s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u
digest[6] = g;
digest[7] = h;
- a = digest[0];
- b = digest[1];
- c = digest[2];
- d = digest[3];
- e = digest[4];
- f = digest[5];
- g = digest[6];
- h = digest[7];
-
SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
@@ -732,55 +973,284 @@ DECLSPEC void m20710s (u32 *w, const u32 pw_len, KERN_ATTR_VECTOR (), LOCAL_AS u
digest[6] += g;
digest[7] += h;
- // add salt
+ // append salt
- u32x s0[4];
- u32x s1[4];
- u32x s2[4];
- u32x s3[4];
+ // sha256_update: ctx_len 64, pos 0, len = salt_len
- s0[0] = salt_buf0[0];
- s0[1] = salt_buf0[1];
- s0[2] = salt_buf0[2];
- s0[3] = salt_buf0[3];
- s1[0] = 0;
- s1[1] = 0;
- s1[2] = 0;
- s1[3] = 0;
- s2[0] = 0;
- s2[1] = 0;
- s2[2] = 0;
- s2[3] = 0;
- s3[0] = 0;
- s3[1] = 0;
- s3[2] = 0;
- s3[3] = 0;
+ w0_t = salt_buf0[0];
+ w1_t = salt_buf0[1];
+ w2_t = salt_buf0[2];
+ w3_t = salt_buf0[3];
+ w4_t = salt_buf1[0];
+ w5_t = salt_buf1[1];
+ w6_t = salt_buf1[2];
+ w7_t = salt_buf1[3];
+ w8_t = salt_buf2[0];
+ w9_t = salt_buf2[1];
+ wa_t = salt_buf2[2];
+ wb_t = salt_buf2[3];
+ wc_t = salt_buf3[0];
+ wd_t = salt_buf3[1];
+ we_t = salt_buf3[2];
+ wf_t = salt_buf3[3];
- // ctx_len 80, pos 16
+ // sha256_update_64: pos 0
- append_0x80_4x4 (s0, s1, s2, s3, 16 ^ 3);
+ if (salt_len == 64)
+ {
+ // sha256 transform
- s3[2] = 0;
- s3[3] = (64 + 16) * 8;
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
- w0_t = s0[0];
- w1_t = s0[1];
- w2_t = s0[2];
- w3_t = s0[3];
- w4_t = s1[0];
- w5_t = s1[1];
- w6_t = s1[2];
- w7_t = s1[3];
- w8_t = s2[0];
- w9_t = s2[1];
- wa_t = s2[2];
- wb_t = s2[3];
- wc_t = s3[0];
- wd_t = s3[1];
- we_t = s3[2];
- wf_t = s3[3];
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
- // sha256 transform
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ const int ctx_len = 64 + salt_len;
+
+ const int pos = ctx_len & 63;
+
+ // append_0x80_4x4, offset = pos ^ 3
+
+ const u32 off = pos ^ 3;
+
+ const u32 c0 = (off & 15) / 4;
+
+ const u32 r0 = 0xff << ((off & 3) * 8);
+
+ const u32 m0[4] = { ((c0 == 0) ? r0 : 0), ((c0 == 1) ? r0 : 0), ((c0 == 2) ? r0 : 0), ((c0 == 3) ? r0 : 0) };
+
+ const u32 off16 = off / 16;
+
+ const u32 v0[4] = { ((off16 == 0) ? 0x80808080 : 0), ((off16 == 1) ? 0x80808080 : 0), ((off16 == 2) ? 0x80808080 : 0), ((off16 == 3) ? 0x80808080 : 0) };
+
+ w0_t |= v0[0] & m0[0];
+ w1_t |= v0[0] & m0[1];
+ w2_t |= v0[0] & m0[2];
+ w3_t |= v0[0] & m0[3];
+ w4_t |= v0[1] & m0[0];
+ w5_t |= v0[1] & m0[1];
+ w6_t |= v0[1] & m0[2];
+ w7_t |= v0[1] & m0[3];
+ w8_t |= v0[2] & m0[0];
+ w9_t |= v0[2] & m0[1];
+ wa_t |= v0[2] & m0[2];
+ wb_t |= v0[2] & m0[3];
+ wc_t |= v0[3] & m0[0];
+ wd_t |= v0[3] & m0[1];
+ we_t |= v0[3] & m0[2];
+ wf_t |= v0[3] & m0[3];
+
+ if (pos >= 56)
+ {
+ // sha256 transform
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+ digest[5] = f;
+ digest[6] = g;
+ digest[7] = h;
+
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
+ SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
+
+ w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
+ w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
+ w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
+ w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
+ w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
+ w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
+ w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
+ w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
+ w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
+ w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
+ wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
+ wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
+ wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
+ wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
+ we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
+ wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+ digest[5] += f;
+ digest[6] += g;
+ digest[7] += h;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ // last sha256 transform
+
+ we_t = 0;
+ wf_t = ctx_len * 8;
a = digest[0];
b = digest[1];
diff --git a/src/modules/module_20710.c b/src/modules/module_20710.c
index d71160c25..6d867729b 100644
--- a/src/modules/module_20710.c
+++ b/src/modules/module_20710.c
@@ -47,13 +47,6 @@ u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig,
const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
-u32 module_pw_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
-{
- const u32 pw_max = 32;
-
- return pw_max;
-}
-
int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
{
u32 *digest = (u32 *) digest_buf;
@@ -244,7 +237,7 @@ void module_init (module_ctx_t *module_ctx)
module_ctx->module_potfile_disable = MODULE_DEFAULT;
module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
module_ctx->module_pwdump_column = MODULE_DEFAULT;
- module_ctx->module_pw_max = module_pw_max;
+ module_ctx->module_pw_max = MODULE_DEFAULT;
module_ctx->module_pw_min = MODULE_DEFAULT;
module_ctx->module_salt_max = MODULE_DEFAULT;
module_ctx->module_salt_min = MODULE_DEFAULT;
diff --git a/src/modules/module_20711.c b/src/modules/module_20711.c
index 0628759be..2cf90e042 100644
--- a/src/modules/module_20711.c
+++ b/src/modules/module_20711.c
@@ -61,13 +61,6 @@ u32 module_salt_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED c
return salt_max;
}
-u32 module_pw_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
-{
- const u32 pw_max = 32;
-
- return pw_max;
-}
-
static const char *SIGNATURE_AUTHME = "$SHA$";
int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
@@ -279,7 +272,7 @@ void module_init (module_ctx_t *module_ctx)
module_ctx->module_potfile_disable = MODULE_DEFAULT;
module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
module_ctx->module_pwdump_column = MODULE_DEFAULT;
- module_ctx->module_pw_max = module_pw_max;
+ module_ctx->module_pw_max = MODULE_DEFAULT;
module_ctx->module_pw_min = MODULE_DEFAULT;
module_ctx->module_salt_max = module_salt_max;
module_ctx->module_salt_min = module_salt_min;
diff --git a/tools/test_modules/m20710.pm b/tools/test_modules/m20710.pm
index 191f4a7c7..3a68ada40 100644
--- a/tools/test_modules/m20710.pm
+++ b/tools/test_modules/m20710.pm
@@ -10,7 +10,7 @@ use warnings;
use Digest::SHA qw (sha256_hex);
-sub module_constraints { [[1, 31], [16, 16], [1, 31], [16, 16], [-1, -1]] }
+sub module_constraints { [[0, 256], [0, 256], [0, 55], [16, 16], [-1, -1]] }
sub module_generate_hash
{
@@ -34,8 +34,6 @@ sub module_verify_hash
return unless defined $salt;
return unless defined $word;
- return unless length ($salt) == 16;
-
my $word_packed = pack_if_HEX_notation ($word);
my $new_hash = module_generate_hash ($word_packed, $salt);
diff --git a/tools/test_modules/m20711.pm b/tools/test_modules/m20711.pm
index 334c20b10..5dd264225 100644
--- a/tools/test_modules/m20711.pm
+++ b/tools/test_modules/m20711.pm
@@ -10,7 +10,7 @@ use warnings;
use Digest::SHA qw (sha256_hex);
-sub module_constraints { [[1, 31], [16, 16], [1, 31], [16, 16], [-1, -1]] }
+sub module_constraints { [[0, 256], [16, 16], [0, 55], [16, 16], [-1, -1]] }
sub module_generate_hash
{
From 06bde16336c7c3c303e239b95d78214ec09a6893 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Sat, 3 Aug 2019 19:53:23 +0200
Subject: [PATCH 068/113] Added hash-mode 4711, Huawei sha1(md5(pass).salt)
---
OpenCL/m04710_a0-optimized.cl | 1447 ++++++++++++++++++++++++++
OpenCL/m04710_a1-optimized.cl | 1555 ++++++++++++++++++++++++++++
OpenCL/m04710_a3-optimized.cl | 1795 +++++++++++++++++++++++++++++++++
src/modules/module_04711.c | 246 +++++
tools/test_modules/m04710.pm | 2 +-
tools/test_modules/m04711.pm | 47 +
6 files changed, 5091 insertions(+), 1 deletion(-)
create mode 100644 OpenCL/m04710_a0-optimized.cl
create mode 100644 OpenCL/m04710_a1-optimized.cl
create mode 100644 OpenCL/m04710_a3-optimized.cl
create mode 100644 src/modules/module_04711.c
create mode 100644 tools/test_modules/m04711.pm
diff --git a/OpenCL/m04710_a0-optimized.cl b/OpenCL/m04710_a0-optimized.cl
new file mode 100644
index 000000000..14457b377
--- /dev/null
+++ b/OpenCL/m04710_a0-optimized.cl
@@ -0,0 +1,1447 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_rp_optimized.h"
+#include "inc_rp_optimized.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04710_m04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
+ salt_buf1[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
+ salt_buf1[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
+ salt_buf1[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
+ salt_buf1[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
+ salt_buf2[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
+ salt_buf2[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
+ salt_buf2[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[10]);
+ salt_buf2[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[11]);
+ salt_buf3[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[12]);
+ salt_buf3[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[13]);
+ salt_buf3[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[14]);
+ salt_buf3[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[15]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ w3[2] = out_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5(pass)
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ // sha1
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 0;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ u32x digest[8];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+
+ // append salt
+
+ // ctx_len 32, pos 32
+
+ int pos = 32;
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = salt_buf1[0];
+ s1[1] = salt_buf1[1];
+ s1[2] = salt_buf1[2];
+ s1[3] = salt_buf1[3];
+ s2[0] = salt_buf2[0];
+ s2[1] = salt_buf2[1];
+ s2[2] = salt_buf2[2];
+ s2[3] = salt_buf2[3];
+ s3[0] = salt_buf3[0];
+ s3[1] = salt_buf3[1];
+ s3[2] = salt_buf3[2];
+ s3[3] = salt_buf3[3];
+
+ if ((pos + salt_len) < 64)
+ {
+ switch_buffer_by_offset_be (s0, s1, s2, s3, pos);
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+ w8_t |= s2[0];
+ w9_t |= s2[1];
+ wa_t |= s2[2];
+ wb_t |= s2[3];
+ wc_t |= s3[0];
+ wd_t |= s3[1];
+ we_t |= s3[2];
+ wf_t |= s3[3];
+ }
+ else
+ {
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_be (s0, s1, s2, s3, _w0, _w1, _w2, _w3, pos);
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+ w8_t |= s2[0];
+ w9_t |= s2[1];
+ wa_t |= s2[2];
+ wb_t |= s2[3];
+ wc_t |= s3[0];
+ wd_t |= s3[1];
+ we_t |= s3[2];
+ wf_t |= s3[3];
+
+ // sha1 transform
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+
+ w0_t = _w0[0];
+ w1_t = _w0[1];
+ w2_t = _w0[2];
+ w3_t = _w0[3];
+ w4_t = _w1[0];
+ w5_t = _w1[1];
+ w6_t = _w1[2];
+ w7_t = _w1[3];
+ w8_t = _w2[0];
+ w9_t = _w2[1];
+ wa_t = _w2[2];
+ wb_t = _w2[3];
+ wc_t = _w3[0];
+ wd_t = _w3[1];
+ we_t = _w3[2];
+ wf_t = _w3[3];
+ }
+
+ const int ctx_len = 32 + salt_len;
+
+ pos = ctx_len & 63;
+
+ // append_0x80_4x4
+
+ const u32 off = pos ^ 3;
+
+ const u32 c0 = (off & 15) / 4;
+
+ const u32 r0 = 0xff << ((off & 3) * 8);
+
+ const u32 m0[4] = { ((c0 == 0) ? r0 : 0), ((c0 == 1) ? r0 : 0), ((c0 == 2) ? r0 : 0), ((c0 == 3) ? r0 : 0) };
+
+ const u32 off16 = off / 16;
+
+ const u32 v0[4] = { ((off16 == 0) ? 0x80808080 : 0), ((off16 == 1) ? 0x80808080 : 0), ((off16 == 2) ? 0x80808080 : 0), ((off16 == 3) ? 0x80808080 : 0) };
+
+ w0_t |= v0[0] & m0[0];
+ w1_t |= v0[0] & m0[1];
+ w2_t |= v0[0] & m0[2];
+ w3_t |= v0[0] & m0[3];
+ w4_t |= v0[1] & m0[0];
+ w5_t |= v0[1] & m0[1];
+ w6_t |= v0[1] & m0[2];
+ w7_t |= v0[1] & m0[3];
+ w8_t |= v0[2] & m0[0];
+ w9_t |= v0[2] & m0[1];
+ wa_t |= v0[2] & m0[2];
+ wb_t |= v0[2] & m0[3];
+ wc_t |= v0[3] & m0[0];
+ wd_t |= v0[3] & m0[1];
+ we_t |= v0[3] & m0[2];
+ wf_t |= v0[3] & m0[3];
+
+ if (pos >= 56)
+ {
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ // last sha1 transform
+
+ we_t = 0;
+ wf_t = ctx_len * 8;
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_M_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m04710_m08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04710_m16 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04710_s04 (KERN_ATTR_RULES ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
+ salt_buf1[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
+ salt_buf1[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
+ salt_buf1[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
+ salt_buf1[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
+ salt_buf2[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
+ salt_buf2[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
+ salt_buf2[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[10]);
+ salt_buf2[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[11]);
+ salt_buf3[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[12]);
+ salt_buf3[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[13]);
+ salt_buf3[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[14]);
+ salt_buf3[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[15]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ u32x w0[4] = { 0 };
+ u32x w1[4] = { 0 };
+ u32x w2[4] = { 0 };
+ u32x w3[4] = { 0 };
+
+ const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
+
+ append_0x80_2x4_VV (w0, w1, out_len);
+
+ w3[2] = out_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5(pass)
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ // sha1
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 0;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ u32x digest[8];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+
+ // append salt
+
+ // ctx_len 32, pos 32
+
+ int pos = 32;
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = salt_buf1[0];
+ s1[1] = salt_buf1[1];
+ s1[2] = salt_buf1[2];
+ s1[3] = salt_buf1[3];
+ s2[0] = salt_buf2[0];
+ s2[1] = salt_buf2[1];
+ s2[2] = salt_buf2[2];
+ s2[3] = salt_buf2[3];
+ s3[0] = salt_buf3[0];
+ s3[1] = salt_buf3[1];
+ s3[2] = salt_buf3[2];
+ s3[3] = salt_buf3[3];
+
+ if ((pos + salt_len) < 64)
+ {
+ switch_buffer_by_offset_be (s0, s1, s2, s3, pos);
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+ w8_t |= s2[0];
+ w9_t |= s2[1];
+ wa_t |= s2[2];
+ wb_t |= s2[3];
+ wc_t |= s3[0];
+ wd_t |= s3[1];
+ we_t |= s3[2];
+ wf_t |= s3[3];
+ }
+ else
+ {
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_be (s0, s1, s2, s3, _w0, _w1, _w2, _w3, pos);
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+ w8_t |= s2[0];
+ w9_t |= s2[1];
+ wa_t |= s2[2];
+ wb_t |= s2[3];
+ wc_t |= s3[0];
+ wd_t |= s3[1];
+ we_t |= s3[2];
+ wf_t |= s3[3];
+
+ // sha1 transform
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+
+ w0_t = _w0[0];
+ w1_t = _w0[1];
+ w2_t = _w0[2];
+ w3_t = _w0[3];
+ w4_t = _w1[0];
+ w5_t = _w1[1];
+ w6_t = _w1[2];
+ w7_t = _w1[3];
+ w8_t = _w2[0];
+ w9_t = _w2[1];
+ wa_t = _w2[2];
+ wb_t = _w2[3];
+ wc_t = _w3[0];
+ wd_t = _w3[1];
+ we_t = _w3[2];
+ wf_t = _w3[3];
+ }
+
+ const int ctx_len = 32 + salt_len;
+
+ pos = ctx_len & 63;
+
+ // append_0x80_4x4
+
+ const u32 off = pos ^ 3;
+
+ const u32 c0 = (off & 15) / 4;
+
+ const u32 r0 = 0xff << ((off & 3) * 8);
+
+ const u32 m0[4] = { ((c0 == 0) ? r0 : 0), ((c0 == 1) ? r0 : 0), ((c0 == 2) ? r0 : 0), ((c0 == 3) ? r0 : 0) };
+
+ const u32 off16 = off / 16;
+
+ const u32 v0[4] = { ((off16 == 0) ? 0x80808080 : 0), ((off16 == 1) ? 0x80808080 : 0), ((off16 == 2) ? 0x80808080 : 0), ((off16 == 3) ? 0x80808080 : 0) };
+
+ w0_t |= v0[0] & m0[0];
+ w1_t |= v0[0] & m0[1];
+ w2_t |= v0[0] & m0[2];
+ w3_t |= v0[0] & m0[3];
+ w4_t |= v0[1] & m0[0];
+ w5_t |= v0[1] & m0[1];
+ w6_t |= v0[1] & m0[2];
+ w7_t |= v0[1] & m0[3];
+ w8_t |= v0[2] & m0[0];
+ w9_t |= v0[2] & m0[1];
+ wa_t |= v0[2] & m0[2];
+ wb_t |= v0[2] & m0[3];
+ wc_t |= v0[3] & m0[0];
+ wd_t |= v0[3] & m0[1];
+ we_t |= v0[3] & m0[2];
+ wf_t |= v0[3] & m0[3];
+
+ if (pos >= 56)
+ {
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ // last sha1 transform
+
+ we_t = 0;
+ wf_t = ctx_len * 8;
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+ if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_S_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m04710_s08 (KERN_ATTR_RULES ())
+{
+}
+
+KERNEL_FQ void m04710_s16 (KERN_ATTR_RULES ())
+{
+}
diff --git a/OpenCL/m04710_a1-optimized.cl b/OpenCL/m04710_a1-optimized.cl
new file mode 100644
index 000000000..9acaac644
--- /dev/null
+++ b/OpenCL/m04710_a1-optimized.cl
@@ -0,0 +1,1555 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
+ salt_buf1[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
+ salt_buf1[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
+ salt_buf1[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
+ salt_buf1[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
+ salt_buf2[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
+ salt_buf2[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
+ salt_buf2[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[10]);
+ salt_buf2[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[11]);
+ salt_buf3[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[12]);
+ salt_buf3[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[13]);
+ salt_buf3[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[14]);
+ salt_buf3[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[15]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = pw_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5(pass)
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ // sha1
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 0;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ u32x digest[8];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+
+ // append salt
+
+ // ctx_len 32, pos 32
+
+ int pos = 32;
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = salt_buf1[0];
+ s1[1] = salt_buf1[1];
+ s1[2] = salt_buf1[2];
+ s1[3] = salt_buf1[3];
+ s2[0] = salt_buf2[0];
+ s2[1] = salt_buf2[1];
+ s2[2] = salt_buf2[2];
+ s2[3] = salt_buf2[3];
+ s3[0] = salt_buf3[0];
+ s3[1] = salt_buf3[1];
+ s3[2] = salt_buf3[2];
+ s3[3] = salt_buf3[3];
+
+ if ((pos + salt_len) < 64)
+ {
+ switch_buffer_by_offset_be (s0, s1, s2, s3, pos);
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+ w8_t |= s2[0];
+ w9_t |= s2[1];
+ wa_t |= s2[2];
+ wb_t |= s2[3];
+ wc_t |= s3[0];
+ wd_t |= s3[1];
+ we_t |= s3[2];
+ wf_t |= s3[3];
+ }
+ else
+ {
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_be (s0, s1, s2, s3, _w0, _w1, _w2, _w3, pos);
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+ w8_t |= s2[0];
+ w9_t |= s2[1];
+ wa_t |= s2[2];
+ wb_t |= s2[3];
+ wc_t |= s3[0];
+ wd_t |= s3[1];
+ we_t |= s3[2];
+ wf_t |= s3[3];
+
+ // sha1 transform
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+
+ w0_t = _w0[0];
+ w1_t = _w0[1];
+ w2_t = _w0[2];
+ w3_t = _w0[3];
+ w4_t = _w1[0];
+ w5_t = _w1[1];
+ w6_t = _w1[2];
+ w7_t = _w1[3];
+ w8_t = _w2[0];
+ w9_t = _w2[1];
+ wa_t = _w2[2];
+ wb_t = _w2[3];
+ wc_t = _w3[0];
+ wd_t = _w3[1];
+ we_t = _w3[2];
+ wf_t = _w3[3];
+ }
+
+ const int ctx_len = 32 + salt_len;
+
+ pos = ctx_len & 63;
+
+ // append_0x80_4x4
+
+ const u32 off = pos ^ 3;
+
+ const u32 c0 = (off & 15) / 4;
+
+ const u32 r0 = 0xff << ((off & 3) * 8);
+
+ const u32 m0[4] = { ((c0 == 0) ? r0 : 0), ((c0 == 1) ? r0 : 0), ((c0 == 2) ? r0 : 0), ((c0 == 3) ? r0 : 0) };
+
+ const u32 off16 = off / 16;
+
+ const u32 v0[4] = { ((off16 == 0) ? 0x80808080 : 0), ((off16 == 1) ? 0x80808080 : 0), ((off16 == 2) ? 0x80808080 : 0), ((off16 == 3) ? 0x80808080 : 0) };
+
+ w0_t |= v0[0] & m0[0];
+ w1_t |= v0[0] & m0[1];
+ w2_t |= v0[0] & m0[2];
+ w3_t |= v0[0] & m0[3];
+ w4_t |= v0[1] & m0[0];
+ w5_t |= v0[1] & m0[1];
+ w6_t |= v0[1] & m0[2];
+ w7_t |= v0[1] & m0[3];
+ w8_t |= v0[2] & m0[0];
+ w9_t |= v0[2] & m0[1];
+ wa_t |= v0[2] & m0[2];
+ wb_t |= v0[2] & m0[3];
+ wc_t |= v0[3] & m0[0];
+ wd_t |= v0[3] & m0[1];
+ we_t |= v0[3] & m0[2];
+ wf_t |= v0[3] & m0[3];
+
+ if (pos >= 56)
+ {
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ // last sha1 transform
+
+ we_t = 0;
+ wf_t = ctx_len * 8;
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_M_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m04710_m08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m04710_m16 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * base
+ */
+
+ u32 pw_buf0[4];
+ u32 pw_buf1[4];
+
+ pw_buf0[0] = pws[gid].i[0];
+ pw_buf0[1] = pws[gid].i[1];
+ pw_buf0[2] = pws[gid].i[2];
+ pw_buf0[3] = pws[gid].i[3];
+ pw_buf1[0] = pws[gid].i[4];
+ pw_buf1[1] = pws[gid].i[5];
+ pw_buf1[2] = pws[gid].i[6];
+ pw_buf1[3] = pws[gid].i[7];
+
+ const u32 pw_l_len = pws[gid].pw_len & 63;
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
+ salt_buf1[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
+ salt_buf1[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
+ salt_buf1[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
+ salt_buf1[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
+ salt_buf2[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
+ salt_buf2[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
+ salt_buf2[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[10]);
+ salt_buf2[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[11]);
+ salt_buf3[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[12]);
+ salt_buf3[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[13]);
+ salt_buf3[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[14]);
+ salt_buf3[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[15]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+ /**
+ * loop
+ */
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
+
+ const u32x pw_len = (pw_l_len + pw_r_len) & 63;
+
+ /**
+ * concat password candidate
+ */
+
+ u32x wordl0[4] = { 0 };
+ u32x wordl1[4] = { 0 };
+ u32x wordl2[4] = { 0 };
+ u32x wordl3[4] = { 0 };
+
+ wordl0[0] = pw_buf0[0];
+ wordl0[1] = pw_buf0[1];
+ wordl0[2] = pw_buf0[2];
+ wordl0[3] = pw_buf0[3];
+ wordl1[0] = pw_buf1[0];
+ wordl1[1] = pw_buf1[1];
+ wordl1[2] = pw_buf1[2];
+ wordl1[3] = pw_buf1[3];
+
+ u32x wordr0[4] = { 0 };
+ u32x wordr1[4] = { 0 };
+ u32x wordr2[4] = { 0 };
+ u32x wordr3[4] = { 0 };
+
+ wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
+ wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
+ wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
+ wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
+ wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
+ wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
+ wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
+ wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
+
+ if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
+ {
+ switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
+ }
+ else
+ {
+ switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
+ }
+
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = wordl0[0] | wordr0[0];
+ w0[1] = wordl0[1] | wordr0[1];
+ w0[2] = wordl0[2] | wordr0[2];
+ w0[3] = wordl0[3] | wordr0[3];
+ w1[0] = wordl1[0] | wordr1[0];
+ w1[1] = wordl1[1] | wordr1[1];
+ w1[2] = wordl1[2] | wordr1[2];
+ w1[3] = wordl1[3] | wordr1[3];
+ w2[0] = wordl2[0] | wordr2[0];
+ w2[1] = wordl2[1] | wordr2[1];
+ w2[2] = wordl2[2] | wordr2[2];
+ w2[3] = wordl2[3] | wordr2[3];
+ w3[0] = wordl3[0] | wordr3[0];
+ w3[1] = wordl3[1] | wordr3[1];
+ w3[2] = pw_len * 8;
+ w3[3] = 0;
+
+ /**
+ * md5(pass)
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w1[1], MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w2[0], MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w2[3], MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w3[2], MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w0[1], MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w1[0], MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w1[3], MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2[2], MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w3[1], MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0[0], MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w0[3], MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w1[2], MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w2[1], MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w3[0], MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3[3], MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w0[2], MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ // sha1
+
+ u32x w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ u32x w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ u32x w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ u32x w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ u32x w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ u32x w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ u32x w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ u32x w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ u32x w8_t = 0;
+ u32x w9_t = 0;
+ u32x wa_t = 0;
+ u32x wb_t = 0;
+ u32x wc_t = 0;
+ u32x wd_t = 0;
+ u32x we_t = 0;
+ u32x wf_t = 0;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ u32x digest[8];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+
+ // append salt
+
+ // ctx_len 32, pos 32
+
+ int pos = 32;
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = salt_buf1[0];
+ s1[1] = salt_buf1[1];
+ s1[2] = salt_buf1[2];
+ s1[3] = salt_buf1[3];
+ s2[0] = salt_buf2[0];
+ s2[1] = salt_buf2[1];
+ s2[2] = salt_buf2[2];
+ s2[3] = salt_buf2[3];
+ s3[0] = salt_buf3[0];
+ s3[1] = salt_buf3[1];
+ s3[2] = salt_buf3[2];
+ s3[3] = salt_buf3[3];
+
+ if ((pos + salt_len) < 64)
+ {
+ switch_buffer_by_offset_be (s0, s1, s2, s3, pos);
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+ w8_t |= s2[0];
+ w9_t |= s2[1];
+ wa_t |= s2[2];
+ wb_t |= s2[3];
+ wc_t |= s3[0];
+ wd_t |= s3[1];
+ we_t |= s3[2];
+ wf_t |= s3[3];
+ }
+ else
+ {
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_be (s0, s1, s2, s3, _w0, _w1, _w2, _w3, pos);
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+ w8_t |= s2[0];
+ w9_t |= s2[1];
+ wa_t |= s2[2];
+ wb_t |= s2[3];
+ wc_t |= s3[0];
+ wd_t |= s3[1];
+ we_t |= s3[2];
+ wf_t |= s3[3];
+
+ // sha1 transform
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+
+ w0_t = _w0[0];
+ w1_t = _w0[1];
+ w2_t = _w0[2];
+ w3_t = _w0[3];
+ w4_t = _w1[0];
+ w5_t = _w1[1];
+ w6_t = _w1[2];
+ w7_t = _w1[3];
+ w8_t = _w2[0];
+ w9_t = _w2[1];
+ wa_t = _w2[2];
+ wb_t = _w2[3];
+ wc_t = _w3[0];
+ wd_t = _w3[1];
+ we_t = _w3[2];
+ wf_t = _w3[3];
+ }
+
+ const int ctx_len = 32 + salt_len;
+
+ pos = ctx_len & 63;
+
+ // append_0x80_4x4
+
+ const u32 off = pos ^ 3;
+
+ const u32 c0 = (off & 15) / 4;
+
+ const u32 r0 = 0xff << ((off & 3) * 8);
+
+ const u32 m0[4] = { ((c0 == 0) ? r0 : 0), ((c0 == 1) ? r0 : 0), ((c0 == 2) ? r0 : 0), ((c0 == 3) ? r0 : 0) };
+
+ const u32 off16 = off / 16;
+
+ const u32 v0[4] = { ((off16 == 0) ? 0x80808080 : 0), ((off16 == 1) ? 0x80808080 : 0), ((off16 == 2) ? 0x80808080 : 0), ((off16 == 3) ? 0x80808080 : 0) };
+
+ w0_t |= v0[0] & m0[0];
+ w1_t |= v0[0] & m0[1];
+ w2_t |= v0[0] & m0[2];
+ w3_t |= v0[0] & m0[3];
+ w4_t |= v0[1] & m0[0];
+ w5_t |= v0[1] & m0[1];
+ w6_t |= v0[1] & m0[2];
+ w7_t |= v0[1] & m0[3];
+ w8_t |= v0[2] & m0[0];
+ w9_t |= v0[2] & m0[1];
+ wa_t |= v0[2] & m0[2];
+ wb_t |= v0[2] & m0[3];
+ wc_t |= v0[3] & m0[0];
+ wd_t |= v0[3] & m0[1];
+ we_t |= v0[3] & m0[2];
+ wf_t |= v0[3] & m0[3];
+
+ if (pos >= 56)
+ {
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ // last sha1 transform
+
+ we_t = 0;
+ wf_t = ctx_len * 8;
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+ if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_S_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m04710_s08 (KERN_ATTR_BASIC ())
+{
+}
+
+KERNEL_FQ void m04710_s16 (KERN_ATTR_BASIC ())
+{
+}
diff --git a/OpenCL/m04710_a3-optimized.cl b/OpenCL/m04710_a3-optimized.cl
new file mode 100644
index 000000000..295c137c0
--- /dev/null
+++ b/OpenCL/m04710_a3-optimized.cl
@@ -0,0 +1,1795 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_md5.cl"
+#include "inc_hash_sha1.cl"
+#endif
+
+#if VECT_SIZE == 1
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i)])
+#elif VECT_SIZE == 2
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
+#elif VECT_SIZE == 4
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
+#elif VECT_SIZE == 8
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
+#elif VECT_SIZE == 16
+#define uint_to_hex_lower8_le(i) make_u32x (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
+#endif
+
+DECLSPEC void m04710m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
+ salt_buf1[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
+ salt_buf1[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
+ salt_buf1[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
+ salt_buf1[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
+ salt_buf2[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
+ salt_buf2[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
+ salt_buf2[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[10]);
+ salt_buf2[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[11]);
+ salt_buf3[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[12]);
+ salt_buf3[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[13]);
+ salt_buf3[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[14]);
+ salt_buf3[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[15]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ u32x w0_t = w0lr;
+ u32x w1_t = w0[1];
+ u32x w2_t = w0[2];
+ u32x w3_t = w0[3];
+ u32x w4_t = w1[0];
+ u32x w5_t = w1[1];
+ u32x w6_t = w1[2];
+ u32x w7_t = w1[3];
+ u32x w8_t = w2[0];
+ u32x w9_t = w2[1];
+ u32x wa_t = w2[2];
+ u32x wb_t = w2[3];
+ u32x wc_t = w3[0];
+ u32x wd_t = w3[1];
+ u32x we_t = w3[2];
+ u32x wf_t = w3[3];
+
+ /**
+ * md5(pass)
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ // sha1
+
+ w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ u32x digest[8];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+
+ // append salt
+
+ // ctx_len 32, pos 32
+
+ int pos = 32;
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = salt_buf1[0];
+ s1[1] = salt_buf1[1];
+ s1[2] = salt_buf1[2];
+ s1[3] = salt_buf1[3];
+ s2[0] = salt_buf2[0];
+ s2[1] = salt_buf2[1];
+ s2[2] = salt_buf2[2];
+ s2[3] = salt_buf2[3];
+ s3[0] = salt_buf3[0];
+ s3[1] = salt_buf3[1];
+ s3[2] = salt_buf3[2];
+ s3[3] = salt_buf3[3];
+
+ if ((pos + salt_len) < 64)
+ {
+ switch_buffer_by_offset_be (s0, s1, s2, s3, pos);
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+ w8_t |= s2[0];
+ w9_t |= s2[1];
+ wa_t |= s2[2];
+ wb_t |= s2[3];
+ wc_t |= s3[0];
+ wd_t |= s3[1];
+ we_t |= s3[2];
+ wf_t |= s3[3];
+ }
+ else
+ {
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_be (s0, s1, s2, s3, _w0, _w1, _w2, _w3, pos);
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+ w8_t |= s2[0];
+ w9_t |= s2[1];
+ wa_t |= s2[2];
+ wb_t |= s2[3];
+ wc_t |= s3[0];
+ wd_t |= s3[1];
+ we_t |= s3[2];
+ wf_t |= s3[3];
+
+ // sha1 transform
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+
+ w0_t = _w0[0];
+ w1_t = _w0[1];
+ w2_t = _w0[2];
+ w3_t = _w0[3];
+ w4_t = _w1[0];
+ w5_t = _w1[1];
+ w6_t = _w1[2];
+ w7_t = _w1[3];
+ w8_t = _w2[0];
+ w9_t = _w2[1];
+ wa_t = _w2[2];
+ wb_t = _w2[3];
+ wc_t = _w3[0];
+ wd_t = _w3[1];
+ we_t = _w3[2];
+ wf_t = _w3[3];
+ }
+
+ const int ctx_len = 32 + salt_len;
+
+ pos = ctx_len & 63;
+
+ // append_0x80_4x4
+
+ const u32 off = pos ^ 3;
+
+ const u32 c0 = (off & 15) / 4;
+
+ const u32 r0 = 0xff << ((off & 3) * 8);
+
+ const u32 m0[4] = { ((c0 == 0) ? r0 : 0), ((c0 == 1) ? r0 : 0), ((c0 == 2) ? r0 : 0), ((c0 == 3) ? r0 : 0) };
+
+ const u32 off16 = off / 16;
+
+ const u32 v0[4] = { ((off16 == 0) ? 0x80808080 : 0), ((off16 == 1) ? 0x80808080 : 0), ((off16 == 2) ? 0x80808080 : 0), ((off16 == 3) ? 0x80808080 : 0) };
+
+ w0_t |= v0[0] & m0[0];
+ w1_t |= v0[0] & m0[1];
+ w2_t |= v0[0] & m0[2];
+ w3_t |= v0[0] & m0[3];
+ w4_t |= v0[1] & m0[0];
+ w5_t |= v0[1] & m0[1];
+ w6_t |= v0[1] & m0[2];
+ w7_t |= v0[1] & m0[3];
+ w8_t |= v0[2] & m0[0];
+ w9_t |= v0[2] & m0[1];
+ wa_t |= v0[2] & m0[2];
+ wb_t |= v0[2] & m0[3];
+ wc_t |= v0[3] & m0[0];
+ wd_t |= v0[3] & m0[1];
+ we_t |= v0[3] & m0[2];
+ wf_t |= v0[3] & m0[3];
+
+ if (pos >= 56)
+ {
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ // last sha1 transform
+
+ we_t = 0;
+ wf_t = ctx_len * 8;
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_M_SIMD (d, e, c, b);
+ }
+}
+
+DECLSPEC void m04710s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KERN_ATTR_BASIC (), LOCAL_AS u32 *l_bin2asc)
+{
+ /**
+ * modifier
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+
+ /**
+ * salt
+ */
+
+ u32 salt_buf0[4];
+ u32 salt_buf1[4];
+ u32 salt_buf2[4];
+ u32 salt_buf3[4];
+
+ salt_buf0[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
+ salt_buf0[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
+ salt_buf0[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
+ salt_buf0[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
+ salt_buf1[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
+ salt_buf1[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
+ salt_buf1[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
+ salt_buf1[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
+ salt_buf2[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
+ salt_buf2[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
+ salt_buf2[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[10]);
+ salt_buf2[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[11]);
+ salt_buf3[0] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[12]);
+ salt_buf3[1] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[13]);
+ salt_buf3[2] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[14]);
+ salt_buf3[3] = hc_swap32_S (salt_bufs[salt_pos].salt_buf[15]);
+
+ const u32 salt_len = salt_bufs[salt_pos].salt_len;
+
+ /**
+ * digest
+ */
+
+ const u32 search[4] =
+ {
+ digests_buf[digests_offset].digest_buf[DGST_R0],
+ digests_buf[digests_offset].digest_buf[DGST_R1],
+ digests_buf[digests_offset].digest_buf[DGST_R2],
+ digests_buf[digests_offset].digest_buf[DGST_R3]
+ };
+
+ /**
+ * reverse
+ */
+
+ const u32 e_rev = hc_rotl32_S (search[1], 2u);
+
+ /**
+ * loop
+ */
+
+ u32 w0l = w0[0];
+
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
+ {
+ const u32x w0r = ix_create_bft (bfs_buf, il_pos);
+
+ const u32x w0lr = w0l | w0r;
+
+ u32x w0_t = w0lr;
+ u32x w1_t = w0[1];
+ u32x w2_t = w0[2];
+ u32x w3_t = w0[3];
+ u32x w4_t = w1[0];
+ u32x w5_t = w1[1];
+ u32x w6_t = w1[2];
+ u32x w7_t = w1[3];
+ u32x w8_t = w2[0];
+ u32x w9_t = w2[1];
+ u32x wa_t = w2[2];
+ u32x wb_t = w2[3];
+ u32x wc_t = w3[0];
+ u32x wd_t = w3[1];
+ u32x we_t = w3[2];
+ u32x wf_t = w3[3];
+
+ /**
+ * md5(pass)
+ */
+
+ u32x a = MD5M_A;
+ u32x b = MD5M_B;
+ u32x c = MD5M_C;
+ u32x d = MD5M_D;
+ u32x e = 0;
+
+ MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
+ MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
+ MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
+ MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
+ MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
+
+ MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
+ MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
+ MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
+ MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
+ MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
+
+ u32x t;
+
+ MD5_STEP (MD5_H1, a, b, c, d, w5_t, MD5C20, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w8_t, MD5C21, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wb_t, MD5C22, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, we_t, MD5C23, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w1_t, MD5C24, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w4_t, MD5C25, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w7_t, MD5C26, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, wa_t, MD5C27, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, wd_t, MD5C28, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, w0_t, MD5C29, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, w3_t, MD5C2a, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w6_t, MD5C2b, MD5S23);
+ MD5_STEP (MD5_H1, a, b, c, d, w9_t, MD5C2c, MD5S20);
+ MD5_STEP (MD5_H2, d, a, b, c, wc_t, MD5C2d, MD5S21);
+ MD5_STEP (MD5_H1, c, d, a, b, wf_t, MD5C2e, MD5S22);
+ MD5_STEP (MD5_H2, b, c, d, a, w2_t, MD5C2f, MD5S23);
+
+ MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
+ MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
+ MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
+ MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
+ MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
+
+ a += MD5M_A;
+ b += MD5M_B;
+ c += MD5M_C;
+ d += MD5M_D;
+
+ // sha1
+
+ w0_t = uint_to_hex_lower8_le ((a >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 0) & 255) << 16;
+ w1_t = uint_to_hex_lower8_le ((a >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((a >> 16) & 255) << 16;
+ w2_t = uint_to_hex_lower8_le ((b >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 0) & 255) << 16;
+ w3_t = uint_to_hex_lower8_le ((b >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((b >> 16) & 255) << 16;
+ w4_t = uint_to_hex_lower8_le ((c >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 0) & 255) << 16;
+ w5_t = uint_to_hex_lower8_le ((c >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((c >> 16) & 255) << 16;
+ w6_t = uint_to_hex_lower8_le ((d >> 8) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 0) & 255) << 16;
+ w7_t = uint_to_hex_lower8_le ((d >> 24) & 255) << 0
+ | uint_to_hex_lower8_le ((d >> 16) & 255) << 16;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+
+ a = SHA1M_A;
+ b = SHA1M_B;
+ c = SHA1M_C;
+ d = SHA1M_D;
+ e = SHA1M_E;
+
+ u32x digest[8];
+
+ digest[0] = a;
+ digest[1] = b;
+ digest[2] = c;
+ digest[3] = d;
+ digest[4] = e;
+
+ // append salt
+
+ // ctx_len 32, pos 32
+
+ int pos = 32;
+
+ u32x s0[4];
+ u32x s1[4];
+ u32x s2[4];
+ u32x s3[4];
+
+ s0[0] = salt_buf0[0];
+ s0[1] = salt_buf0[1];
+ s0[2] = salt_buf0[2];
+ s0[3] = salt_buf0[3];
+ s1[0] = salt_buf1[0];
+ s1[1] = salt_buf1[1];
+ s1[2] = salt_buf1[2];
+ s1[3] = salt_buf1[3];
+ s2[0] = salt_buf2[0];
+ s2[1] = salt_buf2[1];
+ s2[2] = salt_buf2[2];
+ s2[3] = salt_buf2[3];
+ s3[0] = salt_buf3[0];
+ s3[1] = salt_buf3[1];
+ s3[2] = salt_buf3[2];
+ s3[3] = salt_buf3[3];
+
+ if ((pos + salt_len) < 64)
+ {
+ switch_buffer_by_offset_be (s0, s1, s2, s3, pos);
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+ w8_t |= s2[0];
+ w9_t |= s2[1];
+ wa_t |= s2[2];
+ wb_t |= s2[3];
+ wc_t |= s3[0];
+ wd_t |= s3[1];
+ we_t |= s3[2];
+ wf_t |= s3[3];
+ }
+ else
+ {
+ u32x _w0[4] = { 0 };
+ u32x _w1[4] = { 0 };
+ u32x _w2[4] = { 0 };
+ u32x _w3[4] = { 0 };
+
+ switch_buffer_by_offset_carry_be (s0, s1, s2, s3, _w0, _w1, _w2, _w3, pos);
+
+ w0_t |= s0[0];
+ w1_t |= s0[1];
+ w2_t |= s0[2];
+ w3_t |= s0[3];
+ w4_t |= s1[0];
+ w5_t |= s1[1];
+ w6_t |= s1[2];
+ w7_t |= s1[3];
+ w8_t |= s2[0];
+ w9_t |= s2[1];
+ wa_t |= s2[2];
+ wb_t |= s2[3];
+ wc_t |= s3[0];
+ wd_t |= s3[1];
+ we_t |= s3[2];
+ wf_t |= s3[3];
+
+ // sha1 transform
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+
+ w0_t = _w0[0];
+ w1_t = _w0[1];
+ w2_t = _w0[2];
+ w3_t = _w0[3];
+ w4_t = _w1[0];
+ w5_t = _w1[1];
+ w6_t = _w1[2];
+ w7_t = _w1[3];
+ w8_t = _w2[0];
+ w9_t = _w2[1];
+ wa_t = _w2[2];
+ wb_t = _w2[3];
+ wc_t = _w3[0];
+ wd_t = _w3[1];
+ we_t = _w3[2];
+ wf_t = _w3[3];
+ }
+
+ const int ctx_len = 32 + salt_len;
+
+ pos = ctx_len & 63;
+
+ // append_0x80_4x4
+
+ const u32 off = pos ^ 3;
+
+ const u32 c0 = (off & 15) / 4;
+
+ const u32 r0 = 0xff << ((off & 3) * 8);
+
+ const u32 m0[4] = { ((c0 == 0) ? r0 : 0), ((c0 == 1) ? r0 : 0), ((c0 == 2) ? r0 : 0), ((c0 == 3) ? r0 : 0) };
+
+ const u32 off16 = off / 16;
+
+ const u32 v0[4] = { ((off16 == 0) ? 0x80808080 : 0), ((off16 == 1) ? 0x80808080 : 0), ((off16 == 2) ? 0x80808080 : 0), ((off16 == 3) ? 0x80808080 : 0) };
+
+ w0_t |= v0[0] & m0[0];
+ w1_t |= v0[0] & m0[1];
+ w2_t |= v0[0] & m0[2];
+ w3_t |= v0[0] & m0[3];
+ w4_t |= v0[1] & m0[0];
+ w5_t |= v0[1] & m0[1];
+ w6_t |= v0[1] & m0[2];
+ w7_t |= v0[1] & m0[3];
+ w8_t |= v0[2] & m0[0];
+ w9_t |= v0[2] & m0[1];
+ wa_t |= v0[2] & m0[2];
+ wb_t |= v0[2] & m0[3];
+ wc_t |= v0[3] & m0[0];
+ wd_t |= v0[3] & m0[1];
+ we_t |= v0[3] & m0[2];
+ wf_t |= v0[3] & m0[3];
+
+ if (pos >= 56)
+ {
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ digest[0] += a;
+ digest[1] += b;
+ digest[2] += c;
+ digest[3] += d;
+ digest[4] += e;
+
+ w0_t = 0;
+ w1_t = 0;
+ w2_t = 0;
+ w3_t = 0;
+ w4_t = 0;
+ w5_t = 0;
+ w6_t = 0;
+ w7_t = 0;
+ w8_t = 0;
+ w9_t = 0;
+ wa_t = 0;
+ wb_t = 0;
+ wc_t = 0;
+ wd_t = 0;
+ we_t = 0;
+ wf_t = 0;
+ }
+
+ // last sha1 transform
+
+ we_t = 0;
+ wf_t = ctx_len * 8;
+
+ a = digest[0];
+ b = digest[1];
+ c = digest[2];
+ d = digest[3];
+ e = digest[4];
+
+ #undef K
+ #define K SHA1C00
+
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
+ SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
+ SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
+ SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
+ SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
+ SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
+
+ #undef K
+ #define K SHA1C01
+
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
+
+ #undef K
+ #define K SHA1C02
+
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
+
+ #undef K
+ #define K SHA1C03
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
+ w0_t = hc_rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
+ w1_t = hc_rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
+ w2_t = hc_rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
+ w3_t = hc_rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
+ w4_t = hc_rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
+ w5_t = hc_rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
+ w6_t = hc_rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
+ w7_t = hc_rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
+ w8_t = hc_rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
+ w9_t = hc_rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
+ wa_t = hc_rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
+ wb_t = hc_rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
+
+ if (MATCHES_NONE_VS (e, e_rev)) continue;
+
+ wc_t = hc_rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
+ wd_t = hc_rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
+ we_t = hc_rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
+ wf_t = hc_rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
+
+ COMPARE_S_SIMD (d, e, c, b);
+ }
+}
+
+KERNEL_FQ void m04710_m04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_m08 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_m16 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = pws[gid].i[14];
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_s04 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_s08 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = pws[gid].i[14];
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
+
+KERNEL_FQ void m04710_s16 (KERN_ATTR_BASIC ())
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+ const u64 lid = get_local_id (0);
+ const u64 lsz = get_local_size (0);
+
+ /**
+ * bin2asc table
+ */
+
+ LOCAL_VK u32 l_bin2asc[256];
+
+ for (u32 i = lid; i < 256; i += lsz)
+ {
+ const u32 i0 = (i >> 0) & 15;
+ const u32 i1 = (i >> 4) & 15;
+
+ l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
+ | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
+ }
+
+ SYNC_THREADS ();
+
+ if (gid >= gid_max) return;
+
+ /**
+ * modifier
+ */
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = pws[gid].i[ 8];
+ w2[1] = pws[gid].i[ 9];
+ w2[2] = pws[gid].i[10];
+ w2[3] = pws[gid].i[11];
+
+ u32 w3[4];
+
+ w3[0] = pws[gid].i[12];
+ w3[1] = pws[gid].i[13];
+ w3[2] = pws[gid].i[14];
+ w3[3] = pws[gid].i[15];
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m04710s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max, l_bin2asc);
+}
diff --git a/src/modules/module_04711.c b/src/modules/module_04711.c
new file mode 100644
index 000000000..5088f89cb
--- /dev/null
+++ b/src/modules/module_04711.c
@@ -0,0 +1,246 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+
+static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL;
+static const u32 DGST_POS0 = 3;
+static const u32 DGST_POS1 = 4;
+static const u32 DGST_POS2 = 2;
+static const u32 DGST_POS3 = 1;
+static const u32 DGST_SIZE = DGST_SIZE_4_5;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_EAS;
+static const char *HASH_NAME = "Huawei sha1(md5($pass).$salt)";
+static const u64 KERN_TYPE = 4710;
+static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
+ | OPTI_TYPE_PRECOMPUTE_INIT
+ | OPTI_TYPE_EARLY_SKIP
+ | OPTI_TYPE_NOT_ITERATED
+ | OPTI_TYPE_RAW_HASH;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE
+ | OPTS_TYPE_PT_ADD80
+ | OPTS_TYPE_PT_ADDBITS14;
+static const u32 SALT_TYPE = SALT_TYPE_EMBEDDED;
+static const char *ST_PASS = "hashcat";
+static const char *ST_HASH = "53c724b7f34f09787ed3f1b316215fc35c789504:hashcat1";
+
+u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
+u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
+u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
+u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
+u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
+u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
+u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
+const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
+u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
+u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
+u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
+u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
+const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
+const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+
+u32 module_salt_min (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+ const u32 salt_min = 8;
+
+ return salt_min;
+}
+
+u32 module_salt_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+ const u32 salt_max = 8;
+
+ return salt_max;
+}
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+ u32 *digest = (u32 *) digest_buf;
+
+ token_t token;
+
+ token.token_cnt = 2;
+
+ token.sep[0] = hashconfig->separator;
+ token.len_min[0] = 40;
+ token.len_max[0] = 40;
+ token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_HEX;
+
+ token.len_min[1] = 8;
+ token.len_max[1] = 8;
+ token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH;
+
+ if (hashconfig->opts_type & OPTS_TYPE_ST_HEX)
+ {
+ token.len_min[1] *= 2;
+ token.len_max[1] *= 2;
+
+ token.attr[1] |= TOKEN_ATTR_VERIFY_HEX;
+ }
+
+ const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+ if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+ const u8 *hash_pos = token.buf[0];
+
+ digest[0] = hex_to_u32 (hash_pos + 0);
+ digest[1] = hex_to_u32 (hash_pos + 8);
+ digest[2] = hex_to_u32 (hash_pos + 16);
+ digest[3] = hex_to_u32 (hash_pos + 24);
+ digest[4] = hex_to_u32 (hash_pos + 32);
+
+ digest[0] = byte_swap_32 (digest[0]);
+ digest[1] = byte_swap_32 (digest[1]);
+ digest[2] = byte_swap_32 (digest[2]);
+ digest[3] = byte_swap_32 (digest[3]);
+ digest[4] = byte_swap_32 (digest[4]);
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ digest[0] -= SHA1M_A;
+ digest[1] -= SHA1M_B;
+ digest[2] -= SHA1M_C;
+ digest[3] -= SHA1M_D;
+ digest[4] -= SHA1M_E;
+ }
+
+ const u8 *salt_pos = token.buf[1];
+ const int salt_len = token.len[1];
+
+ const bool parse_rc = generic_salt_decode (hashconfig, salt_pos, salt_len, (u8 *) salt->salt_buf, (int *) &salt->salt_len);
+
+ if (parse_rc == false) return (PARSER_SALT_LENGTH);
+
+ return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+ const u32 *digest = (const u32 *) digest_buf;
+
+ // we can not change anything in the original buffer, otherwise destroying sorting
+ // therefore create some local buffer
+
+ u32 tmp[5];
+
+ tmp[0] = digest[0];
+ tmp[1] = digest[1];
+ tmp[2] = digest[2];
+ tmp[3] = digest[3];
+ tmp[4] = digest[4];
+
+ if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
+ {
+ tmp[0] += SHA1M_A;
+ tmp[1] += SHA1M_B;
+ tmp[2] += SHA1M_C;
+ tmp[3] += SHA1M_D;
+ tmp[4] += SHA1M_E;
+ }
+
+ tmp[0] = byte_swap_32 (tmp[0]);
+ tmp[1] = byte_swap_32 (tmp[1]);
+ tmp[2] = byte_swap_32 (tmp[2]);
+ tmp[3] = byte_swap_32 (tmp[3]);
+ tmp[4] = byte_swap_32 (tmp[4]);
+
+ u8 *out_buf = (u8 *) line_buf;
+
+ int out_len = 0;
+
+ u32_to_hex (tmp[0], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[1], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[2], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[3], out_buf + out_len); out_len += 8;
+ u32_to_hex (tmp[4], out_buf + out_len); out_len += 8;
+
+ out_buf[out_len] = hashconfig->separator;
+
+ out_len += 1;
+
+ out_len += generic_salt_encode (hashconfig, (const u8 *) salt->salt_buf, (const int) salt->salt_len, (u8 *) out_buf + out_len);
+
+ return out_len;
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+ module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
+ module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
+
+ module_ctx->module_attack_exec = module_attack_exec;
+ module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_mask = MODULE_DEFAULT;
+ module_ctx->module_benchmark_salt = MODULE_DEFAULT;
+ module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
+ module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
+ module_ctx->module_dgst_pos0 = module_dgst_pos0;
+ module_ctx->module_dgst_pos1 = module_dgst_pos1;
+ module_ctx->module_dgst_pos2 = module_dgst_pos2;
+ module_ctx->module_dgst_pos3 = module_dgst_pos3;
+ module_ctx->module_dgst_size = module_dgst_size;
+ module_ctx->module_dictstat_disable = MODULE_DEFAULT;
+ module_ctx->module_esalt_size = MODULE_DEFAULT;
+ module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
+ module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_count = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_save = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
+ module_ctx->module_hash_decode = module_hash_decode;
+ module_ctx->module_hash_encode_status = MODULE_DEFAULT;
+ module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_encode = module_hash_encode;
+ module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
+ module_ctx->module_hash_mode = MODULE_DEFAULT;
+ module_ctx->module_hash_category = module_hash_category;
+ module_ctx->module_hash_name = module_hash_name;
+ module_ctx->module_hashes_count_min = MODULE_DEFAULT;
+ module_ctx->module_hashes_count_max = MODULE_DEFAULT;
+ module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
+ module_ctx->module_hook12 = MODULE_DEFAULT;
+ module_ctx->module_hook23 = MODULE_DEFAULT;
+ module_ctx->module_hook_salt_size = MODULE_DEFAULT;
+ module_ctx->module_hook_size = MODULE_DEFAULT;
+ module_ctx->module_jit_build_options = MODULE_DEFAULT;
+ module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
+ module_ctx->module_kern_type = module_kern_type;
+ module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
+ module_ctx->module_opti_type = module_opti_type;
+ module_ctx->module_opts_type = module_opts_type;
+ module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
+ module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
+ module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
+ module_ctx->module_potfile_disable = MODULE_DEFAULT;
+ module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
+ module_ctx->module_pwdump_column = MODULE_DEFAULT;
+ module_ctx->module_pw_max = MODULE_DEFAULT;
+ module_ctx->module_pw_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = module_salt_max;
+ module_ctx->module_salt_min = module_salt_min;
+ module_ctx->module_salt_type = module_salt_type;
+ module_ctx->module_separator = MODULE_DEFAULT;
+ module_ctx->module_st_hash = module_st_hash;
+ module_ctx->module_st_pass = module_st_pass;
+ module_ctx->module_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_unstable_warning = MODULE_DEFAULT;
+ module_ctx->module_warmup_disable = MODULE_DEFAULT;
+}
diff --git a/tools/test_modules/m04710.pm b/tools/test_modules/m04710.pm
index ce760a4b1..de4cadd7f 100644
--- a/tools/test_modules/m04710.pm
+++ b/tools/test_modules/m04710.pm
@@ -11,7 +11,7 @@ use warnings;
use Digest::MD5 qw (md5_hex);
use Digest::SHA qw (sha1_hex);
-sub module_constraints { [[0, 256], [0, 223], [-1, -1], [-1, -1], [-1, -1]] }
+sub module_constraints { [[0, 256], [0, 256], [0, 55], [8, 8], [-1, -1]] }
sub module_generate_hash
{
diff --git a/tools/test_modules/m04711.pm b/tools/test_modules/m04711.pm
new file mode 100644
index 000000000..1dde0f7db
--- /dev/null
+++ b/tools/test_modules/m04711.pm
@@ -0,0 +1,47 @@
+#!/usr/bin/env perl
+
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use Digest::MD5 qw (md5_hex);
+use Digest::SHA qw (sha1_hex);
+
+sub module_constraints { [[0, 256], [8, 8], [0, 55], [8, 8], [-1, -1]] }
+
+sub module_generate_hash
+{
+ my $word = shift;
+ my $salt = shift;
+
+ my $digest = sha1_hex (md5_hex ($word) . $salt);
+
+ my $hash = sprintf ("%s:%s", $digest, $salt);
+
+ return $hash;
+}
+
+sub module_verify_hash
+{
+ my $line = shift;
+
+ my ($hash, $salt, $word) = split (':', $line);
+
+ return unless defined $hash;
+ return unless defined $salt;
+ return unless defined $word;
+
+ return unless length ($salt) == 8;
+
+ my $word_packed = pack_if_HEX_notation ($word);
+
+ my $new_hash = module_generate_hash ($word_packed, $salt);
+
+ return ($new_hash, $word);
+}
+
+1;
From 98e17d57743d92802f0c0a6b0c74813bb77d53e3 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 3 Aug 2019 18:19:46 -0700
Subject: [PATCH 069/113] Run through clang-tidy's
readability-uppercase-literal-suffix
1 and l are visually similar and can be confused. This also changes u to U
for consistency.
---
src/autotune.c | 6 +++---
src/backend.c | 14 +++++++-------
src/bitmap.c | 36 ++++++++++++++++++------------------
src/cpu_crc32.c | 4 ++--
src/dispatch.c | 2 +-
src/hwmon.c | 18 +++++++++---------
src/main.c | 2 +-
7 files changed, 41 insertions(+), 41 deletions(-)
diff --git a/src/autotune.c b/src/autotune.c
index 42f2b13de..24aa16979 100644
--- a/src/autotune.c
+++ b/src/autotune.c
@@ -244,7 +244,7 @@ static int autotune (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param
{
for (int i = 0; i < STEPS_CNT; i++)
{
- const u32 kernel_accel_try = 1u << i;
+ const u32 kernel_accel_try = 1U << i;
if (kernel_accel_try < kernel_accel_min) continue;
if (kernel_accel_try > kernel_accel_max) break;
@@ -269,8 +269,8 @@ static int autotune (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param
for (int i = 1; i < STEPS_CNT; i++)
{
- const u32 kernel_accel_try = kernel_accel_orig * (1u << i);
- const u32 kernel_loops_try = kernel_loops_orig / (1u << i);
+ const u32 kernel_accel_try = kernel_accel_orig * (1U << i);
+ const u32 kernel_loops_try = kernel_loops_orig / (1U << i);
if (kernel_accel_try < kernel_accel_min) continue;
if (kernel_accel_try > kernel_accel_max) break;
diff --git a/src/backend.c b/src/backend.c
index 2f3c2523c..d6b15d891 100644
--- a/src/backend.c
+++ b/src/backend.c
@@ -259,7 +259,7 @@ static bool setup_opencl_device_types_filter (hashcat_ctx_t *hashcat_ctx, const
return false;
}
- opencl_device_types_filter |= 1u << device_type;
+ opencl_device_types_filter |= 1U << device_type;
} while ((next = strtok_r (NULL, ",", &saveptr)) != NULL);
@@ -7671,10 +7671,10 @@ int backend_session_begin (hashcat_ctx_t *hashcat_ctx)
if (user_options->benchmark == true)
{
- ((u32 *) hashes->digests_buf)[0] = -1u;
- ((u32 *) hashes->digests_buf)[1] = -1u;
- ((u32 *) hashes->digests_buf)[2] = -1u;
- ((u32 *) hashes->digests_buf)[3] = -1u;
+ ((u32 *) hashes->digests_buf)[0] = -1U;
+ ((u32 *) hashes->digests_buf)[1] = -1U;
+ ((u32 *) hashes->digests_buf)[2] = -1U;
+ ((u32 *) hashes->digests_buf)[3] = -1U;
}
/**
@@ -9271,12 +9271,12 @@ int backend_session_begin (hashcat_ctx_t *hashcat_ctx)
// this value should represent a reasonable amount of memory a host system has per GPU.
// note we're allocating 3 blocks of that size.
- const u64 PWS_SPACE = 1024ull * 1024ull * 1024ull;
+ const u64 PWS_SPACE = 1024ULL * 1024ULL * 1024ULL;
// sometimes device_available_mem and device_maxmem_alloc reported back from the opencl runtime are a bit inaccurate.
// let's add some extra space just to be sure.
- const u64 EXTRA_SPACE = 64ull * 1024ull * 1024ull;
+ const u64 EXTRA_SPACE = 64ULL * 1024ULL * 1024ULL;
while (kernel_accel_max >= kernel_accel_min)
{
diff --git a/src/bitmap.c b/src/bitmap.c
index 6b1da1362..d2184acf0 100644
--- a/src/bitmap.c
+++ b/src/bitmap.c
@@ -13,10 +13,10 @@ static void selftest_to_bitmap (const u32 dgst_shifts, char *digests_buf_ptr, co
{
u32 *digest_ptr = (u32 *) digests_buf_ptr;
- const u32 val0 = 1u << (digest_ptr[dgst_pos0] & 0x1f);
- const u32 val1 = 1u << (digest_ptr[dgst_pos1] & 0x1f);
- const u32 val2 = 1u << (digest_ptr[dgst_pos2] & 0x1f);
- const u32 val3 = 1u << (digest_ptr[dgst_pos3] & 0x1f);
+ const u32 val0 = 1U << (digest_ptr[dgst_pos0] & 0x1f);
+ const u32 val1 = 1U << (digest_ptr[dgst_pos1] & 0x1f);
+ const u32 val2 = 1U << (digest_ptr[dgst_pos2] & 0x1f);
+ const u32 val3 = 1U << (digest_ptr[dgst_pos3] & 0x1f);
const u32 idx0 = (digest_ptr[dgst_pos0] >> dgst_shifts) & bitmap_mask;
const u32 idx1 = (digest_ptr[dgst_pos1] >> dgst_shifts) & bitmap_mask;
@@ -44,10 +44,10 @@ static bool generate_bitmaps (const u32 digests_cnt, const u32 dgst_size, const
digests_buf_ptr += dgst_size;
- const u32 val0 = 1u << (digest_ptr[dgst_pos0] & 0x1f);
- const u32 val1 = 1u << (digest_ptr[dgst_pos1] & 0x1f);
- const u32 val2 = 1u << (digest_ptr[dgst_pos2] & 0x1f);
- const u32 val3 = 1u << (digest_ptr[dgst_pos3] & 0x1f);
+ const u32 val0 = 1U << (digest_ptr[dgst_pos0] & 0x1f);
+ const u32 val1 = 1U << (digest_ptr[dgst_pos1] & 0x1f);
+ const u32 val2 = 1U << (digest_ptr[dgst_pos2] & 0x1f);
+ const u32 val3 = 1U << (digest_ptr[dgst_pos3] & 0x1f);
const u32 idx0 = (digest_ptr[dgst_pos0] >> dgst_shifts) & bitmap_mask;
const u32 idx1 = (digest_ptr[dgst_pos1] >> dgst_shifts) & bitmap_mask;
@@ -99,14 +99,14 @@ int bitmap_ctx_init (hashcat_ctx_t *hashcat_ctx)
const u32 bitmap_min = user_options->bitmap_min;
const u32 bitmap_max = user_options->bitmap_max;
- u32 *bitmap_s1_a = (u32 *) hcmalloc ((1u << bitmap_max) * sizeof (u32));
- u32 *bitmap_s1_b = (u32 *) hcmalloc ((1u << bitmap_max) * sizeof (u32));
- u32 *bitmap_s1_c = (u32 *) hcmalloc ((1u << bitmap_max) * sizeof (u32));
- u32 *bitmap_s1_d = (u32 *) hcmalloc ((1u << bitmap_max) * sizeof (u32));
- u32 *bitmap_s2_a = (u32 *) hcmalloc ((1u << bitmap_max) * sizeof (u32));
- u32 *bitmap_s2_b = (u32 *) hcmalloc ((1u << bitmap_max) * sizeof (u32));
- u32 *bitmap_s2_c = (u32 *) hcmalloc ((1u << bitmap_max) * sizeof (u32));
- u32 *bitmap_s2_d = (u32 *) hcmalloc ((1u << bitmap_max) * sizeof (u32));
+ u32 *bitmap_s1_a = (u32 *) hcmalloc ((1U << bitmap_max) * sizeof (u32));
+ u32 *bitmap_s1_b = (u32 *) hcmalloc ((1U << bitmap_max) * sizeof (u32));
+ u32 *bitmap_s1_c = (u32 *) hcmalloc ((1U << bitmap_max) * sizeof (u32));
+ u32 *bitmap_s1_d = (u32 *) hcmalloc ((1U << bitmap_max) * sizeof (u32));
+ u32 *bitmap_s2_a = (u32 *) hcmalloc ((1U << bitmap_max) * sizeof (u32));
+ u32 *bitmap_s2_b = (u32 *) hcmalloc ((1U << bitmap_max) * sizeof (u32));
+ u32 *bitmap_s2_c = (u32 *) hcmalloc ((1U << bitmap_max) * sizeof (u32));
+ u32 *bitmap_s2_d = (u32 *) hcmalloc ((1U << bitmap_max) * sizeof (u32));
u32 bitmap_bits;
u32 bitmap_nums;
@@ -115,7 +115,7 @@ int bitmap_ctx_init (hashcat_ctx_t *hashcat_ctx)
for (bitmap_bits = bitmap_min; bitmap_bits < bitmap_max; bitmap_bits++)
{
- bitmap_nums = 1u << bitmap_bits;
+ bitmap_nums = 1U << bitmap_bits;
bitmap_mask = bitmap_nums - 1;
@@ -134,7 +134,7 @@ int bitmap_ctx_init (hashcat_ctx_t *hashcat_ctx)
EVENT_DATA (EVENT_BITMAP_FINAL_OVERFLOW, NULL, 0);
}
- bitmap_nums = 1u << bitmap_bits;
+ bitmap_nums = 1U << bitmap_bits;
bitmap_mask = bitmap_nums - 1;
diff --git a/src/cpu_crc32.c b/src/cpu_crc32.c
index e2d0d75d4..f7e9accff 100644
--- a/src/cpu_crc32.c
+++ b/src/cpu_crc32.c
@@ -78,7 +78,7 @@ static const u32 crc32tab[256] =
u32 cpu_crc32_buffer (const u8 *buf, const size_t length)
{
- u32 crc = ~0u;
+ u32 crc = ~0U;
for (size_t pos = 0; pos < length; pos++)
{
@@ -90,7 +90,7 @@ u32 cpu_crc32_buffer (const u8 *buf, const size_t length)
int cpu_crc32 (const char *filename, u8 keytab[64])
{
- u32 crc = ~0u;
+ u32 crc = ~0U;
HCFILE fp;
diff --git a/src/dispatch.c b/src/dispatch.c
index d64dd07ae..9574361a7 100644
--- a/src/dispatch.c
+++ b/src/dispatch.c
@@ -1362,7 +1362,7 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
{
u64 words_off = 0;
u64 words_fin = 0;
- u64 words_extra = -1u;
+ u64 words_extra = -1U;
u64 words_extra_total = 0;
memset (device_param->pws_comp, 0, device_param->size_pws_comp);
diff --git a/src/hwmon.c b/src/hwmon.c
index 512f60b61..905ce6e61 100644
--- a/src/hwmon.c
+++ b/src/hwmon.c
@@ -176,7 +176,7 @@ static int hm_SYSFS_get_fan_speed_current (hashcat_ctx_t *hashcat_ctx, const int
return -1;
}
- const float p1 = (float) pwm1_max / 100.0f;
+ const float p1 = (float) pwm1_max / 100.0F;
const float pwm1_percent = (float) pwm1_cur / p1;
@@ -821,14 +821,14 @@ static int nvapi_init (hashcat_ctx_t *hashcat_ctx)
}
HC_LOAD_FUNC(nvapi, nvapi_QueryInterface, NVAPI_QUERYINTERFACE, NVAPI, 0)
- HC_LOAD_ADDR(nvapi, NvAPI_Initialize, NVAPI_INITIALIZE, nvapi_QueryInterface, 0x0150E828u, NVAPI, 0)
- HC_LOAD_ADDR(nvapi, NvAPI_Unload, NVAPI_UNLOAD, nvapi_QueryInterface, 0xD22BDD7Eu, NVAPI, 0)
- HC_LOAD_ADDR(nvapi, NvAPI_GetErrorMessage, NVAPI_GETERRORMESSAGE, nvapi_QueryInterface, 0x6C2D048Cu, NVAPI, 0)
- HC_LOAD_ADDR(nvapi, NvAPI_EnumPhysicalGPUs, NVAPI_ENUMPHYSICALGPUS, nvapi_QueryInterface, 0xE5AC921Fu, NVAPI, 0)
- HC_LOAD_ADDR(nvapi, NvAPI_GPU_GetPerfPoliciesInfo, NVAPI_GPU_GETPERFPOLICIESINFO, nvapi_QueryInterface, 0x409D9841u, NVAPI, 0)
- HC_LOAD_ADDR(nvapi, NvAPI_GPU_GetPerfPoliciesStatus, NVAPI_GPU_GETPERFPOLICIESSTATUS, nvapi_QueryInterface, 0x3D358A0Cu, NVAPI, 0)
- HC_LOAD_ADDR(nvapi, NvAPI_GPU_GetBusId, NVAPI_GPU_GETBUSID, nvapi_QueryInterface, 0x1BE0B8E5u, NVAPI, 0)
- HC_LOAD_ADDR(nvapi, NvAPI_GPU_GetBusSlotId, NVAPI_GPU_GETBUSSLOTID, nvapi_QueryInterface, 0x2A0A350Fu, NVAPI, 0)
+ HC_LOAD_ADDR(nvapi, NvAPI_Initialize, NVAPI_INITIALIZE, nvapi_QueryInterface, 0x0150E828U, NVAPI, 0)
+ HC_LOAD_ADDR(nvapi, NvAPI_Unload, NVAPI_UNLOAD, nvapi_QueryInterface, 0xD22BDD7EU, NVAPI, 0)
+ HC_LOAD_ADDR(nvapi, NvAPI_GetErrorMessage, NVAPI_GETERRORMESSAGE, nvapi_QueryInterface, 0x6C2D048CU, NVAPI, 0)
+ HC_LOAD_ADDR(nvapi, NvAPI_EnumPhysicalGPUs, NVAPI_ENUMPHYSICALGPUS, nvapi_QueryInterface, 0xE5AC921FU, NVAPI, 0)
+ HC_LOAD_ADDR(nvapi, NvAPI_GPU_GetPerfPoliciesInfo, NVAPI_GPU_GETPERFPOLICIESINFO, nvapi_QueryInterface, 0x409D9841U, NVAPI, 0)
+ HC_LOAD_ADDR(nvapi, NvAPI_GPU_GetPerfPoliciesStatus, NVAPI_GPU_GETPERFPOLICIESSTATUS, nvapi_QueryInterface, 0x3D358A0CU, NVAPI, 0)
+ HC_LOAD_ADDR(nvapi, NvAPI_GPU_GetBusId, NVAPI_GPU_GETBUSID, nvapi_QueryInterface, 0x1BE0B8E5U, NVAPI, 0)
+ HC_LOAD_ADDR(nvapi, NvAPI_GPU_GetBusSlotId, NVAPI_GPU_GETBUSSLOTID, nvapi_QueryInterface, 0x2A0A350FU, NVAPI, 0)
return 0;
}
diff --git a/src/main.c b/src/main.c
index a5123d57b..d7d1f14bf 100644
--- a/src/main.c
+++ b/src/main.c
@@ -476,7 +476,7 @@ static void main_outerloop_mainscreen (MAYBE_UNUSED hashcat_ctx_t *hashcat_ctx,
for (u32 i = 0; i < 32; i++)
{
- const u32 opti_bit = 1u << i;
+ const u32 opti_bit = 1U << i;
if (hashconfig->opti_type & opti_bit) event_log_info (hashcat_ctx, "* %s", stroptitype (opti_bit));
}
From 2f76326c37fdcaa9c192bab411b22aaa887f9297 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 3 Aug 2019 18:28:44 -0700
Subject: [PATCH 070/113] Run through Clang's android-cloexec checkers
This is mainly useful with SELinux.
---
src/backend.c | 8 ++++++--
src/shared.c | 6 +++++-
2 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/src/backend.c b/src/backend.c
index d6b15d891..b0469e8d7 100644
--- a/src/backend.c
+++ b/src/backend.c
@@ -371,8 +371,8 @@ static bool opencl_test_instruction (hashcat_ctx_t *hashcat_ctx, cl_context cont
#ifndef DEBUG
#ifndef _WIN
fflush (stderr);
- int bak = dup (2);
- int tmp = open ("/dev/null", O_WRONLY);
+ int bak = fcntl(2, F_DUPFD_CLOEXEC);
+ int tmp = open ("/dev/null", O_WRONLY | O_CLOEXEC);
dup2 (tmp, 2);
close (tmp);
#endif
@@ -383,7 +383,11 @@ static bool opencl_test_instruction (hashcat_ctx_t *hashcat_ctx, cl_context cont
#ifndef DEBUG
#ifndef _WIN
fflush (stderr);
+ #ifndef __APPLE__
+ dup3 (bak, 2, O_CLOEXEC);
+ #else
dup2 (bak, 2);
+ #endif
close (bak);
#endif
#endif
diff --git a/src/shared.c b/src/shared.c
index b27dbdba1..f9d3a01ab 100644
--- a/src/shared.c
+++ b/src/shared.c
@@ -336,7 +336,11 @@ bool hc_path_create (const char *path)
{
if (hc_path_exist (path) == true) return false;
- const int fd = creat (path, S_IRUSR | S_IWUSR);
+#ifdef O_CLOEXEC
+ const int fd = open (path, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, S_IRUSR | S_IWUSR);
+#else
+ const int fd = open (path, O_WRONLY | O_CREAT | O_TRUNC, S_IRUSR | S_IWUSR);
+#endif
if (fd == -1) return false;
From fb75164126a04703da807aa5947c52fa3b6c1306 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 3 Aug 2019 18:34:38 -0700
Subject: [PATCH 071/113] Run through Clang's google-readability-casting
Removes casts where the type is identical.
---
src/backend.c | 34 +++++++++++++++++-----------------
src/brain.c | 2 +-
src/dispatch.c | 6 +++---
src/filehandling.c | 4 ++--
src/potfile.c | 2 +-
src/shared.c | 2 +-
6 files changed, 25 insertions(+), 25 deletions(-)
diff --git a/src/backend.c b/src/backend.c
index b0469e8d7..c3d0d1ec2 100644
--- a/src/backend.c
+++ b/src/backend.c
@@ -449,7 +449,7 @@ static bool read_kernel_binary (hashcat_ctx_t *hashcat_ctx, const char *kernel_f
hc_fclose (&fp);
- if (num_read != (size_t) klen)
+ if (num_read != klen)
{
event_log_error (hashcat_ctx, "%s: %s", kernel_file, strerror (errno));
@@ -473,7 +473,7 @@ static bool read_kernel_binary (hashcat_ctx_t *hashcat_ctx, const char *kernel_f
klen += extra_len;
}
- kernel_lengths[0] = (size_t) klen;
+ kernel_lengths[0] = klen;
kernel_sources[0] = buf;
}
@@ -2420,7 +2420,7 @@ int hc_clCreateProgramWithBinary (hashcat_ctx_t *hashcat_ctx, cl_context context
cl_int CL_err;
- *program = ocl->clCreateProgramWithBinary (context, num_devices, device_list, lengths, (const unsigned char **) binaries, binary_status, &CL_err);
+ *program = ocl->clCreateProgramWithBinary (context, num_devices, device_list, lengths, binaries, binary_status, &CL_err);
if (CL_err != CL_SUCCESS)
{
@@ -4110,7 +4110,7 @@ int run_cracker (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param, co
if (hashconfig->attack_exec == ATTACK_EXEC_INSIDE_KERNEL) innerloop_step = device_param->kernel_loops;
else innerloop_step = 1;
- if (user_options_extra->attack_kern == ATTACK_KERN_STRAIGHT) innerloop_cnt = (u32) straight_ctx->kernel_rules_cnt;
+ if (user_options_extra->attack_kern == ATTACK_KERN_STRAIGHT) innerloop_cnt = straight_ctx->kernel_rules_cnt;
else if (user_options_extra->attack_kern == ATTACK_KERN_COMBI) innerloop_cnt = (u32) combinator_ctx->combs_cnt;
else if (user_options_extra->attack_kern == ATTACK_KERN_BF) innerloop_cnt = (u32) mask_ctx->bfs_cnt;
}
@@ -4137,7 +4137,7 @@ int run_cracker (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param, co
device_param->innerloop_pos = innerloop_pos;
device_param->innerloop_left = innerloop_left;
- device_param->kernel_params_buf32[30] = (u32) innerloop_left;
+ device_param->kernel_params_buf32[30] = innerloop_left;
device_param->outerloop_multi = (double) innerloop_cnt / (double) (innerloop_pos + innerloop_left);
@@ -4145,7 +4145,7 @@ int run_cracker (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param, co
if (hashes->salts_shown[salt_pos] == 1)
{
- status_ctx->words_progress_done[salt_pos] += (u64) pws_cnt * innerloop_left;
+ status_ctx->words_progress_done[salt_pos] += pws_cnt * innerloop_left;
continue;
}
@@ -4484,7 +4484,7 @@ int run_cracker (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param, co
if (status_ctx->run_thread_level2 == true)
{
- const u64 perf_sum_all = (u64) pws_cnt * innerloop_left;
+ const u64 perf_sum_all = pws_cnt * innerloop_left;
const double speed_msec = hc_timer_get (device_param->timer_speed);
@@ -6796,7 +6796,7 @@ int backend_session_begin (hashcat_ctx_t *hashcat_ctx)
u64 size_plains = (u64) hashes->digests_cnt * sizeof (plain_t);
u64 size_salts = (u64) hashes->salts_cnt * sizeof (salt_t);
- u64 size_esalts = (u64) hashes->digests_cnt * (u64) hashconfig->esalt_size;
+ u64 size_esalts = (u64) hashes->digests_cnt * hashconfig->esalt_size;
u64 size_shown = (u64) hashes->digests_cnt * sizeof (u32);
u64 size_digests = (u64) hashes->digests_cnt * (u64) hashconfig->dgst_size;
@@ -6842,7 +6842,7 @@ int backend_session_begin (hashcat_ctx_t *hashcat_ctx)
// kern type
- u32 kern_type = (u32) hashconfig->kern_type;
+ u32 kern_type = hashconfig->kern_type;
if (module_ctx->module_kern_type_dynamic != MODULE_DEFAULT)
{
@@ -9288,13 +9288,13 @@ int backend_session_begin (hashcat_ctx_t *hashcat_ctx)
// size_pws
- size_pws = (u64) kernel_power_max * sizeof (pw_t);
+ size_pws = kernel_power_max * sizeof (pw_t);
size_pws_amp = (hashconfig->attack_exec == ATTACK_EXEC_INSIDE_KERNEL) ? 1 : size_pws;
// size_pws_comp
- size_pws_comp = (u64) kernel_power_max * (sizeof (u32) * 64);
+ size_pws_comp = kernel_power_max * (sizeof (u32) * 64);
// size_pws_idx
@@ -9302,28 +9302,28 @@ int backend_session_begin (hashcat_ctx_t *hashcat_ctx)
// size_tmps
- size_tmps = (u64) kernel_power_max * (hashconfig->tmp_size + hashconfig->extra_tmp_size);
+ size_tmps = kernel_power_max * (hashconfig->tmp_size + hashconfig->extra_tmp_size);
// size_hooks
- size_hooks = (u64) kernel_power_max * hashconfig->hook_size;
+ size_hooks = kernel_power_max * hashconfig->hook_size;
#ifdef WITH_BRAIN
// size_brains
- size_brain_link_in = (u64) kernel_power_max * 1;
- size_brain_link_out = (u64) kernel_power_max * 8;
+ size_brain_link_in = kernel_power_max * 1;
+ size_brain_link_out = kernel_power_max * 8;
#endif
if (user_options->slow_candidates == true)
{
// size_pws_pre
- size_pws_pre = (u64) kernel_power_max * sizeof (pw_pre_t);
+ size_pws_pre = kernel_power_max * sizeof (pw_pre_t);
// size_pws_base
- size_pws_base = (u64) kernel_power_max * sizeof (pw_pre_t);
+ size_pws_base = kernel_power_max * sizeof (pw_pre_t);
}
// now check if all device-memory sizes which depend on the kernel_accel_max amplifier are within its boundaries
diff --git a/src/brain.c b/src/brain.c
index ce3e629b3..02c20b78e 100644
--- a/src/brain.c
+++ b/src/brain.c
@@ -934,7 +934,7 @@ bool brain_client_connect (hc_device_param_t *device_param, const status_ctx_t *
snprintf (port_str, sizeof (port_str), "%i", port);
- const char *host_real = (host == NULL) ? "127.0.0.1" : (const char *) host;
+ const char *host_real = (host == NULL) ? "127.0.0.1" : host;
bool connected = false;
diff --git a/src/dispatch.c b/src/dispatch.c
index 9574361a7..b2e936235 100644
--- a/src/dispatch.c
+++ b/src/dispatch.c
@@ -541,7 +541,7 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
brain_client_generate_hash ((u64 *) hash, (const char *) extra_info_straight.out_buf, extra_info_straight.out_len);
- u32 *ptr = (u32 *) device_param->brain_link_out_buf;
+ u32 *ptr = device_param->brain_link_out_buf;
ptr[(device_param->pws_pre_cnt * 2) + 0] = hash[0];
ptr[(device_param->pws_pre_cnt * 2) + 1] = hash[1];
@@ -853,7 +853,7 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
brain_client_generate_hash ((u64 *) hash, (const char *) extra_info_combi.out_buf, extra_info_combi.out_len);
- u32 *ptr = (u32 *) device_param->brain_link_out_buf;
+ u32 *ptr = device_param->brain_link_out_buf;
ptr[(device_param->pws_pre_cnt * 2) + 0] = hash[0];
ptr[(device_param->pws_pre_cnt * 2) + 1] = hash[1];
@@ -1108,7 +1108,7 @@ static int calc (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param)
brain_client_generate_hash ((u64 *) hash, (const char *) extra_info_mask.out_buf, extra_info_mask.out_len);
- u32 *ptr = (u32 *) device_param->brain_link_out_buf;
+ u32 *ptr = device_param->brain_link_out_buf;
ptr[(device_param->pws_pre_cnt * 2) + 0] = hash[0];
ptr[(device_param->pws_pre_cnt * 2) + 1] = hash[1];
diff --git a/src/filehandling.c b/src/filehandling.c
index 55cfc1f6a..921e7e0ed 100644
--- a/src/filehandling.c
+++ b/src/filehandling.c
@@ -168,7 +168,7 @@ int hc_fseek (HCFILE *fp, off_t offset, int whence)
if (fp->is_gzip)
{
- r = gzseek (fp->gfp, (z_off_t) offset, whence);
+ r = gzseek (fp->gfp, offset, whence);
}
else if (fp->is_zip)
{
@@ -371,7 +371,7 @@ int hc_fscanf (HCFILE *fp, const char *format, void *ptr)
return -1;
}
- sscanf (b, format, (void *) ptr);
+ sscanf (b, format, ptr);
hcfree (buf);
diff --git a/src/potfile.c b/src/potfile.c
index efc552a48..b0726107a 100644
--- a/src/potfile.c
+++ b/src/potfile.c
@@ -69,7 +69,7 @@ int sort_pot_tree_by_hash (const void *v1, const void *v2)
const hash_t *h1 = (const hash_t *) t1->nodes->hash_buf;
const hash_t *h2 = (const hash_t *) t2->nodes->hash_buf;
- hashconfig_t *hc = (hashconfig_t *) t1->hashconfig; // is same as t2->hashconfig
+ hashconfig_t *hc = t1->hashconfig; // is same as t2->hashconfig
return sort_by_hash (h1, h2, hc);
}
diff --git a/src/shared.c b/src/shared.c
index f9d3a01ab..67134ef25 100644
--- a/src/shared.c
+++ b/src/shared.c
@@ -1147,7 +1147,7 @@ bool generic_salt_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, const u8
if (in_len < (int) (((hashconfig->salt_min * 8) / 6) + 0)) return false;
if (in_len > (int) (((hashconfig->salt_max * 8) / 6) + 3)) return false;
- tmp_len = base64_decode (base64_to_int, (const u8 *) in_buf, in_len, tmp_u8);
+ tmp_len = base64_decode (base64_to_int, in_buf, in_len, tmp_u8);
}
else
{
From 6ecb42b3ea47c99c74b3265f301b2ca79724f843 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 3 Aug 2019 18:38:24 -0700
Subject: [PATCH 072/113] Run through Clang's
readability-inconsistent-declaration-parameter-name
---
include/backend.h | 2 +-
include/hashes.h | 2 +-
include/potfile.h | 2 +-
include/status.h | 2 +-
4 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/include/backend.h b/include/backend.h
index 074a0cd9f..4d24cf4c0 100644
--- a/include/backend.h
+++ b/include/backend.h
@@ -84,7 +84,7 @@ int hc_clCreateKernel (hashcat_ctx_t *hashcat_ctx, cl_program program
int hc_clCreateProgramWithBinary (hashcat_ctx_t *hashcat_ctx, cl_context context, cl_uint num_devices, const cl_device_id *device_list, const size_t *lengths, const unsigned char **binaries, cl_int *binary_status, cl_program *program);
int hc_clCreateProgramWithSource (hashcat_ctx_t *hashcat_ctx, cl_context context, cl_uint count, const char **strings, const size_t *lengths, cl_program *program);
int hc_clEnqueueCopyBuffer (hashcat_ctx_t *hashcat_ctx, cl_command_queue command_queue, cl_mem src_buffer, cl_mem dst_buffer, size_t src_offset, size_t dst_offset, size_t size, cl_uint num_events_in_wait_list, const cl_event *event_wait_list, cl_event *event);
-int hc_clEnqueueMapBuffer (hashcat_ctx_t *hashcat_ctx, cl_command_queue command_queue, cl_mem buffer, cl_bool blocking_map, cl_map_flags map_flags, size_t offset, size_t cb, cl_uint num_events_in_wait_list, const cl_event *event_wait_list, cl_event *event, void **buf);
+int hc_clEnqueueMapBuffer (hashcat_ctx_t *hashcat_ctx, cl_command_queue command_queue, cl_mem buffer, cl_bool blocking_map, cl_map_flags map_flags, size_t offset, size_t size, cl_uint num_events_in_wait_list, const cl_event *event_wait_list, cl_event *event, void **buf);
int hc_clEnqueueNDRangeKernel (hashcat_ctx_t *hashcat_ctx, cl_command_queue command_queue, cl_kernel kernel, cl_uint work_dim, const size_t *global_work_offset, const size_t *global_work_size, const size_t *local_work_size, cl_uint num_events_in_wait_list, const cl_event *event_wait_list, cl_event *event);
int hc_clEnqueueReadBuffer (hashcat_ctx_t *hashcat_ctx, cl_command_queue command_queue, cl_mem buffer, cl_bool blocking_read, size_t offset, size_t size, void *ptr, cl_uint num_events_in_wait_list, const cl_event *event_wait_list, cl_event *event);
int hc_clEnqueueUnmapMemObject (hashcat_ctx_t *hashcat_ctx, cl_command_queue command_queue, cl_mem memobj, void *mapped_ptr, cl_uint num_events_in_wait_list, const cl_event *event_wait_list, cl_event *event);
diff --git a/include/hashes.h b/include/hashes.h
index 7509e944f..2683e84f0 100644
--- a/include/hashes.h
+++ b/include/hashes.h
@@ -6,7 +6,7 @@
#ifndef _HASHES_H
#define _HASHES_H
-int sort_by_string (const void *v1, const void *v2);
+int sort_by_string (const void *p1, const void *p2);
int sort_by_digest_p0p1 (const void *v1, const void *v2, void *v3);
int sort_by_salt (const void *v1, const void *v2);
int sort_by_hash (const void *v1, const void *v2, void *v3);
diff --git a/include/potfile.h b/include/potfile.h
index 51fd6d8d9..fcc8407c6 100644
--- a/include/potfile.h
+++ b/include/potfile.h
@@ -25,7 +25,7 @@ int potfile_handle_show (hashcat_ctx_t *hashcat_ctx);
int potfile_handle_left (hashcat_ctx_t *hashcat_ctx);
void potfile_update_hash (hashcat_ctx_t *hashcat_ctx, hash_t *found, char *line_pw_buf, int line_pw_len);
-void potfile_update_hashes (hashcat_ctx_t *hashcat_ctx, hash_t *search, char *line_pw_buf, int line_pw_len, pot_tree_entry_t *tree);
+void potfile_update_hashes (hashcat_ctx_t *hashcat_ctx, hash_t *hash_buf, char *line_pw_buf, int line_pw_len, pot_tree_entry_t *tree);
void pot_tree_destroy (pot_tree_entry_t *tree);
diff --git a/include/status.h b/include/status.h
index 8a142e54c..5b0bae311 100644
--- a/include/status.h
+++ b/include/status.h
@@ -115,6 +115,6 @@ void status_progress_reset (hashcat_ctx_t *hashcat_ct
int status_ctx_init (hashcat_ctx_t *hashcat_ctx);
void status_ctx_destroy (hashcat_ctx_t *hashcat_ctx);
-void status_status_destroy (hashcat_ctx_t *hashcat_ctx, hashcat_status_t *status_ctx);
+void status_status_destroy (hashcat_ctx_t *hashcat_ctx, hashcat_status_t *hashcat_status);
#endif // _STATUS_H
From 6dc72ebcc570ba15df808a42c43d98f8fe3199e4 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 3 Aug 2019 19:09:07 -0700
Subject: [PATCH 073/113] Run through Clang's readability-else-after-return
There's no need for a return statement in an else path. Just take it out.
Simplifies the code slightly.
---
src/backend.c | 64 +++++++++----------
src/benchmark.c | 26 ++++----
src/brain.c | 144 ++++++++++++++++++++---------------------
src/potfile.c | 10 ++-
src/status.c | 155 ++++++++++++++++-----------------------------
src/user_options.c | 30 ++++-----
6 files changed, 182 insertions(+), 247 deletions(-)
diff --git a/src/backend.c b/src/backend.c
index c3d0d1ec2..8b50941e8 100644
--- a/src/backend.c
+++ b/src/backend.c
@@ -4532,44 +4532,42 @@ int run_cracker (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param, co
break;
}
+
+ double total_msec = device_param->speed_msec[0];
+
+ for (u32 speed_pos = 1; speed_pos < device_param->speed_pos; speed_pos++)
+ {
+ total_msec += device_param->speed_msec[speed_pos];
+ }
+
+ if (user_options->slow_candidates == true)
+ {
+ if ((total_msec > 4000) || (device_param->speed_pos == SPEED_CACHE - 1))
+ {
+ const u32 speed_pos = device_param->speed_pos;
+
+ if (speed_pos)
+ {
+ device_param->speed_cnt[0] = device_param->speed_cnt[speed_pos - 1];
+ device_param->speed_msec[0] = device_param->speed_msec[speed_pos - 1];
+ }
+
+ device_param->speed_pos = 0;
+
+ device_param->speed_only_finish = true;
+
+ break;
+ }
+ }
else
{
- double total_msec = device_param->speed_msec[0];
+ // it's unclear if 4s is enough to turn on boost mode for all backend device
- for (u32 speed_pos = 1; speed_pos < device_param->speed_pos; speed_pos++)
+ if ((total_msec > 4000) || (device_param->speed_pos == SPEED_CACHE - 1))
{
- total_msec += device_param->speed_msec[speed_pos];
- }
+ device_param->speed_only_finish = true;
- if (user_options->slow_candidates == true)
- {
- if ((total_msec > 4000) || (device_param->speed_pos == SPEED_CACHE - 1))
- {
- const u32 speed_pos = device_param->speed_pos;
-
- if (speed_pos)
- {
- device_param->speed_cnt[0] = device_param->speed_cnt[speed_pos - 1];
- device_param->speed_msec[0] = device_param->speed_msec[speed_pos - 1];
- }
-
- device_param->speed_pos = 0;
-
- device_param->speed_only_finish = true;
-
- break;
- }
- }
- else
- {
- // it's unclear if 4s is enough to turn on boost mode for all backend device
-
- if ((total_msec > 4000) || (device_param->speed_pos == SPEED_CACHE - 1))
- {
- device_param->speed_only_finish = true;
-
- break;
- }
+ break;
}
}
}
diff --git a/src/benchmark.c b/src/benchmark.c
index 78f7d9f08..05f0c35a6 100644
--- a/src/benchmark.c
+++ b/src/benchmark.c
@@ -57,28 +57,26 @@ int benchmark_next (hashcat_ctx_t *hashcat_ctx)
return hash_mode;
}
- else
+
+ char *modulefile = (char *) hcmalloc (HCBUFSIZ_TINY);
+
+ for (int i = cur; i < MODULE_HASH_MODES_MAXIMUM; i++)
{
- char *modulefile = (char *) hcmalloc (HCBUFSIZ_TINY);
+ module_filename (folder_config, i, modulefile, HCBUFSIZ_TINY);
- for (int i = cur; i < MODULE_HASH_MODES_MAXIMUM; i++)
+ if (hc_path_exist (modulefile) == true)
{
- module_filename (folder_config, i, modulefile, HCBUFSIZ_TINY);
+ const int hash_mode = i;
- if (hc_path_exist (modulefile) == true)
- {
- const int hash_mode = i;
+ cur = hash_mode + 1;
- cur = hash_mode + 1;
+ hcfree (modulefile);
- hcfree (modulefile);
-
- return hash_mode;
- }
+ return hash_mode;
}
-
- hcfree (modulefile);
}
+ hcfree (modulefile);
+
return -1;
}
diff --git a/src/brain.c b/src/brain.c
index 02c20b78e..d67170cd4 100644
--- a/src/brain.c
+++ b/src/brain.c
@@ -1589,36 +1589,34 @@ bool brain_server_read_hash_dump (brain_server_db_hash_t *brain_server_db_hash,
return false;
}
- else
+
+ i64 temp_cnt = (u64) sb.st_size / sizeof (brain_server_hash_long_t);
+
+ if (brain_server_db_hash_realloc (brain_server_db_hash, temp_cnt) == false)
{
- i64 temp_cnt = (u64) sb.st_size / sizeof (brain_server_hash_long_t);
-
- if (brain_server_db_hash_realloc (brain_server_db_hash, temp_cnt) == false)
- {
- brain_logging (stderr, 0, "%s\n", MSG_ENOMEM);
-
- hc_fclose (&fp);
-
- return false;
- }
-
- const size_t nread = hc_fread (brain_server_db_hash->long_buf, sizeof (brain_server_hash_long_t), temp_cnt, &fp);
-
- if (nread != (size_t) temp_cnt)
- {
- brain_logging (stderr, 0, "%s: only %" PRIu64 " bytes read\n", file, (u64) nread * sizeof (brain_server_hash_long_t));
-
- hc_fclose (&fp);
-
- return false;
- }
-
- brain_server_db_hash->long_cnt = temp_cnt;
- brain_server_db_hash->write_hashes = false;
+ brain_logging (stderr, 0, "%s\n", MSG_ENOMEM);
hc_fclose (&fp);
+
+ return false;
}
+ const size_t nread = hc_fread (brain_server_db_hash->long_buf, sizeof (brain_server_hash_long_t), temp_cnt, &fp);
+
+ if (nread != (size_t) temp_cnt)
+ {
+ brain_logging (stderr, 0, "%s: only %" PRIu64 " bytes read\n", file, (u64) nread * sizeof (brain_server_hash_long_t));
+
+ hc_fclose (&fp);
+
+ return false;
+ }
+
+ brain_server_db_hash->long_cnt = temp_cnt;
+ brain_server_db_hash->write_hashes = false;
+
+ hc_fclose (&fp);
+
const double ms = hc_timer_get (timer_dump);
brain_logging (stdout, 0, "Read %" PRIu64 " bytes from session 0x%08x in %.2f ms\n", (u64) sb.st_size, brain_server_db_hash->brain_session, ms);
@@ -1644,24 +1642,22 @@ bool brain_server_write_hash_dump (brain_server_db_hash_t *brain_server_db_hash,
return false;
}
- else
+
+ const size_t nwrite = hc_fwrite (brain_server_db_hash->long_buf, sizeof (brain_server_hash_long_t), brain_server_db_hash->long_cnt, &fp);
+
+ if (nwrite != (size_t) brain_server_db_hash->long_cnt)
{
- const size_t nwrite = hc_fwrite (brain_server_db_hash->long_buf, sizeof (brain_server_hash_long_t), brain_server_db_hash->long_cnt, &fp);
-
- if (nwrite != (size_t) brain_server_db_hash->long_cnt)
- {
- brain_logging (stderr, 0, "%s: only %" PRIu64 " bytes written\n", file, (u64) nwrite * sizeof (brain_server_hash_long_t));
-
- hc_fclose (&fp);
-
- return false;
- }
+ brain_logging (stderr, 0, "%s: only %" PRIu64 " bytes written\n", file, (u64) nwrite * sizeof (brain_server_hash_long_t));
hc_fclose (&fp);
- brain_server_db_hash->write_hashes = false;
+ return false;
}
+ hc_fclose (&fp);
+
+ brain_server_db_hash->write_hashes = false;
+
// stats
const double ms = hc_timer_get (timer_dump);
@@ -1790,36 +1786,34 @@ bool brain_server_read_attack_dump (brain_server_db_attack_t *brain_server_db_at
return false;
}
- else
+
+ i64 temp_cnt = (u64) sb.st_size / sizeof (brain_server_attack_long_t);
+
+ if (brain_server_db_attack_realloc (brain_server_db_attack, temp_cnt, 0) == false)
{
- i64 temp_cnt = (u64) sb.st_size / sizeof (brain_server_attack_long_t);
-
- if (brain_server_db_attack_realloc (brain_server_db_attack, temp_cnt, 0) == false)
- {
- brain_logging (stderr, 0, "%s\n", MSG_ENOMEM);
-
- hc_fclose (&fp);
-
- return false;
- }
-
- const size_t nread = hc_fread (brain_server_db_attack->long_buf, sizeof (brain_server_attack_long_t), temp_cnt, &fp);
-
- if (nread != (size_t) temp_cnt)
- {
- brain_logging (stderr, 0, "%s: only %" PRIu64 " bytes read\n", file, (u64) nread * sizeof (brain_server_attack_long_t));
-
- hc_fclose (&fp);
-
- return false;
- }
-
- brain_server_db_attack->long_cnt = temp_cnt;
- brain_server_db_attack->write_attacks = false;
+ brain_logging (stderr, 0, "%s\n", MSG_ENOMEM);
hc_fclose (&fp);
+
+ return false;
}
+ const size_t nread = hc_fread (brain_server_db_attack->long_buf, sizeof (brain_server_attack_long_t), temp_cnt, &fp);
+
+ if (nread != (size_t) temp_cnt)
+ {
+ brain_logging (stderr, 0, "%s: only %" PRIu64 " bytes read\n", file, (u64) nread * sizeof (brain_server_attack_long_t));
+
+ hc_fclose (&fp);
+
+ return false;
+ }
+
+ brain_server_db_attack->long_cnt = temp_cnt;
+ brain_server_db_attack->write_attacks = false;
+
+ hc_fclose (&fp);
+
const double ms = hc_timer_get (timer_dump);
brain_logging (stdout, 0, "Read %" PRIu64 " bytes from attack 0x%08x in %.2f ms\n", (u64) sb.st_size, brain_server_db_attack->brain_attack, ms);
@@ -1845,26 +1839,24 @@ bool brain_server_write_attack_dump (brain_server_db_attack_t *brain_server_db_a
return false;
}
- else
+
+ // storing should not include reserved attacks only finished
+
+ const size_t nwrite = hc_fwrite (brain_server_db_attack->long_buf, sizeof (brain_server_attack_long_t), brain_server_db_attack->long_cnt, &fp);
+
+ if (nwrite != (size_t) brain_server_db_attack->long_cnt)
{
- // storing should not include reserved attacks only finished
-
- const size_t nwrite = hc_fwrite (brain_server_db_attack->long_buf, sizeof (brain_server_attack_long_t), brain_server_db_attack->long_cnt, &fp);
-
- if (nwrite != (size_t) brain_server_db_attack->long_cnt)
- {
- brain_logging (stderr, 0, "%s: only %" PRIu64 " bytes written\n", file, (u64) nwrite * sizeof (brain_server_attack_long_t));
-
- hc_fclose (&fp);
-
- return false;
- }
+ brain_logging (stderr, 0, "%s: only %" PRIu64 " bytes written\n", file, (u64) nwrite * sizeof (brain_server_attack_long_t));
hc_fclose (&fp);
- brain_server_db_attack->write_attacks = false;
+ return false;
}
+ hc_fclose (&fp);
+
+ brain_server_db_attack->write_attacks = false;
+
// stats
const double ms = hc_timer_get (timer_dump);
diff --git a/src/potfile.c b/src/potfile.c
index b0726107a..866548bff 100644
--- a/src/potfile.c
+++ b/src/potfile.c
@@ -576,12 +576,10 @@ int potfile_remove_parse (hashcat_ctx_t *hashcat_ctx)
continue;
}
- else
- {
- // should be rejected?
- //const int parser_status = module_ctx->module_hash_decode_potfile (hashconfig, hash_buf.digest, hash_buf.salt, hash_buf.esalt, hash_buf.hook_salt, hash_buf.hash_info, line_hash_buf, line_hash_len, NULL);
- //if (parser_status != PARSER_OK) continue;
- }
+
+ // should be rejected?
+ //const int parser_status = module_ctx->module_hash_decode_potfile (hashconfig, hash_buf.digest, hash_buf.salt, hash_buf.esalt, hash_buf.hook_salt, hash_buf.hash_info, line_hash_buf, line_hash_len, NULL);
+ //if (parser_status != PARSER_OK) continue;
}
else
{
diff --git a/src/status.c b/src/status.c
index 8ece2d694..c8b95a809 100644
--- a/src/status.c
+++ b/src/status.c
@@ -327,34 +327,28 @@ char *status_get_hash_target (const hashcat_ctx_t *hashcat_ctx)
return tmp_buf2;
}
- else
+
+ if (hashconfig->opts_type & OPTS_TYPE_BINARY_HASHFILE)
{
- if (hashconfig->opts_type & OPTS_TYPE_BINARY_HASHFILE)
- {
- return hcstrdup (hashes->hashfile);
- }
- else
- {
- char *tmp_buf = (char *) hcmalloc (HCBUFSIZ_LARGE);
-
- const int tmp_len = hash_encode (hashcat_ctx->hashconfig, hashcat_ctx->hashes, hashcat_ctx->module_ctx, tmp_buf, HCBUFSIZ_LARGE, 0, 0);
-
- tmp_buf[tmp_len] = 0;
-
- compress_terminal_line_length (tmp_buf, 19, 6); // 19 = strlen ("Hash.Target......: ")
-
- char *tmp_buf2 = strdup (tmp_buf);
-
- free (tmp_buf);
-
- return tmp_buf2;
- }
+ return hcstrdup (hashes->hashfile);
}
+
+ char *tmp_buf = (char *) hcmalloc (HCBUFSIZ_LARGE);
+
+ const int tmp_len = hash_encode (hashcat_ctx->hashconfig, hashcat_ctx->hashes, hashcat_ctx->module_ctx, tmp_buf, HCBUFSIZ_LARGE, 0, 0);
+
+ tmp_buf[tmp_len] = 0;
+
+ compress_terminal_line_length (tmp_buf, 19, 6); // 19 = strlen ("Hash.Target......: ")
+
+ char *tmp_buf2 = strdup (tmp_buf);
+
+ free (tmp_buf);
+
+ return tmp_buf2;
}
- else
- {
- return hcstrdup (hashes->hashfile);
- }
+
+ return hcstrdup (hashes->hashfile);
}
int status_get_guess_mode (const hashcat_ctx_t *hashcat_ctx)
@@ -389,30 +383,21 @@ int status_get_guess_mode (const hashcat_ctx_t *hashcat_ctx)
{
return GUESS_MODE_STRAIGHT_FILE_RULES_FILE;
}
- else if (has_rule_gen == true)
+ if (has_rule_gen == true)
{
return GUESS_MODE_STRAIGHT_FILE_RULES_GEN;
}
- else
- {
- return GUESS_MODE_STRAIGHT_FILE;
- }
+ return GUESS_MODE_STRAIGHT_FILE;
}
- else
+ if (has_rule_file == true)
{
- if (has_rule_file == true)
- {
- return GUESS_MODE_STRAIGHT_STDIN_RULES_FILE;
- }
- else if (has_rule_gen == true)
- {
- return GUESS_MODE_STRAIGHT_STDIN_RULES_GEN;
- }
- else
- {
- return GUESS_MODE_STRAIGHT_STDIN;
- }
+ return GUESS_MODE_STRAIGHT_STDIN_RULES_FILE;
}
+ if (has_rule_gen == true)
+ {
+ return GUESS_MODE_STRAIGHT_STDIN_RULES_GEN;
+ }
+ return GUESS_MODE_STRAIGHT_STDIN;
}
if (user_options->attack_mode == ATTACK_MODE_COMBI)
@@ -421,10 +406,7 @@ int status_get_guess_mode (const hashcat_ctx_t *hashcat_ctx)
{
return GUESS_MODE_COMBINATOR_BASE_LEFT;
}
- else
- {
- return GUESS_MODE_COMBINATOR_BASE_RIGHT;
- }
+ return GUESS_MODE_COMBINATOR_BASE_RIGHT;
}
if (user_options->attack_mode == ATTACK_MODE_BF)
@@ -433,10 +415,7 @@ int status_get_guess_mode (const hashcat_ctx_t *hashcat_ctx)
{
return GUESS_MODE_MASK_CS;
}
- else
- {
- return GUESS_MODE_MASK;
- }
+ return GUESS_MODE_MASK;
}
if (user_options->attack_mode == ATTACK_MODE_HYBRID1)
@@ -445,10 +424,7 @@ int status_get_guess_mode (const hashcat_ctx_t *hashcat_ctx)
{
return GUESS_MODE_HYBRID1_CS;
}
- else
- {
- return GUESS_MODE_HYBRID1;
- }
+ return GUESS_MODE_HYBRID1;
}
if (user_options->attack_mode == ATTACK_MODE_HYBRID2)
@@ -457,10 +433,7 @@ int status_get_guess_mode (const hashcat_ctx_t *hashcat_ctx)
{
return GUESS_MODE_HYBRID2_CS;
}
- else
- {
- return GUESS_MODE_HYBRID2;
- }
+ return GUESS_MODE_HYBRID2;
}
return GUESS_MODE_NONE;
@@ -490,10 +463,7 @@ char *status_get_guess_base (const hashcat_ctx_t *hashcat_ctx)
{
return strdup (combinator_ctx->dict1);
}
- else
- {
- return strdup (combinator_ctx->dict2);
- }
+ return strdup (combinator_ctx->dict2);
}
if (user_options->attack_mode == ATTACK_MODE_BF)
@@ -518,14 +488,11 @@ char *status_get_guess_base (const hashcat_ctx_t *hashcat_ctx)
return strdup (mask_ctx->mask);
}
- else
- {
- const straight_ctx_t *straight_ctx = hashcat_ctx->straight_ctx;
- return strdup (straight_ctx->dict);
- }
+ const straight_ctx_t *straight_ctx = hashcat_ctx->straight_ctx;
+
+ return strdup (straight_ctx->dict);
}
-
return NULL;
}
@@ -568,12 +535,10 @@ int status_get_guess_base_offset (const hashcat_ctx_t *hashcat_ctx)
return mask_ctx->masks_pos + 1;
}
- else
- {
- const straight_ctx_t *straight_ctx = hashcat_ctx->straight_ctx;
- return straight_ctx->dicts_pos + 1;
- }
+ const straight_ctx_t *straight_ctx = hashcat_ctx->straight_ctx;
+
+ return straight_ctx->dicts_pos + 1;
}
return 0;
@@ -618,12 +583,10 @@ int status_get_guess_base_count (const hashcat_ctx_t *hashcat_ctx)
return mask_ctx->masks_cnt;
}
- else
- {
- const straight_ctx_t *straight_ctx = hashcat_ctx->straight_ctx;
- return straight_ctx->dicts_cnt;
- }
+ const straight_ctx_t *straight_ctx = hashcat_ctx->straight_ctx;
+
+ return straight_ctx->dicts_cnt;
}
return 0;
@@ -657,10 +620,7 @@ char *status_get_guess_mod (const hashcat_ctx_t *hashcat_ctx)
{
return strdup (combinator_ctx->dict2);
}
- else
- {
- return strdup (combinator_ctx->dict1);
- }
+ return strdup (combinator_ctx->dict1);
}
if (user_options->attack_mode == ATTACK_MODE_BF)
@@ -683,12 +643,10 @@ char *status_get_guess_mod (const hashcat_ctx_t *hashcat_ctx)
return strdup (straight_ctx->dict);
}
- else
- {
- const mask_ctx_t *mask_ctx = hashcat_ctx->mask_ctx;
- return strdup (mask_ctx->mask);
- }
+ const mask_ctx_t *mask_ctx = hashcat_ctx->mask_ctx;
+
+ return strdup (mask_ctx->mask);
}
return NULL;
@@ -729,12 +687,10 @@ int status_get_guess_mod_offset (const hashcat_ctx_t *hashcat_ctx)
return straight_ctx->dicts_pos + 1;
}
- else
- {
- const mask_ctx_t *mask_ctx = hashcat_ctx->mask_ctx;
- return mask_ctx->masks_pos + 1;
- }
+ const mask_ctx_t *mask_ctx = hashcat_ctx->mask_ctx;
+
+ return mask_ctx->masks_pos + 1;
}
return 0;
@@ -775,12 +731,10 @@ int status_get_guess_mod_count (const hashcat_ctx_t *hashcat_ctx)
return straight_ctx->dicts_cnt;
}
- else
- {
- const mask_ctx_t *mask_ctx = hashcat_ctx->mask_ctx;
- return mask_ctx->masks_cnt;
- }
+ const mask_ctx_t *mask_ctx = hashcat_ctx->mask_ctx;
+
+ return mask_ctx->masks_cnt;
}
return 0;
@@ -1196,10 +1150,7 @@ int status_get_progress_mode (const hashcat_ctx_t *hashcat_ctx)
{
return PROGRESS_MODE_KEYSPACE_KNOWN;
}
- else
- {
- return PROGRESS_MODE_KEYSPACE_UNKNOWN;
- }
+ return PROGRESS_MODE_KEYSPACE_UNKNOWN;
}
double status_get_progress_finished_percent (const hashcat_ctx_t *hashcat_ctx)
diff --git a/src/user_options.c b/src/user_options.c
index 89a4b14b2..81078d074 100644
--- a/src/user_options.c
+++ b/src/user_options.c
@@ -1909,28 +1909,26 @@ u64 user_options_extra_amplifier (hashcat_ctx_t *hashcat_ctx)
{
return 1;
}
- else
+
+ if (user_options_extra->attack_kern == ATTACK_KERN_STRAIGHT)
{
- if (user_options_extra->attack_kern == ATTACK_KERN_STRAIGHT)
+ if (straight_ctx->kernel_rules_cnt)
{
- if (straight_ctx->kernel_rules_cnt)
- {
- return straight_ctx->kernel_rules_cnt;
- }
+ return straight_ctx->kernel_rules_cnt;
}
- else if (user_options_extra->attack_kern == ATTACK_KERN_COMBI)
+ }
+ else if (user_options_extra->attack_kern == ATTACK_KERN_COMBI)
+ {
+ if (combinator_ctx->combs_cnt)
{
- if (combinator_ctx->combs_cnt)
- {
- return combinator_ctx->combs_cnt;
- }
+ return combinator_ctx->combs_cnt;
}
- else if (user_options_extra->attack_kern == ATTACK_KERN_BF)
+ }
+ else if (user_options_extra->attack_kern == ATTACK_KERN_BF)
+ {
+ if (mask_ctx->bfs_cnt)
{
- if (mask_ctx->bfs_cnt)
- {
- return mask_ctx->bfs_cnt;
- }
+ return mask_ctx->bfs_cnt;
}
}
From dca1a863152974364ab65f199b6bbd3ab8535203 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 3 Aug 2019 19:46:04 -0700
Subject: [PATCH 074/113] Run through Clang's bugprone-macro-parentheses
---
src/backend.c | 10 +++++-----
src/interface.c | 4 ++--
2 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/src/backend.c b/src/backend.c
index 8b50941e8..edef5c229 100644
--- a/src/backend.c
+++ b/src/backend.c
@@ -921,14 +921,14 @@ int cuda_init (hashcat_ctx_t *hashcat_ctx)
if (cuda->lib == NULL) return -1;
#define HC_LOAD_FUNC_CUDA(ptr,name,cudaname,type,libname,noerr) \
- ptr->name = (type) hc_dlsym (ptr->lib, #cudaname); \
- if (noerr != -1) { \
- if (!ptr->name) { \
- if (noerr == 1) { \
+ ptr->name = (type) hc_dlsym ((ptr)->lib, #cudaname); \
+ if ((noerr) != -1) { \
+ if (!(ptr)->name) { \
+ if ((noerr) == 1) { \
event_log_error (hashcat_ctx, "%s is missing from %s shared library.", #name, #libname); \
return -1; \
} \
- if (noerr != 1) { \
+ if ((noerr) != 1) { \
event_log_warning (hashcat_ctx, "%s is missing from %s shared library.", #name, #libname); \
return 0; \
} \
diff --git a/src/interface.c b/src/interface.c
index 9eb0af983..60ce5e5ec 100644
--- a/src/interface.c
+++ b/src/interface.c
@@ -132,7 +132,7 @@ int hashconfig_init (hashcat_ctx_t *hashcat_ctx)
// check for missing pointer assignements
#define CHECK_DEFINED(func) \
- if (func == NULL) \
+ if ((func) == NULL) \
{ \
event_log_error (hashcat_ctx, "Missing symbol definitions. Old template?"); \
\
@@ -211,7 +211,7 @@ int hashconfig_init (hashcat_ctx_t *hashcat_ctx)
// mandatory functions check
#define CHECK_MANDATORY(func) \
- if (func == MODULE_DEFAULT) \
+ if ((func) == MODULE_DEFAULT) \
{ \
event_log_error (hashcat_ctx, "Missing mandatory symbol definitions"); \
\
From df618e861e3777f84e2e57d9c91932c44995aa85 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 3 Aug 2019 19:49:07 -0700
Subject: [PATCH 075/113] Run through Clang's
performance-type-promotion-in-math-fn
Only changed log2 to log2f. Rightly so.
---
src/shared.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/shared.c b/src/shared.c
index 67134ef25..7c0a67391 100644
--- a/src/shared.c
+++ b/src/shared.c
@@ -794,7 +794,7 @@ float get_entropy (const u8 *buf, const int len)
float w = (float) r / len;
- entropy += -w * log2 (w);
+ entropy += -w * log2f (w);
}
return entropy;
From ab061ba761578382c50d50bc634795af9eb1d3f0 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 3 Aug 2019 22:34:48 -0700
Subject: [PATCH 076/113] Run Clang's bugprone-narrowing-conversions
Fairly minor issue.
---
src/hashes.c | 4 ++--
src/mpsp.c | 4 ++--
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/src/hashes.c b/src/hashes.c
index e9e0a3e7e..3e93b6579 100644
--- a/src/hashes.c
+++ b/src/hashes.c
@@ -773,7 +773,7 @@ int hashes_init_stage1 (hashcat_ctx_t *hashcat_ctx)
if ((user_options->username == true) || (hashconfig->opts_type & OPTS_TYPE_HASH_COPY) || (hashconfig->opts_type & OPTS_TYPE_HASH_SPLIT))
{
- u32 hash_pos;
+ u64 hash_pos;
for (hash_pos = 0; hash_pos < hashes_avail; hash_pos++)
{
@@ -820,7 +820,7 @@ int hashes_init_stage1 (hashcat_ctx_t *hashcat_ctx)
salts_buf = (salt_t *) hccalloc (1, sizeof (salt_t));
}
- for (u32 hash_pos = 0; hash_pos < hashes_avail; hash_pos++)
+ for (u64 hash_pos = 0; hash_pos < hashes_avail; hash_pos++)
{
hashes_buf[hash_pos].digest = ((char *) digests_buf) + (hash_pos * hashconfig->dgst_size);
diff --git a/src/mpsp.c b/src/mpsp.c
index 4345374ff..03f1836ac 100644
--- a/src/mpsp.c
+++ b/src/mpsp.c
@@ -365,8 +365,8 @@ static int mp_gen_css (hashcat_ctx_t *hashcat_ctx, char *mask_buf, size_t mask_l
{
const user_options_t *user_options = hashcat_ctx->user_options;
- u32 mask_pos;
- u32 css_pos;
+ size_t mask_pos;
+ size_t css_pos;
for (mask_pos = 0, css_pos = 0; mask_pos < mask_len; mask_pos++, css_pos++)
{
From f3a3d5aed934cd2fece909366c86e813393567b8 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 3 Aug 2019 22:58:56 -0700
Subject: [PATCH 077/113] bash to sh for two scripts
These don't use any special bash features. They can use regular sh.
---
tools/install_modules.sh | 2 +-
tools/package_bin.sh | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/install_modules.sh b/tools/install_modules.sh
index 0cfa90698..268e09b9f 100755
--- a/tools/install_modules.sh
+++ b/tools/install_modules.sh
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
##
## Author......: See docs/credits.txt
diff --git a/tools/package_bin.sh b/tools/package_bin.sh
index b289cce06..8e109803d 100755
--- a/tools/package_bin.sh
+++ b/tools/package_bin.sh
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
##
## Author......: See docs/credits.txt
From 9ac03652592e44cfbd6491698e555051a3c43ac2 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 3 Aug 2019 23:43:15 -0700
Subject: [PATCH 078/113] Run test.sh through shellcheck
It uses a lot of bashisms. Cannot be used with /bin/sh.
---
tools/test.sh | 234 +++++++++++++++++++++++++-------------------------
1 file changed, 117 insertions(+), 117 deletions(-)
diff --git a/tools/test.sh b/tools/test.sh
index d42e15e3a..c634aab2f 100755
--- a/tools/test.sh
+++ b/tools/test.sh
@@ -26,14 +26,14 @@ LUKS_MODE="14600"
# missing hash types: 5200
-HASH_TYPES=$(ls ${TDIR}/test_modules/*.pm | sed -E 's/.*m0*([0-9]+).pm/\1/')
+HASH_TYPES=$(ls "${TDIR}/test_modules/*.pm" | sed -E 's/.*m0*([0-9]+).pm/\1/')
HASH_TYPES="${HASH_TYPES} ${TC_MODES} ${VC_MODES} ${LUKS_MODE}"
-HASH_TYPES="$(echo -n ${HASH_TYPES} | tr ' ' '\n' | sort -u -n | tr '\n' ' ')"
+HASH_TYPES=$(echo -n "${HASH_TYPES}" | tr ' ' '\n' | sort -u -n | tr '\n' ' ')
VECTOR_WIDTHS="1 2 4 8 16"
-HASHFILE_ONLY=$(grep -l OPTS_TYPE_BINARY_HASHFILE ${TDIR}/../src/modules/module_*.c | sed -E 's/.*module_0*([0-9]+).c/\1/' | tr '\n' ' ')
-SLOW_ALGOS=$(grep -l ATTACK_EXEC_OUTSIDE_KERNEL ${TDIR}/../src/modules/module_*.c | sed -E 's/.*module_0*([0-9]+).c/\1/' | tr '\n' ' ')
+HASHFILE_ONLY=$(grep -l OPTS_TYPE_BINARY_HASHFILE "${TDIR}/../src/modules/module_*.c" | sed -E 's/.*module_0*([0-9]+).c/\1/' | tr '\n' ' ')
+SLOW_ALGOS=$(grep -l ATTACK_EXEC_OUTSIDE_KERNEL "${TDIR}/../src/modules/module_*.c" | sed -E 's/.*module_0*([0-9]+).c/\1/' | tr '\n' ' ')
OUTD="test_$(date +%s)"
@@ -165,13 +165,13 @@ function init()
fi
- rm -rf ${OUTD}/${hash_type}.sh ${OUTD}/${hash_type}_passwords.txt ${OUTD}/${hash_type}_hashes.txt
+ rm -rf "${OUTD}/${hash_type}.sh" "${OUTD}/${hash_type}_passwords.txt" "${OUTD}/${hash_type}_hashes.txt"
# Exclude TrueCrypt and VeraCrypt testing modes
- if is_in_array ${hash_type} ${TC_MODES}; then
+ if is_in_array "${hash_type}" "${TC_MODES}"; then
return 0
fi
- if is_in_array ${hash_type} ${VC_MODES}; then
+ if is_in_array "${hash_type} ${VC_MODES}"; then
return 0
fi
@@ -189,7 +189,7 @@ function init()
luks_tests="hashcat_luks_testfiles.7z"
luks_tests_url="https://hashcat.net/misc/example_hashes/${luks_tests}"
- cd ${TDIR}
+ cd "${TDIR}" || exit
# if the file already exists, but was not successfully extracted, we assume it's a broken
# downloaded file and therefore it should be deleted
@@ -221,7 +221,7 @@ function init()
# cleanup:
rm -f "${luks_tests}"
- cd - >/dev/null
+ cd - >/dev/null || exit
# just to be very sure, check again that (one of) the files now exist:
@@ -245,7 +245,7 @@ function init()
if [ "${hash_type}" -eq 10300 ]; then
#cat ${OUTD}/${hash_type}.sh | cut -d' ' -f11- | cut -d"'" -f2 > ${OUTD}/${hash_type}_hashes.txt
- cat ${OUTD}/${hash_type}.sh | cut -d"'" -f2 > ${OUTD}/${hash_type}_hashes.txt
+ cut -d"'" -f2 ${OUTD}/${hash_type}.sh > ${OUTD}/${hash_type}_hashes.txt
fi
# truncate dicts
@@ -279,7 +279,7 @@ function init()
i=1
- while read -u 9 pass; do
+ while read -r -u 9 pass; do
if [ ${i} -gt ${min} ]; then
@@ -293,8 +293,8 @@ function init()
if [ "${pass_len}" -gt 1 ]
then
- p1=$((p1 + ${min_offset}))
- p0=$((p0 + ${min_offset}))
+ p1=$((p1 + min_offset))
+ p0=$((p0 + min_offset))
if [ "${p1}" -gt ${pass_len} ]; then
@@ -354,17 +354,17 @@ function init()
if [ "${hash_type}" -eq 10300 ]; then
#cat ${OUTD}/${hash_type}_multi_${i}.txt | cut -d' ' -f11- | cut -d"'" -f2 > ${OUTD}/${hash_type}_hashes_multi_${i}.txt
- cat ${OUTD}/${hash_type}_multi_${i}.txt | cut -d"'" -f2 > ${OUTD}/${hash_type}_hashes_multi_${i}.txt
+ cut -d"'" -f2 ${OUTD}/${hash_type}_multi_${i}.txt > ${OUTD}/${hash_type}_hashes_multi_${i}.txt
fi
# split password, 'i' is the len
p0=$((i / 2))
p1=$((p0 + 1))
- p0=$((p0 + ${min_len}))
- p1=$((p1 + ${min_len}))
+ p0=$((p0 + min_len))
+ p1=$((p1 + min_len))
- while read -u 9 pass; do
+ while read -r -u 9 pass; do
# add splitted password to dicts
echo ${pass} | cut -c -${p0} >> ${OUTD}/${hash_type}_dict1_multi_${i}
@@ -447,7 +447,7 @@ function attack_0()
i=0
- while read -u 9 line; do
+ while read -r -u 9 line; do
if [ "${i}" -ge ${max} ]; then
@@ -478,7 +478,7 @@ function attack_0()
pass=$(echo "${pass}" | cut -b 7-) # skip the first 6 chars
fi
- CMD="echo "${pass}" | ./${BIN} ${OPTS} -a 0 -m ${hash_type} '${hash}'"
+ CMD="echo ${pass} | ./${BIN} ${OPTS} -a 0 -m ${hash_type} '${hash}'"
echo -n "[ len $((i + 1)) ] " >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
@@ -516,7 +516,7 @@ function attack_0()
msg="OK"
- if [ "${e_nf}" -ne 0 -o "${e_nm}" -ne 0 ]; then
+ if [ "${e_nf}" -ne 0 ] || [ "${e_nm}" -ne 0 ]; then
msg="Error"
@@ -551,7 +551,7 @@ function attack_0()
hash_file=${temp_file}
- while read base64_hash; do
+ while read -r base64_hash; do
echo -n ${base64_hash} | base64 -d >> ${temp_file}
@@ -561,7 +561,7 @@ function attack_0()
CMD="cat ${OUTD}/${hash_type}_passwords.txt | ./${BIN} ${OPTS} -a 0 -m ${hash_type} ${hash_file}"
- output=$(cat ${OUTD}/${hash_type}_passwords.txt | ./${BIN} ${OPTS} -a 0 -m ${hash_type} ${hash_file} 2>&1)
+ output=$(./${BIN} ${OPTS} -a 0 -m ${hash_type} ${hash_file} < ${OUTD}/${hash_type}_passwords.txt 2>&1)
ret=${?}
@@ -571,7 +571,7 @@ function attack_0()
i=1
- while read -u 9 hash; do
+ while read -r -u 9 hash; do
pass=$(sed -n ${i}p ${OUTD}/${hash_type}_passwords.txt)
@@ -601,7 +601,7 @@ function attack_0()
msg="OK"
- if [ "${e_nf}" -ne 0 -o "${e_nm}" -ne 0 ]; then
+ if [ "${e_nf}" -ne 0 ] || [ "${e_nm}" -ne 0 ]; then
msg="Error"
@@ -648,7 +648,7 @@ function attack_1()
echo "> Testing hash type $hash_type with attack mode 1, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
i=1
- while read -u 9 hash; do
+ while read -r -u 9 hash; do
if [ $i -gt ${min} ]; then
@@ -663,7 +663,7 @@ function attack_1()
line_nr=1
if [ "${i}" -gt 1 ]; then
- line_nr=$((${i} - 1))
+ line_nr=$((i - 1))
fi
dict1="${OUTD}/${hash_type}_dict1"
@@ -682,10 +682,10 @@ function attack_1()
else
# we need to also "steal" some chars from the second dict
num_to_steal=$((6 - ${#line_dict1}))
- num_steal_start=$((${num_to_steal} + 1))
+ num_steal_start=$((num_to_steal + 1))
if [ "${#line_dict2}" -ge 6 ]; then
- num_to_steal_new=$(((${#line_dict2} - ${num_to_steal}) / 2))
+ num_to_steal_new=$(((${#line_dict2} - num_to_steal) / 2))
if [ "${num_to_steal_new}" -gt ${num_to_steal} ]; then
num_to_steal=${num_to_steal_new}
@@ -695,24 +695,24 @@ function attack_1()
line_chars_stolen=$(echo "${line_dict2}" | cut -b -${num_to_steal} | cut -b ${num_steal_start}-)
line_dict1="${line_chars_stolen}"
- line_dict2=$(echo "${line_dict2}" | cut -b $((${num_to_steal} + 1))-)
+ line_dict2=$(echo "${line_dict2}" | cut -b $((num_to_steal + 1))-)
fi
# finally, modify the dicts accordingly:
tmp_file="${dict1}_mod"
- head -n $((${line_nr} - 1)) ${dict1} > ${tmp_file}
+ head -n $((line_nr - 1)) ${dict1} > ${tmp_file}
echo "${line_dict1}" >> ${tmp_file}
- tail -n $((${line_num} - ${line_nr} - 1)) ${dict1} >> ${tmp_file}
+ tail -n $((line_num - line_nr - 1)) ${dict1} >> ${tmp_file}
dict1=${tmp_file}
tmp_file="${dict2}_mod"
- head -n $((${line_nr} - 1)) ${dict2} > ${tmp_file}
+ head -n $((line_nr - 1)) ${dict2} > ${tmp_file}
echo "${line_dict2}" >> ${tmp_file}
- tail -n $((${line_num} - ${line_nr} - 1)) ${dict2} >> ${tmp_file}
+ tail -n $((line_num - line_nr - 1)) ${dict2} >> ${tmp_file}
dict2=${tmp_file}
fi
@@ -758,7 +758,7 @@ function attack_1()
msg="OK"
- if [ "${e_nf}" -ne 0 -o "${e_nm}" -ne 0 ]; then
+ if [ "${e_nf}" -ne 0 ] || [ "${e_nm}" -ne 0 ]; then
msg="Error"
@@ -813,7 +813,7 @@ function attack_1()
hash_file=${temp_file}
- while read base64_hash; do
+ while read -r base64_hash; do
echo -n ${base64_hash} | base64 -d >> ${temp_file}
@@ -835,12 +835,12 @@ function attack_1()
i=0
- while read -u 9 hash; do
+ while read -r -u 9 hash; do
line_nr=1
if [ "${offset}" -gt ${i} ]; then
- line_nr=$((${offset} - ${i}))
+ line_nr=$((offset - i))
fi
line_dict1=$(tail -n ${line_nr} ${OUTD}/${hash_type}_dict1 | head -1)
@@ -872,7 +872,7 @@ function attack_1()
msg="OK"
- if [ "${e_nf}" -ne 0 -o "${e_nm}" -ne 0 ]; then
+ if [ "${e_nf}" -ne 0 ] || [ "${e_nm}" -ne 0 ]; then
msg="Error"
@@ -927,7 +927,7 @@ function attack_3()
i=1
- while read -u 9 hash; do
+ while read -r -u 9 hash; do
if [ "${i}" -gt 6 ]; then
@@ -961,7 +961,7 @@ function attack_3()
continue
fi
- pass_part_2=$(echo -n ${pass} | cut -b $((${i} + 1))-)
+ pass_part_2=$(echo -n ${pass} | cut -b $((i + 1))-)
mask=""
@@ -989,7 +989,7 @@ function attack_3()
continue
fi
- cut_pos=$((${i} * 2 + 6 - ${i} + 1)) # skip it in groups of 2 ("?d"), at least 6, offset +1 for cut to work
+ cut_pos=$((i * 2 + 6 - i + 1)) # skip it in groups of 2 ("?d"), at least 6, offset +1 for cut to work
if [ "${i}" -gt 6 ]; then
cut_pos=13 # 6 * ?d + 1 (6 * 2 + 1)
@@ -1038,7 +1038,7 @@ function attack_3()
msg="OK"
- if [ "${e_nf}" -ne 0 -o "${e_nm}" -ne 0 ]; then
+ if [ "${e_nf}" -ne 0 ] || [ "${e_nm}" -ne 0 ]; then
msg="Error"
@@ -1101,7 +1101,7 @@ function attack_3()
hash_file=${temp_file}
- while read base64_hash; do
+ while read -r base64_hash; do
echo -n ${base64_hash} | base64 -d >> ${temp_file}
@@ -1149,12 +1149,12 @@ function attack_3()
cracks_offset=0
if [ ${need_hcmask} -eq 0 ]; then
- cracks_offset=$((${head_hashes} - ${tail_hashes}))
+ cracks_offset=$((head_hashes - tail_hashes))
mask=${mask_3[${mask_pos}]}
else
- num_hashes=$(cat ${OUTD}/${hash_type}_hashes.txt | wc -l)
- cracks_offset=$((${num_hashes} - ${tail_hashes}))
+ num_hashes=$(wc -l < ${OUTD}/${hash_type}_hashes.txt)
+ cracks_offset=$((num_hashes - tail_hashes))
mask=${OUTD}/${hash_type}_passwords.txt # fake hcmask file (i.e. the original dict)
fi
@@ -1188,25 +1188,25 @@ function attack_3()
i=1
- while read -u 9 hash; do
+ while read -r -u 9 hash; do
pass=$(sed -n ${i}p ${OUTD}/${hash_type}_passwords.txt)
# charset 1
char=$(echo "${pass}" | cut -b ${charset_1_pos})
- charset_1=$(echo -e "${charset_1}\n${char}")
+ charset_1=$(printf "%s\n%s\n" "${charset_1}" "${char}")
# charset 2
char=$(echo "${pass}" | cut -b ${charset_2_pos})
- charset_2=$(echo -e "${charset_2}\n${char}")
+ charset_2=$(printf "%s\n%s\n" "${charset_2}" "${char}")
# charset 3
char=$(echo "${pass}" | cut -b ${charset_3_pos})
- charset_3=$(echo -e "${charset_3}\n${char}")
+ charset_3=$(printf "%s\n%s\n" "${charset_3}" "${char}")
# charset 4
char=$(echo "${pass}" | cut -b ${charset_4_pos})
- charset_4=$(echo -e "${charset_4}\n${char}")
+ charset_4=$(printf "%s\n%s\n" "${charset_4}" "${char}")
i=$((i + 1))
@@ -1273,7 +1273,7 @@ function attack_3()
i=1
- while read -u 9 hash; do
+ while read -r -u 9 hash; do
pass=$(sed -n ${i}p ${OUTD}/${hash_type}_passwords.txt)
@@ -1357,8 +1357,8 @@ function attack_3()
i=1
- while read -u 9 hash; do
- line_nr=$((${i} + ${cracks_offset}))
+ while read -r -u 9 hash; do
+ line_nr=$((i + cracks_offset))
pass=$(sed -n ${line_nr}p ${OUTD}/${hash_type}_passwords.txt)
@@ -1388,7 +1388,7 @@ function attack_3()
msg="OK"
- if [ "${e_nf}" -ne 0 -o "${e_nm}" -ne 0 ]; then
+ if [ "${e_nf}" -ne 0 ] || [ "${e_nm}" -ne 0 ]; then
msg="Error"
@@ -1458,21 +1458,21 @@ function attack_6()
pass="${pass_part_1}${pass_part_2}"
- echo -n ${pass} | cut -b -$((${mask_offset} + 0)) > ${OUTD}/${hash_type}_dict1_custom
- echo -n ${pass} | cut -b $((${mask_offset} + 1))- > ${OUTD}/${hash_type}_dict2_custom
+ echo -n ${pass} | cut -b -$((mask_offset + 0)) > ${OUTD}/${hash_type}_dict1_custom
+ echo -n ${pass} | cut -b $((mask_offset + 1))- > ${OUTD}/${hash_type}_dict2_custom
mask_custom=""
- for i in $(seq 1 $((${#pass} - ${mask_offset}))); do
+ for i in $(seq 1 $((${#pass} - mask_offset))); do
if [ "${hash_type}" -eq 14000 ]; then
- char=$(echo -n ${pass} | cut -b $((${i} + ${mask_offset})))
+ char=$(echo -n ${pass} | cut -b $((i + mask_offset)))
mask_custom="${mask_custom}${char}"
elif [ "${hash_type}" -eq 14100 ]; then
- char=$(echo -n ${pass} | cut -b $((${i} + ${mask_offset})))
+ char=$(echo -n ${pass} | cut -b $((i + mask_offset)))
mask_custom="${mask_custom}${char}"
else
@@ -1488,7 +1488,7 @@ function attack_6()
i=1
- while read -u 9 hash; do
+ while read -r -u 9 hash; do
if [ "${i}" -gt 6 ]; then
@@ -1528,7 +1528,7 @@ function attack_6()
continue
fi
- echo ${pass} | cut -b -$((${#pass} - ${i})) >> ${dict1_a6}
+ echo ${pass} | cut -b -$((${#pass} - i)) >> ${dict1_a6}
# the block below is just a fancy way to do a "shuf" (or sort -R) because macOS doesn't really support it natively
# we do not really need a shuf, but it's actually better for testing purposes
@@ -1541,8 +1541,8 @@ function attack_6()
for lines in $(seq 1 ${line_num}); do
- random_num=$((${RANDOM} % ${line_num}))
- random_num=$((${random_num} + 1)) # sed -n [n]p starts counting with 1 (not 0)
+ random_num=$((RANDOM % line_num))
+ random_num=$((random_num + 1)) # sed -n [n]p starts counting with 1 (not 0)
random_line=$(echo -n "${sorted_lines}" | sed -n ${random_num}p)
@@ -1552,7 +1552,7 @@ function attack_6()
sorted_lines=$(echo -n "${sorted_lines}" | grep -v "^${random_line}$")
- line_num=$((${line_num} - 1))
+ line_num=$((line_num - 1))
done
@@ -1582,7 +1582,7 @@ function attack_6()
line_nr=1
if [ "${i}" -gt 1 ]; then
- line_nr=$((${i} - 1))
+ line_nr=$((i - 1))
fi
line_dict1=$(sed -n ${line_nr}p ${dict1})
@@ -1616,7 +1616,7 @@ function attack_6()
msg="OK"
- if [ "${e_nf}" -ne 0 -o "${e_nm}" -ne 0 ]; then
+ if [ "${e_nf}" -ne 0 ] || [ "${e_nm}" -ne 0 ]; then
msg="Error"
@@ -1679,7 +1679,7 @@ function attack_6()
fi
- for ((i = 2; i < ${max}; i++)); do
+ for ((i = 2; i < max; i++)); do
hash_file=${OUTD}/${hash_type}_hashes_multi_${i}.txt
@@ -1692,7 +1692,7 @@ function attack_6()
hash_file=${temp_file}
- while read base64_hash; do
+ while read -r base64_hash; do
echo -n ${base64_hash} | base64 -d >> ${temp_file}
@@ -1716,7 +1716,7 @@ function attack_6()
j=1
- while read -u 9 hash; do
+ while read -r -u 9 hash; do
line_dict1=$(sed -n ${j}p ${OUTD}/${hash_type}_dict1_multi_${i})
line_dict2=$(sed -n ${j}p ${OUTD}/${hash_type}_dict2_multi_${i})
@@ -1749,7 +1749,7 @@ function attack_6()
msg="OK"
- if [ "${e_nf}" -ne 0 -o "${e_nm}" -ne 0 ]; then
+ if [ "${e_nf}" -ne 0 ] || [ "${e_nm}" -ne 0 ]; then
msg="Error"
@@ -1820,8 +1820,8 @@ function attack_7()
pass="${pass_part_1}${pass_part_2}"
- echo -n ${pass} | cut -b -$((${mask_offset} + 0)) > ${OUTD}/${hash_type}_dict1_custom
- echo -n ${pass} | cut -b $((${mask_offset} + 1))- > ${OUTD}/${hash_type}_dict2_custom
+ echo -n ${pass} | cut -b -$((mask_offset + 0)) > ${OUTD}/${hash_type}_dict1_custom
+ echo -n ${pass} | cut -b $((mask_offset + 1))- > ${OUTD}/${hash_type}_dict2_custom
mask_custom=""
@@ -1849,7 +1849,7 @@ function attack_7()
i=1
- while read -u 9 hash; do
+ while read -r -u 9 hash; do
if [ ${i} -gt ${min} ]; then
@@ -1868,7 +1868,7 @@ function attack_7()
line_nr=1
if [ "${i}" -gt 1 ]; then
- line_nr=$((${i} - 1))
+ line_nr=$((i - 1))
fi
if [ "${hash_type}" -eq 2500 ]; then
@@ -1887,7 +1887,7 @@ function attack_7()
mask_len=${#mask}
mask_len=$((mask_len / 2))
- mask_prefix=$(echo ${pass} | cut -b -$((pass_len - ${mask_len} - ${pass_part_2_len})))
+ mask_prefix=$(echo ${pass} | cut -b -$((pass_len - mask_len - pass_part_2_len)))
mask=${mask_prefix}${mask}
fi
@@ -1907,7 +1907,7 @@ function attack_7()
mask_len=${#mask}
mask_len=$((mask_len / 2))
- mask_prefix=$(echo ${pass} | cut -b -$((pass_len - ${mask_len} - ${pass_part_2_len})))
+ mask_prefix=$(echo ${pass} | cut -b -$((pass_len - mask_len - pass_part_2_len)))
mask=${mask_prefix}${mask}
fi
@@ -1932,8 +1932,8 @@ function attack_7()
mask_len=$((${#mask} / 2))
- echo "${pass_old}" | cut -b -$((6 + ${mask_len})) > ${OUTD}/${hash_type}_dict1_custom
- echo "${pass}" | cut -b $((${mask_len} + 1))- > ${OUTD}/${hash_type}_dict2_custom
+ echo "${pass_old}" | cut -b -$((6 + mask_len)) > ${OUTD}/${hash_type}_dict1_custom
+ echo "${pass}" | cut -b $((mask_len + 1))- > ${OUTD}/${hash_type}_dict2_custom
min=0 # hack to use the custom dict
mask_custom=${mask}
@@ -1965,7 +1965,7 @@ function attack_7()
line_nr=1
if [ "${i}" -gt 1 ]; then
- line_nr=$((${i} - 1))
+ line_nr=$((i - 1))
fi
line_dict1=$(sed -n ${line_nr}p ${dict1})
@@ -1999,7 +1999,7 @@ function attack_7()
msg="OK"
- if [ "${e_nf}" -ne 0 -o "${e_nm}" -ne 0 ]; then
+ if [ "${e_nf}" -ne 0 ] || [ "${e_nm}" -ne 0 ]; then
msg="Error"
@@ -2070,7 +2070,7 @@ function attack_7()
fi
- for ((i = 2; i < ${max}; i++)); do
+ for ((i = 2; i < max; i++)); do
hash_file=${OUTD}/${hash_type}_hashes_multi_${i}.txt
dict_file=${OUTD}/${hash_type}_dict2_multi_${i}
@@ -2086,7 +2086,7 @@ function attack_7()
hash_file=${temp_file}
- while read base64_hash; do
+ while read -r base64_hash; do
echo -n ${base64_hash} | base64 -d >> ${temp_file}
@@ -2103,7 +2103,7 @@ function attack_7()
j=1
- while read -u 9 hash; do
+ while read -r -u 9 hash; do
pass_part_1=$(sed -n ${j}p ${OUTD}/${hash_type}_dict1_multi_${i})
pass_part_2=$(sed -n ${j}p ${OUTD}/${hash_type}_dict2_multi_${i})
@@ -2134,7 +2134,7 @@ function attack_7()
j=1
- while read -u 9 hash; do
+ while read -r -u 9 hash; do
line_dict1=$(sed -n ${j}p ${OUTD}/${hash_type}_dict1_multi_${i})
line_dict2=$(sed -n ${j}p ${OUTD}/${hash_type}_dict2_multi_${i})
@@ -2167,7 +2167,7 @@ function attack_7()
msg="OK"
- if [ "${e_nf}" -ne 0 -o "${e_nm}" -ne 0 ]; then
+ if [ "${e_nf}" -ne 0 ] || [ "${e_nm}" -ne 0 ]; then
msg="Error"
@@ -2515,7 +2515,7 @@ function luks_test()
;;
1)
luks_pass_part1_len=$((${#LUKS_PASSWORD} / 2))
- luks_pass_part2_start=$((${luks_pass_part1_len} + 1))
+ luks_pass_part2_start=$((luks_pass_part1_len + 1))
echo "${LUKS_PASSWORD}" | cut -c-${luks_pass_part1_len} > "${luks_pass_part_file1}"
echo "${LUKS_PASSWORD}" | cut -c${luks_pass_part2_start}- > "${luks_pass_part_file2}"
@@ -2654,17 +2654,17 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
case ${opt} in
"V")
- if [ ${OPTARG} == "1" ]; then
+ if [ ${OPTARG} = "1" ]; then
VECTOR=1
- elif [ ${OPTARG} == "2" ]; then
+ elif [ ${OPTARG} = "2" ]; then
VECTOR=2
- elif [ ${OPTARG} == "4" ]; then
+ elif [ ${OPTARG} = "4" ]; then
VECTOR=4
- elif [ ${OPTARG} == "8" ]; then
+ elif [ ${OPTARG} = "8" ]; then
VECTOR=8
- elif [ ${OPTARG} == "16" ]; then
+ elif [ ${OPTARG} = "16" ]; then
VECTOR=16
- elif [ ${OPTARG} == "all" ]; then
+ elif [ ${OPTARG} = "all" ]; then
VECTOR="all"
else
usage
@@ -2672,11 +2672,11 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"t")
- if [ ${OPTARG} == "single" ]; then
+ if [ ${OPTARG} = "single" ]; then
MODE=0
- elif [ ${OPTARG} == "multi" ]; then
+ elif [ ${OPTARG} = "multi" ]; then
MODE=1
- elif [ ${OPTARG} == "all" ]; then
+ elif [ ${OPTARG} = "all" ]; then
MODE=2
else
usage
@@ -2684,7 +2684,7 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"m")
- if [ ${OPTARG} == "all" ]; then
+ if [ ${OPTARG} = "all" ]; then
HT=65535
else
HT=${OPTARG}
@@ -2692,17 +2692,17 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"a")
- if [ ${OPTARG} == "all" ]; then
+ if [ ${OPTARG} = "all" ]; then
ATTACK=65535
- elif [ ${OPTARG} == "0" ]; then
+ elif [ ${OPTARG} = "0" ]; then
ATTACK=0
- elif [ ${OPTARG} == "1" ]; then
+ elif [ ${OPTARG} = "1" ]; then
ATTACK=1
- elif [ ${OPTARG} == "3" ]; then
+ elif [ ${OPTARG} = "3" ]; then
ATTACK=3
- elif [ ${OPTARG} == "6" ]; then
+ elif [ ${OPTARG} = "6" ]; then
ATTACK=6
- elif [ ${OPTARG} == "7" ]; then
+ elif [ ${OPTARG} = "7" ]; then
ATTACK=7
else
usage
@@ -2727,9 +2727,9 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"x")
- if [ ${OPTARG} == "32" ]; then
+ if [ ${OPTARG} = "32" ]; then
ARCHITECTURE=32
- elif [ ${OPTARG} == "64" ]; then
+ elif [ ${OPTARG} = "64" ]; then
ARCHITECTURE=64
else
usage
@@ -2737,11 +2737,11 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"o")
- if [ ${OPTARG} == "win" ]; then
+ if [ ${OPTARG} = "win" ]; then
EXTENSION="exe"
- elif [ ${OPTARG} == "linux" ]; then
+ elif [ ${OPTARG} = "linux" ]; then
EXTENSION="bin"
- elif [ ${OPTARG} == "macos" ]; then
+ elif [ ${OPTARG} = "macos" ]; then
EXTENSION="app"
else
usage
@@ -2757,10 +2757,10 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"D")
- if [ ${OPTARG} == "1" ]; then
+ if [ ${OPTARG} = "1" ]; then
OPTS="${OPTS} -D 1"
TYPE="Cpu"
- elif [ ${OPTARG} == "2" ]; then
+ elif [ ${OPTARG} = "2" ]; then
OPTS="${OPTS} -D 2"
TYPE="Gpu"
else
@@ -2794,7 +2794,7 @@ if [ "${OPTIMIZED}" -eq 1 ]; then
OPTS="${OPTS} -O"
fi
-if [ "${TYPE}" == "null" ]; then
+if [ "${TYPE}" = "null" ]; then
OPTS="${OPTS} -D 2"
TYPE="Gpu"
fi
@@ -2827,7 +2827,7 @@ if [ -n "${PACKAGE_FOLDER}" ]; then
fi
-if [ "${PACKAGE}" -eq 0 -o -z "${PACKAGE_FOLDER}" ]; then
+if [ "${PACKAGE}" -eq 0 ] || [ -z "${PACKAGE_FOLDER}" ]; then
# check existence of binary
if [ ! -e "${BIN}" ]; then
@@ -2923,7 +2923,7 @@ if [ "${PACKAGE}" -eq 0 -o -z "${PACKAGE_FOLDER}" ]; then
# for these particular algos we need to save the output to a temporary file
IFS=';' read -ra FILE_BASED_ALGOS <<< "${HASHFILE_ONLY}"
- for hash_type in $(echo $HASH_TYPES); do
+ for hash_type in $HASH_TYPES; do
if [ "${HT}" -ne 65535 ]; then
@@ -2972,11 +2972,11 @@ if [ "${PACKAGE}" -eq 0 -o -z "${PACKAGE_FOLDER}" ]; then
MODE=0 # force single only
fi
- for CUR_WIDTH in $(echo $VECTOR_WIDTHS); do
+ for CUR_WIDTH in $VECTOR_WIDTHS; do
- if [ "${VECTOR_OLD}" == "all" ] || [ "${VECTOR_OLD}" == "default" ] || [ "${VECTOR_OLD}" == "${CUR_WIDTH}" ]; then
+ if [ "${VECTOR_OLD}" = "all" ] || [ "${VECTOR_OLD}" = "default" ] || [ "${VECTOR_OLD}" = "${CUR_WIDTH}" ]; then
- if [ "${VECTOR_OLD}" == "default" ] && \
+ if [ "${VECTOR_OLD}" = "default" ] && \
[ "${CUR_WIDTH}" != "1" ] && \
[ "${CUR_WIDTH}" != "4" ]; then
@@ -3132,7 +3132,7 @@ if [ "${PACKAGE}" -eq 1 ]; then
UNAME=$(uname -s)
# of course macOS requires us to implement a special case (sed -i "" for the backup file)
- if [ "${UNAME}" == "Darwin" ] ; then
+ if [ "${UNAME}" = "Darwin" ] ; then
SED_IN_PLACE='-i ""'
fi
From 7532058be0383f78f39d9b782c0578bcae4af650 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Mon, 5 Aug 2019 01:40:49 +0200
Subject: [PATCH 079/113] Added hash-mode 21500 - SHA512(PBKDF2-HMAC-SHA1)
---
OpenCL/m21500-pure.cl | 260 +++++++++++++++++++++++++++++++++
src/modules/module_21500.c | 274 +++++++++++++++++++++++++++++++++++
tools/test_modules/m21500.pm | 82 +++++++++++
3 files changed, 616 insertions(+)
create mode 100644 OpenCL/m21500-pure.cl
create mode 100644 src/modules/module_21500.c
create mode 100644 tools/test_modules/m21500.pm
diff --git a/OpenCL/m21500-pure.cl b/OpenCL/m21500-pure.cl
new file mode 100644
index 000000000..ff81e2b05
--- /dev/null
+++ b/OpenCL/m21500-pure.cl
@@ -0,0 +1,260 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#define NEW_SIMD_CODE
+
+#ifdef KERNEL_STATIC
+#include "inc_vendor.h"
+#include "inc_types.h"
+#include "inc_platform.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
+#include "inc_hash_sha1.cl"
+#include "inc_hash_sha512.cl"
+#endif
+
+#define COMPARE_S "inc_comp_single.cl"
+#define COMPARE_M "inc_comp_multi.cl"
+
+typedef struct pbkdf2_sha1_tmp
+{
+ u32 ipad[5];
+ u32 opad[5];
+
+ u32 dgst[260];
+ u32 out[260];
+
+} pbkdf2_sha1_tmp_t;
+
+typedef struct pbkdf2_sha1
+{
+ u32 salt_buf[64];
+
+} pbkdf2_sha1_t;
+
+DECLSPEC void hmac_sha1_run_V (u32x *w0, u32x *w1, u32x *w2, u32x *w3, u32x *ipad, u32x *opad, u32x *digest)
+{
+ digest[0] = ipad[0];
+ digest[1] = ipad[1];
+ digest[2] = ipad[2];
+ digest[3] = ipad[3];
+ digest[4] = ipad[4];
+
+ sha1_transform_vector (w0, w1, w2, w3, digest);
+
+ w0[0] = digest[0];
+ w0[1] = digest[1];
+ w0[2] = digest[2];
+ w0[3] = digest[3];
+ w1[0] = digest[4];
+ w1[1] = 0x80000000;
+ w1[2] = 0;
+ w1[3] = 0;
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = (64 + 20) * 8;
+
+ digest[0] = opad[0];
+ digest[1] = opad[1];
+ digest[2] = opad[2];
+ digest[3] = opad[3];
+ digest[4] = opad[4];
+
+ sha1_transform_vector (w0, w1, w2, w3, digest);
+}
+
+KERNEL_FQ void m21500_init (KERN_ATTR_TMPS_ESALT (pbkdf2_sha1_tmp_t, pbkdf2_sha1_t))
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ sha1_hmac_ctx_t sha1_hmac_ctx;
+
+ sha1_hmac_init_global_swap (&sha1_hmac_ctx, pws[gid].i, pws[gid].pw_len);
+
+ tmps[gid].ipad[0] = sha1_hmac_ctx.ipad.h[0];
+ tmps[gid].ipad[1] = sha1_hmac_ctx.ipad.h[1];
+ tmps[gid].ipad[2] = sha1_hmac_ctx.ipad.h[2];
+ tmps[gid].ipad[3] = sha1_hmac_ctx.ipad.h[3];
+ tmps[gid].ipad[4] = sha1_hmac_ctx.ipad.h[4];
+
+ tmps[gid].opad[0] = sha1_hmac_ctx.opad.h[0];
+ tmps[gid].opad[1] = sha1_hmac_ctx.opad.h[1];
+ tmps[gid].opad[2] = sha1_hmac_ctx.opad.h[2];
+ tmps[gid].opad[3] = sha1_hmac_ctx.opad.h[3];
+ tmps[gid].opad[4] = sha1_hmac_ctx.opad.h[4];
+
+ sha1_hmac_update_global_swap (&sha1_hmac_ctx, esalt_bufs[digests_offset].salt_buf, salt_bufs[salt_pos].salt_len);
+
+ for (u32 i = 0, j = 1; i < 256; i += 5, j += 1)
+ {
+ sha1_hmac_ctx_t sha1_hmac_ctx2 = sha1_hmac_ctx;
+
+ u32 w0[4];
+ u32 w1[4];
+ u32 w2[4];
+ u32 w3[4];
+
+ w0[0] = j;
+ w0[1] = 0;
+ w0[2] = 0;
+ w0[3] = 0;
+ w1[0] = 0;
+ w1[1] = 0;
+ w1[2] = 0;
+ w1[3] = 0;
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ sha1_hmac_update_64 (&sha1_hmac_ctx2, w0, w1, w2, w3, 4);
+
+ sha1_hmac_final (&sha1_hmac_ctx2);
+
+ tmps[gid].dgst[i + 0] = sha1_hmac_ctx2.opad.h[0];
+ tmps[gid].dgst[i + 1] = sha1_hmac_ctx2.opad.h[1];
+ tmps[gid].dgst[i + 2] = sha1_hmac_ctx2.opad.h[2];
+ tmps[gid].dgst[i + 3] = sha1_hmac_ctx2.opad.h[3];
+ tmps[gid].dgst[i + 4] = sha1_hmac_ctx2.opad.h[4];
+
+ tmps[gid].out[i + 0] = tmps[gid].dgst[i + 0];
+ tmps[gid].out[i + 1] = tmps[gid].dgst[i + 1];
+ tmps[gid].out[i + 2] = tmps[gid].dgst[i + 2];
+ tmps[gid].out[i + 3] = tmps[gid].dgst[i + 3];
+ tmps[gid].out[i + 4] = tmps[gid].dgst[i + 4];
+ }
+}
+
+KERNEL_FQ void m21500_loop (KERN_ATTR_TMPS_ESALT (pbkdf2_sha1_tmp_t, pbkdf2_sha1_t))
+{
+ const u64 gid = get_global_id (0);
+
+ if ((gid * VECT_SIZE) >= gid_max) return;
+
+ u32x ipad[5];
+ u32x opad[5];
+
+ ipad[0] = packv (tmps, ipad, gid, 0);
+ ipad[1] = packv (tmps, ipad, gid, 1);
+ ipad[2] = packv (tmps, ipad, gid, 2);
+ ipad[3] = packv (tmps, ipad, gid, 3);
+ ipad[4] = packv (tmps, ipad, gid, 4);
+
+ opad[0] = packv (tmps, opad, gid, 0);
+ opad[1] = packv (tmps, opad, gid, 1);
+ opad[2] = packv (tmps, opad, gid, 2);
+ opad[3] = packv (tmps, opad, gid, 3);
+ opad[4] = packv (tmps, opad, gid, 4);
+
+ for (u32 i = 0; i < 256; i += 5)
+ {
+ u32x dgst[5];
+ u32x out[5];
+
+ dgst[0] = packv (tmps, dgst, gid, i + 0);
+ dgst[1] = packv (tmps, dgst, gid, i + 1);
+ dgst[2] = packv (tmps, dgst, gid, i + 2);
+ dgst[3] = packv (tmps, dgst, gid, i + 3);
+ dgst[4] = packv (tmps, dgst, gid, i + 4);
+
+ out[0] = packv (tmps, out, gid, i + 0);
+ out[1] = packv (tmps, out, gid, i + 1);
+ out[2] = packv (tmps, out, gid, i + 2);
+ out[3] = packv (tmps, out, gid, i + 3);
+ out[4] = packv (tmps, out, gid, i + 4);
+
+ for (u32 j = 0; j < loop_cnt; j++)
+ {
+ u32x w0[4];
+ u32x w1[4];
+ u32x w2[4];
+ u32x w3[4];
+
+ w0[0] = dgst[0];
+ w0[1] = dgst[1];
+ w0[2] = dgst[2];
+ w0[3] = dgst[3];
+ w1[0] = dgst[4];
+ w1[1] = 0x80000000;
+ w1[2] = 0;
+ w1[3] = 0;
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = (64 + 20) * 8;
+
+ hmac_sha1_run_V (w0, w1, w2, w3, ipad, opad, dgst);
+
+ out[0] ^= dgst[0];
+ out[1] ^= dgst[1];
+ out[2] ^= dgst[2];
+ out[3] ^= dgst[3];
+ out[4] ^= dgst[4];
+ }
+
+ unpackv (tmps, dgst, gid, i + 0, dgst[0]);
+ unpackv (tmps, dgst, gid, i + 1, dgst[1]);
+ unpackv (tmps, dgst, gid, i + 2, dgst[2]);
+ unpackv (tmps, dgst, gid, i + 3, dgst[3]);
+ unpackv (tmps, dgst, gid, i + 4, dgst[4]);
+
+ unpackv (tmps, out, gid, i + 0, out[0]);
+ unpackv (tmps, out, gid, i + 1, out[1]);
+ unpackv (tmps, out, gid, i + 2, out[2]);
+ unpackv (tmps, out, gid, i + 3, out[3]);
+ unpackv (tmps, out, gid, i + 4, out[4]);
+ }
+}
+
+KERNEL_FQ void m21500_comp (KERN_ATTR_TMPS_ESALT (pbkdf2_sha1_tmp_t, pbkdf2_sha1_t))
+{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ const u64 lid = get_local_id (0);
+
+ sha512_ctx_t ctx;
+
+ sha512_init (&ctx);
+
+ sha512_update (&ctx, (const u32 *)tmps[gid].out, 1024);
+
+ sha512_final (&ctx);
+
+ const u32 r0 = l32_from_64_S (ctx.h[7]);
+ const u32 r1 = h32_from_64_S (ctx.h[7]);
+ const u32 r2 = l32_from_64_S (ctx.h[3]);
+ const u32 r3 = h32_from_64_S (ctx.h[3]);
+
+ #define il_pos 0
+
+ #ifdef KERNEL_STATIC
+ #include COMPARE_M
+ #endif
+}
diff --git a/src/modules/module_21500.c b/src/modules/module_21500.c
new file mode 100644
index 000000000..a33949735
--- /dev/null
+++ b/src/modules/module_21500.c
@@ -0,0 +1,274 @@
+/**
+ * Author......: See docs/credits.txt
+ * License.....: MIT
+ */
+
+#include "common.h"
+#include "types.h"
+#include "modules.h"
+#include "bitops.h"
+#include "convert.h"
+#include "shared.h"
+
+static const u32 ATTACK_EXEC = ATTACK_EXEC_OUTSIDE_KERNEL;
+static const u32 DGST_POS0 = 14;
+static const u32 DGST_POS1 = 15;
+static const u32 DGST_POS2 = 6;
+static const u32 DGST_POS3 = 7;
+static const u32 DGST_SIZE = DGST_SIZE_8_8;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_GENERIC_KDF;
+static const char *HASH_NAME = "SHA512(PBKDF2-HMAC-SHA1)";
+static const u64 KERN_TYPE = 21500;
+static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
+ | OPTI_TYPE_USES_BITS_64
+ | OPTI_TYPE_SLOW_HASH_SIMD_LOOP;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE
+ | OPTS_TYPE_ST_BASE64
+ | OPTS_TYPE_HASH_COPY;
+static const u32 SALT_TYPE = SALT_TYPE_EMBEDDED;
+static const char *ST_PASS = "hashcat";
+static const char *ST_HASH = "sha1:1000:aGFzaGNhdDE=:Dnz04T9ptYINnj9mckXTuk80w6f1vkZLwv02HiufklgnDw53BU1bgn4gsHia/Q6kxYSqK4PDbxRMwa6HB5KA/w==";
+
+u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
+u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
+u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
+u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
+u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
+u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
+u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
+const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
+u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
+u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
+u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
+u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
+const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
+const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
+
+typedef struct pbkdf2_sha1_tmp
+{
+ u32 ipad[5];
+ u32 opad[5];
+
+ u32 dgst[260];
+ u32 out[260];
+
+} pbkdf2_sha1_tmp_t;
+
+typedef struct pbkdf2_sha1
+{
+ u32 salt_buf[64];
+
+} pbkdf2_sha1_t;
+
+static const char *SIGNATURE_PBKDF2_SHA1 = "sha1";
+
+u64 module_esalt_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+ const u64 esalt_size = (const u64) sizeof (pbkdf2_sha1_t);
+
+ return esalt_size;
+}
+
+u64 module_tmp_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+ const u64 tmp_size = (const u64) sizeof (pbkdf2_sha1_tmp_t);
+
+ return tmp_size;
+}
+
+u32 module_pw_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+ // this overrides the reductions of PW_MAX in case optimized kernel is selected
+ // IOW, even in optimized kernel mode it support length 256
+
+ const u32 pw_max = PW_MAX;
+
+ return pw_max;
+}
+
+char *module_jit_build_options (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra, MAYBE_UNUSED const hashes_t *hashes, MAYBE_UNUSED const hc_device_param_t *device_param)
+{
+ char *jit_build_options = NULL;
+
+ if (device_param->opencl_device_vendor_id == VENDOR_ID_AMD)
+ {
+ hc_asprintf (&jit_build_options, "-D NO_UNROLL");
+ }
+
+ return jit_build_options;
+}
+
+int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
+{
+ u64 *digest = (u64 *) digest_buf;
+
+ pbkdf2_sha1_t *pbkdf2_sha1 = (pbkdf2_sha1_t *) esalt_buf;
+
+ token_t token;
+
+ token.token_cnt = 4;
+
+ token.signatures_cnt = 1;
+ token.signatures_buf[0] = SIGNATURE_PBKDF2_SHA1;
+
+ token.sep[0] = ':';
+ token.len_min[0] = 4;
+ token.len_max[0] = 4;
+ token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_SIGNATURE;
+
+ token.sep[1] = ':';
+ token.len_min[1] = 1;
+ token.len_max[1] = 6;
+ token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_DIGIT;
+
+ token.sep[2] = ':';
+ token.len_min[2] = 12;
+ token.len_max[2] = 24;
+ token.attr[2] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_BASE64A;
+
+ token.len_min[3] = 64;
+ token.len_max[3] = 256;
+ token.attr[3] = TOKEN_ATTR_VERIFY_LENGTH
+ | TOKEN_ATTR_VERIFY_BASE64A;
+
+ const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
+
+ if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
+
+ u8 tmp_buf[512];
+ int tmp_len;
+
+ // iter
+
+ const u8 *iter_pos = token.buf[1];
+
+ const u32 iter = hc_strtoul ((const char *) iter_pos, NULL, 10);
+
+ salt->salt_iter = iter - 1;
+
+ // salt
+
+ const u8 *salt_pos = token.buf[2];
+ const int salt_len = token.len[2];
+
+ memset (tmp_buf, 0, sizeof (tmp_buf));
+
+ tmp_len = base64_decode (base64_to_int, salt_pos, salt_len, tmp_buf);
+
+ if (tmp_len < 8 || tmp_len > 16) return (PARSER_SALT_LENGTH);
+
+ memcpy (pbkdf2_sha1->salt_buf, tmp_buf, tmp_len);
+
+ salt->salt_len = tmp_len;
+
+ salt->salt_buf[0] = pbkdf2_sha1->salt_buf[0];
+ salt->salt_buf[1] = pbkdf2_sha1->salt_buf[1];
+ salt->salt_buf[2] = pbkdf2_sha1->salt_buf[2];
+ salt->salt_buf[3] = pbkdf2_sha1->salt_buf[3];
+ salt->salt_buf[4] = salt->salt_iter;
+
+ // hash
+
+ const u8 *hash_pos = token.buf[3];
+ const int hash_len = token.len[3];
+
+ memset (tmp_buf, 0, sizeof (tmp_buf));
+
+ tmp_len = base64_decode (base64_to_int, hash_pos, hash_len, tmp_buf);
+
+ if (tmp_len < 64) return (PARSER_HASH_LENGTH);
+
+ memcpy (digest, tmp_buf, tmp_len);
+
+ digest[0] = byte_swap_64 (digest[0]);
+ digest[1] = byte_swap_64 (digest[1]);
+ digest[2] = byte_swap_64 (digest[2]);
+ digest[3] = byte_swap_64 (digest[3]);
+ digest[4] = byte_swap_64 (digest[4]);
+ digest[5] = byte_swap_64 (digest[5]);
+ digest[6] = byte_swap_64 (digest[6]);
+ digest[7] = byte_swap_64 (digest[7]);
+
+ return (PARSER_OK);
+}
+
+int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
+{
+ return snprintf (line_buf, line_size, "%s", hash_info->orighash);
+}
+
+void module_init (module_ctx_t *module_ctx)
+{
+ module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
+ module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
+
+ module_ctx->module_attack_exec = module_attack_exec;
+ module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
+ module_ctx->module_benchmark_mask = MODULE_DEFAULT;
+ module_ctx->module_benchmark_salt = MODULE_DEFAULT;
+ module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
+ module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
+ module_ctx->module_dgst_pos0 = module_dgst_pos0;
+ module_ctx->module_dgst_pos1 = module_dgst_pos1;
+ module_ctx->module_dgst_pos2 = module_dgst_pos2;
+ module_ctx->module_dgst_pos3 = module_dgst_pos3;
+ module_ctx->module_dgst_size = module_dgst_size;
+ module_ctx->module_dictstat_disable = MODULE_DEFAULT;
+ module_ctx->module_esalt_size = module_esalt_size;
+ module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
+ module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
+ module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_count = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
+ module_ctx->module_hash_binary_save = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
+ module_ctx->module_hash_decode = module_hash_decode;
+ module_ctx->module_hash_encode_status = MODULE_DEFAULT;
+ module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
+ module_ctx->module_hash_encode = module_hash_encode;
+ module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
+ module_ctx->module_hash_mode = MODULE_DEFAULT;
+ module_ctx->module_hash_category = module_hash_category;
+ module_ctx->module_hash_name = module_hash_name;
+ module_ctx->module_hashes_count_min = MODULE_DEFAULT;
+ module_ctx->module_hashes_count_max = MODULE_DEFAULT;
+ module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
+ module_ctx->module_hook12 = MODULE_DEFAULT;
+ module_ctx->module_hook23 = MODULE_DEFAULT;
+ module_ctx->module_hook_salt_size = MODULE_DEFAULT;
+ module_ctx->module_hook_size = MODULE_DEFAULT;
+ module_ctx->module_jit_build_options = module_jit_build_options;
+ module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
+ module_ctx->module_kern_type = module_kern_type;
+ module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
+ module_ctx->module_opti_type = module_opti_type;
+ module_ctx->module_opts_type = module_opts_type;
+ module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
+ module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
+ module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
+ module_ctx->module_potfile_disable = MODULE_DEFAULT;
+ module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
+ module_ctx->module_pwdump_column = MODULE_DEFAULT;
+ module_ctx->module_pw_max = module_pw_max;
+ module_ctx->module_pw_min = MODULE_DEFAULT;
+ module_ctx->module_salt_max = MODULE_DEFAULT;
+ module_ctx->module_salt_min = MODULE_DEFAULT;
+ module_ctx->module_salt_type = module_salt_type;
+ module_ctx->module_separator = MODULE_DEFAULT;
+ module_ctx->module_st_hash = module_st_hash;
+ module_ctx->module_st_pass = module_st_pass;
+ module_ctx->module_tmp_size = module_tmp_size;
+ module_ctx->module_unstable_warning = MODULE_DEFAULT;
+ module_ctx->module_warmup_disable = MODULE_DEFAULT;
+}
diff --git a/tools/test_modules/m21500.pm b/tools/test_modules/m21500.pm
new file mode 100644
index 000000000..4579efa33
--- /dev/null
+++ b/tools/test_modules/m21500.pm
@@ -0,0 +1,82 @@
+#!/usr/bin/env perl
+
+##
+## Author......: See docs/credits.txt
+## License.....: MIT
+##
+
+use strict;
+use warnings;
+
+use MIME::Base64 qw (encode_base64 decode_base64);
+use Crypt::PBKDF2;
+use Digest::SHA qw (sha512);
+use Encode;
+
+sub module_constraints { [[0, 256], [8, 16], [-1, -1], [-1, -1], [-1, -1]] }
+
+sub module_generate_hash
+{
+ my $word = shift;
+ my $salt = shift;
+ my $iter = 1000;
+
+ my $kdf = Crypt::PBKDF2->new
+ (
+ hash_class => 'HMACSHA1',
+ iterations => $iter,
+ output_len => 1024
+ );
+
+ my $key = $kdf->PBKDF2 ($salt, $word);
+
+ my $key_b64 = encode_base64 (sha512($key), "");
+
+ my $salt_b64 = encode_base64 ($salt, "");
+
+ my $hash = sprintf ("sha1:%i:%s:%s", $iter, $salt_b64, $key_b64);
+
+ return $hash;
+}
+
+sub module_verify_hash
+{
+ my $line = shift;
+
+ return unless (substr ($line, 0, 5) eq 'sha1:');
+
+ # iterations
+ my $index1 = index ($line, ":", 5);
+
+ return if $index1 < 1;
+
+ my $iter = substr ($line, 5, $index1 - 5);
+
+ # salt
+
+ my $index2 = index ($line, ":", $index1 + 1);
+
+ return if $index2 < 1;
+
+ my $salt = substr ($line, $index1 + 1, $index2 - $index1 - 1);
+
+ $salt = decode_base64 ($salt);
+
+ # end of digest
+
+ $index1 = index ($line, ":", $index2 + 1);
+
+ return if $index1 < 1;
+
+ # word / hash
+
+ my $word = substr ($line, $index1 + 1);
+
+ my $word_packed = pack_if_HEX_notation ($word);
+
+ my $new_hash = module_generate_hash ($word_packed, $salt, $iter);
+
+ return ($new_hash, $word);
+}
+
+1;
From d1ca0615774074880bd91e481fea26fc9a77feb2 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Mon, 5 Aug 2019 12:09:55 +0200
Subject: [PATCH 080/113] Update docs/changes.txt with recent changes
---
docs/changes.txt | 91 ++++++++++++++++++++++++++++++++++--------------
1 file changed, 65 insertions(+), 26 deletions(-)
diff --git a/docs/changes.txt b/docs/changes.txt
index 511a0d95f..bb37c2c85 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -1,70 +1,90 @@
-* changes v5.1.0 -> v5.x.x
+* changes v5.1.0 -> v6.0.0
##
## Feature
##
- Fully modularized hash-mode integration via plugin interface and converted all existing hash-modes
+- Refactor hashcat backend interface to allow adding compute API other than OpenCL
+- Add CUDA as a new compute API to hashcat backend (enables hashcat to run on NVIDIA Jetson or IBM POWER9)
+- Support use of all available GPU memory using CUDA backend
+- Support on-the-fly loading of compressed wordlists in zip and gzip format
- Support for inline VeraCrypt PIM Brute-Force
-- Support Deflate decompression for the 7-Zip hash type using zlib
-- Compressed wordlists, gzip and zip format, using zlib
+- Support deflate decompression for the 7-Zip hash-mode using zlib hook
##
## Algorithms
##
-- Added hash-mode: Open Document Format (ODF) 1.2 (SHA-256, AES)
-- Added hash-mode: Open Document Format (ODF) 1.1 (SHA-1, Blowfish)
-- Added hash-mode: Java Object hashCode()
-- Added hash-mode: Blockchain, My Wallet, Second Password (SHA256)
-- Added hash-mode: Electrum Wallet (Salt-Type 3)
- Added hash-mode: Android Backup
-- Added hash-mode: QNX /etc/shadow (MD5)
-- Added hash-mode: QNX /etc/shadow (SHA256)
-- Added hash-mode: QNX /etc/shadow (SHA512)
-- Added hash-mode: Kerberos 5 TGS-REP etype 17 (AES128-CTS-HMAC-SHA1-96)
-- Added hash-mode: Kerberos 5 TGS-REP etype 18 (AES256-CTS-HMAC-SHA1-96)
+- Added hash-mode: AuthMe sha256
+- Added hash-mode: BitShares v0.x
+- Added hash-mode: Blockchain, My Wallet, Second Password (SHA256)
+- Added hash-mode: DiskCryptor
+- Added hash-mode: Electrum Wallet (Salt-Type 3)
+- Added hash-mode: Huawei Router sha1(md5($pass).$salt)
+- Added hash-mode: Java Object hashCode()
- Added hash-mode: Kerberos 5 Pre-Auth etype 17 (AES128-CTS-HMAC-SHA1-96)
- Added hash-mode: Kerberos 5 Pre-Auth etype 18 (AES256-CTS-HMAC-SHA1-96)
-- Added hash-mode: sha1(md5(md5($pass)))
-- Added hash-mode: sha1($salt1.$pass.$salt2)
-- Added hash-mode: Ruby on Rails Restful-Authentication
+- Added hash-mode: Kerberos 5 TGS-REP etype 17 (AES128-CTS-HMAC-SHA1-96)
+- Added hash-mode: Kerberos 5 TGS-REP etype 18 (AES256-CTS-HMAC-SHA1-96)
+- Added hash-mode: Open Document Format (ODF) 1.1 (SHA-1, Blowfish)
+- Added hash-mode: Open Document Format (ODF) 1.2 (SHA-256, AES)
+- Added hash-mode: Oracle Transportation Management (SHA256)
- Added hash-mode: PKZIP archive encryption
- Added hash-mode: PKZIP Master Key
-- Added hash-mode: DiskCryptor
- Added hash-mode: Python passlib pbkdf2-sha1
- Added hash-mode: Python passlib pbkdf2-sha256
- Added hash-mode: Python passlib pbkdf2-sha512
-- Added hash-mode: Oracle Transportation Management (SHA256)
+- Added hash-mode: QNX /etc/shadow (MD5)
+- Added hash-mode: QNX /etc/shadow (SHA256)
+- Added hash-mode: QNX /etc/shadow (SHA512)
+- Added hash-mode: Ruby on Rails Restful-Authentication
+- Added hash-mode: md5($salt.sha1($salt.$pass))
+- Added hash-mode: md5(sha1($pass).md5($pass).sha1($pass))
+- Added hash-mode: md5(sha1($salt).md5($pass))
+- Added hash-mode: sha1(md5(md5($pass)))
+- Added hash-mode: sha1(md5($pass.$salt))
- Added hash-mode: sha1(md5($pass).$salt)
+- Added hash-mode: sha1($salt1.$pass.$salt2)
+- Added hash-mode: sha256(md5($pass))
+- Added hash-mode: sha256(sha256_bin(pass))
+- Added hash-mode: sha256(sha256($pass).$salt)
##
## Bugs
##
+- Fixed buffer overflow in build_plain() function
+- Fixed copy/paste error leading to invalid "Integer overflow detected in keyspace of mask" in attack-mode 6 and 7
- Fixed cracking of Cisco-PIX and Cisco-ASA MD5 passwords in mask-attack mode if mask > length 16
- Fixed cracking of Electrum Wallet Salt-Type 2 hashes
- Fixed cracking of NetNTLMv1 passwords in mask-attack mode if mask > length 16 (optimized kernels only)
- Fixed cracking raw Streebog-HMAC 256 and 512 hashes with password of length >= 64
- Fixed cracking raw Whirlpool hashes cracking with password of length >= 32
- Fixed incorrect progress-only result in a special race condition
+- Fixed invalid call of mp_css_utf16le_expand()/mp_css_utf16be_expand() in a slow-candidate session
+- Fixed invalid password truncation in attack-mode 1 if final password is longer than 32 character
- Fixed maximum password length limit which was announced as 256 but actually was 255
- Fixed output of IKE PSK (mode 5300 and 5400) hashes to have separators at right position
- Fixed output password of "e" rule in pure and cpu rule engine if separator character is also the first letter
+- Fixed problem with the usage of the hexadecimal notations (\x00-\xff) within rules
+- Fixed some memory leaks in case hashcat is shutting down due to some file error
- Fixed the 7-Zip parser to allow the entire supported range of encrypted and decrypted data lengths
- Fixed the validation of the --brain-client-features command line argument (only values 1, 2 or 3 are allowed)
-- Fixed problem with the usage of the hexadecimal notations (\x00-\xff) within rules
##
## Improvements
##
-- Startup Checks: Improved the pidfile check: Do not just check for existing PID but also check executable filename
-- Cracking bcrypt and Password Safe v2: Use a feedback from the OpenCL runtime to dynamically find out optimal thread count
- Bitcoin Wallet: Be more user friendly by allowing a larger data range for ckey and public_key
+- Building: Fix for library compilation failure due to multiple defenition of sbob_xx64()
- Building: Updated BUILD.md
+- Cracking bcrypt and Password Safe v2: Use a feedback from the compute API backend to dynamically find out optimal thread count
+- Documents: Added README on how to build hashcat on MSYS2
- My Wallet: Added additional plaintext pattern used in newer versions
- OpenCL Runtime: Disable OpenCL kernel cache on Apple for Intel CPU (throws CL_BUILD_PROGRAM_FAILURE for no reason)
+- OpenCL Runtime: Do not run a shared- and constant-memory size check if their memory type is of type global memory (typically CPU)
- OpenCL Runtime: Improve ROCM detection and make sure to not confuse with recent AMDGPU drivers
- OpenCL Runtime: Not using amd_bytealign (amd_bitalign is fine) on AMDGPU driver drastically reduces JiT segfaults
- OpenCL Runtime: Unlocked maximum thread count
@@ -73,25 +93,44 @@
- OpenCL Runtime: Workaround JiT compiler error on ROCM 2.3 driver if the 'inline' keyword is used in function declaration
- OpenCL Runtime: Workaround memory allocation error on AMD driver on Windows leading to CL_MEM_OBJECT_ALLOCATION_FAILURE
- OpenCL Runtime: Workaround ROCm OpenCL driver problem trying to write temporary file into readonly folder by setting TMPDIR
-- OpenCL Runtime: Do not run a shared- and constant-memory size check if their memory type is of type global memory (typically CPU)
+- Startup Checks: Improved the pidfile check: Do not just check for existing PID but also check executable filename
+- Startup Screen: Add extra warning when using --force
- Startup Screen: Provide an estimate of host memory requirements for the requested attack
+- Status Screen: Added brain status for all devices
+- Status Screen: Added remaining counts and changed recovered count logic
+- Status Screen: Added --status-json flag for easier machine reading of hashcat status output
+- Tab Completion: Allow using "make install" version of hashcat
- Tuning Database: Updated hashcat.hctune with new models and refreshed vector width values
-- WPA/WPA2 cracking: In the potfile, replace password with PMK in order to detect already cracked networks across all WPA modes
- WipZip cracking: Added two byte early reject, resulting in higher cracking speed
+- WPA/WPA2 cracking: In the potfile, replace password with PMK in order to detect already cracked networks across all WPA modes
##
## Technical
##
- Binary Distribution: Removed 32 bit binary executables
+- Building: On macOS, switch from ar to /usr/bin/ar to improve building compatibility
+- Building: Skipping Travis/Appveyor build for non-code changes
+- Codebase: Cleanup of many unused rc_* variables
+- Codebase: Fixed some printf() format arguments
+- Codebase: Fixed some type casting to avoid truncLongCastAssignment warnings
+- Codebase: Moved hc_* file functions from shared.c to filehandling.c
+- Codebase: Ran through a bunch of clang-tidy checkers and updated code accordingly
+- Codebase: Remove redundant calls to fclose()
+- Dependencies: Updated LZMA-Headers from 18.05 to 19.00
- Dependencies: Updated OpenCL-Headers to latest version from GitHub master repository
+- Hash-mode 1460 (HMAC-SHA256 (key = $salt)): Allow up to 64 byte of salt
+- Hash-Mode 1680x (WPA-PMKID) specific: Changed separator character from '*' to ':'
+- Hash-Mode 8300 (DNSSEC (NSEC3)) specific: Allow empty salt
- Keep Guessing: No longer automatically activate --keep-guessing for modes 9720, 9820, 14900 and 18100
- Kernel Cache: Reactivate OpenCL runtime specific kernel caches
- Kernel Compile: Removed -cl-std= from all kernel build options since we're compatible to all OpenCL versions
-- Mode 16800/16801 hash format: Changed separator character from '*' to ':'
-- Requirements: Update runtime check for minimum NVIDIA driver version from 367.x to 418.56 or later
-- Requirements: Add new requirement for NVIDIA GPU: CUDA Toolkit (10.1 or later)
+- OpenCL Kernels: Fix OpenCL compiler warning on double precision constants
- OpenCL Options: Removed --opencl-platforms filter in order to force backend device numbers to stay constant
+- Parsers: switched from strtok() to strtok_r() for thread safety
+- Requirements: Add new requirement for NVIDIA GPU: CUDA Toolkit (10.1 or later)
+- Requirements: Update runtime check for minimum NVIDIA driver version from 367.x to 418.56 or later
+- Test Script: Switched from /bin/bash to generic /bin/sh and updated code accordingly
* changes v5.0.0 -> v5.1.0
From e8326f0ddfe0514d9650d0bcc5bc7992983cc168 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Mon, 5 Aug 2019 12:39:10 +0200
Subject: [PATCH 081/113] Fix copy/paste bug in -m 15700
---
OpenCL/m15700-pure.cl | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/OpenCL/m15700-pure.cl b/OpenCL/m15700-pure.cl
index 2bd7b709c..813806bd7 100644
--- a/OpenCL/m15700-pure.cl
+++ b/OpenCL/m15700-pure.cl
@@ -36,7 +36,7 @@ inline __device__ uint4 operator ^= ( uint4 &a, const uint4 b) {
inline __device__ uint4 rotate (const uint4 a, const int n)
{
- return ((a >> n) | ((a >> (32 - n))));
+ return ((a << n) | ((a >> (32 - n))));
}
#endif
From ba99ce69a3e877d73c87ba948001a9cba940756e Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Mon, 5 Aug 2019 12:41:17 +0200
Subject: [PATCH 082/113] Fix CUDA JiT compiler warning in SCRYPT based kernels
---
OpenCL/m08900-pure.cl | 2 +-
OpenCL/m15700-pure.cl | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/OpenCL/m08900-pure.cl b/OpenCL/m08900-pure.cl
index c5242d18e..706f7f2e4 100644
--- a/OpenCL/m08900-pure.cl
+++ b/OpenCL/m08900-pure.cl
@@ -32,7 +32,7 @@ inline __device__ uint4 operator >> (const uint4 a, const u32 b) { return mak
inline __device__ uint4 operator + (const uint4 a, const uint4 b) { return make_uint4 ((a.x + b.x), (a.y + b.y), (a.z + b.z), (a.w + b.w)); }
inline __device__ uint4 operator ^ (const uint4 a, const uint4 b) { return make_uint4 ((a.x ^ b.x), (a.y ^ b.y), (a.z ^ b.z), (a.w ^ b.w)); }
inline __device__ uint4 operator | (const uint4 a, const uint4 b) { return make_uint4 ((a.x | b.x), (a.y | b.y), (a.z | b.z), (a.w | b.w)); }
-inline __device__ uint4 operator ^= ( uint4 &a, const uint4 b) { a.x ^= b.x; a.y ^= b.y; a.z ^= b.z; a.w ^= b.w; }
+inline __device__ void operator ^= ( uint4 &a, const uint4 b) { a.x ^= b.x; a.y ^= b.y; a.z ^= b.z; a.w ^= b.w; }
inline __device__ uint4 rotate (const uint4 a, const int n)
{
diff --git a/OpenCL/m15700-pure.cl b/OpenCL/m15700-pure.cl
index 813806bd7..291b7b2d7 100644
--- a/OpenCL/m15700-pure.cl
+++ b/OpenCL/m15700-pure.cl
@@ -32,7 +32,7 @@ inline __device__ uint4 operator >> (const uint4 a, const u32 b) { return mak
inline __device__ uint4 operator + (const uint4 a, const uint4 b) { return make_uint4 ((a.x + b.x), (a.y + b.y), (a.z + b.z), (a.w + b.w)); }
inline __device__ uint4 operator ^ (const uint4 a, const uint4 b) { return make_uint4 ((a.x ^ b.x), (a.y ^ b.y), (a.z ^ b.z), (a.w ^ b.w)); }
inline __device__ uint4 operator | (const uint4 a, const uint4 b) { return make_uint4 ((a.x | b.x), (a.y | b.y), (a.z | b.z), (a.w | b.w)); }
-inline __device__ uint4 operator ^= ( uint4 &a, const uint4 b) { a.x ^= b.x; a.y ^= b.y; a.z ^= b.z; a.w ^= b.w; }
+inline __device__ void operator ^= ( uint4 &a, const uint4 b) { a.x ^= b.x; a.y ^= b.y; a.z ^= b.z; a.w ^= b.w; }
inline __device__ uint4 rotate (const uint4 a, const int n)
{
From 8c717ffa21b618351b5e8d89e84211342888afba Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Mon, 5 Aug 2019 13:14:29 +0200
Subject: [PATCH 083/113] removed the debug printf
---
OpenCL/m21200_a3-optimized.cl | 2 --
1 file changed, 2 deletions(-)
diff --git a/OpenCL/m21200_a3-optimized.cl b/OpenCL/m21200_a3-optimized.cl
index 84f09e7d0..dc5960d4f 100644
--- a/OpenCL/m21200_a3-optimized.cl
+++ b/OpenCL/m21200_a3-optimized.cl
@@ -773,8 +773,6 @@ DECLSPEC void m21200s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
const u32x d0 = d;
const u32x e0 = e;
-if (gid == 0) printf("sha1(salt): %08x %08x %08x %08x %08x\n", a0, b0, c0, d0, e0);
-
/**
* digest
*/
From d1fa66b79cbfa0fb8fef54a7aedc18c486d598ce Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Mon, 5 Aug 2019 13:18:38 +0200
Subject: [PATCH 084/113] fix hash-mode 4710 module_constraints
---
tools/test_modules/m04710.pm | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/test_modules/m04710.pm b/tools/test_modules/m04710.pm
index de4cadd7f..824676936 100644
--- a/tools/test_modules/m04710.pm
+++ b/tools/test_modules/m04710.pm
@@ -11,7 +11,7 @@ use warnings;
use Digest::MD5 qw (md5_hex);
use Digest::SHA qw (sha1_hex);
-sub module_constraints { [[0, 256], [0, 256], [0, 55], [8, 8], [-1, -1]] }
+sub module_constraints { [[0, 256], [0, 256], [0, 55], [0, 15], [-1, -1]] }
sub module_generate_hash
{
From 2aa529999266f76b7a4d1a88fb4943432333e67b Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Mon, 5 Aug 2019 15:23:00 +0200
Subject: [PATCH 085/113] Workaround too much register use in -m 14600 on
low-end GPU
---
src/modules/module_14600.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/src/modules/module_14600.c b/src/modules/module_14600.c
index 9b8fcc357..74c962be4 100644
--- a/src/modules/module_14600.c
+++ b/src/modules/module_14600.c
@@ -178,6 +178,17 @@ typedef struct luks_tmp
} luks_tmp_t;
+u32 module_kernel_threads_max (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
+{
+ // the module requires a lot of registers for key schedulers on _comp kernel.
+ // it's possible, if using too many threads, there's not enough registers available, typically ending with misleading error message:
+ // cuLaunchKernel(): out of memory
+
+ const u32 kernel_threads_max = 64;
+
+ return kernel_threads_max;
+}
+
void *module_benchmark_esalt (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
{
luks_t *luks = (luks_t *) hcmalloc (sizeof (luks_t));
@@ -628,7 +639,7 @@ void module_init (module_ctx_t *module_ctx)
module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
- module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
+ module_ctx->module_kernel_threads_max = module_kernel_threads_max;
module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
module_ctx->module_kern_type = module_kern_type;
module_ctx->module_kern_type_dynamic = module_kern_type_dynamic;
From 8e081e69c5f8bbb584ed72873012f79eca6e1616 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Mon, 5 Aug 2019 10:33:09 -0700
Subject: [PATCH 086/113] Fix overzealous quoting from last sh patch
Characters with glob characters should not be quoted.
---
tools/test.sh | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/tools/test.sh b/tools/test.sh
index c634aab2f..018687de3 100755
--- a/tools/test.sh
+++ b/tools/test.sh
@@ -26,14 +26,14 @@ LUKS_MODE="14600"
# missing hash types: 5200
-HASH_TYPES=$(ls "${TDIR}/test_modules/*.pm" | sed -E 's/.*m0*([0-9]+).pm/\1/')
+HASH_TYPES=$(ls ${TDIR}/test_modules/*.pm | sed -E 's/.*m0*([0-9]+).pm/\1/')
HASH_TYPES="${HASH_TYPES} ${TC_MODES} ${VC_MODES} ${LUKS_MODE}"
HASH_TYPES=$(echo -n "${HASH_TYPES}" | tr ' ' '\n' | sort -u -n | tr '\n' ' ')
VECTOR_WIDTHS="1 2 4 8 16"
-HASHFILE_ONLY=$(grep -l OPTS_TYPE_BINARY_HASHFILE "${TDIR}/../src/modules/module_*.c" | sed -E 's/.*module_0*([0-9]+).c/\1/' | tr '\n' ' ')
-SLOW_ALGOS=$(grep -l ATTACK_EXEC_OUTSIDE_KERNEL "${TDIR}/../src/modules/module_*.c" | sed -E 's/.*module_0*([0-9]+).c/\1/' | tr '\n' ' ')
+HASHFILE_ONLY=$(grep -l OPTS_TYPE_BINARY_HASHFILE ${TDIR}/../src/modules/module_*.c | sed -E 's/.*module_0*([0-9]+).c/\1/' | tr '\n' ' ')
+SLOW_ALGOS=$(grep -l ATTACK_EXEC_OUTSIDE_KERNEL ${TDIR}/../src/modules/module_*.c | sed -E 's/.*module_0*([0-9]+).c/\1/' | tr '\n' ' ')
OUTD="test_$(date +%s)"
From 54f8811b4ed3dfd03b76c8b9ce7f1dfa4db4bd9e Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 6 Aug 2019 02:29:52 +0200
Subject: [PATCH 087/113] update SolarWinds Orion patch (1)
---
OpenCL/m21500-pure.cl | 2 +-
docs/changes.txt | 1 +
docs/credits.txt | 1 +
docs/readme.txt | 1 +
src/modules/module_21500.c | 111 ++++++++++++++++++++++++-------------
5 files changed, 76 insertions(+), 40 deletions(-)
diff --git a/OpenCL/m21500-pure.cl b/OpenCL/m21500-pure.cl
index ff81e2b05..f0614c07d 100644
--- a/OpenCL/m21500-pure.cl
+++ b/OpenCL/m21500-pure.cl
@@ -30,7 +30,7 @@ typedef struct pbkdf2_sha1_tmp
typedef struct pbkdf2_sha1
{
- u32 salt_buf[64];
+ u32 salt_buf[4];
} pbkdf2_sha1_t;
diff --git a/docs/changes.txt b/docs/changes.txt
index 511a0d95f..8443e93e3 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -37,6 +37,7 @@
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
- Added hash-mode: sha1(md5($pass).$salt)
+- Added hash-mode: SolarWinds Orion, SHA512(PBKDF2-HMAC-SHA1)
##
## Bugs
diff --git a/docs/credits.txt b/docs/credits.txt
index 9eb7b0dac..58360d3de 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,6 +18,7 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
+* SolarWinds Orion, SHA512(PBKDF2-HMAC-SHA1), kernel module
* sha1(md5($pass).$salt) kernel module
* gzip wordlists feature
* SHA-224 kernel module + optimizations
diff --git a/docs/readme.txt b/docs/readme.txt
index 7e3e8d468..442dab752 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -279,6 +279,7 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- Ethereum Wallet, SCRYPT
- Ethereum Pre-Sale Wallet, PBKDF2-HMAC-SHA256
- Ansible Vault
+- SolarWinds Orion, SHA512(PBKDF2-HMAC-SHA1)
- Plaintext
##
diff --git a/src/modules/module_21500.c b/src/modules/module_21500.c
index a33949735..cd6bbec6d 100644
--- a/src/modules/module_21500.c
+++ b/src/modules/module_21500.c
@@ -17,7 +17,7 @@ static const u32 DGST_POS2 = 6;
static const u32 DGST_POS3 = 7;
static const u32 DGST_SIZE = DGST_SIZE_8_8;
static const u32 HASH_CATEGORY = HASH_CATEGORY_GENERIC_KDF;
-static const char *HASH_NAME = "SHA512(PBKDF2-HMAC-SHA1)";
+static const char *HASH_NAME = "SolarWinds Orion";
static const u64 KERN_TYPE = 21500;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_USES_BITS_64
@@ -27,7 +27,9 @@ static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE
| OPTS_TYPE_HASH_COPY;
static const u32 SALT_TYPE = SALT_TYPE_EMBEDDED;
static const char *ST_PASS = "hashcat";
-static const char *ST_HASH = "sha1:1000:aGFzaGNhdDE=:Dnz04T9ptYINnj9mckXTuk80w6f1vkZLwv02HiufklgnDw53BU1bgn4gsHia/Q6kxYSqK4PDbxRMwa6HB5KA/w==";
+static const char *ST_HASH = "$solarwinds$0$hashcat1$Dnz04T9ptYINnj9mckXTuk80w6f1vkZLwv02HiufklgnDw53BU1bgn4gsHia/Q6kxYSqK4PDbxRMwa6HB5KA/w==";
+
+static const char *SALT_PADDING = "1244352345234";
u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
@@ -60,7 +62,7 @@ typedef struct pbkdf2_sha1
} pbkdf2_sha1_t;
-static const char *SIGNATURE_PBKDF2_SHA1 = "sha1";
+static const char *SIGNATURE_SOLARWINDS_ORION = "$solarwinds$0$";
u64 module_esalt_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
{
@@ -106,63 +108,67 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
token_t token;
- token.token_cnt = 4;
+ token.token_cnt = 3;
token.signatures_cnt = 1;
- token.signatures_buf[0] = SIGNATURE_PBKDF2_SHA1;
+ token.signatures_buf[0] = SIGNATURE_SOLARWINDS_ORION;
- token.sep[0] = ':';
- token.len_min[0] = 4;
- token.len_max[0] = 4;
- token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
+ token.len[0] = 14;
+ token.attr[0] = TOKEN_ATTR_FIXED_LENGTH
| TOKEN_ATTR_VERIFY_SIGNATURE;
- token.sep[1] = ':';
- token.len_min[1] = 1;
- token.len_max[1] = 6;
- token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH
- | TOKEN_ATTR_VERIFY_DIGIT;
+ token.sep[1] = '$';
+ token.len_min[1] = 0;
+ token.len_max[1] = 16;
+ token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH;
- token.sep[2] = ':';
- token.len_min[2] = 12;
- token.len_max[2] = 24;
+ token.sep[2] = '$';
+ token.len_min[2] = 64;
+ token.len_max[2] = 256;
token.attr[2] = TOKEN_ATTR_VERIFY_LENGTH
| TOKEN_ATTR_VERIFY_BASE64A;
- token.len_min[3] = 64;
- token.len_max[3] = 256;
- token.attr[3] = TOKEN_ATTR_VERIFY_LENGTH
- | TOKEN_ATTR_VERIFY_BASE64A;
-
const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
- u8 tmp_buf[512];
- int tmp_len;
-
// iter
- const u8 *iter_pos = token.buf[1];
-
- const u32 iter = hc_strtoul ((const char *) iter_pos, NULL, 10);
+ const u32 iter = 1000;
salt->salt_iter = iter - 1;
// salt
- const u8 *salt_pos = token.buf[2];
- const int salt_len = token.len[2];
+ char *salt_pos = (char *) token.buf[1];
+ int salt_len = token.len[1];
- memset (tmp_buf, 0, sizeof (tmp_buf));
+ if (salt_len > 16) return (PARSER_SALT_LENGTH);
- tmp_len = base64_decode (base64_to_int, salt_pos, salt_len, tmp_buf);
+ char custom_salt[17];
- if (tmp_len < 8 || tmp_len > 16) return (PARSER_SALT_LENGTH);
+ memset (custom_salt, 0, sizeof (custom_salt));
- memcpy (pbkdf2_sha1->salt_buf, tmp_buf, tmp_len);
+ for (int i = 0; i < salt_len; i++, salt_pos++)
+ {
+ if (*salt_pos >= 'A' && *salt_pos <= 'Z') {
+ custom_salt[i] = *salt_pos + 32;
+ } else {
+ custom_salt[i] = *salt_pos;
+ }
+ }
- salt->salt_len = tmp_len;
+ if (salt_len < 8)
+ {
+ strncat (custom_salt, SALT_PADDING, 8 - salt_len);
+ salt_len = 8;
+ }
+
+ salt_pos = custom_salt;
+
+ memcpy (pbkdf2_sha1->salt_buf, salt_pos, salt_len);
+
+ salt->salt_len = salt_len;
salt->salt_buf[0] = pbkdf2_sha1->salt_buf[0];
salt->salt_buf[1] = pbkdf2_sha1->salt_buf[1];
@@ -172,12 +178,14 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
// hash
- const u8 *hash_pos = token.buf[3];
- const int hash_len = token.len[3];
+ const u8 *hash_pos = token.buf[2];
+ const int hash_len = token.len[2];
+
+ u8 tmp_buf[256];
memset (tmp_buf, 0, sizeof (tmp_buf));
- tmp_len = base64_decode (base64_to_int, hash_pos, hash_len, tmp_buf);
+ int tmp_len = base64_decode (base64_to_int, hash_pos, hash_len, tmp_buf);
if (tmp_len < 64) return (PARSER_HASH_LENGTH);
@@ -197,7 +205,32 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
{
- return snprintf (line_buf, line_size, "%s", hash_info->orighash);
+ const u64 *digest = (u64 *) digest_buf;
+
+ const pbkdf2_sha1_t *pbkdf2_sha1 = (const pbkdf2_sha1_t *) esalt_buf;
+
+ // hash
+
+ u64 tmp[9];
+
+ tmp[0] = byte_swap_64 (digest[0]);
+ tmp[1] = byte_swap_64 (digest[1]);
+ tmp[2] = byte_swap_64 (digest[2]);
+ tmp[3] = byte_swap_64 (digest[3]);
+ tmp[4] = byte_swap_64 (digest[4]);
+ tmp[5] = byte_swap_64 (digest[5]);
+ tmp[6] = byte_swap_64 (digest[6]);
+ tmp[7] = byte_swap_64 (digest[7]);
+ tmp[8] = 0;
+
+ char hash_enc[256] = { 0 };
+
+ base64_encode (int_to_base64, (const u8 *) tmp, 64, (u8 *) hash_enc);
+
+ // output
+ const int line_len = snprintf (line_buf, line_size, "%s%s$%s", SIGNATURE_SOLARWINDS_ORION, (const u8 *) pbkdf2_sha1->salt_buf, hash_enc);
+
+ return line_len;
}
void module_init (module_ctx_t *module_ctx)
From 18834efa3fadc87e68e0824386833558d26fe181 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 6 Aug 2019 02:31:41 +0200
Subject: [PATCH 088/113] cleanup changes.txt
---
docs/changes.txt | 1 -
1 file changed, 1 deletion(-)
diff --git a/docs/changes.txt b/docs/changes.txt
index 8443e93e3..511a0d95f 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -37,7 +37,6 @@
- Added hash-mode: Python passlib pbkdf2-sha512
- Added hash-mode: Oracle Transportation Management (SHA256)
- Added hash-mode: sha1(md5($pass).$salt)
-- Added hash-mode: SolarWinds Orion, SHA512(PBKDF2-HMAC-SHA1)
##
## Bugs
From 1ecdffb580201684adbec00c88740540fe50ab09 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Tue, 6 Aug 2019 11:26:56 +0200
Subject: [PATCH 089/113] Fix some code formatting
---
src/terminal.c | 62 ++++++++++++++++++++++++++------------------------
1 file changed, 32 insertions(+), 30 deletions(-)
diff --git a/src/terminal.c b/src/terminal.c
index 618dce6a6..e0ae0137f 100644
--- a/src/terminal.c
+++ b/src/terminal.c
@@ -1450,51 +1450,53 @@ void status_display (hashcat_ctx_t *hashcat_ctx)
"Speed.#*.........: %9sH/s",
hashcat_status->speed_sec_all);
}
-
+
if (hashcat_status->salts_cnt > 1)
{
- event_log_info (hashcat_ctx,
- "Recovered........: %d/%d (%.2f%%) Digests, %d/%d (%.2f%%) Salts",
- hashcat_status->digests_done,
- hashcat_status->digests_cnt,
- hashcat_status->digests_percent,
- hashcat_status->salts_done,
- hashcat_status->salts_cnt,
- hashcat_status->salts_percent);
+ event_log_info (hashcat_ctx,
+ "Recovered........: %d/%d (%.2f%%) Digests, %d/%d (%.2f%%) Salts",
+ hashcat_status->digests_done,
+ hashcat_status->digests_cnt,
+ hashcat_status->digests_percent,
+ hashcat_status->salts_done,
+ hashcat_status->salts_cnt,
+ hashcat_status->salts_percent);
}
else
{
- event_log_info (hashcat_ctx,
- "Recovered........: %d/%d (%.2f%%) Digests",
- hashcat_status->digests_done,
- hashcat_status->digests_cnt,
- hashcat_status->digests_percent);
+ event_log_info (hashcat_ctx,
+ "Recovered........: %d/%d (%.2f%%) Digests",
+ hashcat_status->digests_done,
+ hashcat_status->digests_cnt,
+ hashcat_status->digests_percent);
}
-
+
if (hashcat_status->digests_cnt > 1000)
{
- int digests_remain = hashcat_status->digests_cnt - hashcat_status->digests_done;
- double digests_remain_percent = (double) digests_remain / (double) hashcat_status->digests_cnt * 100;
- int salts_remain = hashcat_status->salts_cnt - hashcat_status->salts_done;
- double salts_remain_percent = (double) salts_remain / (double) hashcat_status->salts_cnt * 100;
+ const int digests_remain = hashcat_status->digests_cnt - hashcat_status->digests_done;
+ const double digests_remain_percent = (double) digests_remain / (double) hashcat_status->digests_cnt * 100;
+
+ const int salts_remain = hashcat_status->salts_cnt - hashcat_status->salts_done;
+ const double salts_remain_percent = (double) salts_remain / (double) hashcat_status->salts_cnt * 100;
+
if (hashcat_status->salts_cnt > 1)
{
- event_log_info (hashcat_ctx,
- "Remaining........: %d (%.2f%%) Digests, %d (%.2f%%) Salts",
- digests_remain,
- digests_remain_percent,
- salts_remain,
- salts_remain_percent);
+ event_log_info (hashcat_ctx,
+ "Remaining........: %d (%.2f%%) Digests, %d (%.2f%%) Salts",
+ digests_remain,
+ digests_remain_percent,
+ salts_remain,
+ salts_remain_percent);
}
else
{
- event_log_info (hashcat_ctx,
- "Remaining........: %d (%.2f%%) Digests",
- digests_remain,
- digests_remain_percent);
+ event_log_info (hashcat_ctx,
+ "Remaining........: %d (%.2f%%) Digests",
+ digests_remain,
+ digests_remain_percent);
}
}
-
+
if (hashcat_status->digests_cnt > 1000)
{
event_log_info (hashcat_ctx,
From 97c9e86d155df741fc50bc61453d63888427ef86 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Tue, 6 Aug 2019 12:22:24 +0200
Subject: [PATCH 090/113] Filehandling: Print a truncation warning in case an
oversized line was detected
---
docs/changes.txt | 1 +
include/filehandling.h | 3 ++-
src/backend.c | 4 ++--
src/filehandling.c | 18 +++++++++++++++---
src/hashes.c | 2 +-
src/hlfmt.c | 2 +-
src/keyboard_layout.c | 2 +-
src/mpsp.c | 6 +++---
src/outfile_check.c | 2 +-
src/potfile.c | 2 +-
src/rp.c | 2 +-
src/slow_candidates.c | 4 ++--
12 files changed, 31 insertions(+), 17 deletions(-)
diff --git a/docs/changes.txt b/docs/changes.txt
index bb37c2c85..0d5998a54 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -82,6 +82,7 @@
- Building: Updated BUILD.md
- Cracking bcrypt and Password Safe v2: Use a feedback from the compute API backend to dynamically find out optimal thread count
- Documents: Added README on how to build hashcat on MSYS2
+- Filehandling: Print a truncation warning in case an oversized line was detected
- My Wallet: Added additional plaintext pattern used in newer versions
- OpenCL Runtime: Disable OpenCL kernel cache on Apple for Intel CPU (throws CL_BUILD_PROGRAM_FAILURE for no reason)
- OpenCL Runtime: Do not run a shared- and constant-memory size check if their memory type is of type global memory (typically CPU)
diff --git a/include/filehandling.h b/include/filehandling.h
index 32f3044b0..8b73699d4 100644
--- a/include/filehandling.h
+++ b/include/filehandling.h
@@ -9,6 +9,7 @@
#include <stdio.h>
#include <string.h>
#include <errno.h>
+#include <inttypes.h>
#if defined (__CYGWIN__)
int _wopen (const char *path, int oflag, ...);
@@ -31,7 +32,7 @@ char *hc_fgets (char *buf, int len, HCFILE *fp);
size_t hc_fwrite (void *ptr, size_t size, size_t nmemb, HCFILE *fp);
size_t hc_fread (void *ptr, size_t size, size_t nmemb, HCFILE *fp);
-size_t fgetl (HCFILE *fp, char *line_buf);
+size_t fgetl (HCFILE *fp, char *line_buf, const size_t line_sz);
u64 count_lines (HCFILE *fp);
size_t in_superchop (char *buf);
size_t superchop_with_length (char *buf, const size_t len);
diff --git a/src/backend.c b/src/backend.c
index edef5c229..4c0ff1179 100644
--- a/src/backend.c
+++ b/src/backend.c
@@ -4183,7 +4183,7 @@ int run_cracker (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param, co
{
if (hc_feof (combs_fp)) break;
- size_t line_len = fgetl (combs_fp, line_buf);
+ size_t line_len = fgetl (combs_fp, line_buf, HCBUFSIZ_LARGE);
line_len = convert_from_hex (hashcat_ctx, line_buf, line_len);
@@ -4328,7 +4328,7 @@ int run_cracker (hashcat_ctx_t *hashcat_ctx, hc_device_param_t *device_param, co
{
if (hc_feof (combs_fp)) break;
- size_t line_len = fgetl (combs_fp, line_buf);
+ size_t line_len = fgetl (combs_fp, line_buf, HCBUFSIZ_LARGE);
line_len = convert_from_hex (hashcat_ctx, line_buf, line_len);
diff --git a/src/filehandling.c b/src/filehandling.c
index 921e7e0ed..9ea564f2a 100644
--- a/src/filehandling.c
+++ b/src/filehandling.c
@@ -454,8 +454,10 @@ void hc_fclose (HCFILE *fp)
fp->mode = NULL;
}
-size_t fgetl (HCFILE *fp, char *line_buf)
+size_t fgetl (HCFILE *fp, char *line_buf, const size_t line_sz)
{
+ size_t line_truncated = 0;
+
size_t line_len = 0;
while (!hc_feof (fp))
@@ -464,15 +466,25 @@ size_t fgetl (HCFILE *fp, char *line_buf)
if (c == EOF) break;
+ if (line_len == line_sz)
+ {
+ line_truncated++;
+
+ continue;
+ }
+
line_buf[line_len] = (char) c;
line_len++;
- if (line_len == HCBUFSIZ_LARGE) line_len--;
-
if (c == '\n') break;
}
+ if (line_truncated > 0)
+ {
+ fprintf (stderr, "\nOversized line detected! Truncated %" PRIu64 " bytes\n", line_truncated);
+ }
+
if (line_len == 0) return 0;
while (line_len)
diff --git a/src/hashes.c b/src/hashes.c
index 3e93b6579..a92af200e 100644
--- a/src/hashes.c
+++ b/src/hashes.c
@@ -1018,7 +1018,7 @@ int hashes_init_stage1 (hashcat_ctx_t *hashcat_ctx)
{
line_num++;
- const size_t line_len = fgetl (&fp, line_buf);
+ const size_t line_len = fgetl (&fp, line_buf, HCBUFSIZ_LARGE);
if (line_len == 0) continue;
diff --git a/src/hlfmt.c b/src/hlfmt.c
index c049f24fc..68ea27c82 100644
--- a/src/hlfmt.c
+++ b/src/hlfmt.c
@@ -350,7 +350,7 @@ u32 hlfmt_detect (hashcat_ctx_t *hashcat_ctx, HCFILE *fp, u32 max_check)
while (!hc_feof (fp))
{
- const size_t line_len = fgetl (fp, line_buf);
+ const size_t line_len = fgetl (fp, line_buf, HCBUFSIZ_LARGE);
if (line_len == 0) continue;
diff --git a/src/keyboard_layout.c b/src/keyboard_layout.c
index b20ec6d35..fd1680388 100644
--- a/src/keyboard_layout.c
+++ b/src/keyboard_layout.c
@@ -30,7 +30,7 @@ bool initialize_keyboard_layout_mapping (const char *filename, keyboard_layout_m
while (!hc_feof (&fp))
{
- const size_t line_len = fgetl (&fp, line_buf);
+ const size_t line_len = fgetl (&fp, line_buf, HCBUFSIZ_LARGE);
if (line_len == 0) continue;
diff --git a/src/mpsp.c b/src/mpsp.c
index 03f1836ac..3d7d64dfe 100644
--- a/src/mpsp.c
+++ b/src/mpsp.c
@@ -1434,7 +1434,7 @@ int mask_ctx_init (hashcat_ctx_t *hashcat_ctx)
while (!hc_feof (&mask_fp))
{
- const size_t line_len = fgetl (&mask_fp, line_buf);
+ const size_t line_len = fgetl (&mask_fp, line_buf, HCBUFSIZ_LARGE);
if (line_len == 0) continue;
@@ -1519,7 +1519,7 @@ int mask_ctx_init (hashcat_ctx_t *hashcat_ctx)
while (!hc_feof (&mask_fp))
{
- const size_t line_len = fgetl (&mask_fp, line_buf);
+ const size_t line_len = fgetl (&mask_fp, line_buf, HCBUFSIZ_LARGE);
if (line_len == 0) continue;
@@ -1589,7 +1589,7 @@ int mask_ctx_init (hashcat_ctx_t *hashcat_ctx)
while (!hc_feof (&mask_fp))
{
- const size_t line_len = fgetl (&mask_fp, line_buf);
+ const size_t line_len = fgetl (&mask_fp, line_buf, HCBUFSIZ_LARGE);
if (line_len == 0) continue;
diff --git a/src/outfile_check.c b/src/outfile_check.c
index c67b9429c..84d47b1e9 100644
--- a/src/outfile_check.c
+++ b/src/outfile_check.c
@@ -185,7 +185,7 @@ static int outfile_remove (hashcat_ctx_t *hashcat_ctx)
while (!hc_feof (&fp))
{
- size_t line_len = fgetl (&fp, line_buf);
+ size_t line_len = fgetl (&fp, line_buf, HCBUFSIZ_LARGE);
if (line_len == 0) continue;
diff --git a/src/potfile.c b/src/potfile.c
index 866548bff..58a247406 100644
--- a/src/potfile.c
+++ b/src/potfile.c
@@ -521,7 +521,7 @@ int potfile_remove_parse (hashcat_ctx_t *hashcat_ctx)
while (!hc_feof (&potfile_ctx->fp))
{
- size_t line_len = fgetl (&potfile_ctx->fp, line_buf);
+ size_t line_len = fgetl (&potfile_ctx->fp, line_buf, HCBUFSIZ_LARGE);
if (line_len == 0) continue;
diff --git a/src/rp.c b/src/rp.c
index 716e451bf..2fdce44ca 100644
--- a/src/rp.c
+++ b/src/rp.c
@@ -751,7 +751,7 @@ int kernel_rules_load (hashcat_ctx_t *hashcat_ctx, kernel_rule_t **out_buf, u32
while (!hc_feof (&fp))
{
- rule_len = (u32) fgetl (&fp, rule_buf);
+ rule_len = (u32) fgetl (&fp, rule_buf, HCBUFSIZ_LARGE);
rule_line++;
diff --git a/src/slow_candidates.c b/src/slow_candidates.c
index 76b8386f7..222cc4a92 100644
--- a/src/slow_candidates.c
+++ b/src/slow_candidates.c
@@ -123,7 +123,7 @@ void slow_candidates_seek (hashcat_ctx_t *hashcat_ctx, void *extra_info, const u
while (1)
{
- line_len = (u32) fgetl (combs_fp, line_buf);
+ line_len = (u32) fgetl (combs_fp, line_buf, HCBUFSIZ_LARGE);
// post-process rule engine
@@ -286,7 +286,7 @@ void slow_candidates_next (hashcat_ctx_t *hashcat_ctx, void *extra_info)
while (1)
{
- line_len = (u32) fgetl (combs_fp, line_buf);
+ line_len = (u32) fgetl (combs_fp, line_buf, HCBUFSIZ_LARGE);
// post-process rule engine
From 57a149276c5a20d5af1b2364628b3a305772ab3d Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Tue, 6 Aug 2019 12:44:39 +0200
Subject: [PATCH 091/113] Do alias check only in case both CUDA and OpenCL
devices were detected
---
src/backend.c | 18 +++++++++++-------
1 file changed, 11 insertions(+), 7 deletions(-)
diff --git a/src/backend.c b/src/backend.c
index 4c0ff1179..832175b8a 100644
--- a/src/backend.c
+++ b/src/backend.c
@@ -6130,14 +6130,18 @@ int backend_ctx_devices_init (hashcat_ctx_t *hashcat_ctx, const int comptime)
backend_ctx->backend_devices_cnt = cuda_devices_cnt + opencl_devices_cnt;
backend_ctx->backend_devices_active = cuda_devices_active + opencl_devices_active;
- // find duplicate devices (typically cuda and opencl!)
- // using force here enables both devices, which is the worst possible outcome
- // many users force by default, so this is not a good idea
+ // find duplicate devices (typically CUDA and OpenCL)
- //if (user_options->force == false)
- //{
- backend_ctx_find_alias_devices (hashcat_ctx);
- //}
+ if ((cuda_devices_cnt > 0) && (opencl_devices_cnt > 0))
+ {
+ // using force here enables both devices, which is the worst possible outcome
+ // many users force by default, so this is not a good idea
+
+ //if (user_options->force == false)
+ //{
+ backend_ctx_find_alias_devices (hashcat_ctx);
+ //{
+ }
if (backend_ctx->backend_devices_active == 0)
{
From ca31ef43aff1726113aaef85d06aa5c3cbca6697 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Tue, 6 Aug 2019 14:07:43 +0200
Subject: [PATCH 092/113] Fixed race condition in maskfile mode by using a
dedicated flag for restore execution
---
docs/changes.txt | 1 +
include/types.h | 2 ++
src/hashcat.c | 17 +++++++----------
src/restore.c | 4 ++++
4 files changed, 14 insertions(+), 10 deletions(-)
diff --git a/docs/changes.txt b/docs/changes.txt
index 0d5998a54..bb2889bab 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -69,6 +69,7 @@
- Fixed output of IKE PSK (mode 5300 and 5400) hashes to have separators at right position
- Fixed output password of "e" rule in pure and cpu rule engine if separator character is also the first letter
- Fixed problem with the usage of the hexadecimal notations (\x00-\xff) within rules
+- Fixed race condition in maskfile mode by using a dedicated flag for restore execution
- Fixed some memory leaks in case hashcat is shutting down due to some file error
- Fixed the 7-Zip parser to allow the entire supported range of encrypted and decrypted data lengths
- Fixed the validation of the --brain-client-features command line argument (only values 1, 2 or 3 are allowed)
diff --git a/include/types.h b/include/types.h
index 08e3f88c0..e23e0e75b 100644
--- a/include/types.h
+++ b/include/types.h
@@ -1716,6 +1716,8 @@ typedef struct restore_ctx
{
bool enabled;
+ bool restore_execute;
+
int argc;
char **argv;
diff --git a/src/hashcat.c b/src/hashcat.c
index 0f21a91aa..01a069ab7 100644
--- a/src/hashcat.c
+++ b/src/hashcat.c
@@ -84,21 +84,18 @@ static int inner2_loop (hashcat_ctx_t *hashcat_ctx)
status_ctx->words_off = 0;
status_ctx->words_cur = 0;
- if (restore_ctx->rd)
+ if (restore_ctx->restore_execute == true)
{
+ restore_ctx->restore_execute = false;
+
restore_data_t *rd = restore_ctx->rd;
- if (rd->words_cur > 0)
- {
- status_ctx->words_off = rd->words_cur;
- status_ctx->words_cur = status_ctx->words_off;
+ status_ctx->words_off = rd->words_cur;
+ status_ctx->words_cur = status_ctx->words_off;
- rd->words_cur = 0;
+ // --restore always overrides --skip
- // --restore always overrides --skip
-
- user_options->skip = 0;
- }
+ user_options->skip = 0;
}
if (user_options->skip > 0)
diff --git a/src/restore.c b/src/restore.c
index 94a7a1f3d..a56c1aa08 100644
--- a/src/restore.c
+++ b/src/restore.c
@@ -332,6 +332,8 @@ int restore_ctx_init (hashcat_ctx_t *hashcat_ctx, int argc, char **argv)
restore_ctx->enabled = true;
+ restore_ctx->restore_execute = false;
+
if (user_options->restore == true)
{
if (read_restore (hashcat_ctx) == -1) return -1;
@@ -348,6 +350,8 @@ int restore_ctx_init (hashcat_ctx_t *hashcat_ctx, int argc, char **argv)
user_options_init (hashcat_ctx);
if (user_options_getopt (hashcat_ctx, rd->argc, rd->argv) == -1) return -1;
+
+ restore_ctx->restore_execute = true;
}
return 0;
From 5f44ce06f67aa74a9e524e912e07e38fde379568 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Tue, 6 Aug 2019 20:23:37 +0200
Subject: [PATCH 093/113] update SolarWinds Orion patch (2)
---
OpenCL/inc_hash_sha512.h | 1 +
OpenCL/m21500-pure.cl | 2 +-
src/Makefile | 2 +-
src/modules/module_21500.c | 25 +++++++--------------
tools/test_modules/m21500.pm | 43 ++++++++++++++----------------------
5 files changed, 28 insertions(+), 45 deletions(-)
diff --git a/OpenCL/inc_hash_sha512.h b/OpenCL/inc_hash_sha512.h
index 923eae678..f30dc2b86 100644
--- a/OpenCL/inc_hash_sha512.h
+++ b/OpenCL/inc_hash_sha512.h
@@ -127,6 +127,7 @@ DECLSPEC void sha512_hmac_init (sha512_hmac_ctx_t *ctx, const u32 *w, const int
DECLSPEC void sha512_hmac_init_swap (sha512_hmac_ctx_t *ctx, const u32 *w, const int len);
DECLSPEC void sha512_hmac_init_global (sha512_hmac_ctx_t *ctx, GLOBAL_AS const u32 *w, const int len);
DECLSPEC void sha512_hmac_init_global_swap (sha512_hmac_ctx_t *ctx, GLOBAL_AS const u32 *w, const int len);
+DECLSPEC void sha512_hmac_init_global_utf16le_swap (sha512_hmac_ctx_t *ctx, GLOBAL_AS const u32 *w, const int len);
DECLSPEC void sha512_hmac_update_128 (sha512_hmac_ctx_t *ctx, u32 *w0, u32 *w1, u32 *w2, u32 *w3, u32 *w4, u32 *w5, u32 *w6, u32 *w7, const int len);
DECLSPEC void sha512_hmac_update (sha512_hmac_ctx_t *ctx, const u32 *w, const int len);
DECLSPEC void sha512_hmac_update_swap (sha512_hmac_ctx_t *ctx, const u32 *w, const int len);
diff --git a/OpenCL/m21500-pure.cl b/OpenCL/m21500-pure.cl
index f0614c07d..0a8cad2f4 100644
--- a/OpenCL/m21500-pure.cl
+++ b/OpenCL/m21500-pure.cl
@@ -30,7 +30,7 @@ typedef struct pbkdf2_sha1_tmp
typedef struct pbkdf2_sha1
{
- u32 salt_buf[4];
+ u32 salt_buf[5];
} pbkdf2_sha1_t;
diff --git a/src/Makefile b/src/Makefile
index c61078a4a..a0fc8e842 100644
--- a/src/Makefile
+++ b/src/Makefile
@@ -4,7 +4,7 @@
##
SHARED := 0
-DEBUG := 0
+DEBUG := 1
PRODUCTION := 0
PRODUCTION_VERSION := v5.1.0
ENABLE_BRAIN := 1
diff --git a/src/modules/module_21500.c b/src/modules/module_21500.c
index cd6bbec6d..4afb4d687 100644
--- a/src/modules/module_21500.c
+++ b/src/modules/module_21500.c
@@ -16,7 +16,7 @@ static const u32 DGST_POS1 = 15;
static const u32 DGST_POS2 = 6;
static const u32 DGST_POS3 = 7;
static const u32 DGST_SIZE = DGST_SIZE_8_8;
-static const u32 HASH_CATEGORY = HASH_CATEGORY_GENERIC_KDF;
+static const u32 HASH_CATEGORY = HASH_CATEGORY_EAS;
static const char *HASH_NAME = "SolarWinds Orion";
static const u64 KERN_TYPE = 21500;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
@@ -58,10 +58,12 @@ typedef struct pbkdf2_sha1_tmp
typedef struct pbkdf2_sha1
{
- u32 salt_buf[64];
+ u32 salt_buf[5];
} pbkdf2_sha1_t;
+static const u32 ROUNDS_SOLARWINDS_ORION = 1000;
+
static const char *SIGNATURE_SOLARWINDS_ORION = "$solarwinds$0$";
u64 module_esalt_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
@@ -134,16 +136,13 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
// iter
- const u32 iter = 1000;
-
- salt->salt_iter = iter - 1;
+ salt->salt_iter = ROUNDS_SOLARWINDS_ORION - 1;
// salt
- char *salt_pos = (char *) token.buf[1];
- int salt_len = token.len[1];
+ const u8 *salt_pos = token.buf[1];
- if (salt_len > 16) return (PARSER_SALT_LENGTH);
+ int salt_len = token.len[1];
char custom_salt[17];
@@ -164,18 +163,10 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
salt_len = 8;
}
- salt_pos = custom_salt;
-
- memcpy (pbkdf2_sha1->salt_buf, salt_pos, salt_len);
+ memcpy (pbkdf2_sha1->salt_buf, custom_salt, salt_len);
salt->salt_len = salt_len;
- salt->salt_buf[0] = pbkdf2_sha1->salt_buf[0];
- salt->salt_buf[1] = pbkdf2_sha1->salt_buf[1];
- salt->salt_buf[2] = pbkdf2_sha1->salt_buf[2];
- salt->salt_buf[3] = pbkdf2_sha1->salt_buf[3];
- salt->salt_buf[4] = salt->salt_iter;
-
// hash
const u8 *hash_pos = token.buf[2];
diff --git a/tools/test_modules/m21500.pm b/tools/test_modules/m21500.pm
index 4579efa33..209a9c16b 100644
--- a/tools/test_modules/m21500.pm
+++ b/tools/test_modules/m21500.pm
@@ -32,9 +32,7 @@ sub module_generate_hash
my $key_b64 = encode_base64 (sha512($key), "");
- my $salt_b64 = encode_base64 ($salt, "");
-
- my $hash = sprintf ("sha1:%i:%s:%s", $iter, $salt_b64, $key_b64);
+ my $hash = sprintf ("\$solarwinds\$0\$%s\$%s", $salt, $key_b64);
return $hash;
}
@@ -43,38 +41,31 @@ sub module_verify_hash
{
my $line = shift;
- return unless (substr ($line, 0, 5) eq 'sha1:');
+ my ($hash, $word) = split (':', $line);
- # iterations
- my $index1 = index ($line, ":", 5);
+ return unless defined $hash;
+ return unless defined $word;
- return if $index1 < 1;
+ my @data = split ('\$', $hash);
- my $iter = substr ($line, 5, $index1 - 5);
+ return unless scalar @data == 4;
- # salt
+ shift @data;
- my $index2 = index ($line, ":", $index1 + 1);
+ my $signature = shift @data;
+ my $sig_dec = shift @data;
+ my $salt = shift @data;
+ my $hash_b64 = shift @data;
+ my $hash_raw = decode_base64 ($hash_b64);
- return if $index2 < 1;
-
- my $salt = substr ($line, $index1 + 1, $index2 - $index1 - 1);
-
- $salt = decode_base64 ($salt);
-
- # end of digest
-
- $index1 = index ($line, ":", $index2 + 1);
-
- return if $index1 < 1;
-
- # word / hash
-
- my $word = substr ($line, $index1 + 1);
+ return unless ($signature eq "solarwinds");
+ return unless ($sig_dec eq "0");
+ return unless (length ($salt) > 16);
+ return unless (length ($hash_raw) != 128);
my $word_packed = pack_if_HEX_notation ($word);
- my $new_hash = module_generate_hash ($word_packed, $salt, $iter);
+ my $new_hash = module_generate_hash ($word_packed, $salt);
return ($new_hash, $word);
}
From f1ed35a5f60e515cf7cbfac74fa24694a93d4d72 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Tue, 6 Aug 2019 18:30:37 -0700
Subject: [PATCH 094/113] tools.sh: Fix remaining quote warnings
---
tools/test.sh | 657 +++++++++++++++++++++++++-------------------------
1 file changed, 329 insertions(+), 328 deletions(-)
diff --git a/tools/test.sh b/tools/test.sh
index 018687de3..f19f4438d 100755
--- a/tools/test.sh
+++ b/tools/test.sh
@@ -26,14 +26,14 @@ LUKS_MODE="14600"
# missing hash types: 5200
-HASH_TYPES=$(ls ${TDIR}/test_modules/*.pm | sed -E 's/.*m0*([0-9]+).pm/\1/')
+HASH_TYPES=$(ls "${TDIR}"/test_modules/*.pm | sed -E 's/.*m0*([0-9]+).pm/\1/')
HASH_TYPES="${HASH_TYPES} ${TC_MODES} ${VC_MODES} ${LUKS_MODE}"
HASH_TYPES=$(echo -n "${HASH_TYPES}" | tr ' ' '\n' | sort -u -n | tr '\n' ' ')
VECTOR_WIDTHS="1 2 4 8 16"
-HASHFILE_ONLY=$(grep -l OPTS_TYPE_BINARY_HASHFILE ${TDIR}/../src/modules/module_*.c | sed -E 's/.*module_0*([0-9]+).c/\1/' | tr '\n' ' ')
-SLOW_ALGOS=$(grep -l ATTACK_EXEC_OUTSIDE_KERNEL ${TDIR}/../src/modules/module_*.c | sed -E 's/.*module_0*([0-9]+).c/\1/' | tr '\n' ' ')
+HASHFILE_ONLY=$(grep -l OPTS_TYPE_BINARY_HASHFILE "${TDIR}"/../src/modules/module_*.c | sed -E 's/.*module_0*([0-9]+).c/\1/' | tr '\n' ' ')
+SLOW_ALGOS=$(grep -l ATTACK_EXEC_OUTSIDE_KERNEL "${TDIR}"/../src/modules/module_*.c | sed -E 's/.*module_0*([0-9]+).c/\1/' | tr '\n' ' ')
OUTD="test_$(date +%s)"
@@ -148,7 +148,7 @@ mask_7[31]="?d?d?d?d?d?d?d?d0000000"
function is_in_array()
{
for e in "${@:2}"; do
- [[ "$e" == "$1" ]] && return 0
+ [ "$e" = "$1" ] && return 0
done
return 1
}
@@ -168,14 +168,14 @@ function init()
rm -rf "${OUTD}/${hash_type}.sh" "${OUTD}/${hash_type}_passwords.txt" "${OUTD}/${hash_type}_hashes.txt"
# Exclude TrueCrypt and VeraCrypt testing modes
- if is_in_array "${hash_type}" "${TC_MODES}"; then
+ if is_in_array "${hash_type}" ${TC_MODES}; then
return 0
fi
- if is_in_array "${hash_type} ${VC_MODES}"; then
+ if is_in_array "${hash_type}" ${VC_MODES}; then
return 0
fi
- if [[ ${hash_type} -eq ${LUKS_MODE} ]]; then
+ if [ "${hash_type}" -eq ${LUKS_MODE} ]; then
luks_tests_folder="${TDIR}/luks_tests/"
@@ -237,20 +237,20 @@ function init()
# create list of password and hashes of same type
cmd_file=${OUTD}/${hash_type}.sh
- grep " ${hash_type} '" ${OUTD}/all.sh > ${cmd_file} 2>/dev/null
+ grep " ${hash_type} '" "${OUTD}/all.sh" > "${cmd_file}" 2>/dev/null
# create separate list of password and hashes
- sed 's/^echo *|.*$//' ${cmd_file} | awk '{print $2}' > ${OUTD}/${hash_type}_passwords.txt
- sed 's/^echo *|/echo "" |/' ${cmd_file} | awk '{print $10}' | cut -d"'" -f2 > ${OUTD}/${hash_type}_hashes.txt
+ sed 's/^echo *|.*$//' "${cmd_file}" | awk '{print $2}' > "${OUTD}/${hash_type}_passwords.txt"
+ sed 's/^echo *|/echo "" |/' "${cmd_file}" | awk '{print $10}' | cut -d"'" -f2 > "${OUTD}/${hash_type}_hashes.txt"
if [ "${hash_type}" -eq 10300 ]; then
#cat ${OUTD}/${hash_type}.sh | cut -d' ' -f11- | cut -d"'" -f2 > ${OUTD}/${hash_type}_hashes.txt
- cut -d"'" -f2 ${OUTD}/${hash_type}.sh > ${OUTD}/${hash_type}_hashes.txt
+ cut -d"'" -f2 "${OUTD}/${hash_type}.sh" > "${OUTD}/${hash_type}_hashes.txt"
fi
# truncate dicts
- rm -rf ${OUTD}/${hash_type}_dict1 ${OUTD}/${hash_type}_dict2
- touch ${OUTD}/${hash_type}_dict1 ${OUTD}/${hash_type}_dict2
+ rm -rf "${OUTD}/${hash_type}_dict1" "${OUTD}/${hash_type}_dict2"
+ touch "${OUTD}/${hash_type}_dict1" "${OUTD}/${hash_type}_dict2"
# minimum password length
@@ -296,7 +296,7 @@ function init()
p1=$((p1 + min_offset))
p0=$((p0 + min_offset))
- if [ "${p1}" -gt ${pass_len} ]; then
+ if [ "${p1}" -gt "${pass_len}" ]; then
p1=${pass_len}
p0=$((p1 - 1))
@@ -304,21 +304,21 @@ function init()
fi
# add splitted password to dicts
- echo ${pass} | cut -c -${p0} >> ${OUTD}/${hash_type}_dict1
- echo ${pass} | cut -c ${p1}- >> ${OUTD}/${hash_type}_dict2
+ echo "${pass}" | cut -c -${p0} >> "${OUTD}/${hash_type}_dict1"
+ echo "${pass}" | cut -c ${p1}- >> "${OUTD}/${hash_type}_dict2"
elif [ "${pass_len}" -eq 1 ]; then
- echo ${pass} >> ${OUTD}/${hash_type}_dict1
- echo >> ${OUTD}/${hash_type}_dict2
+ echo "${pass}" >> "${OUTD}/${hash_type}_dict1"
+ echo >> "${OUTD}/${hash_type}_dict2"
else
- echo >> ${OUTD}/${hash_type}_dict1
- echo >> ${OUTD}/${hash_type}_dict2
+ echo >> "${OUTD}/${hash_type}_dict1"
+ echo >> "${OUTD}/${hash_type}_dict2"
fi
fi
((i++))
- done 9< ${OUTD}/${hash_type}_passwords.txt
+ done 9< "${OUTD}/${hash_type}_passwords.txt"
min_len=0
@@ -337,24 +337,24 @@ function init()
fi
# generate multiple pass/hash foreach len (2 to 8)
- if [ ${MODE} -ge 1 ]; then
+ if [ "${MODE}" -ge 1 ]; then
for ((i = 2; i < 9; i++)); do
cmd_file=${OUTD}/${hash_type}_multi_${i}.txt
- rm -rf ${cmd_file} ${OUTD}/${hash_type}_passwords_multi_${i}.txt ${OUTD}/${hash_type}_hashes_multi_${i}.txt
- rm -rf ${OUTD}/${hash_type}_dict1_multi_${i} ${OUTD}/${hash_type}_dict2_multi_${i}
- touch ${OUTD}/${hash_type}_dict1_multi_${i} ${OUTD}/${hash_type}_dict2_multi_${i}
+ rm -rf "${cmd_file}" "${OUTD}/${hash_type}_passwords_multi_${i}.txt" "${OUTD}/${hash_type}_hashes_multi_${i}.txt"
+ rm -rf "${OUTD}/${hash_type}_dict1_multi_${i}" "${OUTD}/${hash_type}_dict2_multi_${i}"
+ touch "${OUTD}/${hash_type}_dict1_multi_${i}" "${OUTD}/${hash_type}_dict2_multi_${i}"
- perl tools/test.pl single ${hash_type} ${i} > ${cmd_file}
+ perl tools/test.pl single "${hash_type}" ${i} > "${cmd_file}"
- sed 's/^echo *|.*$//' ${cmd_file} | awk '{print $2}' > ${OUTD}/${hash_type}_passwords_multi_${i}.txt
- sed 's/^echo *|/echo "" |/' ${cmd_file} | awk '{print $10}' | cut -d"'" -f2 > ${OUTD}/${hash_type}_hashes_multi_${i}.txt
+ sed 's/^echo *|.*$//' "${cmd_file}" | awk '{print $2}' > "${OUTD}/${hash_type}_passwords_multi_${i}.txt"
+ sed 's/^echo *|/echo "" |/' "${cmd_file}" | awk '{print $10}' | cut -d"'" -f2 > "${OUTD}/${hash_type}_hashes_multi_${i}.txt"
if [ "${hash_type}" -eq 10300 ]; then
#cat ${OUTD}/${hash_type}_multi_${i}.txt | cut -d' ' -f11- | cut -d"'" -f2 > ${OUTD}/${hash_type}_hashes_multi_${i}.txt
- cut -d"'" -f2 ${OUTD}/${hash_type}_multi_${i}.txt > ${OUTD}/${hash_type}_hashes_multi_${i}.txt
+ cut -d"'" -f2 "${OUTD}/${hash_type}_multi_${i}.txt" > "${OUTD}/${hash_type}_hashes_multi_${i}.txt"
fi
# split password, 'i' is the len
@@ -367,10 +367,10 @@ function init()
while read -r -u 9 pass; do
# add splitted password to dicts
- echo ${pass} | cut -c -${p0} >> ${OUTD}/${hash_type}_dict1_multi_${i}
- echo ${pass} | cut -c ${p1}- >> ${OUTD}/${hash_type}_dict2_multi_${i}
+ echo "${pass}" | cut -c -${p0} >> "${OUTD}/${hash_type}_dict1_multi_${i}"
+ echo "${pass}" | cut -c ${p1}- >> "${OUTD}/${hash_type}_dict2_multi_${i}"
- done 9< ${OUTD}/${hash_type}_passwords_multi_${i}.txt
+ done 9< "${OUTD}/${hash_type}_passwords_multi_${i}.txt"
done
@@ -383,33 +383,33 @@ function status()
((cnt++))
- if [ ${RET} -ne 0 ]; then
+ if [ "${RET}" -ne 0 ]; then
case ${RET} in
1)
- if ! is_in_array ${hash_type} ${NEVER_CRACK_ALGOS}; then
+ if ! is_in_array "${hash_type}" ${NEVER_CRACK_ALGOS}; then
- echo "password not found, cmdline : ${CMD}" >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "password not found, cmdline : ${CMD}" >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
((e_nf++))
fi
;;
4)
- echo "timeout reached, cmdline : ${CMD}" >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "timeout reached, cmdline : ${CMD}" >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
((e_to++))
;;
10)
if [ "${pass_only}" -eq 1 ]; then
- echo "plains not found in output, cmdline : ${CMD}" >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "plains not found in output, cmdline : ${CMD}" >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
else
- echo "hash:plains not matched in output, cmdline : ${CMD}" >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "hash:plains not matched in output, cmdline : ${CMD}" >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.tx"t
fi
((e_nm++))
;;
*)
- echo "! unhandled return code ${RET}, cmdline : ${CMD}" >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "! unhandled return code ${RET}, cmdline : ${CMD}" >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
echo "! unhandled return code, see ${OUTD}/logfull.txt for details."
((e_nf++))
;;
@@ -421,25 +421,25 @@ function attack_0()
{
file_only=0
- if is_in_array ${hash_type} ${FILE_BASED_ALGOS}; then
+ if is_in_array "${hash_type}" ${FILE_BASED_ALGOS}; then
file_only=1
fi
# single hash
- if [ ${MODE} -ne 1 ]; then
+ if [ "${MODE}" -ne 1 ]; then
e_to=0
e_nf=0
e_nm=0
cnt=0
- echo "> Testing hash type $hash_type with attack mode 0, markov ${MARKOV}, single hash, device-type ${TYPE}, vector-width ${VECTOR}." >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type $hash_type with attack mode 0, markov ${MARKOV}, single hash, device-type ${TYPE}, vector-width ${VECTOR}." >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
max=32
- if is_in_array ${hash_type} ${TIMEOUT_ALGOS}; then
+ if is_in_array "${hash_type}" ${TIMEOUT_ALGOS}; then
max=12
@@ -467,7 +467,7 @@ function attack_0()
if [ "${file_only}" -eq 1 ]; then
temp_file="${OUTD}/${hash_type}_filebased_only_temp.txt"
- echo ${hash} | base64 -d > ${temp_file}
+ echo "${hash}" | base64 -d > "${temp_file}"
hash="${temp_file}"
fi
@@ -480,7 +480,7 @@ function attack_0()
CMD="echo ${pass} | ./${BIN} ${OPTS} -a 0 -m ${hash_type} '${hash}'"
- echo -n "[ len $((i + 1)) ] " >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo -n "[ len $((i + 1)) ] " >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
output=$(echo "${pass}" | ./${BIN} ${OPTS} -a 0 -m ${hash_type} "${hash}" 2>&1)
@@ -488,11 +488,11 @@ function attack_0()
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
if [ "${ret}" -eq 0 ]; then
- if [ ${pass_only} -eq 1 ]; then
+ if [ "${pass_only}" -eq 1 ]; then
search=":${pass}"
else
search="${hash}:${pass}"
@@ -512,7 +512,7 @@ function attack_0()
i=$((i + 1))
- done 9< ${OUTD}/${hash_type}.sh
+ done 9< "${OUTD}/${hash_type}.sh"
msg="OK"
@@ -531,14 +531,14 @@ function attack_0()
fi
# multihash
- if [ ${MODE} -ne 0 ]; then
+ if [ "${MODE}" -ne 0 ]; then
e_to=0
e_nf=0
e_nm=0
cnt=0
- echo "> Testing hash type $hash_type with attack mode 0, markov ${MARKOV}, multi hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type $hash_type with attack mode 0, markov ${MARKOV}, multi hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
hash_file=${OUTD}/${hash_type}_hashes.txt
@@ -547,15 +547,15 @@ function attack_0()
if [ "${file_only}" -eq 1 ]; then
temp_file="${OUTD}/${hash_type}_filebased_only_temp.txt"
- rm -f ${temp_file}
+ rm -f "${temp_file}"
hash_file=${temp_file}
while read -r base64_hash; do
- echo -n ${base64_hash} | base64 -d >> ${temp_file}
+ echo -n "${base64_hash}" | base64 -d >> "${temp_file}"
- done < ${OUTD}/${hash_type}_hashes.txt
+ done < "${OUTD}/${hash_type}_hashes.txt"
fi
@@ -565,7 +565,7 @@ function attack_0()
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
if [ "${ret}" -eq 0 ]; then
@@ -573,9 +573,9 @@ function attack_0()
while read -r -u 9 hash; do
- pass=$(sed -n ${i}p ${OUTD}/${hash_type}_passwords.txt)
+ pass=$(sed -n ${i}p "${OUTD}/${hash_type}_passwords.txt")
- if [ ${pass_only} -eq 1 ]; then
+ if [ "${pass_only}" -eq 1 ]; then
search=":${pass}"
else
search="${hash}:${pass}"
@@ -593,7 +593,7 @@ function attack_0()
i=$((i + 1))
- done 9< ${OUTD}/${hash_type}_hashes.txt
+ done 9< "${OUTD}/${hash_type}_hashes.txt"
fi
@@ -620,14 +620,14 @@ function attack_1()
{
file_only=0
- if is_in_array ${hash_type} ${FILE_BASED_ALGOS}; then
+ if is_in_array "${hash_type}" ${FILE_BASED_ALGOS}; then
file_only=1
fi
# single hash
- if [ ${MODE} -ne 1 ]; then
+ if [ "${MODE}" -ne 1 ]; then
e_to=0
e_nf=0
@@ -646,7 +646,7 @@ function attack_1()
min=0
fi
- echo "> Testing hash type $hash_type with attack mode 1, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type $hash_type with attack mode 1, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
i=1
while read -r -u 9 hash; do
@@ -655,7 +655,7 @@ function attack_1()
if [ "${file_only}" -eq 1 ]; then
temp_file="${OUTD}/${hash_type}_filebased_only_temp.txt"
- echo ${hash} | base64 -d > ${temp_file}
+ echo "${hash}" | base64 -d > "${temp_file}"
hash="${temp_file}"
fi
@@ -670,9 +670,9 @@ function attack_1()
dict2="${OUTD}/${hash_type}_dict2"
if [ "${hash_type}" -eq 20510 ]; then # special case for PKZIP Master Key
- line_dict1=$(sed -n ${line_nr}p ${dict1})
- line_dict2=$(sed -n ${line_nr}p ${dict2})
- line_num=$(wc -l ${dict1} | sed -E 's/ *([0-9]+) .*$/\1/')
+ line_dict1=$(sed -n ${line_nr}p "${dict1}")
+ line_dict2=$(sed -n ${line_nr}p "${dict2}")
+ line_num=$(wc -l "${dict1}" | sed -E 's/ *([0-9]+) .*$/\1/')
line_dict1_orig=${line_dict1}
line_dict2_orig=${line_dict2}
@@ -702,37 +702,37 @@ function attack_1()
tmp_file="${dict1}_mod"
- head -n $((line_nr - 1)) ${dict1} > ${tmp_file}
- echo "${line_dict1}" >> ${tmp_file}
- tail -n $((line_num - line_nr - 1)) ${dict1} >> ${tmp_file}
+ head -n $((line_nr - 1)) "${dict1}" > "${tmp_file}"
+ echo "${line_dict1}" >> "${tmp_file}"
+ tail -n $((line_num - line_nr - 1)) "${dict1}" >> "${tmp_file}"
dict1=${tmp_file}
tmp_file="${dict2}_mod"
- head -n $((line_nr - 1)) ${dict2} > ${tmp_file}
- echo "${line_dict2}" >> ${tmp_file}
- tail -n $((line_num - line_nr - 1)) ${dict2} >> ${tmp_file}
+ head -n $((line_nr - 1)) "${dict2}" > "${tmp_file}"
+ echo "${line_dict2}" >> "${tmp_file}"
+ tail -n $((line_num - line_nr - 1)) "${dict2}" >> "${tmp_file}"
dict2=${tmp_file}
fi
CMD="./${BIN} ${OPTS} -a 1 -m ${hash_type} '${hash}' ${dict1} ${dict2}"
- echo -n "[ len $i ] " >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo -n "[ len $i ] " >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
output=$(./${BIN} ${OPTS} -a 1 -m ${hash_type} "${hash}" ${dict1} ${dict2} 2>&1)
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
if [ "${ret}" -eq 0 ]; then
- line_dict1=$(sed -n ${line_nr}p ${OUTD}/${hash_type}_dict1)
- line_dict2=$(sed -n ${line_nr}p ${OUTD}/${hash_type}_dict2)
+ line_dict1=$(sed -n ${line_nr}p "${OUTD}/${hash_type}_dict1")
+ line_dict2=$(sed -n ${line_nr}p "${OUTD}/${hash_type}_dict2")
- if [ ${pass_only} -eq 1 ]; then
+ if [ "${pass_only}" -eq 1 ]; then
search=":${line_dict1}${line_dict2}"
else
search="${hash}:${line_dict1}${line_dict2}"
@@ -754,7 +754,7 @@ function attack_1()
((i++))
- done 9< ${OUTD}/${hash_type}_hashes.txt
+ done 9< "${OUTD}/${hash_type}_hashes.txt"
msg="OK"
@@ -773,7 +773,7 @@ function attack_1()
fi
# multihash
- if [ ${MODE} -ne 0 ]; then
+ if [ "${MODE}" -ne 0 ]; then
# no multi hash checks for these modes (because we only have 1 hash for each of them)
@@ -794,42 +794,42 @@ function attack_1()
offset=7
- if [ ${hash_type} -eq 5800 ]; then
+ if [ "${hash_type}" -eq 5800 ]; then
offset=6
- elif [ ${hash_type} -eq 3000 ]; then
+ elif [ "${hash_type}" -eq 3000 ]; then
offset=6
fi
hash_file=${OUTD}/${hash_type}_multihash_combi.txt
- tail -n ${offset} ${OUTD}/${hash_type}_hashes.txt > ${hash_file}
+ tail -n ${offset} "${OUTD}/${hash_type}_hashes.txt" > "${hash_file}"
# if file_only -> decode all base64 "hashes" and put them in the temporary file
if [ "${file_only}" -eq 1 ]; then
temp_file="${OUTD}/${hash_type}_filebased_only_temp.txt"
- rm -f ${temp_file}
+ rm -f "${temp_file}"
hash_file=${temp_file}
while read -r base64_hash; do
- echo -n ${base64_hash} | base64 -d >> ${temp_file}
+ echo -n "${base64_hash}" | base64 -d >> "${temp_file}"
- done < ${OUTD}/${hash_type}_multihash_combi.txt
+ done < "${OUTD}/${hash_type}_multihash_combi.txt"
fi
CMD="./${BIN} ${OPTS} -a 1 -m ${hash_type} ${hash_file} ${OUTD}/${hash_type}_dict1 ${OUTD}/${hash_type}_dict2"
- echo "> Testing hash type $hash_type with attack mode 1, markov ${MARKOV}, multi hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type $hash_type with attack mode 1, markov ${MARKOV}, multi hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
output=$(./${BIN} ${OPTS} -a 1 -m ${hash_type} ${hash_file} ${OUTD}/${hash_type}_dict1 ${OUTD}/${hash_type}_dict2 2>&1)
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
if [ "${ret}" -eq 0 ]; then
@@ -843,10 +843,10 @@ function attack_1()
line_nr=$((offset - i))
fi
- line_dict1=$(tail -n ${line_nr} ${OUTD}/${hash_type}_dict1 | head -1)
- line_dict2=$(tail -n ${line_nr} ${OUTD}/${hash_type}_dict2 | head -1)
+ line_dict1=$(tail -n ${line_nr} "${OUTD}/${hash_type}_dict1" | head -1)
+ line_dict2=$(tail -n ${line_nr} "${OUTD}/${hash_type}_dict2" | head -1)
- if [ ${pass_only} -eq 1 ]; then
+ if [ "${pass_only}" -eq 1 ]; then
search=":${line_dict1}${line_dict2}"
else
search="${hash}:${line_dict1}${line_dict2}"
@@ -864,7 +864,7 @@ function attack_1()
i=$((i + 1))
- done 9< ${OUTD}/${hash_type}_multihash_combi.txt
+ done 9< "${OUTD}/${hash_type}_multihash_combi.txt"
fi
@@ -891,21 +891,21 @@ function attack_3()
{
file_only=0
- if is_in_array ${hash_type} ${FILE_BASED_ALGOS}; then
+ if is_in_array "${hash_type}" ${FILE_BASED_ALGOS}; then
file_only=1
fi
# single hash
- if [ ${MODE} -ne 1 ]; then
+ if [ "${MODE}" -ne 1 ]; then
e_to=0
e_nf=0
e_nm=0
cnt=0
- echo "> Testing hash type $hash_type with attack mode 3, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type $hash_type with attack mode 3, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
max=8
@@ -931,7 +931,7 @@ function attack_3()
if [ "${i}" -gt 6 ]; then
- if is_in_array ${hash_type} ${TIMEOUT_ALGOS}; then
+ if is_in_array "${hash_type}" ${TIMEOUT_ALGOS}; then
break
@@ -942,7 +942,7 @@ function attack_3()
if [ "${file_only}" -eq 1 ]; then
temp_file="${OUTD}/${hash_type}_filebased_only_temp.txt"
- echo ${hash} | base64 -d > ${temp_file}
+ echo "${hash}" | base64 -d > "${temp_file}"
hash="${temp_file}"
fi
@@ -952,7 +952,7 @@ function attack_3()
dict="${OUTD}/${hash_type}_passwords.txt"
- pass=$(sed -n ${i}p ${dict})
+ pass=$(sed -n ${i}p "${dict}")
# passwords can't be smaller than mask in -a 3 = mask attack
@@ -961,7 +961,7 @@ function attack_3()
continue
fi
- pass_part_2=$(echo -n ${pass} | cut -b $((i + 1))-)
+ pass_part_2=$(echo -n "${pass}" | cut -b $((i + 1))-)
mask=""
@@ -1000,19 +1000,19 @@ function attack_3()
CMD="./${BIN} ${OPTS} -a 3 -m ${hash_type} '${hash}' ${mask}"
- echo -n "[ len $i ] " >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo -n "[ len $i ] " >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
output=$(./${BIN} ${OPTS} -a 3 -m ${hash_type} "${hash}" ${mask} 2>&1)
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
if [ "${ret}" -eq 0 ]; then
- line_dict=$(sed -n ${i}p ${dict})
+ line_dict=$(sed -n ${i}p "${dict}")
- if [ ${pass_only} -eq 1 ]; then
+ if [ "${pass_only}" -eq 1 ]; then
search=":${line_dict}"
else
search="${hash}:${line_dict}"
@@ -1034,7 +1034,7 @@ function attack_3()
((i++))
- done 9< ${OUTD}/${hash_type}_hashes.txt
+ done 9< "${OUTD}/${hash_type}_hashes.txt"
msg="OK"
@@ -1053,7 +1053,7 @@ function attack_3()
fi
# multihash
- if [ ${MODE} -ne 0 ]; then
+ if [ "${MODE}" -ne 0 ]; then
# no multi hash checks for these modes (because we only have 1 hash for each of them)
@@ -1074,7 +1074,7 @@ function attack_3()
increment_max=8
- if is_in_array ${hash_type} ${TIMEOUT_ALGOS}; then
+ if is_in_array "${hash_type}" ${TIMEOUT_ALGOS}; then
increment_max=5
@@ -1097,46 +1097,46 @@ function attack_3()
if [ "${file_only}" -eq 1 ]; then
temp_file="${OUTD}/${hash_type}_filebased_only_temp.txt"
- rm -f ${temp_file}
+ rm -f "${temp_file}"
hash_file=${temp_file}
while read -r base64_hash; do
- echo -n ${base64_hash} | base64 -d >> ${temp_file}
+ echo -n "${base64_hash}" | base64 -d >> "${temp_file}"
- done < ${OUTD}/${hash_type}_multihash_bruteforce.txt
+ done < "${OUTD}/${hash_type}_multihash_bruteforce.txt"
fi
hash_file=${OUTD}/${hash_type}_multihash_bruteforce.txt
- tail_hashes=$(awk "length >= ${increment_min} && length <= ${increment_max}" ${OUTD}/${hash_type}_passwords.txt | wc -l)
- head_hashes=$(awk "length <= ${increment_max}" ${OUTD}/${hash_type}_passwords.txt | wc -l)
+ tail_hashes=$(awk "length >= ${increment_min} && length <= ${increment_max}" "${OUTD}/${hash_type}_passwords.txt" | wc -l)
+ head_hashes=$(awk "length <= ${increment_max}" "${OUTD}/${hash_type}_passwords.txt" | wc -l)
# in very rare cases (e.g. without -O and long passwords) we need to use .hcmask files with the passwords in it
# otherwise there are no good masks we can test for such long passwords
need_hcmask=0
- if [ ${tail_hashes} -gt ${head_hashes} ]; then
+ if [ "${tail_hashes}" -gt "${head_hashes}" ]; then
need_hcmask=1
fi
- if [ ${tail_hashes} -lt 1 ]; then
+ if [ "${tail_hashes}" -lt 1 ]; then
need_hcmask=1
fi
if [ ${need_hcmask} -eq 0 ]; then
- head -n ${head_hashes} ${OUTD}/${hash_type}_hashes.txt | tail -n ${tail_hashes} > ${hash_file}
+ head -n "${head_hashes}" "${OUTD}/${hash_type}_hashes.txt" | tail -n "${tail_hashes}" > "${hash_file}"
else
- tail_hashes=$(awk "length >= ${increment_min}" ${OUTD}/${hash_type}_passwords.txt | wc -l)
+ tail_hashes=$(awk "length >= ${increment_min}" "${OUTD}/${hash_type}_passwords.txt" | wc -l)
- if [ ${tail_hashes} -lt 1 ]; then
+ if [ "${tail_hashes}" -lt 1 ]; then
return
fi
- tail -n ${tail_hashes} ${OUTD}/${hash_type}_hashes.txt > ${hash_file}
+ tail -n "${tail_hashes}" "${OUTD}/${hash_type}_hashes.txt" > "${hash_file}"
fi
mask_pos=8
@@ -1153,7 +1153,7 @@ function attack_3()
mask=${mask_3[${mask_pos}]}
else
- num_hashes=$(wc -l < ${OUTD}/${hash_type}_hashes.txt)
+ num_hashes=$(wc -l < "${OUTD}/${hash_type}_hashes.txt")
cracks_offset=$((num_hashes - tail_hashes))
mask=${OUTD}/${hash_type}_passwords.txt # fake hcmask file (i.e. the original dict)
@@ -1190,7 +1190,7 @@ function attack_3()
while read -r -u 9 hash; do
- pass=$(sed -n ${i}p ${OUTD}/${hash_type}_passwords.txt)
+ pass=$(sed -n ${i}p "${OUTD}/${hash_type}_passwords.txt")
# charset 1
char=$(echo "${pass}" | cut -b ${charset_1_pos})
@@ -1210,7 +1210,7 @@ function attack_3()
i=$((i + 1))
- done 9< ${OUTD}/${hash_type}_multihash_bruteforce.txt
+ done 9< "${OUTD}/${hash_type}_multihash_bruteforce.txt"
# just make sure that all custom charset fields are initialized
@@ -1275,27 +1275,28 @@ function attack_3()
while read -r -u 9 hash; do
- pass=$(sed -n ${i}p ${OUTD}/${hash_type}_passwords.txt)
+ pass=$(sed -n ${i}p "${OUTD}/${hash_type}_passwords.txt")
# charset 1
char=$(echo "${pass}" | cut -b ${charset_1_pos})
charset_1=$(echo -e "${charset_1}\n${char}")
+ charset_1=$(printf "%s\n%s\n" "${charset_1}" "${char}")
# charset 2
char=$(echo "${pass}" | cut -b ${charset_2_pos})
- charset_2=$(echo -e "${charset_2}\n${char}")
+ charset_2=$(printf "%s\n%s\n" "${charset_2}" "${char}")
# charset 3
char=$(echo "${pass}" | cut -b ${charset_3_pos})
- charset_3=$(echo -e "${charset_3}\n${char}")
+ charset_3=$(printf "%s\n%s\n" "${charset_3}" "${char}")
# charset 4
char=$(echo "${pass}" | cut -b ${charset_4_pos})
- charset_4=$(echo -e "${charset_4}\n${char}")
+ charset_4=$(printf "%s\n%s\n" "${charset_4}" "${char}")
i=$((i + 1))
- done 9< ${OUTD}/${hash_type}_multihash_bruteforce.txt
+ done 9< "${OUTD}/${hash_type}_multihash_bruteforce.txt"
# just make sure that all custom charset fields are initialized
@@ -1345,13 +1346,13 @@ function attack_3()
CMD="./${BIN} ${OPTS} -a 3 -m ${hash_type} ${increment_charset_opts} ${hash_file} ${mask} "
- echo "> Testing hash type $hash_type with attack mode 3, markov ${MARKOV}, multi hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type $hash_type with attack mode 3, markov ${MARKOV}, multi hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
output=$(./${BIN} ${OPTS} -a 3 -m ${hash_type} ${increment_charset_opts} ${hash_file} ${mask} 2>&1)
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
if [ "${ret}" -eq 0 ]; then
@@ -1360,9 +1361,9 @@ function attack_3()
while read -r -u 9 hash; do
line_nr=$((i + cracks_offset))
- pass=$(sed -n ${line_nr}p ${OUTD}/${hash_type}_passwords.txt)
+ pass=$(sed -n ${line_nr}p "${OUTD}/${hash_type}_passwords.txt")
- if [ ${pass_only} -eq 1 ]; then
+ if [ "${pass_only}" -eq 1 ]; then
search=":${pass}"
else
search="${hash}:${pass}"
@@ -1380,7 +1381,7 @@ function attack_3()
i=$((i + 1))
- done 9< ${OUTD}/${hash_type}_multihash_bruteforce.txt
+ done 9< "${OUTD}/${hash_type}_multihash_bruteforce.txt"
fi
@@ -1407,21 +1408,21 @@ function attack_6()
{
file_only=0
- if is_in_array ${hash_type} ${FILE_BASED_ALGOS}; then
+ if is_in_array "${hash_type}" ${FILE_BASED_ALGOS}; then
file_only=1
fi
# single hash
- if [ ${MODE} -ne 1 ]; then
+ if [ "${MODE}" -ne 1 ]; then
e_to=0
e_nf=0
e_nm=0
cnt=0
- echo "> Testing hash type $hash_type with attack mode 6, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type $hash_type with attack mode 6, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
min=1
max=8
@@ -1453,13 +1454,13 @@ function attack_6()
if [ "${min}" -eq 0 ]; then
- pass_part_1=$(sed -n 1p ${OUTD}/${hash_type}_dict1)
- pass_part_2=$(sed -n 1p ${OUTD}/${hash_type}_dict2)
+ pass_part_1=$(sed -n 1p "${OUTD}/${hash_type}_dict1")
+ pass_part_2=$(sed -n 1p "${OUTD}/${hash_type}_dict2")
pass="${pass_part_1}${pass_part_2}"
- echo -n ${pass} | cut -b -$((mask_offset + 0)) > ${OUTD}/${hash_type}_dict1_custom
- echo -n ${pass} | cut -b $((mask_offset + 1))- > ${OUTD}/${hash_type}_dict2_custom
+ echo -n "${pass}" | cut -b -$((mask_offset + 0)) > "${OUTD}/${hash_type}_dict1_custom"
+ echo -n "${pass}" | cut -b $((mask_offset + 1))- > "${OUTD}/${hash_type}_dict2_custom"
mask_custom=""
@@ -1467,12 +1468,12 @@ function attack_6()
if [ "${hash_type}" -eq 14000 ]; then
- char=$(echo -n ${pass} | cut -b $((i + mask_offset)))
+ char=$(echo -n "${pass}" | cut -b $((i + mask_offset)))
mask_custom="${mask_custom}${char}"
elif [ "${hash_type}" -eq 14100 ]; then
- char=$(echo -n ${pass} | cut -b $((i + mask_offset)))
+ char=$(echo -n "${pass}" | cut -b $((i + mask_offset)))
mask_custom="${mask_custom}${char}"
else
@@ -1492,7 +1493,7 @@ function attack_6()
if [ "${i}" -gt 6 ]; then
- if is_in_array ${hash_type} ${TIMEOUT_ALGOS}; then
+ if is_in_array "${hash_type}" ${TIMEOUT_ALGOS}; then
break
@@ -1505,7 +1506,7 @@ function attack_6()
if [ "${file_only}" -eq 1 ]; then
temp_file="${OUTD}/${hash_type}_filebased_only_temp.txt"
- echo ${hash} | base64 -d > ${temp_file}
+ echo "${hash}" | base64 -d > "${temp_file}"
hash="${temp_file}"
fi
@@ -1515,9 +1516,9 @@ function attack_6()
dict1_a6=${OUTD}/${hash_type}_dict1_a6
- cp ${dict1} ${dict1_a6}
+ cp "${dict1}" "${dict1_a6}"
- pass=$(sed -n ${i}p ${OUTD}/${hash_type}_passwords.txt)
+ pass=$(sed -n ${i}p "${OUTD}/${hash_type}_passwords.txt")
if [ "${hash_type}" -eq 20510 ]; then # special case for PKZIP Master Key
pass=$(echo "${pass}" | cut -b 7-) # skip the first 6 chars
@@ -1528,25 +1529,25 @@ function attack_6()
continue
fi
- echo ${pass} | cut -b -$((${#pass} - i)) >> ${dict1_a6}
+ echo "${pass}" | cut -b -$((${#pass} - i)) >> "${dict1_a6}"
# the block below is just a fancy way to do a "shuf" (or sort -R) because macOS doesn't really support it natively
# we do not really need a shuf, but it's actually better for testing purposes
- rm -f ${dict1_a6}.txt # temporary file
+ rm -f "${dict1_a6}.txt" # temporary file
- line_num=$(wc -l ${dict1_a6} | sed -E 's/ *([0-9]+) .*$/\1/')
+ line_num=$(wc -l "${dict1_a6}" | sed -E 's/ *([0-9]+) .*$/\1/')
- sorted_lines=$(seq 1 ${line_num})
+ sorted_lines=$(seq 1 "${line_num}")
- for lines in $(seq 1 ${line_num}); do
+ for lines in $(seq 1 "${line_num}"); do
random_num=$((RANDOM % line_num))
random_num=$((random_num + 1)) # sed -n [n]p starts counting with 1 (not 0)
random_line=$(echo -n "${sorted_lines}" | sed -n ${random_num}p)
- sed -n ${random_line}p ${dict1_a6} >> ${dict1_a6}.txt
+ sed -n ${random_line}p "${dict1_a6}" >> "${dict1_a6}.txt"
# update the temp list of lines
@@ -1556,7 +1557,7 @@ function attack_6()
done
- mv ${dict1_a6}.txt ${dict1_a6}
+ mv "${dict1_a6}.txt" "${dict1_a6}"
# end of shuf/sort -R
@@ -1569,13 +1570,13 @@ function attack_6()
CMD="./${BIN} ${OPTS} -a 6 -m ${hash_type} '${hash}' ${dict1_a6} ${mask}"
- echo -n "[ len $i ] " >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo -n "[ len $i ] " >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
output=$(./${BIN} ${OPTS} -a 6 -m ${hash_type} "${hash}" ${dict1_a6} ${mask} 2>&1)
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
if [ "${ret}" -eq 0 ]; then
@@ -1585,10 +1586,10 @@ function attack_6()
line_nr=$((i - 1))
fi
- line_dict1=$(sed -n ${line_nr}p ${dict1})
- line_dict2=$(sed -n ${line_nr}p ${dict2})
+ line_dict1=$(sed -n ${line_nr}p "${dict1}")
+ line_dict2=$(sed -n ${line_nr}p "${dict2}")
- if [ ${pass_only} -eq 1 ]; then
+ if [ "${pass_only}" -eq 1 ]; then
search=":${line_dict1}${line_dict2}"
else
search="${hash}:${line_dict1}${line_dict2}"
@@ -1612,7 +1613,7 @@ function attack_6()
((i++))
- done 9< ${OUTD}/${hash_type}_hashes.txt
+ done 9< "${OUTD}/${hash_type}_hashes.txt"
msg="OK"
@@ -1628,13 +1629,13 @@ function attack_6()
echo "[ ${OUTD} ] [ Type ${hash_type}, Attack 6, Mode single, Device-Type ${TYPE}, Vector-Width ${VECTOR} ] > $msg : ${e_nf}/${cnt} not found, ${e_nm}/${cnt} not matched, ${e_to}/${cnt} timeout"
- rm -f ${OUTD}/${hash_type}_dict1_custom
- rm -f ${OUTD}/${hash_type}_dict2_custom
+ rm -f "${OUTD}/${hash_type}_dict1_custom"
+ rm -f "${OUTD}/${hash_type}_dict2_custom"
fi
# multihash
- if [ ${MODE} -ne 0 ]; then
+ if [ "${MODE}" -ne 0 ]; then
# no multi hash checks for these modes (because we only have 1 hash for each of them)
@@ -1655,19 +1656,19 @@ function attack_6()
max=9
- if [ ${hash_type} -eq 2500 ]; then
+ if [ "${hash_type}" -eq 2500 ]; then
max=5
- elif [ ${hash_type} -eq 3000 ]; then
+ elif [ "${hash_type}" -eq 3000 ]; then
max=8
- elif [ ${hash_type} -eq 7700 ] || [ ${hash_type} -eq 7701 ]; then
+ elif [ "${hash_type}" -eq 7700 ] || [ "${hash_type}" -eq 7701 ]; then
max=8
- elif [ ${hash_type} -eq 8500 ]; then
+ elif [ "${hash_type}" -eq 8500 ]; then
max=8
- elif [ ${hash_type} -eq 16800 ]; then
+ elif [ "${hash_type}" -eq 16800 ]; then
max=5
fi
- if is_in_array ${hash_type} ${TIMEOUT_ALGOS}; then
+ if is_in_array "${hash_type}" ${TIMEOUT_ALGOS}; then
max=5
@@ -1688,15 +1689,15 @@ function attack_6()
if [ "${file_only}" -eq 1 ]; then
temp_file="${OUTD}/${hash_type}_filebased_only_temp.txt"
- rm -f ${temp_file}
+ rm -f "${temp_file}"
hash_file=${temp_file}
while read -r base64_hash; do
- echo -n ${base64_hash} | base64 -d >> ${temp_file}
+ echo -n "${base64_hash}" | base64 -d >> "${temp_file}"
- done < ${OUTD}/${hash_type}_hashes_multi_${i}.txt
+ done < "${OUTD}/${hash_type}_hashes_multi_${i}.txt"
fi
@@ -1704,13 +1705,13 @@ function attack_6()
CMD="./${BIN} ${OPTS} -a 6 -m ${hash_type} ${hash_file} ${OUTD}/${hash_type}_dict1_multi_${i} ${mask}"
- echo "> Testing hash type $hash_type with attack mode 6, markov ${MARKOV}, multi hash with word len ${i}." >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type $hash_type with attack mode 6, markov ${MARKOV}, multi hash with word len ${i}." >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
output=$(./${BIN} ${OPTS} -a 6 -m ${hash_type} ${hash_file} ${OUTD}/${hash_type}_dict1_multi_${i} ${mask} 2>&1)
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
if [ "${ret}" -eq 0 ]; then
@@ -1718,10 +1719,10 @@ function attack_6()
while read -r -u 9 hash; do
- line_dict1=$(sed -n ${j}p ${OUTD}/${hash_type}_dict1_multi_${i})
- line_dict2=$(sed -n ${j}p ${OUTD}/${hash_type}_dict2_multi_${i})
+ line_dict1=$(sed -n ${j}p "${OUTD}/${hash_type}_dict1_multi_${i}")
+ line_dict2=$(sed -n ${j}p "${OUTD}/${hash_type}_dict2_multi_${i}")
- if [ ${pass_only} -eq 1 ]; then
+ if [ "${pass_only}" -eq 1 ]; then
search=":${line_dict1}${line_dict2}"
else
search="${hash}:${line_dict1}${line_dict2}"
@@ -1739,7 +1740,7 @@ function attack_6()
j=$((j + 1))
- done 9< ${OUTD}/${hash_type}_hashes_multi_${i}.txt
+ done 9< "${OUTD}/${hash_type}_hashes_multi_${i}.txt"
fi
@@ -1768,21 +1769,21 @@ function attack_7()
{
file_only=0
- if is_in_array ${hash_type} ${FILE_BASED_ALGOS}; then
+ if is_in_array "${hash_type}" ${FILE_BASED_ALGOS}; then
file_only=1
fi
# single hash
- if [ ${MODE} -ne 1 ]; then
+ if [ "${MODE}" -ne 1 ]; then
e_to=0
e_nf=0
e_nm=0
cnt=0
- echo "> Testing hash type $hash_type with attack mode 7, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type $hash_type with attack mode 7, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}." >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
min=1
max=8
@@ -1815,13 +1816,13 @@ function attack_7()
if [ "${min}" -eq 0 ]; then
- pass_part_1=$(sed -n 1p ${OUTD}/${hash_type}_dict1)
- pass_part_2=$(sed -n 1p ${OUTD}/${hash_type}_dict2)
+ pass_part_1=$(sed -n 1p "${OUTD}/${hash_type}_dict1")
+ pass_part_2=$(sed -n 1p "${OUTD}/${hash_type}_dict2")
pass="${pass_part_1}${pass_part_2}"
- echo -n ${pass} | cut -b -$((mask_offset + 0)) > ${OUTD}/${hash_type}_dict1_custom
- echo -n ${pass} | cut -b $((mask_offset + 1))- > ${OUTD}/${hash_type}_dict2_custom
+ echo -n "${pass}" | cut -b -$((mask_offset + 0)) > "${OUTD}/${hash_type}_dict1_custom"
+ echo -n "${pass}" | cut -b $((mask_offset + 1))- > "${OUTD}/${hash_type}_dict2_custom"
mask_custom=""
@@ -1829,12 +1830,12 @@ function attack_7()
if [ "${hash_type}" -eq 14000 ]; then
- char=$(echo -n ${pass} | cut -b ${i})
+ char=$(echo -n "${pass}" | cut -b ${i})
mask_custom="${mask_custom}${char}"
elif [ "${hash_type}" -eq 14100 ]; then
- char=$(echo -n ${pass} | cut -b ${i})
+ char=$(echo -n "${pass}" | cut -b ${i})
mask_custom="${mask_custom}${char}"
else
@@ -1856,7 +1857,7 @@ function attack_7()
if [ "${file_only}" -eq 1 ]; then
temp_file="${OUTD}/${hash_type}_filebased_only_temp.txt"
- echo ${hash} | base64 -d > ${temp_file}
+ echo "${hash}" | base64 -d > "${temp_file}"
hash="${temp_file}"
fi
@@ -1873,8 +1874,8 @@ function attack_7()
if [ "${hash_type}" -eq 2500 ]; then
- pass_part_1=$(sed -n ${line_nr}p ${OUTD}/${hash_type}_dict1)
- pass_part_2=$(sed -n ${line_nr}p ${OUTD}/${hash_type}_dict2)
+ pass_part_1=$(sed -n ${line_nr}p "${OUTD}/${hash_type}_dict1")
+ pass_part_2=$(sed -n ${line_nr}p "${OUTD}/${hash_type}_dict2")
pass_part_2_len=${#pass_part_2}
@@ -1894,8 +1895,8 @@ function attack_7()
if [ "${hash_type}" -eq 16800 ]; then
- pass_part_1=$(sed -n ${line_nr}p ${OUTD}/${hash_type}_dict1)
- pass_part_2=$(sed -n ${line_nr}p ${OUTD}/${hash_type}_dict2)
+ pass_part_1=$(sed -n ${line_nr}p "${OUTD}/${hash_type}_dict1")
+ pass_part_2=$(sed -n ${line_nr}p "${OUTD}/${hash_type}_dict2")
pass_part_2_len=${#pass_part_2}
@@ -1907,15 +1908,15 @@ function attack_7()
mask_len=${#mask}
mask_len=$((mask_len / 2))
- mask_prefix=$(echo ${pass} | cut -b -$((pass_len - mask_len - pass_part_2_len)))
+ mask_prefix=$(echo "${pass}" | cut -b -$((pass_len - mask_len - pass_part_2_len)))
mask=${mask_prefix}${mask}
fi
if [ "${hash_type}" -eq 20510 ]; then
- pass_part_1=$(sed -n ${line_nr}p ${OUTD}/${hash_type}_dict1)
- pass_part_2=$(sed -n ${line_nr}p ${OUTD}/${hash_type}_dict2)
+ pass_part_1=$(sed -n ${line_nr}p "${OUTD}/${hash_type}_dict1")
+ pass_part_2=$(sed -n ${line_nr}p "${OUTD}/${hash_type}_dict2")
pass=${pass_part_1}${pass_part_2}
@@ -1932,8 +1933,8 @@ function attack_7()
mask_len=$((${#mask} / 2))
- echo "${pass_old}" | cut -b -$((6 + mask_len)) > ${OUTD}/${hash_type}_dict1_custom
- echo "${pass}" | cut -b $((mask_len + 1))- > ${OUTD}/${hash_type}_dict2_custom
+ echo "${pass_old}" | cut -b -$((6 + mask_len)) > "${OUTD}/${hash_type}_dict1_custom"
+ echo "${pass}" | cut -b $((mask_len + 1))- > "${OUTD}/${hash_type}_dict2_custom"
min=0 # hack to use the custom dict
mask_custom=${mask}
@@ -1952,13 +1953,13 @@ function attack_7()
CMD="./${BIN} ${OPTS} -a 7 -m ${hash_type} '${hash}' ${mask} ${dict2}"
- echo -n "[ len $i ] " >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo -n "[ len $i ] " >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
output=$(./${BIN} ${OPTS} -a 7 -m ${hash_type} "${hash}" ${mask} ${dict2} 2>&1)
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
if [ "${ret}" -eq 0 ]; then
@@ -1968,10 +1969,10 @@ function attack_7()
line_nr=$((i - 1))
fi
- line_dict1=$(sed -n ${line_nr}p ${dict1})
- line_dict2=$(sed -n ${line_nr}p ${dict2})
+ line_dict1=$(sed -n ${line_nr}p "${dict1}")
+ line_dict2=$(sed -n ${line_nr}p "${dict2}")
- if [ ${pass_only} -eq 1 ]; then
+ if [ "${pass_only}" -eq 1 ]; then
search=":${line_dict1}${line_dict2}"
else
search="${hash}:${line_dict1}${line_dict2}"
@@ -1995,7 +1996,7 @@ function attack_7()
((i++))
- done 9< ${OUTD}/${hash_type}_hashes.txt
+ done 9< "${OUTD}/${hash_type}_hashes.txt"
msg="OK"
@@ -2011,13 +2012,13 @@ function attack_7()
echo "[ ${OUTD} ] [ Type ${hash_type}, Attack 7, Mode single, Device-Type ${TYPE}, Vector-Width ${VECTOR} ] > $msg : ${e_nf}/${cnt} not found, ${e_nm}/${cnt} not matched, ${e_to}/${cnt} timeout"
- rm -f ${OUTD}/${hash_type}_dict1_custom
- rm -f ${OUTD}/${hash_type}_dict2_custom
+ rm -f "${OUTD}/${hash_type}_dict1_custom"
+ rm -f "${OUTD}/${hash_type}_dict2_custom"
fi
# multihash
- if [ ${MODE} -ne 0 ]; then
+ if [ "${MODE}" -ne 0 ]; then
# no multi hash checks for these modes (because we only have 1 hash for each of them)
@@ -2038,27 +2039,27 @@ function attack_7()
max=9
- if [ ${hash_type} -eq 2500 ]; then
+ if [ "${hash_type}" -eq 2500 ]; then
max=5
- elif [ ${hash_type} -eq 3000 ]; then
+ elif [ "${hash_type}" -eq 3000 ]; then
max=8
- elif [ ${hash_type} -eq 7700 ] || [ ${hash_type} -eq 7701 ]; then
+ elif [ "${hash_type}" -eq 7700 ] || [ "${hash_type}" -eq 7701 ]; then
max=8
- elif [ ${hash_type} -eq 8500 ]; then
+ elif [ "${hash_type}" -eq 8500 ]; then
max=8
- elif [ ${hash_type} -eq 14000 ]; then
+ elif [ "${hash_type}" -eq 14000 ]; then
max=5
- elif [ ${hash_type} -eq 14100 ]; then
+ elif [ "${hash_type}" -eq 14100 ]; then
max=5
- elif [ ${hash_type} -eq 14900 ]; then
+ elif [ "${hash_type}" -eq 14900 ]; then
max=5
- elif [ ${hash_type} -eq 15400 ]; then
+ elif [ "${hash_type}" -eq 15400 ]; then
max=5
- elif [ ${hash_type} -eq 16800 ]; then
+ elif [ "${hash_type}" -eq 16800 ]; then
max=5
fi
- if is_in_array ${hash_type} ${TIMEOUT_ALGOS}; then
+ if is_in_array "${hash_type}" ${TIMEOUT_ALGOS}; then
max=7
@@ -2082,21 +2083,21 @@ function attack_7()
if [ "${file_only}" -eq 1 ]; then
temp_file="${OUTD}/${hash_type}_filebased_only_temp.txt"
- rm -f ${temp_file}
+ rm -f "${temp_file}"
hash_file=${temp_file}
while read -r base64_hash; do
- echo -n ${base64_hash} | base64 -d >> ${temp_file}
+ echo -n "${base64_hash}" | base64 -d >> "${temp_file}"
- done < ${OUTD}/${hash_type}_hashes_multi_${i}.txt
+ done < "${OUTD}/${hash_type}_hashes_multi_${i}.txt"
# a little hack: since we don't want to have a very large mask (and wpa has minimum length of 8),
# we need to create a temporary dict file on-the-fly and use it like this: [small mask] [long(er) words in dict]
dict_file=${OUTD}/${hash_type}_dict2_multi_${i}_longer
- rm -f ${dict_file}
+ rm -f "${dict_file}"
mask_len=${#mask}
mask_len=$((mask_len / 2))
@@ -2105,30 +2106,30 @@ function attack_7()
while read -r -u 9 hash; do
- pass_part_1=$(sed -n ${j}p ${OUTD}/${hash_type}_dict1_multi_${i})
- pass_part_2=$(sed -n ${j}p ${OUTD}/${hash_type}_dict2_multi_${i})
+ pass_part_1=$(sed -n ${j}p "${OUTD}/${hash_type}_dict1_multi_${i}")
+ pass_part_2=$(sed -n ${j}p "${OUTD}/${hash_type}_dict2_multi_${i}")
pass="${pass_part_1}${pass_part_2}"
pass_suffix=$(echo "${pass}" | cut -b $((mask_len + 1))-)
- echo "${pass_suffix}" >> ${dict_file}
+ echo "${pass_suffix}" >> "${dict_file}"
j=$((j + 1))
- done 9< ${OUTD}/${hash_type}_hashes_multi_${i}.txt
+ done 9< "${OUTD}/${hash_type}_hashes_multi_${i}.txt"
fi
CMD="./${BIN} ${OPTS} -a 7 -m ${hash_type} ${hash_file} ${mask} ${dict_file}"
- echo "> Testing hash type $hash_type with attack mode 7, markov ${MARKOV}, multi hash with word len ${i}." >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type $hash_type with attack mode 7, markov ${MARKOV}, multi hash with word len ${i}." >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
output=$(./${BIN} ${OPTS} -a 7 -m ${hash_type} ${hash_file} ${mask} ${dict_file} 2>&1)
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
if [ "${ret}" -eq 0 ]; then
@@ -2136,10 +2137,10 @@ function attack_7()
while read -r -u 9 hash; do
- line_dict1=$(sed -n ${j}p ${OUTD}/${hash_type}_dict1_multi_${i})
- line_dict2=$(sed -n ${j}p ${OUTD}/${hash_type}_dict2_multi_${i})
+ line_dict1=$(sed -n ${j}p "${OUTD}/${hash_type}_dict1_multi_${i}")
+ line_dict2=$(sed -n ${j}p "${OUTD}/${hash_type}_dict2_multi_${i}")
- if [ ${pass_only} -eq 1 ]; then
+ if [ "${pass_only}" -eq 1 ]; then
search=":${line_dict1}${line_dict2}"
else
search="${hash}:${line_dict1}${line_dict2}"
@@ -2157,7 +2158,7 @@ function attack_7()
j=$((j + 1))
- done 9< ${OUTD}/${hash_type}_hashes_multi_${i}.txt
+ done 9< "${OUTD}/${hash_type}_hashes_multi_${i}.txt"
fi
@@ -2342,13 +2343,13 @@ function truecrypt_test()
esac
if [ ${#CMD} -gt 5 ]; then
- echo "> Testing hash type $hashType with attack mode 3, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}, tcMode ${tcMode}" >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type $hashType with attack mode 3, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}, tcMode ${tcMode}" >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
output=$(${CMD} 2>&1)
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
cnt=1
e_nf=0
@@ -2388,25 +2389,25 @@ function veracrypt_test()
cipher_digit="${hash_type:4:1}"
case $cipher_digit in
1)
- [ $cipher_variation -eq "0" ] && cipher_cascade="aes"
- [ $cipher_variation -eq "1" ] && cipher_cascade="serpent"
- [ $cipher_variation -eq "2" ] && cipher_cascade="twofish"
- [ $cipher_variation -eq "3" ] && cipher_cascade="camellia"
- [ $cipher_variation -eq "5" ] && cipher_cascade="kuznyechik"
+ [ "$cipher_variation" -eq "0" ] && cipher_cascade="aes"
+ [ "$cipher_variation" -eq "1" ] && cipher_cascade="serpent"
+ [ "$cipher_variation" -eq "2" ] && cipher_cascade="twofish"
+ [ "$cipher_variation" -eq "3" ] && cipher_cascade="camellia"
+ [ "$cipher_variation" -eq "5" ] && cipher_cascade="kuznyechik"
;;
2)
- [ $cipher_variation -eq "0" ] && cipher_cascade="aes-twofish"
- [ $cipher_variation -eq "1" ] && cipher_cascade="serpent-aes"
- [ $cipher_variation -eq "2" ] && cipher_cascade="twofish-serpent"
- [ $cipher_variation -eq "3" ] && cipher_cascade="camellia-kuznyechik"
- [ $cipher_variation -eq "4" ] && cipher_cascade="camellia-serpent"
- [ $cipher_variation -eq "5" ] && cipher_cascade="kuznyechik-aes"
- [ $cipher_variation -eq "6" ] && cipher_cascade="kuznyechik-twofish"
+ [ "$cipher_variation" -eq "0" ] && cipher_cascade="aes-twofish"
+ [ "$cipher_variation" -eq "1" ] && cipher_cascade="serpent-aes"
+ [ "$cipher_variation" -eq "2" ] && cipher_cascade="twofish-serpent"
+ [ "$cipher_variation" -eq "3" ] && cipher_cascade="camellia-kuznyechik"
+ [ "$cipher_variation" -eq "4" ] && cipher_cascade="camellia-serpent"
+ [ "$cipher_variation" -eq "5" ] && cipher_cascade="kuznyechik-aes"
+ [ "$cipher_variation" -eq "6" ] && cipher_cascade="kuznyechik-twofish"
;;
3)
- [ $cipher_variation -eq "0" ] && cipher_cascade="aes-twofish-serpent"
- [ $cipher_variation -eq "1" ] && cipher_cascade="serpent-twofish-aes"
- [ $cipher_variation -eq "5" ] && cipher_cascade="kuznyechik-serpent-camellia"
+ [ "$cipher_variation" -eq "0" ] && cipher_cascade="aes-twofish-serpent"
+ [ "$cipher_variation" -eq "1" ] && cipher_cascade="serpent-twofish-aes"
+ [ "$cipher_variation" -eq "5" ] && cipher_cascade="kuznyechik-serpent-camellia"
;;
esac
@@ -2419,13 +2420,13 @@ function veracrypt_test()
CMD="echo hashca{a..z} | ./${BIN} ${OPTS} -a 0 -m ${hash_type} ${filename}"
- echo "> Testing hash type ${hash_type} with attack mode 0, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}, cipher ${cipher_cascade}" >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type ${hash_type} with attack mode 0, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}, cipher ${cipher_cascade}" >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
output=$(${CMD} 2>&1)
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
cnt=1
e_nf=0
@@ -2545,12 +2546,12 @@ function luks_test()
esac
if [ -n "${CMD}" ]; then
- echo "> Testing hash type ${hashType} with attack mode ${attackType}, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}, luksMode ${luks_mode}" >>${OUTD}/logfull.txt 2>>${OUTD}/logfull.txt
+ echo "> Testing hash type ${hashType} with attack mode ${attackType}, markov ${MARKOV}, single hash, Device-Type ${TYPE}, vector-width ${VECTOR}, luksMode ${luks_mode}" >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
output=$(${CMD} 2>&1)
ret=${?}
- echo "${output}" >> ${OUTD}/logfull.txt
+ echo "${output}" >> "${OUTD}/logfull.txt"
cnt=1
e_nf=0
@@ -2654,17 +2655,17 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
case ${opt} in
"V")
- if [ ${OPTARG} = "1" ]; then
+ if [ "${OPTARG}" = "1" ]; then
VECTOR=1
- elif [ ${OPTARG} = "2" ]; then
+ elif [ "${OPTARG}" = "2" ]; then
VECTOR=2
- elif [ ${OPTARG} = "4" ]; then
+ elif [ "${OPTARG}" = "4" ]; then
VECTOR=4
- elif [ ${OPTARG} = "8" ]; then
+ elif [ "${OPTARG}" = "8" ]; then
VECTOR=8
- elif [ ${OPTARG} = "16" ]; then
+ elif [ "${OPTARG}" = "16" ]; then
VECTOR=16
- elif [ ${OPTARG} = "all" ]; then
+ elif [ "${OPTARG}" = "all" ]; then
VECTOR="all"
else
usage
@@ -2672,11 +2673,11 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"t")
- if [ ${OPTARG} = "single" ]; then
+ if [ "${OPTARG}" = "single" ]; then
MODE=0
- elif [ ${OPTARG} = "multi" ]; then
+ elif [ "${OPTARG}" = "multi" ]; then
MODE=1
- elif [ ${OPTARG} = "all" ]; then
+ elif [ "${OPTARG}" = "all" ]; then
MODE=2
else
usage
@@ -2684,7 +2685,7 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"m")
- if [ ${OPTARG} = "all" ]; then
+ if [ "${OPTARG}" = "all" ]; then
HT=65535
else
HT=${OPTARG}
@@ -2692,17 +2693,17 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"a")
- if [ ${OPTARG} = "all" ]; then
+ if [ "${OPTARG}" = "all" ]; then
ATTACK=65535
- elif [ ${OPTARG} = "0" ]; then
+ elif [ "${OPTARG}" = "0" ]; then
ATTACK=0
- elif [ ${OPTARG} = "1" ]; then
+ elif [ "${OPTARG}" = "1" ]; then
ATTACK=1
- elif [ ${OPTARG} = "3" ]; then
+ elif [ "${OPTARG}" = "3" ]; then
ATTACK=3
- elif [ ${OPTARG} = "6" ]; then
+ elif [ "${OPTARG}" = "6" ]; then
ATTACK=6
- elif [ ${OPTARG} = "7" ]; then
+ elif [ "${OPTARG}" = "7" ]; then
ATTACK=7
else
usage
@@ -2715,7 +2716,7 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"I")
- PACKAGE_FOLDER=$( echo ${OPTARG} | sed 's!/$!!g' )
+ PACKAGE_FOLDER=$( echo "${OPTARG}" | sed 's!/$!!g' )
;;
"s")
@@ -2727,9 +2728,9 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"x")
- if [ ${OPTARG} = "32" ]; then
+ if [ "${OPTARG}" = "32" ]; then
ARCHITECTURE=32
- elif [ ${OPTARG} = "64" ]; then
+ elif [ "${OPTARG}" = "64" ]; then
ARCHITECTURE=64
else
usage
@@ -2737,11 +2738,11 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"o")
- if [ ${OPTARG} = "win" ]; then
+ if [ "${OPTARG}" = "win" ]; then
EXTENSION="exe"
- elif [ ${OPTARG} = "linux" ]; then
+ elif [ "${OPTARG}" = "linux" ]; then
EXTENSION="bin"
- elif [ ${OPTARG} = "macos" ]; then
+ elif [ "${OPTARG}" = "macos" ]; then
EXTENSION="app"
else
usage
@@ -2757,10 +2758,10 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"D")
- if [ ${OPTARG} = "1" ]; then
+ if [ "${OPTARG}" = "1" ]; then
OPTS="${OPTS} -D 1"
TYPE="Cpu"
- elif [ ${OPTARG} = "2" ]; then
+ elif [ "${OPTARG}" = "2" ]; then
OPTS="${OPTS} -D 2"
TYPE="Gpu"
else
@@ -2770,7 +2771,7 @@ while getopts "V:t:m:a:b:hcpd:x:o:d:D:F:POI:s:" opt; do
;;
"F")
- OUTD=$( echo ${OPTARG} | sed 's!/$!!g' )
+ OUTD=$( echo "${OPTARG}" | sed 's!/$!!g' )
;;
"P")
@@ -2838,15 +2839,15 @@ if [ "${PACKAGE}" -eq 0 ] || [ -z "${PACKAGE_FOLDER}" ]; then
HT_MIN=0
HT_MAX=0
- if echo -n ${HT} | grep -q '^[0-9]\+$'; then
+ if echo -n "${HT}" | grep -q '^[0-9]\+$'; then
HT_MIN=${HT}
HT_MAX=${HT}
- elif echo -n ${HT} | grep -q '^[0-9]\+-[1-9][0-9]*$'; then
+ elif echo -n "${HT}" | grep -q '^[0-9]\+-[1-9][0-9]*$'; then
HT_MIN=$(echo -n ${HT} | sed "s/-.*//")
HT_MAX=$(echo -n ${HT} | sed "s/.*-//")
- if [ "${HT_MIN}" -gt ${HT_MAX} ]; then
+ if [ "${HT_MIN}" -gt "${HT_MAX}" ]; then
echo "! hash type range -m ${HT} is not valid ..."
usage
fi
@@ -2858,16 +2859,16 @@ if [ "${PACKAGE}" -eq 0 ] || [ -z "${PACKAGE_FOLDER}" ]; then
HT=${HT_MIN}
# filter by hash_type
- if [ ${HT} -ne 65535 ]; then
+ if [ "${HT}" -ne 65535 ]; then
# validate filter
- if ! is_in_array ${HT_MIN} ${HASH_TYPES}; then
+ if ! is_in_array "${HT_MIN}" ${HASH_TYPES}; then
echo "! invalid hash type selected ..."
usage
fi
- if ! is_in_array ${HT_MAX} ${HASH_TYPES}; then
+ if ! is_in_array "${HT_MAX}" ${HASH_TYPES}; then
echo "! invalid hash type selected ..."
usage
fi
@@ -2876,30 +2877,30 @@ if [ "${PACKAGE}" -eq 0 ] || [ -z "${PACKAGE_FOLDER}" ]; then
if [ -z "${PACKAGE_FOLDER}" ]; then
# make new dir
- mkdir -p ${OUTD}
+ mkdir -p "${OUTD}"
# generate random test entry
- if [ ${HT} -eq 65535 ]; then
+ if [ "${HT}" -eq 65535 ]; then
for TMP_HT in ${HASH_TYPES}; do
- if [[ ${TMP_HT} -ne ${LUKS_MODE} ]]; then
- if ! is_in_array ${TMP_HT} ${TC_MODES}; then
- if ! is_in_array ${TMP_HT} ${VC_MODES}; then
- perl tools/test.pl single ${TMP_HT} >> ${OUTD}/all.sh
+ if [ "${TMP_HT}" -ne ${LUKS_MODE} ]; then
+ if ! is_in_array "${TMP_HT}" ${TC_MODES}; then
+ if ! is_in_array "${TMP_HT}" ${VC_MODES}; then
+ perl tools/test.pl single "${TMP_HT}" >> "${OUTD}/all.sh"
fi
fi
fi
done
else
- for TMP_HT in $(seq ${HT_MIN} ${HT_MAX}); do
- if ! is_in_array ${TMP_HT} ${HASH_TYPES}; then
+ for TMP_HT in $(seq "${HT_MIN}" "${HT_MAX}"); do
+ if ! is_in_array "${TMP_HT}" ${HASH_TYPES}; then
continue
fi
- if [[ ${TMP_HT} -ne ${LUKS_MODE} ]]; then
+ if [ "${TMP_HT}" -ne ${LUKS_MODE} ]; then
# Exclude TrueCrypt and VeraCrypt testing modes
- if ! is_in_array ${TMP_HT} ${TC_MODES}; then
- if ! is_in_array ${TMP_HT} ${VC_MODES}; then
- perl tools/test.pl single ${TMP_HT} >> ${OUTD}/all.sh
+ if ! is_in_array "${TMP_HT}" ${TC_MODES}; then
+ if ! is_in_array "${TMP_HT}" ${VC_MODES}; then
+ perl tools/test.pl single "${TMP_HT}" >> "${OUTD}/all.sh"
fi
fi
fi
@@ -2912,7 +2913,7 @@ if [ "${PACKAGE}" -eq 0 ] || [ -z "${PACKAGE_FOLDER}" ]; then
fi
- rm -rf ${OUTD}/logfull.txt && touch ${OUTD}/logfull.txt
+ rm -rf "${OUTD}/logfull.txt" && touch "${OUTD}/logfull.txt"
# populate array of hash types where we only should check if pass is in output (not both hash:pass)
IFS=';' read -ra PASS_ONLY <<< "${HASHFILE_ONLY} ${NOCHECK_ENCODING}"
@@ -2929,9 +2930,9 @@ if [ "${PACKAGE}" -eq 0 ] || [ -z "${PACKAGE_FOLDER}" ]; then
# check if the loop variable "hash_type" is between HT_MIN and HT_MAX (both included)
- if [ "${hash_type}" -lt ${HT_MIN} ]; then
+ if [ "${hash_type}" -lt "${HT_MIN}" ]; then
continue
- elif [ "${hash_type}" -gt ${HT_MAX} ]; then
+ elif [ "${hash_type}" -gt "${HT_MAX}" ]; then
# we are done because hash_type is larger than range:
break
fi
@@ -2952,13 +2953,13 @@ if [ "${PACKAGE}" -eq 0 ] || [ -z "${PACKAGE_FOLDER}" ]; then
# should we check only the pass?
pass_only=0
- is_in_array ${hash_type} ${PASS_ONLY} && pass_only=1
+ is_in_array "${hash_type}" ${PASS_ONLY} && pass_only=1
IS_SLOW=0
- is_in_array ${hash_type} ${SLOW_ALGOS} && IS_SLOW=1
+ is_in_array "${hash_type}" ${SLOW_ALGOS} && IS_SLOW=1
# we use phpass as slow hash for testing the AMP kernel
- [[ ${hash_type} -eq 400 ]] && IS_SLOW=0
+ [ "${hash_type}" -eq 400 ] && IS_SLOW=0
OPTS_OLD=${OPTS}
VECTOR_OLD=${VECTOR}
@@ -2986,10 +2987,10 @@ if [ "${PACKAGE}" -eq 0 ] || [ -z "${PACKAGE_FOLDER}" ]; then
VECTOR=${CUR_WIDTH}
OPTS="${OPTS_OLD} --backend-vector-width ${VECTOR}"
- if [[ ${IS_SLOW} -eq 1 ]]; then
+ if [ ${IS_SLOW} -eq 1 ]; then
# Look up if this is one of supported VeraCrypt modes
- if is_in_array ${hash_type} ${VC_MODES}; then
+ if is_in_array "${hash_type}" ${VC_MODES}; then
veracrypt_test 0 # aes
veracrypt_test 1 # serpent
veracrypt_test 2 # twofish
@@ -2998,35 +2999,35 @@ if [ "${PACKAGE}" -eq 0 ] || [ -z "${PACKAGE_FOLDER}" ]; then
veracrypt_test 5 # kuznyechik
veracrypt_test 6 # kuznyechik (alternative cascade)
- elif is_in_array ${hash_type} ${TC_MODES}; then
+ elif is_in_array "${hash_type}" ${TC_MODES}; then
# run truecrypt tests
- truecrypt_test ${hash_type} 0
- truecrypt_test ${hash_type} 1
- truecrypt_test ${hash_type} 2
- elif [[ ${hash_type} -eq ${LUKS_MODE} ]]; then
+ truecrypt_test "${hash_type}" 0
+ truecrypt_test "${hash_type}" 1
+ truecrypt_test "${hash_type}" 2
+ elif [ "${hash_type}" -eq ${LUKS_MODE} ]; then
# run luks tests
- luks_test ${hash_type} ${ATTACK}
+ luks_test "${hash_type}" ${ATTACK}
else
# run attack mode 0 (stdin)
- if [[ ${ATTACK} -eq 65535 ]] || [[ ${ATTACK} -eq 0 ]]; then attack_0; fi
+ if [ ${ATTACK} -eq 65535 ] || [ ${ATTACK} -eq 0 ]; then attack_0; fi
fi
else
# run attack mode 0 (stdin)
- if [[ ${ATTACK} -eq 65535 ]] || [[ ${ATTACK} -eq 0 ]]; then attack_0; fi
+ if [ ${ATTACK} -eq 65535 ] || [ ${ATTACK} -eq 0 ]; then attack_0; fi
# run attack mode 1 (combinator)
- if [[ ${ATTACK} -eq 65535 ]] || [[ ${ATTACK} -eq 1 ]]; then attack_1; fi
+ if [ ${ATTACK} -eq 65535 ] || [ ${ATTACK} -eq 1 ]; then attack_1; fi
# run attack mode 3 (bruteforce)
- if [[ ${ATTACK} -eq 65535 ]] || [[ ${ATTACK} -eq 3 ]]; then attack_3; fi
+ if [ ${ATTACK} -eq 65535 ] || [ ${ATTACK} -eq 3 ]; then attack_3; fi
# run attack mode 6 (dict+mask)
- if [[ ${ATTACK} -eq 65535 ]] || [[ ${ATTACK} -eq 6 ]]; then attack_6; fi
+ if [ ${ATTACK} -eq 65535 ] || [ ${ATTACK} -eq 6 ]; then attack_6; fi
# run attack mode 7 (mask+dict)
- if [[ ${ATTACK} -eq 65535 ]] || [[ ${ATTACK} -eq 7 ]]; then attack_7; fi
+ if [ ${ATTACK} -eq 65535 ] || [ ${ATTACK} -eq 7 ]; then attack_7; fi
fi
fi
@@ -3046,51 +3047,51 @@ fi
# fix logfile
if [ "${PACKAGE}" -eq 0 ]; then
- cat -vet ${OUTD}/logfull.txt | sed -e 's/\^M \^M//g' | sed -e 's/\$$//g' > ${OUTD}/test_report.log
+ cat -vet "${OUTD}/logfull.txt" | sed -e 's/\^M \^M//g' | sed -e 's/\$$//g' > "${OUTD}/test_report.log"
fi
-rm -rf ${OUTD}/logfull.txt
+rm -rf "${OUTD}/logfull.txt"
if [ "${PACKAGE}" -eq 1 ]; then
echo "[ ${OUTD} ] > Generate package ${OUTD}/${OUTD}.7z"
- cp "${BASH_SOURCE[0]}" ${OUTD}/test.sh
+ cp "${BASH_SOURCE[0]}" "${OUTD}/test.sh"
copy_luks_dir=0
copy_tc_dir=0
copy_vc_dir=0
- if [ ${HT} -eq 65535 ]; then
+ if [ "${HT}" -eq 65535 ]; then
copy_luks_dir=1
copy_tc_dir=1
copy_vc_dir=1
else
- for TMP_HT in $(seq ${HT_MIN} ${HT_MAX}); do
- if [[ ${TMP_HT} -eq ${LUKS_MODE} ]]; then
+ for TMP_HT in $(seq "${HT_MIN}" "${HT_MAX}"); do
+ if [ "${TMP_HT}" -eq "${LUKS_MODE}" ]; then
copy_luks_dir=1
- elif is_in_array ${TMP_HT} ${TC_MODES}; then
+ elif is_in_array "${TMP_HT}" ${TC_MODES}; then
copy_tc_dir=1
- elif is_in_array ${TMP_HT} ${VC_MODES}; then
+ elif is_in_array "${TMP_HT}" ${VC_MODES}; then
copy_vc_dir=1
fi
done
fi
if [ "${copy_luks_dir}" -eq 1 ]; then
- mkdir ${OUTD}/luks_tests/
- cp ${TDIR}/luks_tests/* ${OUTD}/luks_tests/
+ mkdir "${OUTD}/luks_tests/"
+ cp ${TDIR}/luks_tests/* "${OUTD}/luks_tests/"
fi
if [ "${copy_tc_dir}" -eq 1 ]; then
- mkdir ${OUTD}/tc_tests/
- cp ${TDIR}/tc_tests/* ${OUTD}/tc_tests/
+ mkdir "${OUTD}/tc_tests/"
+ cp ${TDIR}/tc_tests/* "${OUTD}/tc_tests/"
fi
if [ "${copy_vc_dir}" -eq 1 ]; then
- mkdir ${OUTD}/vc_tests/
- cp ${TDIR}/vc_tests/* ${OUTD}/vc_tests/
+ mkdir "${OUTD}/vc_tests/"
+ cp ${TDIR}/vc_tests/* "${OUTD}/vc_tests/"
fi
# if we package from a given folder, we need to check if e.g. the files needed for multi mode are there
@@ -3108,7 +3109,7 @@ if [ "${PACKAGE}" -eq 1 ]; then
fi
- HT=$(grep -o -- "-m *[0-9]*" ${PACKAGE_FOLDER}/all.sh | sort -u | sed 's/-m //' 2> /dev/null)
+ HT=$(grep -o -- "-m *[0-9]*" "${PACKAGE_FOLDER}/all.sh" | sort -u | sed 's/-m //' 2> /dev/null)
if [ -n "${HT}" ]; then
@@ -3142,10 +3143,10 @@ if [ "${PACKAGE}" -eq 1 ]; then
HT_PACKAGED=${HT_MIN}-${HT_MAX}
fi
- HASH_TYPES_PACKAGED=$( echo ${HASH_TYPES} | tr '\n' ' ' | sed 's/ $//')
- HASHFILE_ONLY_PACKAGED=$(echo ${HASHFILE_ONLY} | tr '\n' ' ' | sed 's/ $//')
- NEVER_CRACK_PACKAGED=$( echo ${NEVER_CRACK} | tr '\n' ' ' | sed 's/ $//')
- SLOW_ALGOS_PACKAGED=$( echo ${SLOW_ALGOS} | tr '\n' ' ' | sed 's/ $//')
+ HASH_TYPES_PACKAGED=$( echo "${HASH_TYPES}" | tr '\n' ' ' | sed 's/ $//')
+ HASHFILE_ONLY_PACKAGED=$(echo "${HASHFILE_ONLY}" | tr '\n' ' ' | sed 's/ $//')
+ NEVER_CRACK_PACKAGED=$( echo "${NEVER_CRACK}" | tr '\n' ' ' | sed 's/ $//')
+ SLOW_ALGOS_PACKAGED=$( echo "${SLOW_ALGOS}" | tr '\n' ' ' | sed 's/ $//')
sed "${SED_IN_PLACE}" -e 's/^\(PACKAGE_FOLDER\)=""/\1="$( echo "${BASH_SOURCE[0]}" | sed \"s!test.sh\\$!!\" )"/' \
-e "s/^\(HASH_TYPES\)=\$(.*/\1=\"${HASH_TYPES_PACKAGED}\"/" \
@@ -3155,8 +3156,8 @@ if [ "${PACKAGE}" -eq 1 ]; then
-e "s/^\(HT\)=0/\1=${HT_PACKAGED}/" \
-e "s/^\(MODE\)=0/\1=${MODE}/" \
-e "s/^\(ATTACK\)=0/\1=${ATTACK}/" \
- ${OUTD}/test.sh
+ "${OUTD}/test.sh"
- ${PACKAGE_CMD} ${OUTD}/${OUTD}.7z ${OUTD}/ >/dev/null 2>/dev/null
+ "${PACKAGE_CMD}" "${OUTD}/${OUTD}.7z" "${OUTD}/" >/dev/null 2>/dev/null
fi
From 884f0037250697be37e8fc2977708935ddd9478b Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Wed, 7 Aug 2019 14:20:32 +0200
Subject: [PATCH 095/113] Fixed some memory leaks in case mask-files are used
in optimized mode
---
docs/changes.txt | 1 +
include/types.h | 2 +-
src/mpsp.c | 41 ++++++++++++++++++++---------------------
3 files changed, 22 insertions(+), 22 deletions(-)
diff --git a/docs/changes.txt b/docs/changes.txt
index bb2889bab..9f93e4006 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -71,6 +71,7 @@
- Fixed problem with the usage of the hexadecimal notations (\x00-\xff) within rules
- Fixed race condition in maskfile mode by using a dedicated flag for restore execution
- Fixed some memory leaks in case hashcat is shutting down due to some file error
+- Fixed some memory leaks in case mask-files are used in optimized mode
- Fixed the 7-Zip parser to allow the entire supported range of encrypted and decrypted data lengths
- Fixed the validation of the --brain-client-features command line argument (only values 1, 2 or 3 are allowed)
diff --git a/include/types.h b/include/types.h
index e23e0e75b..e29944b13 100644
--- a/include/types.h
+++ b/include/types.h
@@ -2051,7 +2051,7 @@ typedef struct mask_ctx
u64 bfs_cnt;
- cs_t *css_buf;
+ cs_t css_buf[256];
u32 css_cnt;
hcstat_table_t *root_table_buf;
diff --git a/src/mpsp.c b/src/mpsp.c
index 3d7d64dfe..fc85a31e1 100644
--- a/src/mpsp.c
+++ b/src/mpsp.c
@@ -117,23 +117,16 @@ static int mp_css_append_salt (hashcat_ctx_t *hashcat_ctx, salt_t *salt_buf)
u32 salt_len = salt_buf->salt_len;
u8 *salt_buf_ptr = (u8 *) salt_buf->salt_buf;
- u32 css_cnt_salt = mask_ctx->css_cnt + salt_len;
-
- cs_t *css_buf_salt = (cs_t *) hccalloc (css_cnt_salt, sizeof (cs_t));
-
- memcpy (css_buf_salt, mask_ctx->css_buf, mask_ctx->css_cnt * sizeof (cs_t));
+ if ((mask_ctx->css_cnt + salt_len) > 256) return -1;
for (u32 i = 0, j = mask_ctx->css_cnt; i < salt_len; i++, j++)
{
- css_buf_salt[j].cs_buf[0] = salt_buf_ptr[i];
- css_buf_salt[j].cs_len = 1;
+ mask_ctx->css_buf[j].cs_buf[0] = salt_buf_ptr[i];
+ mask_ctx->css_buf[j].cs_len = 1;
+
+ mask_ctx->css_cnt++;
}
- hcfree (mask_ctx->css_buf);
-
- mask_ctx->css_buf = css_buf_salt;
- mask_ctx->css_cnt = css_cnt_salt;
-
return 0;
}
@@ -143,6 +136,8 @@ static int mp_css_utf16le_expand (hashcat_ctx_t *hashcat_ctx)
u32 css_cnt_utf16le = mask_ctx->css_cnt * 2;
+ if (css_cnt_utf16le > 256) return -1;
+
cs_t *css_buf_utf16le = (cs_t *) hccalloc (css_cnt_utf16le, sizeof (cs_t));
for (u32 i = 0, j = 0; i < mask_ctx->css_cnt; i += 1, j += 2)
@@ -153,11 +148,12 @@ static int mp_css_utf16le_expand (hashcat_ctx_t *hashcat_ctx)
css_buf_utf16le[j + 1].cs_len = 1;
}
- hcfree (mask_ctx->css_buf);
+ memcpy (mask_ctx->css_buf, css_buf_utf16le, css_cnt_utf16le * sizeof (cs_t));
- mask_ctx->css_buf = css_buf_utf16le;
mask_ctx->css_cnt = css_cnt_utf16le;
+ hcfree (css_buf_utf16le);
+
return 0;
}
@@ -167,6 +163,8 @@ static int mp_css_utf16be_expand (hashcat_ctx_t *hashcat_ctx)
u32 css_cnt_utf16be = mask_ctx->css_cnt * 2;
+ if (css_cnt_utf16be > 256) return -1;
+
cs_t *css_buf_utf16be = (cs_t *) hccalloc (css_cnt_utf16be, sizeof (cs_t));
for (u32 i = 0, j = 0; i < mask_ctx->css_cnt; i += 1, j += 2)
@@ -177,11 +175,12 @@ static int mp_css_utf16be_expand (hashcat_ctx_t *hashcat_ctx)
memcpy (&css_buf_utf16be[j + 1], &mask_ctx->css_buf[i], sizeof (cs_t));
}
- hcfree (mask_ctx->css_buf);
+ memcpy (mask_ctx->css_buf, css_buf_utf16be, css_cnt_utf16be * sizeof (cs_t));
- mask_ctx->css_buf = css_buf_utf16be;
mask_ctx->css_cnt = css_cnt_utf16be;
+ hcfree (css_buf_utf16be);
+
return 0;
}
@@ -1197,7 +1196,7 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
if (mask_ctx_parse_maskfile (hashcat_ctx) == -1) return -1;
- mask_ctx->css_buf = (cs_t *) hccalloc (256, sizeof (cs_t));
+ //mask_ctx->css_buf = (cs_t *) hccalloc (256, sizeof (cs_t));
if (mp_gen_css (hashcat_ctx, mask_ctx->mask, strlen (mask_ctx->mask), mask_ctx->mp_sys, mask_ctx->mp_usr, mask_ctx->css_buf, &mask_ctx->css_cnt) == -1) return -1;
@@ -1222,7 +1221,7 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
if (mask_ctx_parse_maskfile (hashcat_ctx) == -1) return -1;
- mask_ctx->css_buf = (cs_t *) hccalloc (256, sizeof (cs_t));
+ //mask_ctx->css_buf = (cs_t *) hccalloc (256, sizeof (cs_t));
if (mp_gen_css (hashcat_ctx, mask_ctx->mask, strlen (mask_ctx->mask), mask_ctx->mp_sys, mask_ctx->mp_usr, mask_ctx->css_buf, &mask_ctx->css_cnt) == -1) return -1;
@@ -1253,7 +1252,7 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
if (user_options->attack_mode == ATTACK_MODE_BF) // always true
{
- mask_ctx->css_buf = (cs_t *) hccalloc (256, sizeof (cs_t));
+ //mask_ctx->css_buf = (cs_t *) hccalloc (256, sizeof (cs_t));
if (mp_gen_css (hashcat_ctx, mask_ctx->mask, strlen (mask_ctx->mask), mask_ctx->mp_sys, mask_ctx->mp_usr, mask_ctx->css_buf, &mask_ctx->css_cnt) == -1) return -1;
@@ -1382,7 +1381,7 @@ int mask_ctx_init (hashcat_ctx_t *hashcat_ctx)
mask_ctx->markov_css_buf = (cs_t *) hccalloc (SP_PW_MAX * CHARSIZ, sizeof (cs_t));
mask_ctx->css_cnt = 0;
- mask_ctx->css_buf = NULL;
+ //mask_ctx->css_buf = NULL;
mask_ctx->mask_from_file = false;
@@ -1647,7 +1646,7 @@ void mask_ctx_destroy (hashcat_ctx_t *hashcat_ctx)
if (mask_ctx->enabled == false) return;
- hcfree (mask_ctx->css_buf);
+ //hcfree (mask_ctx->css_buf);
hcfree (mask_ctx->root_css_buf);
hcfree (mask_ctx->markov_css_buf);
From 154e2b0b8f68dc5b1a3783e42c75eabf35d0022b Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Wed, 7 Aug 2019 15:46:21 +0200
Subject: [PATCH 096/113] Update docs/readme.txt with new header and updated
hash-mode list
---
docs/readme.txt | 330 ++++++++++++++++++++++++++----------------------
1 file changed, 182 insertions(+), 148 deletions(-)
diff --git a/docs/readme.txt b/docs/readme.txt
index 7e3e8d468..f698c8745 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -1,3 +1,12 @@
+
+ _____: _____________ _____: -aTZ! _______ ____
+ _\ |__\_______ _/_______ _\ |_____ _______\______ /__ ______
+ | _ | __ \ ____/____ _ | ___/____ __ |_______/
+ |: | .| \ _\____ / | .| \ / \ :| |
+ |_____| :|______/ / //____| :|___ //_________| :|
+ |_____| /___________/ |_____| /_____/ /_______|
+ : : :
+
hashcat v5.1.0
==============
@@ -40,7 +49,6 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- MD4
- MD5
-- Half MD5
- SHA1
- SHA2-224
- SHA2-256
@@ -50,52 +58,60 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- SHA3-256
- SHA3-384
- SHA3-512
+- RIPEMD-160
+- BLAKE2b-512
+- GOST R 34.11-2012 (Streebog) 256-bit, big-endian
+- GOST R 34.11-2012 (Streebog) 512-bit, big-endian
+- GOST R 34.11-94
+- Half MD5
+- Java Object hashCode()
- Keccak-224
- Keccak-256
- Keccak-384
- Keccak-512
-- BLAKE2b-512
-- SipHash
-- RIPEMD-160
+- sha256(sha256_bin(pass))
- Whirlpool
-- GOST R 34.11-94
-- GOST R 34.11-2012 (Streebog) 256-bit
-- GOST R 34.11-2012 (Streebog) 512-bit
-- Java Object hashCode()
+- SipHash
+- BitShares v0.x - sha512(sha512_bin(pass))
- md5($pass.$salt)
- md5($salt.$pass)
-- md5(utf16le($pass).$salt)
-- md5($salt.utf16le($pass))
- md5($salt.$pass.$salt)
- md5($salt.md5($pass))
-- md5($salt.md5($salt.$pass))
- md5($salt.md5($pass.$salt))
+- md5($salt.md5($salt.$pass))
+- md5($salt.sha1($salt.$pass))
+- md5($salt.utf16le($pass))
- md5(md5($pass))
- md5(md5($pass).md5($salt))
-- md5(strtoupper(md5($pass)))
- md5(sha1($pass))
+- md5(sha1($pass).md5($pass).sha1($pass))
+- md5(sha1($salt).md5($pass))
+- md5(strtoupper(md5($pass)))
+- md5(utf16le($pass).$salt)
- sha1($pass.$salt)
- sha1($salt.$pass)
-- sha1(utf16le($pass).$salt)
-- sha1($salt.utf16le($pass))
-- sha1(sha1($pass))
+- sha1($salt.$pass.$salt)
- sha1($salt.sha1($pass))
+- sha1($salt.utf16le($pass))
+- sha1($salt1.$pass.$salt2)
+- sha1(CX)
- sha1(md5($pass))
- sha1(md5($pass).$salt)
+- sha1(md5($pass.$salt))
- sha1(md5(md5($pass)))
-- sha1($salt.$pass.$salt)
-- sha1(CX)
+- sha1(sha1($pass))
+- sha1(utf16le($pass).$salt)
- sha256($pass.$salt)
- sha256($salt.$pass)
-- sha256(utf16le($pass).$salt)
- sha256($salt.utf16le($pass))
- sha256(md5($pass))
+- sha256(sha256($pass).$salt)
+- sha256(utf16le($pass).$salt)
- sha512($pass.$salt)
- sha512($salt.$pass)
-- sha512(utf16le($pass).$salt)
- sha512($salt.utf16le($pass))
-- sha256(sha256($pass).$salt)
-- AuthMe sha256
+- sha512(utf16le($pass).$salt)
+- Ruby on Rails Restful-Authentication
- HMAC-MD5 (key = $pass)
- HMAC-MD5 (key = $salt)
- HMAC-SHA1 (key = $pass)
@@ -104,182 +120,200 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- HMAC-SHA256 (key = $salt)
- HMAC-SHA512 (key = $pass)
- HMAC-SHA512 (key = $salt)
-- DES (PT = $salt, key = $pass)
+- HMAC-Streebog-256 (key = $pass), big-endian
+- HMAC-Streebog-256 (key = $salt), big-endian
+- HMAC-Streebog-512 (key = $pass), big-endian
+- HMAC-Streebog-512 (key = $salt), big-endian
+- CRC32
- 3DES (PT = $salt, key = $pass)
-- Skip32 (PT = $salt, key = $pass)
+- DES (PT = $salt, key = $pass)
- ChaCha20
-- phpass
-- scrypt
+- Skip32 (PT = $salt, key = $pass)
- PBKDF2-HMAC-MD5
- PBKDF2-HMAC-SHA1
- PBKDF2-HMAC-SHA256
- PBKDF2-HMAC-SHA512
-- Python passlib pbkdf2-sha1
-- Python passlib pbkdf2-sha256
+- scrypt
+- phpass
+- Ansible Vault
+- Atlassian (PBKDF2-HMAC-SHA1)
- Python passlib pbkdf2-sha512
-- Skype
+- Python passlib pbkdf2-sha256
+- Python passlib pbkdf2-sha1
+- TACACS+
+- SIP digest authentication (MD5)
+- IKE-PSK MD5
+- IKE-PSK SHA1
- WPA-EAPOL-PBKDF2
- WPA-EAPOL-PMK
- WPA-PMKID-PBKDF2
- WPA-PMKID-PMK
-- iSCSI CHAP authentication, MD5(CHAP)
-- IKE-PSK MD5
-- IKE-PSK SHA1
-- NetNTLMv1
-- NetNTLMv1+ESS
-- NetNTLMv2
- IPMI2 RAKP HMAC-SHA1
-- Kerberos 5 AS-REQ Pre-Auth etype 23
-- Kerberos 5 AS-REP etype 23
-- Kerberos 5 TGS-REP etype 23 (RC4-HMAC-MD5)
-- Kerberos 5 Pre-Auth etype 17/18 (AES128-CTS-HMAC-SHA1-96)
-- Kerberos 5 TGS-REP etype 17/18 (AES128-CTS-HMAC-SHA1-96)
-- DNSSEC (NSEC3)
- CRAM-MD5
+- iSCSI CHAP authentication, MD5(CHAP)
+- JWT (JSON Web Token)
+- Kerberos 5, etype 23, AS-REQ Pre-Auth
+- Kerberos 5, etype 23, TGS-REP
+- Kerberos 5, etype 23, AS-REP
+- Kerberos 5, etype 17, TGS-REP
+- Kerberos 5, etype 18, TGS-REP
+- Kerberos 5, etype 17, Pre-Auth
+- Kerberos 5, etype 18, Pre-Auth
+- NetNTLMv1 / NetNTLMv1+ESS
+- NetNTLMv2
+- Skype
- PostgreSQL CRAM (MD5)
- MySQL CRAM (SHA1)
-- SIP digest authentication (MD5)
-- TACACS+
-- JWT (JSON Web Token)
-- SMF (Simple Machines Forum) > v1.1
-- phpBB3 (MD5)
-- vBulletin < v3.8.5
-- vBulletin >= v3.8.5
-- MyBB 1.2+
-- IPB2+ (Invision Power Board)
-- WBB3 (Woltlab Burning Board)
-- Joomla < 2.5.18
-- Joomla >= 2.5.18 (MD5)
-- WordPress (MD5)
-- PHPS
-- Drupal7
-- osCommerce
-- xt:Commerce
-- PrestaShop
-- Django (SHA-1)
-- Django (PBKDF2-SHA256)
-- Tripcode
-- MediaWiki B type
-- OpenCart
-- Redmine
-- PunBB
-- Atlassian (PBKDF2-HMAC-SHA1)
-- PostgreSQL
-- MSSQL (2000)
-- MSSQL (2005)
-- MSSQL (2012, 2014)
-- MySQL323
-- MySQL4.1/MySQL5
-- Oracle H: Type (Oracle 7+)
-- Oracle S: Type (Oracle 11+)
-- Oracle T: Type (Oracle 12+)
-- Sybase ASE
-- Episerver 6.x < .NET 4
-- Episerver 6.x >= .NET 4
-- Apache $apr1$ MD5, md5apr1, MD5 (APR)
-- ColdFusion 10+
-- hMailServer
-- nsldap, SHA-1(Base64), Netscape LDAP SHA
-- nsldaps, SSHA-1(Base64), Netscape LDAP SSHA
-- SSHA-256(Base64), LDAP {SSHA256}
-- SSHA-512(Base64), LDAP {SSHA512}
-- CRAM-MD5 Dovecot
-- FileZilla Server >= 0.9.55
-- CRC32
-- LM
-- NTLM
-- Domain Cached Credentials (DCC), MS Cache
-- Domain Cached Credentials 2 (DCC2), MS Cache 2
-- DPAPI masterkey file v1
-- DPAPI masterkey file v2
-- MS-AzureSync PBKDF2-HMAC-SHA256
-- descrypt, DES (Unix), Traditional DES
-- BSDi Crypt, Extended DES
-- md5crypt, MD5 (Unix), Cisco-IOS $1$ (MD5)
-- bcrypt $2*$, Blowfish (Unix)
-- sha256crypt $5$, SHA256 (Unix)
-- sha512crypt $6$, SHA512 (Unix)
-- macOS v10.4, MacOS v10.5, MacOS v10.6
-- macOS v10.7
-- macOS v10.8+ (PBKDF2-SHA512)
+- RACF
- AIX {smd5}
- AIX {ssha1}
- AIX {ssha256}
- AIX {ssha512}
-- Cisco-PIX MD5
+- LM
+- QNX /etc/shadow (MD5)
+- QNX /etc/shadow (SHA256)
+- QNX /etc/shadow (SHA512)
+- DPAPI masterkey file v1
+- DPAPI masterkey file v2
+- GRUB 2
+- MS-AzureSync PBKDF2-HMAC-SHA256
+- BSDi Crypt, Extended DES
+- NTLM
+- macOS v10.4, macOS v10.5, MacOS v10.6
+- macOS v10.7
+- macOS v10.8+ (PBKDF2-SHA512)
+- Radmin2
+- Samsung Android Password/PIN
+- bcrypt $2*$, Blowfish (Unix)
+- md5crypt, MD5 (Unix), Cisco-IOS $1$ (MD5)
+- descrypt, DES (Unix), Traditional DES
+- sha256crypt $5$, SHA256 (Unix)
+- sha512crypt $6$, SHA512 (Unix)
+- Windows Phone 8+ PIN/password
- Cisco-ASA MD5
-- Cisco-IOS $1$ (MD5)
-- Cisco-IOS type 4 (SHA256)
- Cisco-IOS $8$ (PBKDF2-SHA256)
- Cisco-IOS $9$ (scrypt)
-- Juniper NetScreen/SSG (ScreenOS)
-- Juniper IVE
-- Juniper/NetBSD sha1crypt
-- FortiGate (FortiOS)
-- Samsung Android Password/PIN
-- Windows Phone 8+ PIN/password
+- Cisco-IOS type 4 (SHA256)
+- Cisco-PIX MD5
- Citrix NetScaler
-- RACF
-- GRUB 2
-- Radmin2
+- Domain Cached Credentials (DCC), MS Cache
+- Domain Cached Credentials 2 (DCC2), MS Cache 2
+- FortiGate (FortiOS)
- ArubaOS
+- Juniper IVE
+- Juniper NetScreen/SSG (ScreenOS)
+- Juniper/NetBSD sha1crypt
+- MSSQL (2000)
+- MSSQL (2005)
+- MSSQL (2012, 2014)
+- PostgreSQL
+- Oracle H: Type (Oracle 7+)
+- Oracle S: Type (Oracle 11+)
+- Oracle T: Type (Oracle 12+)
+- MySQL323
+- MySQL4.1/MySQL5
+- Sybase ASE
+- hMailServer
+- DNSSEC (NSEC3)
+- CRAM-MD5 Dovecot
+- SSHA-256(Base64), LDAP {SSHA256}
+- SSHA-512(Base64), LDAP {SSHA512}
+- FileZilla Server >= 0.9.55
+- ColdFusion 10+
+- Apache $apr1$ MD5, md5apr1, MD5 (APR)
+- Episerver 6.x < .NET 4
+- Episerver 6.x >= .NET 4
+- nsldap, SHA-1(Base64), Netscape LDAP SHA
+- nsldaps, SSHA-1(Base64), Netscape LDAP SSHA
- SAP CODVN B (BCODE)
+- SAP CODVN B (BCODE) from RFC_READ_TABLE
- SAP CODVN F/G (PASSCODE)
+- SAP CODVN F/G (PASSCODE) from RFC_READ_TABLE
- SAP CODVN H (PWDSALTEDHASH) iSSHA-1
+- PeopleSoft
+- PeopleSoft PS_TOKEN
- Lotus Notes/Domino 5
- Lotus Notes/Domino 6
- Lotus Notes/Domino 8
-- PeopleSoft
-- PeopleSoft PS_TOKEN
- Oracle Transportation Management (SHA256)
-- 7-Zip
-- RAR3-hp
-- RAR5
-- AxCrypt
-- AxCrypt in-memory SHA1
-- WinZip
-- PKZIP archive encryption
-- PKZIP Master Key
-- iTunes backup < 10.0
-- iTunes backup >= 10.0
-- Android Backup
-- TrueCrypt
-- Android FDE <= 4.3
-- Android FDE (Samsung DEK)
+- Huawei sha1(md5($pass).$salt)
+- AuthMe sha256
- eCryptfs
-- VeraCrypt
- LUKS
-- DiskCryptor
+- VeraCrypt
- FileVault 2
+- DiskCryptor
+- Android FDE (Samsung DEK)
+- Android FDE <= 4.3
- Apple File System (APFS)
-- MS Office <= 2003
-- MS Office 2007
-- MS Office 2010
-- MS Office 2013
+- TrueCrypt
- PDF 1.1 - 1.3 (Acrobat 2 - 4)
+- PDF 1.1 - 1.3 (Acrobat 2 - 4), collider #1
+- PDF 1.1 - 1.3 (Acrobat 2 - 4), collider #2
- PDF 1.4 - 1.6 (Acrobat 5 - 8)
- PDF 1.7 Level 3 (Acrobat 9)
- PDF 1.7 Level 8 (Acrobat 10 - 11)
-- Apple Secure Notes
-- Open Document Format (ODF) 1.1 (SHA-1, Blowfish)
+- MS Office 2007
+- MS Office 2010
+- MS Office 2013
+- MS Office <= 2003 $0/$1, MD5 + RC4
+- MS Office <= 2003 $0/$1, MD5 + RC4, collider #1
+- MS Office <= 2003 $0/$1, MD5 + RC4, collider #2
+- MS Office <= 2003 $3/$4, SHA1 + RC4
+- MS Office <= 2003 $3, SHA1 + RC4, collider #1
+- MS Office <= 2003 $3, SHA1 + RC4, collider #2
- Open Document Format (ODF) 1.2 (SHA-256, AES)
+- Open Document Format (ODF) 1.1 (SHA-1, Blowfish)
+- Apple Secure Notes
+- JKS Java Key Store Private Keys (SHA1)
+- 1Password, agilekeychain
+- 1Password, cloudkeychain
- Password Safe v2
- Password Safe v3
- LastPass + LastPass sniffed
-- 1Password, agilekeychain
-- 1Password, cloudkeychain
+- KeePass 1 (AES/Twofish) and KeePass 2 (AES)
- Bitcoin/Litecoin wallet.dat
+- Electrum Wallet (Salt-Type 1-3)
- Blockchain, My Wallet
- Blockchain, My Wallet, V2
- Blockchain, My Wallet, Second Password (SHA256)
-- Electrum Wallet (Salt-Type 1-3)
-- KeePass 1 (AES/Twofish) and KeePass 2 (AES)
-- JKS Java Key Store Private Keys (SHA1)
+- Ethereum Pre-Sale Wallet, PBKDF2-HMAC-SHA256
- Ethereum Wallet, PBKDF2-HMAC-SHA256
- Ethereum Wallet, SCRYPT
-- Ethereum Pre-Sale Wallet, PBKDF2-HMAC-SHA256
-- Ansible Vault
-- Plaintext
+- 7-Zip
+- RAR3-hp
+- RAR5
+- PKZIP (Compressed)
+- PKZIP (Compressed Multi-File)
+- PKZIP (Mixed Multi-File)
+- PKZIP (Mixed Multi-File Checksum-Only)
+- PKZIP (Uncompressed)
+- PKZIP Master Key
+- PKZIP Master Key (6 byte optimization)
+- iTunes backup < 10.0
+- iTunes backup >= 10.0
+- WinZip
+- Android Backup
+- AxCrypt
+- AxCrypt in-memory SHA1
+- WBB3 (Woltlab Burning Board)
+- vBulletin < v3.8.5
+- vBulletin >= v3.8.5
+- PHPS
+- SMF (Simple Machines Forum) > v1.1
+- MediaWiki B type
+- Redmine
+- Django (PBKDF2-SHA256)
+- Django (SHA-1)
+- Joomla < 2.5.18
+- OpenCart
+- PrestaShop
+- Tripcode
+- Drupal7
+- osCommerce, xt:Commerce
+- PunBB
+- MyBB 1.2+, IPB2+ (Invision Power Board)
+- TOTP (HMAC-SHA1)
##
## Attack-Modes
From 7284b934cb84a51a9cba4580de22e3116fbbf582 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Wed, 7 Aug 2019 16:20:26 +0200
Subject: [PATCH 097/113] Fix null pointer dereference in case LM hash with
both LM parts was given without hash file
---
src/status.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/src/status.c b/src/status.c
index c8b95a809..718336f43 100644
--- a/src/status.c
+++ b/src/status.c
@@ -309,7 +309,7 @@ char *status_get_hash_target (const hashcat_ctx_t *hashcat_ctx)
const hashes_t *hashes = hashcat_ctx->hashes;
const module_ctx_t *module_ctx = hashcat_ctx->module_ctx;
- if (hashes->digests_cnt == 1)
+ if ((hashes->digests_cnt == 1) || (hashes->hashfile == NULL))
{
if (module_ctx->module_hash_encode_status != MODULE_DEFAULT)
{
From e921fbdf19b1958a7849c2b4eb0bff025a2dada9 Mon Sep 17 00:00:00 2001
From: Gabriele Gristina <gabriele.gristina@gmail.com>
Date: Wed, 7 Aug 2019 21:21:14 +0200
Subject: [PATCH 098/113] update SolarWinds Orion patch (3)
---
OpenCL/m21500-pure.cl | 4 ++--
docs/readme.txt | 1 -
src/Makefile | 2 +-
src/modules/module_21500.c | 45 +++++++-------------------------------
4 files changed, 11 insertions(+), 41 deletions(-)
diff --git a/OpenCL/m21500-pure.cl b/OpenCL/m21500-pure.cl
index 0a8cad2f4..5864d8a61 100644
--- a/OpenCL/m21500-pure.cl
+++ b/OpenCL/m21500-pure.cl
@@ -30,7 +30,7 @@ typedef struct pbkdf2_sha1_tmp
typedef struct pbkdf2_sha1
{
- u32 salt_buf[5];
+ u32 salt_buf[64];
} pbkdf2_sha1_t;
@@ -243,7 +243,7 @@ KERNEL_FQ void m21500_comp (KERN_ATTR_TMPS_ESALT (pbkdf2_sha1_tmp_t, pbkdf2_sha1
sha512_init (&ctx);
- sha512_update (&ctx, (const u32 *)tmps[gid].out, 1024);
+ sha512_update_global (&ctx, tmps[gid].out, 1024);
sha512_final (&ctx);
diff --git a/docs/readme.txt b/docs/readme.txt
index 442dab752..7e3e8d468 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -279,7 +279,6 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- Ethereum Wallet, SCRYPT
- Ethereum Pre-Sale Wallet, PBKDF2-HMAC-SHA256
- Ansible Vault
-- SolarWinds Orion, SHA512(PBKDF2-HMAC-SHA1)
- Plaintext
##
diff --git a/src/Makefile b/src/Makefile
index a0fc8e842..c61078a4a 100644
--- a/src/Makefile
+++ b/src/Makefile
@@ -4,7 +4,7 @@
##
SHARED := 0
-DEBUG := 1
+DEBUG := 0
PRODUCTION := 0
PRODUCTION_VERSION := v5.1.0
ENABLE_BRAIN := 1
diff --git a/src/modules/module_21500.c b/src/modules/module_21500.c
index 4afb4d687..53d4fd46b 100644
--- a/src/modules/module_21500.c
+++ b/src/modules/module_21500.c
@@ -58,7 +58,7 @@ typedef struct pbkdf2_sha1_tmp
typedef struct pbkdf2_sha1
{
- u32 salt_buf[5];
+ u32 salt_buf[64];
} pbkdf2_sha1_t;
@@ -140,7 +140,7 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
// salt
- const u8 *salt_pos = token.buf[1];
+ const char *salt_pos = (char *) token.buf[1];
int salt_len = token.len[1];
@@ -148,14 +148,9 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
memset (custom_salt, 0, sizeof (custom_salt));
- for (int i = 0; i < salt_len; i++, salt_pos++)
- {
- if (*salt_pos >= 'A' && *salt_pos <= 'Z') {
- custom_salt[i] = *salt_pos + 32;
- } else {
- custom_salt[i] = *salt_pos;
- }
- }
+ strncpy (custom_salt, salt_pos, salt_len);
+
+ lowercase ((u8 *) custom_salt, salt_len);
if (salt_len < 8)
{
@@ -163,7 +158,8 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
salt_len = 8;
}
- memcpy (pbkdf2_sha1->salt_buf, custom_salt, salt_len);
+ memcpy ((char *) pbkdf2_sha1->salt_buf, custom_salt, salt_len);
+ memcpy (salt->salt_buf, custom_salt, salt_len);
salt->salt_len = salt_len;
@@ -196,32 +192,7 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
{
- const u64 *digest = (u64 *) digest_buf;
-
- const pbkdf2_sha1_t *pbkdf2_sha1 = (const pbkdf2_sha1_t *) esalt_buf;
-
- // hash
-
- u64 tmp[9];
-
- tmp[0] = byte_swap_64 (digest[0]);
- tmp[1] = byte_swap_64 (digest[1]);
- tmp[2] = byte_swap_64 (digest[2]);
- tmp[3] = byte_swap_64 (digest[3]);
- tmp[4] = byte_swap_64 (digest[4]);
- tmp[5] = byte_swap_64 (digest[5]);
- tmp[6] = byte_swap_64 (digest[6]);
- tmp[7] = byte_swap_64 (digest[7]);
- tmp[8] = 0;
-
- char hash_enc[256] = { 0 };
-
- base64_encode (int_to_base64, (const u8 *) tmp, 64, (u8 *) hash_enc);
-
- // output
- const int line_len = snprintf (line_buf, line_size, "%s%s$%s", SIGNATURE_SOLARWINDS_ORION, (const u8 *) pbkdf2_sha1->salt_buf, hash_enc);
-
- return line_len;
+ return snprintf (line_buf, line_size, "%s", hash_info->orighash);
}
void module_init (module_ctx_t *module_ctx)
From cadf20b4b9d7ae67ac798429fd267e94526f1811 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Thu, 8 Aug 2019 10:47:09 +0200
Subject: [PATCH 099/113] Fix some code in -m 21500
---
OpenCL/m21500-pure.cl | 18 ++++----
src/modules/module_21500.c | 85 +++++++++++++++++++++++-------------
tools/test_modules/m21500.pm | 26 ++++++-----
3 files changed, 80 insertions(+), 49 deletions(-)
diff --git a/OpenCL/m21500-pure.cl b/OpenCL/m21500-pure.cl
index 5864d8a61..510aa7b23 100644
--- a/OpenCL/m21500-pure.cl
+++ b/OpenCL/m21500-pure.cl
@@ -18,7 +18,7 @@
#define COMPARE_S "inc_comp_single.cl"
#define COMPARE_M "inc_comp_multi.cl"
-typedef struct pbkdf2_sha1_tmp
+typedef struct solarwinds_tmp
{
u32 ipad[5];
u32 opad[5];
@@ -26,13 +26,13 @@ typedef struct pbkdf2_sha1_tmp
u32 dgst[260];
u32 out[260];
-} pbkdf2_sha1_tmp_t;
+} solarwinds_tmp_t;
-typedef struct pbkdf2_sha1
+typedef struct solarwinds
{
- u32 salt_buf[64];
+ u32 salt_buf[64 + 1];
-} pbkdf2_sha1_t;
+} solarwinds_t;
DECLSPEC void hmac_sha1_run_V (u32x *w0, u32x *w1, u32x *w2, u32x *w3, u32x *ipad, u32x *opad, u32x *digest)
{
@@ -70,7 +70,7 @@ DECLSPEC void hmac_sha1_run_V (u32x *w0, u32x *w1, u32x *w2, u32x *w3, u32x *ipa
sha1_transform_vector (w0, w1, w2, w3, digest);
}
-KERNEL_FQ void m21500_init (KERN_ATTR_TMPS_ESALT (pbkdf2_sha1_tmp_t, pbkdf2_sha1_t))
+KERNEL_FQ void m21500_init (KERN_ATTR_TMPS_ESALT (solarwinds_tmp_t, solarwinds_t))
{
/**
* base
@@ -96,7 +96,7 @@ KERNEL_FQ void m21500_init (KERN_ATTR_TMPS_ESALT (pbkdf2_sha1_tmp_t, pbkdf2_sha1
tmps[gid].opad[3] = sha1_hmac_ctx.opad.h[3];
tmps[gid].opad[4] = sha1_hmac_ctx.opad.h[4];
- sha1_hmac_update_global_swap (&sha1_hmac_ctx, esalt_bufs[digests_offset].salt_buf, salt_bufs[salt_pos].salt_len);
+ sha1_hmac_update_global_swap (&sha1_hmac_ctx, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
for (u32 i = 0, j = 1; i < 256; i += 5, j += 1)
{
@@ -142,7 +142,7 @@ KERNEL_FQ void m21500_init (KERN_ATTR_TMPS_ESALT (pbkdf2_sha1_tmp_t, pbkdf2_sha1
}
}
-KERNEL_FQ void m21500_loop (KERN_ATTR_TMPS_ESALT (pbkdf2_sha1_tmp_t, pbkdf2_sha1_t))
+KERNEL_FQ void m21500_loop (KERN_ATTR_TMPS_ESALT (solarwinds_tmp_t, solarwinds_t))
{
const u64 gid = get_global_id (0);
@@ -227,7 +227,7 @@ KERNEL_FQ void m21500_loop (KERN_ATTR_TMPS_ESALT (pbkdf2_sha1_tmp_t, pbkdf2_sha1
}
}
-KERNEL_FQ void m21500_comp (KERN_ATTR_TMPS_ESALT (pbkdf2_sha1_tmp_t, pbkdf2_sha1_t))
+KERNEL_FQ void m21500_comp (KERN_ATTR_TMPS_ESALT (solarwinds_tmp_t, solarwinds_t))
{
/**
* base
diff --git a/src/modules/module_21500.c b/src/modules/module_21500.c
index 53d4fd46b..7a774dcd8 100644
--- a/src/modules/module_21500.c
+++ b/src/modules/module_21500.c
@@ -22,14 +22,10 @@ static const u64 KERN_TYPE = 21500;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_USES_BITS_64
| OPTI_TYPE_SLOW_HASH_SIMD_LOOP;
-static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE
- | OPTS_TYPE_ST_BASE64
- | OPTS_TYPE_HASH_COPY;
+static const u64 OPTS_TYPE = OPTS_TYPE_PT_GENERATE_LE;
static const u32 SALT_TYPE = SALT_TYPE_EMBEDDED;
static const char *ST_PASS = "hashcat";
-static const char *ST_HASH = "$solarwinds$0$hashcat1$Dnz04T9ptYINnj9mckXTuk80w6f1vkZLwv02HiufklgnDw53BU1bgn4gsHia/Q6kxYSqK4PDbxRMwa6HB5KA/w==";
-
-static const char *SALT_PADDING = "1244352345234";
+static const char *ST_HASH = "$solarwinds$0$admin$fj4EBQewCQUZ7IYHl0qL8uj9kQSBb3m7N4u0crkKK0Uj9rbbAnSrBZMXO7oWx9KqL3sCzwncvPZ9hyDV9QCFTg==";
u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
@@ -46,7 +42,7 @@ u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig,
const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
-typedef struct pbkdf2_sha1_tmp
+typedef struct solarwinds_tmp
{
u32 ipad[5];
u32 opad[5];
@@ -54,13 +50,13 @@ typedef struct pbkdf2_sha1_tmp
u32 dgst[260];
u32 out[260];
-} pbkdf2_sha1_tmp_t;
+} solarwinds_tmp_t;
-typedef struct pbkdf2_sha1
+typedef struct solarwinds
{
- u32 salt_buf[64];
+ u32 salt_buf[64 + 1];
-} pbkdf2_sha1_t;
+} solarwinds_t;
static const u32 ROUNDS_SOLARWINDS_ORION = 1000;
@@ -68,14 +64,14 @@ static const char *SIGNATURE_SOLARWINDS_ORION = "$solarwinds$0$";
u64 module_esalt_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
{
- const u64 esalt_size = (const u64) sizeof (pbkdf2_sha1_t);
+ const u64 esalt_size = (const u64) sizeof (solarwinds_t);
return esalt_size;
}
u64 module_tmp_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra)
{
- const u64 tmp_size = (const u64) sizeof (pbkdf2_sha1_tmp_t);
+ const u64 tmp_size = (const u64) sizeof (solarwinds_tmp_t);
return tmp_size;
}
@@ -106,7 +102,7 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
{
u64 *digest = (u64 *) digest_buf;
- pbkdf2_sha1_t *pbkdf2_sha1 = (pbkdf2_sha1_t *) esalt_buf;
+ solarwinds_t *solarwinds = (solarwinds_t *) esalt_buf;
token_t token;
@@ -121,12 +117,12 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
token.sep[1] = '$';
token.len_min[1] = 0;
- token.len_max[1] = 16;
+ token.len_max[1] = 256;
token.attr[1] = TOKEN_ATTR_VERIFY_LENGTH;
token.sep[2] = '$';
- token.len_min[2] = 64;
- token.len_max[2] = 256;
+ token.len_min[2] = 88;
+ token.len_max[2] = 88;
token.attr[2] = TOKEN_ATTR_VERIFY_LENGTH
| TOKEN_ATTR_VERIFY_BASE64A;
@@ -138,30 +134,34 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
salt->salt_iter = ROUNDS_SOLARWINDS_ORION - 1;
- // salt
+ // save original salt for encode function
+ // this is the only reason why we have an esalt in this hash-mode
const char *salt_pos = (char *) token.buf[1];
+ const int salt_len = token.len[1];
- int salt_len = token.len[1];
+ memcpy (solarwinds->salt_buf, salt_pos, salt_len);
- char custom_salt[17];
+ // for pbkdf2 salt we need to do hash-mode specific modifications
- memset (custom_salt, 0, sizeof (custom_salt));
+ #define FIXED_SALT_LEN 8
- strncpy (custom_salt, salt_pos, salt_len);
+ char custom_salt[FIXED_SALT_LEN];
- lowercase ((u8 *) custom_salt, salt_len);
+ memcpy (custom_salt, salt_pos, MIN (FIXED_SALT_LEN, salt_len));
- if (salt_len < 8)
+ if (salt_len < FIXED_SALT_LEN)
{
- strncat (custom_salt, SALT_PADDING, 8 - salt_len);
- salt_len = 8;
+ static const char *SALT_PADDING = "1244352345234";
+
+ memcpy (custom_salt + salt_len, SALT_PADDING, FIXED_SALT_LEN - salt_len);
}
- memcpy ((char *) pbkdf2_sha1->salt_buf, custom_salt, salt_len);
- memcpy (salt->salt_buf, custom_salt, salt_len);
+ lowercase ((u8 *) custom_salt, FIXED_SALT_LEN);
- salt->salt_len = salt_len;
+ memcpy (salt->salt_buf, custom_salt, FIXED_SALT_LEN);
+
+ salt->salt_len = FIXED_SALT_LEN;
// hash
@@ -192,7 +192,32 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
{
- return snprintf (line_buf, line_size, "%s", hash_info->orighash);
+ const u64 *digest = (u64 *) digest_buf;
+
+ const solarwinds_t *solarwinds = (const solarwinds_t *) esalt_buf;
+
+ // hash
+
+ u64 tmp[9];
+
+ tmp[0] = byte_swap_64 (digest[0]);
+ tmp[1] = byte_swap_64 (digest[1]);
+ tmp[2] = byte_swap_64 (digest[2]);
+ tmp[3] = byte_swap_64 (digest[3]);
+ tmp[4] = byte_swap_64 (digest[4]);
+ tmp[5] = byte_swap_64 (digest[5]);
+ tmp[6] = byte_swap_64 (digest[6]);
+ tmp[7] = byte_swap_64 (digest[7]);
+ tmp[8] = 0;
+
+ char hash_enc[256] = { 0 };
+
+ base64_encode (int_to_base64, (const u8 *) tmp, 64, (u8 *) hash_enc);
+
+ // output
+ const int line_len = snprintf (line_buf, line_size, "%s%s$%s", SIGNATURE_SOLARWINDS_ORION, (const char *) solarwinds->salt_buf, hash_enc);
+
+ return line_len;
}
void module_init (module_ctx_t *module_ctx)
diff --git a/tools/test_modules/m21500.pm b/tools/test_modules/m21500.pm
index 209a9c16b..c09d3eb9a 100644
--- a/tools/test_modules/m21500.pm
+++ b/tools/test_modules/m21500.pm
@@ -13,24 +13,30 @@ use Crypt::PBKDF2;
use Digest::SHA qw (sha512);
use Encode;
-sub module_constraints { [[0, 256], [8, 16], [-1, -1], [-1, -1], [-1, -1]] }
+sub module_constraints { [[0, 256], [0, 256], [-1, -1], [-1, -1], [-1, -1]] }
sub module_generate_hash
{
my $word = shift;
my $salt = shift;
- my $iter = 1000;
my $kdf = Crypt::PBKDF2->new
(
hash_class => 'HMACSHA1',
- iterations => $iter,
+ iterations => 1000,
output_len => 1024
);
- my $key = $kdf->PBKDF2 ($salt, $word);
+ my $custom_salt = substr ($salt, 0, 8);
- my $key_b64 = encode_base64 (sha512($key), "");
+ if (length $custom_salt < 8)
+ {
+ $custom_salt = substr ($custom_salt . "1244352345234", 0, 8);
+ }
+
+ my $key = $kdf->PBKDF2 ($custom_salt, $word);
+
+ my $key_b64 = encode_base64 (sha512 ($key), "");
my $hash = sprintf ("\$solarwinds\$0\$%s\$%s", $salt, $key_b64);
@@ -48,20 +54,20 @@ sub module_verify_hash
my @data = split ('\$', $hash);
- return unless scalar @data == 4;
+ return unless scalar @data == 5;
shift @data;
my $signature = shift @data;
my $sig_dec = shift @data;
my $salt = shift @data;
- my $hash_b64 = shift @data;
- my $hash_raw = decode_base64 ($hash_b64);
+ my $digest = shift @data;
return unless ($signature eq "solarwinds");
return unless ($sig_dec eq "0");
- return unless (length ($salt) > 16);
- return unless (length ($hash_raw) != 128);
+
+ return if length ($salt) > 256;
+ return unless length ($digest) == 88;
my $word_packed = pack_if_HEX_notation ($word);
From 706d69ba08f3efa11c94ee112252dfbb28ff367a Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Thu, 8 Aug 2019 11:30:24 +0200
Subject: [PATCH 100/113] Add SolarWinds Orion info to readme and changes
---
docs/changes.txt | 1 +
docs/readme.txt | 1 +
2 files changed, 2 insertions(+)
diff --git a/docs/changes.txt b/docs/changes.txt
index 9f93e4006..f22cc8768 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -40,6 +40,7 @@
- Added hash-mode: QNX /etc/shadow (SHA256)
- Added hash-mode: QNX /etc/shadow (SHA512)
- Added hash-mode: Ruby on Rails Restful-Authentication
+- Added hash-mode: SolarWinds Orion
- Added hash-mode: md5($salt.sha1($salt.$pass))
- Added hash-mode: md5(sha1($pass).md5($pass).sha1($pass))
- Added hash-mode: md5(sha1($salt).md5($pass))
diff --git a/docs/readme.txt b/docs/readme.txt
index f698c8745..dc1da35d9 100644
--- a/docs/readme.txt
+++ b/docs/readme.txt
@@ -232,6 +232,7 @@ NVIDIA GPUs require "NVIDIA Driver" (418.56 or later) and "CUDA Toolkit" (10.1 o
- SAP CODVN H (PWDSALTEDHASH) iSSHA-1
- PeopleSoft
- PeopleSoft PS_TOKEN
+- SolarWinds Orion
- Lotus Notes/Domino 5
- Lotus Notes/Domino 6
- Lotus Notes/Domino 8
From 0dd4ffbd6b6022490fff08386d6425157b425419 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 10 Aug 2019 13:13:29 -0700
Subject: [PATCH 101/113] Replace loop bashisms
++var to var=$((var + 1))
---
tools/test.sh | 40 +++++++++++++++++++++++-----------------
1 file changed, 23 insertions(+), 17 deletions(-)
diff --git a/tools/test.sh b/tools/test.sh
index f19f4438d..0ecd5ec5b 100755
--- a/tools/test.sh
+++ b/tools/test.sh
@@ -316,7 +316,7 @@ function init()
fi
- ((i++))
+ i=$((i + 1))
done 9< "${OUTD}/${hash_type}_passwords.txt"
@@ -339,7 +339,8 @@ function init()
# generate multiple pass/hash foreach len (2 to 8)
if [ "${MODE}" -ge 1 ]; then
- for ((i = 2; i < 9; i++)); do
+ i=2
+ while [ "$i" -lt 9 ]; do
cmd_file=${OUTD}/${hash_type}_multi_${i}.txt
@@ -371,6 +372,7 @@ function init()
echo "${pass}" | cut -c ${p1}- >> "${OUTD}/${hash_type}_dict2_multi_${i}"
done 9< "${OUTD}/${hash_type}_passwords_multi_${i}.txt"
+ i=$((i + 1))
done
@@ -381,7 +383,7 @@ function status()
{
RET=$1
- ((cnt++))
+ cnt=$((cnt + 1))
if [ "${RET}" -ne 0 ]; then
case ${RET} in
@@ -389,14 +391,14 @@ function status()
if ! is_in_array "${hash_type}" ${NEVER_CRACK_ALGOS}; then
echo "password not found, cmdline : ${CMD}" >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
- ((e_nf++))
+ e_nf=$((e_nf + 1))
fi
;;
4)
echo "timeout reached, cmdline : ${CMD}" >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
- ((e_to++))
+ e_to=$((e_to + 1))
;;
10)
@@ -405,13 +407,13 @@ function status()
else
echo "hash:plains not matched in output, cmdline : ${CMD}" >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.tx"t
fi
- ((e_nm++))
+ e_nm=$((e_nm + 1))
;;
*)
echo "! unhandled return code ${RET}, cmdline : ${CMD}" >> "${OUTD}/logfull.txt" 2>> "${OUTD}/logfull.txt"
echo "! unhandled return code, see ${OUTD}/logfull.txt for details."
- ((e_nf++))
+ e_nf=$((e_nf + 1))
;;
esac
fi
@@ -752,7 +754,7 @@ function attack_1()
fi
- ((i++))
+ i=$((i + 1))
done 9< "${OUTD}/${hash_type}_hashes.txt"
@@ -957,7 +959,7 @@ function attack_3()
# passwords can't be smaller than mask in -a 3 = mask attack
if [ "${#pass}" -lt ${i} ]; then
- ((i++))
+ i=$((i + 1))
continue
fi
@@ -985,7 +987,7 @@ function attack_3()
if [ "${hash_type}" -eq 20510 ]; then # special case for PKZIP Master Key
if [ "${i}" -le 1 ]; then
- ((i++))
+ i=$((i + 1))
continue
fi
@@ -1032,7 +1034,7 @@ function attack_3()
if [ $i -eq ${max} ]; then break; fi
- ((i++))
+ i=$((i + 1))
done 9< "${OUTD}/${hash_type}_hashes.txt"
@@ -1525,7 +1527,7 @@ function attack_6()
fi
if [ ${#pass} -le ${i} ]; then
- ((i++))
+ i=$((i + 1))
continue
fi
@@ -1611,7 +1613,7 @@ function attack_6()
if [ "${i}" -eq ${max} ]; then break; fi
- ((i++))
+ i=$((i + 1))
done 9< "${OUTD}/${hash_type}_hashes.txt"
@@ -1680,7 +1682,8 @@ function attack_6()
fi
- for ((i = 2; i < max; i++)); do
+ i=2
+ while [ "$i" -lt "$max" ]; do
hash_file=${OUTD}/${hash_type}_hashes_multi_${i}.txt
@@ -1745,6 +1748,7 @@ function attack_6()
fi
status ${ret}
+ i=$((i + 1))
done
@@ -1923,7 +1927,7 @@ function attack_7()
pass_len=${#pass}
if [ "${pass_len}" -le 6 ]; then
- ((i++))
+ i=$((i + 1))
continue
fi
@@ -1994,7 +1998,7 @@ function attack_7()
if [ $i -eq ${max} ]; then break; fi
- ((i++))
+ i=$((i + 1))
done 9< "${OUTD}/${hash_type}_hashes.txt"
@@ -2071,7 +2075,8 @@ function attack_7()
fi
- for ((i = 2; i < max; i++)); do
+ i=2
+ while [ "$i" -lt "$max" ]; do
hash_file=${OUTD}/${hash_type}_hashes_multi_${i}.txt
dict_file=${OUTD}/${hash_type}_dict2_multi_${i}
@@ -2163,6 +2168,7 @@ function attack_7()
fi
status ${ret}
+ i=$((i + 1))
done
From 0965e25943bedb13866d240430526d0baf8cdd0c Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 10 Aug 2019 13:16:14 -0700
Subject: [PATCH 102/113] Remove extra echo
Seems I forgot to remove this when converting to printf.
---
tools/test.sh | 1 -
1 file changed, 1 deletion(-)
diff --git a/tools/test.sh b/tools/test.sh
index 0ecd5ec5b..0adb8e174 100755
--- a/tools/test.sh
+++ b/tools/test.sh
@@ -1281,7 +1281,6 @@ function attack_3()
# charset 1
char=$(echo "${pass}" | cut -b ${charset_1_pos})
- charset_1=$(echo -e "${charset_1}\n${char}")
charset_1=$(printf "%s\n%s\n" "${charset_1}" "${char}")
# charset 2
From 685bcde52eb89b9968ad3802b0cf72223b7ff1be Mon Sep 17 00:00:00 2001
From: Mitar <mitar.github@tnode.com>
Date: Sun, 11 Aug 2019 02:30:42 -0700
Subject: [PATCH 103/113] Explaining prefix performance issues.
See: https://github.com/hashcat/hashcat/issues/2153
---
docs/performance.txt | 2 ++
1 file changed, 2 insertions(+)
diff --git a/docs/performance.txt b/docs/performance.txt
index c6455d1f0..6b728243a 100644
--- a/docs/performance.txt
+++ b/docs/performance.txt
@@ -3,6 +3,8 @@ Performance Notes:
- Always Use the latest display driver
- To significantly improve performance use -w 3
+- Cracking with a mask with a fixed prefix can be slow.
+ Consider instead using a mode with salt as a prefix and set salt to that fixed prefix.
Also read this:
From 417a1f65928da54ee4e8f1bbf6e3d086b6317053 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Mon, 12 Aug 2019 11:25:21 +0200
Subject: [PATCH 104/113] Add new hash-mode category 'framework'
---
include/types.h | 1 +
src/shared.c | 2 ++
2 files changed, 3 insertions(+)
diff --git a/include/types.h b/include/types.h
index e29944b13..0bc8ac636 100644
--- a/include/types.h
+++ b/include/types.h
@@ -2508,6 +2508,7 @@ typedef enum hash_category
HASH_CATEGORY_FORUM_SOFTWARE = 16,
HASH_CATEGORY_OTP = 17,
HASH_CATEGORY_PLAIN = 18,
+ HASH_CATEGORY_FRAMEWORK = 19,
} hash_category_t;
diff --git a/src/shared.c b/src/shared.c
index 7c0a67391..009322c48 100644
--- a/src/shared.c
+++ b/src/shared.c
@@ -95,6 +95,7 @@ static const char *HASH_CATEGORY_DOCUMENTS_STR = "Documents";
static const char *HASH_CATEGORY_PASSWORD_MANAGER_STR = "Password Managers";
static const char *HASH_CATEGORY_OTP_STR = "One-Time Passwords";
static const char *HASH_CATEGORY_PLAIN_STR = "Plaintext";
+static const char *HASH_CATEGORY_FRAMEWORK_STR = "Framework";
static inline int get_msb32 (const u32 v)
{
@@ -903,6 +904,7 @@ const char *strhashcategory (const u32 hash_category)
case HASH_CATEGORY_PASSWORD_MANAGER: return HASH_CATEGORY_PASSWORD_MANAGER_STR;
case HASH_CATEGORY_OTP: return HASH_CATEGORY_OTP_STR;
case HASH_CATEGORY_PLAIN: return HASH_CATEGORY_PLAIN_STR;
+ case HASH_CATEGORY_FRAMEWORK: return HASH_CATEGORY_FRAMEWORK_STR;
}
return NULL;
From 9268686eb4a734490132d0df59db2f9157c1bd75 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Mon, 12 Aug 2019 12:30:09 +0200
Subject: [PATCH 105/113] Updated docs/teams.txt and docs/credits.txt
---
docs/credits.txt | 14 +++-----------
docs/team.txt | 11 ++++++-----
2 files changed, 9 insertions(+), 16 deletions(-)
diff --git a/docs/credits.txt b/docs/credits.txt
index 58360d3de..e89ffe2a3 100644
--- a/docs/credits.txt
+++ b/docs/credits.txt
@@ -18,22 +18,16 @@ Philipp "philsmd" Schmidt <philsmd@hashcat.net> (@philsmd)
Gabriele "matrix" Gristina <matrix@hashcat.net> (@gm4tr1x)
-* SolarWinds Orion, SHA512(PBKDF2-HMAC-SHA1), kernel module
-* sha1(md5($pass).$salt) kernel module
-* gzip wordlists feature
-* SHA-224 kernel module + optimizations
-* Some AES OpenCL kernel module optimizations
+* Multiple kernel modules
+* Compressed wordlist feature
* OpenCL Info feature
* Apple macOS port
* Hardware monitor initial code base
* Test suite initial code base
-* Makefiles initial code base
+* Makefile initial code base
* Multithreading initial code base
* MultiGPU initial code base
* Benchmarks initial code base
-* Offline OpenCL Kernel Compiler support
-* SHA-512 initial code base
-* Some MD5 and SHA1 OpenCL optimizations
Jean-Christophe "Fist0urs" Delaunay <jean-christophe.delaunay@synacktiv.com> (@Fist0urs)
@@ -51,7 +45,6 @@ Jeremi "epixoip" Gosney <jgosney@terahash.com> (@jmgosney)
* Moderating the hashcat forum
* Helping tons of new users find their way into the hashcat universe
-
Other contributors to hashcat
* A full list and their commits can be found here:
@@ -85,4 +78,3 @@ Brandon Chalk <brandon@casaba.com> (@brandoncasaba)
* Kerberos Pre-Auth 17/18 kernel module, ported from @Fist0urs TGS kernel modules
!!! All the package maintainer of hashcat !!!
-
diff --git a/docs/team.txt b/docs/team.txt
index 76ca66eb9..d0ce79285 100644
--- a/docs/team.txt
+++ b/docs/team.txt
@@ -22,6 +22,7 @@ We're a group of people participating in the yearly repeating password cracking
| PCrack | SAINTCON, Utah | 2017 | 1st |
| Crack Me If You Can | DEF CON, Las Vegas | 2018 | 2nd |
| CracktheCon | Cyphercon, Milwaukee | 2019 | 1st |
+| Crack Me If You Can | DEF CON, Las Vegas | 2019 | 1st |
* Special recognition for team hashcat goes to:
@@ -34,8 +35,8 @@ abaco alotdv atom blandyuk blaz
BlowCane chancas Chick3nman coolbry95 dakykilla
deutsch dropdead epixoip EvilMog franky
gpufreak hashtka Hydraze J0hnnyBrav0 K9
-kontrast23 legion m3g9tr0n matrix minga
-N|IGHT5 NSAKEY NullMode philsmd purehate
-radix Rolf rurapenthe s3in!c SuperJames
-Szul tehnlulz The_Mechanic T0XlC TychoTithonus
-undeath unix-ninja Xanadrel xmisery
+kontrast23 Kryczek legion m3g9tr0n matrix
+minga N|IGHT5 NSAKEY NullMode philsmd
+purehate radix Rolf rurapenthe s3in!c
+SuperJames Szul tehnlulz The_Mechanic T0XlC
+TychoTithonus undeath unix-ninja Xanadrel xmisery
From 6c2d2565810f94eef4aa1030e771d702d51c6e09 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Wed, 14 Aug 2019 12:23:21 +0200
Subject: [PATCH 106/113] Documentation on keyboard-layout mapping feature
---
docs/keyboard-layout-mapping.md | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
create mode 100644 docs/keyboard-layout-mapping.md
diff --git a/docs/keyboard-layout-mapping.md b/docs/keyboard-layout-mapping.md
new file mode 100644
index 000000000..3a1009510
--- /dev/null
+++ b/docs/keyboard-layout-mapping.md
@@ -0,0 +1,19 @@
+## Some notes about the --keyboard-layout-mapping feature ##
+
+This new configuration item was added to handle a special TrueCrypt and VeraCrypt "feature" which is automatically active during the setup of encryption for a system partition or an entire system drive. Due to BIOS requirements, the user's keyboard layout is always set to the US keyboard layout during the pre-boot stage (no matter which layout is actually in use). In other words, in the pre-boot stage, when TC/VC asks the user to enter the password, the layout is actually set to the US keyboard layout.
+
+To avoid conflicts with the real keyboard layout configured in the OS, both TC and VC have a little trick: they set the OS keyboard layout to US keyboard layout while the password prompt window is opened. You can actually verify this in the language task bar while the password prompt window is open. It will switch from whatever is configured to English, and after the window is closed, the original keyboard layout is restored.
+
+This has a serious impact on cracking the password. For example, my German keyboard layout is a "QWERTZ" keyboard layout. The US keyboard, however used a "QWERTY" layout. The difference is that the position of the "y" and "z" letter is exchanged. If it was just that, this wouldn't be much of a problem - but almost all the special symbols are mapped very differently. (I won't go into the details; you might want to compare it yourself for fun.)
+
+And when it comes to non-Latin based languages, this behaviour gets completely out of control. Just one example: If the user enters the password بين التخصصات (interdisciplinary) on an Arabic keyboard, the password we need to guess is: fdk hgjowwhj[g.
+
+To deal with all of this, a hashcat user needs to know exactly which keyboard was enabled when the password was entered into the password window during setup. For German, I've added an example keyboard layout to the newly created folder "layouts", which now ships with the binary and on GitHub master. For instance, if you know a German keyboard was used, you can now add "--keyboard-layout-mapping layouts/de.hckmap" to the commandline.
+
+Unfortunately, since I don't own all of the existing keyboards, it will be necessary for hashcat users to contribute the rest of the missing mapping tables - ideally, as a GitHub PR. Almost every language I know has special keyboard layouts. There's even a difference between the UK and US layouts.
+
+Here's how you can help. To create a language-specific mapping table, open a text editor, and press every key on the keyboard, starting from the top left to the top right. Press Enter after every key. Use only keys which represent a real character, and ignore control keys such as Backspace, Caps Lock, etc. Then move to the next row below and repeat the process from the left to the right, and so on until you reach the space character. At that point, repeat exactly the same sequence, but with Shift pressed. When done, add a Tab after each character (Tab is used as separator character). Then switch the keyboard layout to English and repeat the entire process exactly in the same order, adding each character after the tab character. Hashcat fully supports all multibyte characters up to 32 bits on both sides of the mapping table (even if the right side side will be always a single byte character). As an example, see the layouts/de.hckmap file.
+
+Note that when it comes to Alt/AltGr, this behavior is exploitable. TC/VC does not accept those modifier keys. If a user uses AltGr while entering the password, a window appears that tells the user that the use of this key is not allowed. For instance, on my German keyboard layout, I need to use AltGr+q to get the "@" character. As a consequence of this, we know that the TC/VC password cannot include any of the characters ("@", "[", "]", "\", "€", "|", "{", "}", "~") if the user was using a German keyboard to enter the password.
+
+At the same time, we can guarantee that "@" will never be listed on the left side of the mapping table - because the only characters that can appear there are the ones that are are reachable only without any modifier or by using shift (but not AltGr). If we combine these concepts, we could add some code to reject all passwords which contain at least one character not listed in a mapping table. This is not yet implemented - but I'll add it if hashcat users agree that there is value in it.
From e5604bb65d8bdd636c81a387c20731314432f523 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Wed, 14 Aug 2019 12:24:16 +0200
Subject: [PATCH 107/113] Documentation on slow-candidates feature
---
docs/slow-candidates-mode.md | 34 ++++++++++++++++++++++++++++++++++
1 file changed, 34 insertions(+)
create mode 100644 docs/slow-candidates-mode.md
diff --git a/docs/slow-candidates-mode.md b/docs/slow-candidates-mode.md
new file mode 100644
index 000000000..273cdb1d7
--- /dev/null
+++ b/docs/slow-candidates-mode.md
@@ -0,0 +1,34 @@
+## Hashcat has a new generic password candidate interface called "slow candidates" ##
+
+The first goal of this new interface is to allow attachment of advanced password candidate generators in the future (for example hashcat's table attack, kwprocessor, OMEN, PassGAN, PCFG, princeprocessor, etc.). At this time, the only attack modes that have been added are hashcat's straight attack (including rules engine), combinator attack, and mask attack (AKA brute-force with Markov optimizer). You can enable this new general password-candidate interface by using the new -S/--slow-candidates option.
+
+The second goal of the slow candidates engine is to generate password candidates on-host (on CPU). This is useful when attacking large hashlists with fast hashes (but many salts), or generally with slow hashes. Sometimes we cannot fully run large wordlists in combination with rules, because it simply takes too much time. But if we know of a useful pattern that works well with rules, we often want to use rules with a smaller, targeted wordlist instead, in order to exploit the pattern. On GPU, this creates a bottleneck in hashcat's architecture - because hashcat can only assign the words from the wordlist to the GPU compute units.
+
+A common workaround for this is to use a pipe, and feed hashcat to itself. But this traditional piping approach came at a cost - no ETA, no way to easily distribute chunks, etc. It was also completely incompatible with overlays like Hashtopolis. And if piping hashcat to itself isn't feasible for some reason, you quickly run into performance problems with small wordlists and large rulesets.
+
+To demonstrate this, here's an example where you have a very small wordlist with just a single word in the wordlist, but a huge ruleset to exploit some pattern:
+
+```
+$ wc -l wordlist.txt
+1 wordlist.txt
+$ wc -l pattern.rule
+99092 pattern.rule
+```
+
+Since the total number of candidates is ([number-of-words-from-wordlist] * [number-of-rules]), this attack should theoretically be enough to fully feed all GPU compute units. But in practice, hashcat works differently internally - mostly to deal with fast hashes. This makes the performance of such an attack terrible:
+
+```
+$ ./hashcat -m 400 example400.hash wordlist.txt -r pattern.rule --speed-only
+...
+Speed.#2.........: 145 H/s (0.07ms)
+```
+
+This is where slow candidates comes into play. To feed the GPU compute units more efficiently, hashcat applies rules on-host instead, creating a virtual wordlist in memory for fast access. But more importantly from hashcat's perspective, we now have a large wordlist, which allows hashcat to supply all GPU compute units with candidates. Since hashcat still needs to transfer the candidates over PCI-Express, this slows down cracking performance. In exchange, we get a large overall performance increase - multiple times higher, even considering the PCI-Express bottleneck - for both slow hashes and salted fast hashes with many salts,
+
+Here's the exact same attack, but using the new -S option to turn on slow candidates:
+
+```
+$ ./hashcat -m 400 example400.hash wordlist.txt -r pattern.rule --speed-only -S
+...
+Speed.#2.........: 361.3 kH/s (3.54ms)
+```
From 59b67bd8017085fa50da770a47d123c939eb9c8b Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Wed, 14 Aug 2019 12:25:53 +0200
Subject: [PATCH 108/113] Documentation on brain feature
---
docs/hashcat-brain.md | 303 +++++++++++++++++++++++++++++++++++
docs/slow-candidates-mode.md | 2 +-
2 files changed, 304 insertions(+), 1 deletion(-)
create mode 100644 docs/hashcat-brain.md
diff --git a/docs/hashcat-brain.md b/docs/hashcat-brain.md
new file mode 100644
index 000000000..87f194ff3
--- /dev/null
+++ b/docs/hashcat-brain.md
@@ -0,0 +1,303 @@
+## The hashcat brain ##
+
+This feature will have a significant impact on the art of password cracking - either cracking alone, in small teams over a local network, or in large teams over the Internet.
+
+From a technical perspective, the hashcat brain consists of two in-memory databases called "long-term" and "short-term". When I realized that the human brain also has such a long-term and a short-term memory, that's when I chose to name this feature the "hashcat brain". No worries, you don't need to understand artificial intelligence (AI) here - we are simply talking about the "memory features" of the human brain.
+
+Put simply, the hashcat brain persistently remembers the attacks you've executed against a particular hashlist in the past ... but on a low level.
+
+Hashcat will check each password candidate against the "brain" to find out if that candidate was already checked in the past and then accept it or reject it. The brain will check each candidate for existence in both the long-term and short-term memory areas. The nice thing is that it does not matter which attack-mode originally was used - it can be straight attack, mask attack or any of the advanced future generators.
+
+The brain computes a hash (a very fast one called xxHash) of every password candidate and store it in the short-term memory first. Hashcat then starts cracking the usual way. Once it's done cracking, it sends a "commit" signal to the hashcat brain, which then moves the candidates from the short-term memory into the long-term memory.
+
+The hashcat brain feature uses a client/server architecture. That means that the hashcat brain itself is actually a network server. I know, I know - you don't want any network sockets in your hashcat process? No problem, then disable the feature in the makefile by setting ENABLE_BRAIN=0 and it will be gone forever.
+
+It's a network server for a reason. This way we can run multiple hashcat clients ... all using the same hashcat brain. This is great for collaboration with many people involved - plus it stays alive after the client shuts down. (Note, however, that even if you want to only use brain functionality locally, you must run two separate instances of hashcat - one to be the brain server, and one to be the client and perform attacks).
+
+That's it from the technical perspective. It's hard to explain how much potential there is in this, and I'm wondering why I didn't invent this sooner. Maybe it took the Crack Me If You Can password-cracking challenge to realize that we need a feature like this.
+
+Before you try it out yourself, let me show you a few examples.
+
+### Example 1: Duplicate candidates all around us ###
+
+There's no doubt that rule-based attacks are the greatest general purpose attack-modifier on an existing wordlist. But they have a little-known problem: They produce a lot of duplicate candidates. While this is not relevant for fast hashes, it has a large impact on slow hashes.
+
+In this example, we apply best64.rule to example.dict, and writes the result to test.txt:
+
+```
+$ ./hashcat --stdout example.dict -r rules/best64.rule -o test.txt
+```
+
+Now we can see how many candidates were produced:
+
+```
+$ cat test.txt | wc -l
+9888032
+```
+
+And now, let's see how many unique candidates are inside:
+
+```
+$ sort -u test.txt | wc -l
+7508620
+```
+
+Of course, the wordlist and rules used have a large impact on the number of duplicates. In our example - a common wordlist and general purpose rule - the average ratio of produced dupes seems to be around 25%. And all of these dupes are detected by the brain:
+
+```
+$ ./hashcat -z example0.hash example.dict -r rules/best64.rule
+...
+Rejected.........: 2379391/9888032 (24.06%)
+```
+
+Note:
+Hashcat brain rejects dynamically created duplicate candidates
+Average dynamically created duplicate candidates is around 25%
+Eliminating the duplicate 25% reduces the attack time by 25%
+
+### Example 2: stop caring about what you've done in the past ###
+
+Think of this: you have a single hash, but it is very high profile. You can use all of your resources. You start cracking - nothing. You try a different attack - still nothing. You're frustrated, but you must continue.. So try more attacks ... but even after two or more days - nothing. You start wondering what you've already done, but you're starting to lose track, getting tired, and making mistakes. Guess what? The hashcat brain comes to the rescue! Here's an attack that you've tried:
+
+```
+$ ./hashcat -z -m 6211 hashcat_ripemd160_aes.tc rockyou.txt
+...
+Time.Started.....: xxx (32 mins, 6 secs)
+```
+
+Note that the way you use hashcat doesn't change at all. The hash mode and attack mode can be replaced with anything you'd like. The only difference in your attack is that you add the new -z option to enable hashcat's new brain "client" functionality. By using -z you will also automatically enable the use of "slow candidates" -S mode.
+
+Now let's say that two days later, you forgot that you already performed the attack before. Or maybe it wasn't you who forgot, it's just your coworker on a different machine also trying. This is what happens:
+
+```
+$ ./hashcat -z -m 6211 hashcat_ripemd160_aes.tc rockyou.txt
+...
+Rejected.........: 14344384/14344384 (100.00%)
+Time.Started.....: xxx (15 secs)
+```
+
+The hashcat brain correctly rejected *all* of the candidates.
+
+Important things to note here:
+The rejected count exactly matches the keyspace.
+The attack took a bit of time - it's not 0 seconds. The process is not completely without cost. The client must hash all of the candidates, and transfer them to the hashcat brain; the hashcat brain must then search for those candidates in both memory regions, and send back a reject list; and then hashcat must select new candidates to fill the reject gaps, and so on ...
+Most important: 15 seconds is less than 32 minutes
+
+### Example 3: It's the candidates that matter, not the attack ###
+
+As I've stated above, it's not the command line that is stored somehow - it's not high level storage in this mode. This is where the hashcat brain server starts to create a strong advantage over manual (even organized) selection of attacks, because of the overlaps that naturally occur when carrying out a variety of attacks:
+
+```
+$ ./hashcat -z -m 6211 hashcat_ripemd160_aes.tc -a 3 ?d?d?d?d
+...
+Rejected.........: 6359/10000 (63.59%)
+```
+
+So what happened here? It rejected 63.59% of a mask? Yes, it did. The reason is this:
+
+```
+$ grep -c '^[0123456789]\{4\}$' rockyou.txt
+6359
+```
+
+Notes:
+The previous command from the second example kicks in here. In the rockyou wordlist, we have 6359 pure digits with length 4 and the hashcat brain was able to reject them - because the mask ?d?d?d?d will also produce them
+The hashcat brain does not care about your attack mode. Actually, you could say that the hashcat brain creates a kind of dynamic cross attack-mode while you are using it. As you can see here, attack-mode 0 and attack-mode 3 work together.
+The hashcat brain does not end after hashcat finishes - it stays intact because it's a stand-alone process
+
+### Example 4: Improve on what you've done in the past ###
+
+So you're out of ideas, and you start to run some simple brute-force. But you're clever, because you know the target tends to use the symbol "$" somewhere inside the password, and you optimize your mask for this. Let's start with an example not using the hashcat brain:
+
+```
+$ ./hashcat -m 6211 hashcat_ripemd160_aes.tc -a 3 -1 ?l?d$ ?1?1?1?1?1?1
+...
+Time.Started.....: xxx (5 hours, 37 mins)
+Progress.........: 2565726409/2565726409 (100.00%)
+```
+
+Damn - it did not crack. But then your coworker shows up and tells you that he found out that the target isn't just using the "$" symbol in his passwords, but also the "!" symbol. Damn, this makes your previous run (which took 5.5 hours) completely useless - wasted! You now need even more time for the correct run:
+
+```
+$ ./hashcat -m 6211 hashcat_ripemd160_aes.tc -a 3 -1 ?l?d$! ?1?1?1?1?1?1
+...
+Time.Started.....: xxx (6 hours, 39 mins)
+Progress.........: 3010936384/3010936384 (100.00%)
+```
+
+Now we do the same again, but with hashcat brain enabled. All of the work of that first command will no longer be wasted. The same commandline history, but this time with hashcat brain enabled, looks like this:
+
+```
+$ ./hashcat -z -m 6211 hashcat_ripemd160_aes.tc -a 3 -1 ?l?d$ ?1?1?1?1?1?1
+...
+Time.Started.....: xxx (5 hours, 37 mins)
+```
+
+But now, if we add the "!" character, we see the difference:
+
+```
+$ ./hashcat -z -m 6211 hashcat_ripemd160_aes.tc -a 3 -1 ?l?d$! ?1?1?1?1?1?1
+...
+Time.Started.....: xxx (1 hour, 5 mins)
+```
+
+So you can see here how the hashcat brain helps you to reduce the time for the second attack, from ~6 hours to ~1 hour.
+
+### Example 5: The resurrection of the random rules ###
+
+Random rules and salts? No way! Take a look at this, it's horrible:
+
+```
+$ cat wordlist.txt
+password
+$ ./hashcat wordlist.txt --stdout -g 100000 | sort -u | wc -l
+20473
+```
+
+What I'm trying to show here is how inefficient the random rules actually are (and always have been). They produce tons of duplicate work.
+
+As you can see from the above example, only 20473 of 100000 tested passwords of the produced random candidates are unique - and the remaining 80% is just wasted time.
+
+I cannot believe that I've never thought about this in detail, but now the hashcat brain brings this to an end:
+
+```
+./hashcat -z hashlist.txt wordlist.txt -g 100000
+...
+Rejected.........: 82093/100000 (82.09%)
+```
+
+This alone gives -g a new role in password cracking. If you've ever attended a password cracking contest, you know how important it is to find the patterns that were used to generate the password candidates. Because finding new patterns using the combination of random-rules and debug-rules is a very efficient way to find new attack vectors.
+
+For example, Team Hashcat managed to crack 188k/300k of the SSHA hashlist from the 2018 CMIYC contest - a strong showing. But with random rules, there's a really good chance that you'll discover what you missed. Here's an example of an attack I ran for only few minutes while writing this document:
+
+```
+$ ./hashcat -z -m 111 c0_111.list.txt wordlist.txt -g 100000 --debug-mode 4
+...
+INFO: Removed 188292 hashes found in potfile.
+...
+time:Z4 R3:tim2eeee
+sexual:Y3 Z5 O35:sexllllll
+poodle:Y2 T3 sBh:pooDlele
+pass123:C z5:ppppppASS123
+pool:y4 Z2 Y1:poolpoollll
+profit:o8F ^_:_profit
+smashing:Z3:smashingggg
+```
+
+These are real passwords that Team Hashcat didn't crack during the contest. What matters here is that you can see hints for possible patterns - which counts much more than just cracking a single password. And if you run the exact same command again, hashcat will generate different rules and you get more cracks, and discover more new patterns. You can do this again and again. We call this technique "raking".
+
+Note: It can occur that a pattern discovered from random rules matches an already known pattern. In such a case, it's a strong sign that this pattern may have been searched already, but has not yet been searched exhaustively. Perhaps a previous attack was stopped too early. But with the hashcat brain, that's no longer important - we can just apply the pattern without any worry about creating double work.
+
+## The costs of hashcat brain ##
+
+It should now be clear now what the potential is here. There are many other examples where this feature really kicks in, but I'm sure you already have your own ideas.
+
+Of course, the hashcat brain does not come for free - there are limitations. It's important to know some key numbers to decide when to use it (and when not to).
+
+Each password candidate creates a hash of 8 bytes that has to be transferred, looked up and stored in the hashcat brain. This brings us to the first question: What kind of hardware do you need? Fortunately, this is pretty easy to calculate. If you have a server with 64 GB of physical memory, then you can store 8,000,000,000 candidates. I guess that's the typical size of every serious password cracker's wordlist; if you have more, you typically have too much trash in your wordlists. If you have less, then you just haven't been collecting them long enough.
+
+So let's assume a candidate list size of 8,000,000,000. That doesn't sound like too much - especially if you want to work with rules and masks. It should be clear that using the hashcat brain against a raw MD5 is not very efficient. But now things become interesting, because of some unexpected effects that kick in.
+
+Imagine you have a salted MD5 list, let's say VBULL which is a fast hash (not a slow hash) - and you have many of them. In thise case, each of the salts starts to work for us.
+
+Yes, you read that right - the more salts, the better!!
+
+Let's continue with our calculation and our 8,000,000,000 password example. The speed of a typical VBULL on a Vega64 is 2170.6 MH/s. If we have 300,000 salts, the speed drops to 7235 H/s. Now to feed the hashcat brain at a rate of 7235 H/s, it will take you 1,105,736 seconds (or 12 days). That means you can run the hashcat brain for 12 days. It's an OK time I think, though I don't let many attacks run for such a long time. Also, this is an inexpensive server with 64GB physical RAM, and you could simply add more RAM, right? At this point we should also consider using swap memory. I think there's actually room for that - but I leave testing this to our users.
+
+Lookup times are pretty good. The hashcat brain uses two binary trees, which means that the more hashes that are added, the more efficient it becomes. Of course, the lookup times will increase drastically in the first moments, but will stabilize at some point. Note that we typically do not compare just one entry vs. million of entries - we compare hundreds of thousands of entries vs. millions of entries.
+
+## Technical details on the hashcat brain server ##
+
+The hashcat brain server saves the long-term memory to disc every 5 minutes automatically
+The server also saves the long-term memory if the hashcat brain server is killed using Ctrl-C
+There's no mitigation against database poisoning - this would cost too many resources
+There's currently no mitigation against an evil client requesting the server to allocate too much memory
+Make sure your hashcat brain server is protected with a good password, because you have to trust your clients
+I'll add a standalone hashcat brain seeding tool later which enables you to easily push all the words from an entire wordlist or a mask very fast. At this time you can use the --hashcat-session option to do so with hashcat itself
+You can use --brain-server-whitelist in order to force the clients to use a specific hashlist
+The protocol used is pretty simple and does not contain hashcat specific information, which should make it possible for other cracking tools to utilize the server, too
+
+## Technical details on the hashcat brain client ##
+
+The client calculates the hashcat brain session based on the hashlist entries, to efficiently let a high number of salts work for us. You can override the session calculated with --brain-session, which makes sense if you want to use a fast hash in order to "seed" the hashcat brain with already-tried wordlists or masks.
+The use of --remove is forbidden, but this should not really be a problem, since the potfile will do the same for you. Make sure to remove --potfile-disable in case you use it.
+If multiple clients use the same attack on the same hashcat brain (which is a clever idea), you end up with a distributed solution - without the need of an overlay for keyspace distribution. This is not the intended use of the hashcat brain and should not be used as it. I'll explain later.
+Since each password candidate is creating a hash of 8 bytes, some serious network upstream traffic can be generated from your client. I'll explain later.
+The use of xxHash as hash is not required; we can exchange it with whatever hash we want. However so far it's doing a great job.
+The status view was updated to give you some real-time statistics about the network usage:
+
+```
+Speed.#1.........: 0 H/s (0.00ms) @ Accel:64 Loops:1 Thr:1024 Vec:1
+Speed.#2.........: 0 H/s (0.00ms) @ Accel:64 Loops:1 Thr:1024 Vec:1
+Speed.#3.........: 0 H/s (0.00ms) @ Accel:64 Loops:1 Thr:1024 Vec:1
+Speed.#4.........: 0 H/s (0.00ms) @ Accel:64 Loops:1 Thr:1024 Vec:1
+...
+Brain.Link.#1....: RX: 0 B (0.00 Mbps), TX: 4.1 MB (1.22 Mbps), sending
+Brain.Link.#2....: RX: 0 B (0.00 Mbps), TX: 4.7 MB (1.09 Mbps), sending
+Brain.Link.#3....: RX: 0 B (0.00 Mbps), TX: 3.5 MB (0.88 Mbps), sending
+Brain.Link.#4....: RX: 0 B (0.00 Mbps), TX: 4.1 MB (0.69 Mbps), sending
+```
+
+When the data is transferred, there's no cracking. You can see it's doing 0 H/s. But if you have a slow hash, or a fast hash with multiple salts, this time can be seen as minor overhead. The major time taken is still in the cracking phase. So if you have a fast hash, the more salts the better! As soon as hashcat is done with the network communication, it's starting to work as always:
+
+```
+Speed.#1.........: 869.1 MH/s (1.36ms) @ Accel:64 Loops:1 Thr:1024 Vec:1
+Speed.#2.........: 870.8 MH/s (1.36ms) @ Accel:64 Loops:1 Thr:1024 Vec:1
+Speed.#3.........: 876.2 MH/s (1.36ms) @ Accel:64 Loops:1 Thr:1024 Vec:1
+Speed.#4.........: 872.6 MH/s (1.36ms) @ Accel:64 Loops:1 Thr:1024 Vec:1
+...
+Brain.Link.#1....: RX: 1.3 MB (0.00 Mbps), TX: 10.5 MB (0.00 Mbps), idle
+Brain.Link.#2....: RX: 1.3 MB (0.00 Mbps), TX: 10.5 MB (0.00 Mbps), idle
+Brain.Link.#3....: RX: 1.3 MB (0.00 Mbps), TX: 10.5 MB (0.00 Mbps), idle
+Brain.Link.#4....: RX: 1.3 MB (0.00 Mbps), TX: 10.5 MB (0.00 Mbps), idle
+```
+
+## The brain and the bottlenecks ##
+
+While working with Team Hashcat to test how the brain performs with large numbers of clients and over the Internet, I learned about some serious bottlenecks.
+
+The most important insight was about the performance of lookups against the brain. That should be obvious solely from the huge amount of data that we're talking about here, but the brain does not just have to look up millions of candidates against millions of existing database entries - it must also insert them into the database after each commit and ensure the ordering stays intact otherwise it would break the binary tree. This simply takes time, even if the lookup process was already threaded. But the feature was so promising that I did not want to abandon development just because of the performance challenge.
+
+But to start from the beginning, keep the following number in mind: 50kH/s
+
+This was the speed that was the maximum performance of the hashcat brain after the first development alpha was finished. In other words, if the performance of your attack was faster than this speed, the hashcat brain becomes the bottleneck. Now there's good and bad news about this:
+
+Bad: This is the total number. Which means, the entire network of all GPUs participating as clients cannot create more than 50kH/s before the bottleneck effect kicks in.
+
+Good: Salts come to the rescue. If you have a large salted hashlist - with, for example 300,000 SSHA1 hashes (as in the last Crack Me If You Can) - this means that the real maximum performance that the brain can handle jumps to 15 GH/s. (You can simply multiply the 50kH/s with the number of unique salts of your hashlist.)
+
+Then there's another bottleneck: the network bandwidth required. For those of you who plan to use the brain inside a local network with 100Mbit, you can skip this section entirely. But for those who plan to use the brain in a large group, over VPN or in general over the Internet, keep in mind that a single GPU can create around 5Mbit/s of upstream before bandwidth becomes a bottleneck. That doesn't mean that a hashcat client will stop working - it will just reduce your theoretical maximum cracking performance.
+
+Both of these lessons learned lead to an upgrade to the brain during development. (This means that everything that you've read up to this point is already outdated!) The bottlenecks still exist, but there's kind of a mitigation to them. To better understand what we mean when talking about how to mitigate the problem, we need new terminology in the hashcat brain universe - something we'll call brain client "features".
+
+When running as a client, hashcat now has a new parameter called --brain-client-features. With this parameter, you can select from two features (so far) that the client has to offer:
+Brain "Hashes" feature
+Brain "Attacks" feature
+The brain "hashes" feature is everything that we've explained from the beginning - the *low-level* function of the brain. The brain "attacks" feature is the *high-level* strategy which I added to mitigate the bottlenecks. By default, both "features" are active, and run in parallel. Depending on your use case, you can selectively enable or disable either one.
+
+The brain "attack" feature should be explained in more detail in order to understand what it is doing. It is a high-level approach, or a compressed hint. Hashcat clients request this "hint" from the brain about a given attack as soon as the client is assigned a new work package from the local hashcat dispatcher. For example, if you have a system with 4 GPUs, the local hashcat dispatcher is responsible for distributing the workload across the local GPUs. What's new is that before a GPU starts actually working on the package, it asks the brain for a high level confirmation of whether or not to proceed. The process of how this work is basically the same as with the low-level architecture: the client "reserves" a package when the hashcat brain moves it to short-term memory - and once it is done, it will be moved to long-term memory.
+
+The attack package itself is another 8-byte checksum - but that's more than enough to assign all feasible combinations of attacks a unique identifier. For example, hashcat takes options like the attack mode itself, rules with -r (but also -j and -k rules), masks, user-defined custom charset, Markov options, a checksum of the wordlists (if used) and so on. All of these options are combined in a repeatable way, and from that unique combination of options, a checksum is created that uniquely "fingerprints" all of the components of the attack.
+
+When the clients connect to the hashcat brain, they send this attack checksum (along with the session ID) to the brain, so that the brain knows precisely which attack is running on a particular hashcat client. Now, if the local dispatcher creates a new package, the local start point and end point of this attack is sent to the brain so that the brain can track it. The client will automatically reject an entire package - for example, an entire wordlist, or an entire wordlist plus a specific list of rules - if the attack has some overlaps. This is done *before* the client sends any password candidate hashes to the brain. This means that if a package is rejected:
+The client doesn't need to transfer the hashes (which mitigates the bandwidth bottleneck)
+The brain server doesn't need to compare it (which mitigates the lookup bottleneck)
+If the attack package itself is not rejected, the hashes are still sent to the brain and compared.
+
+The hashcat brain is kind of clever when it comes to the packages. It recognizes overlapping packages on a low level - in cases where only part of one package overlaps with another package. When this occurs, the brain only rejects the overlapping section of the package and informs the client about that. It is then up to the client to decide whether it wants to either launch the attack with a minimized package size, or to ask the local dispatcher for another (smaller) portion to fill the gap. Of course, this newly creates portion is also first sent to the brain, in case it can be rejected. The entire process is packed into a loop and it will repeat the process until the client decides that the package is big enough (and the default setting for accepting a package and to start executing is half of the original package size.)
+
+Something I realized - after I had already finished with the implementation of the high-level feature - was that the new brain "attack" feature is a very strong feature for standalone use. By setting --brain-client-features 2, you tell the client to only use the attack feature. This completely eliminates all bottlenecks - the network bandwidth, but even more importantly, the lookup bottleneck. The drawback is that you lose cross-attack functionality.
+
+If you think that this new feature is a nice way to get a native hashcat multi-system distribution ... you are wrong. The brain client still requires running in -S mode, which means that this is all about slow hashes or fast hashes with many salts. There's also no wordlist distribution, and most importantly, there's no distribution of cracked hashes across all network clients. So the brain "attack" feature is not meant to be an alternative to existing distribution solutions, but just as a mitigation for the bottlenecks (and it works exactly as such).
+
+## Commandline Options ##
+
+Most of the commands are self-explaining. I'm just adding them here to inform you which ones exist:
+
+- Add new option --brain-server to start a hashcat brain server
+- Add new option --brain-client to start a hashcat brain client, automatically activates --slow-candidates
+- Add new option --brain-host and --brain-port to specify ip and port of brain server, both listening and connecting
+- Add new option --brain-session to override automatically calculated brain session ID
+- Add new option --brain-session-whitelist to allow only explicit written session ID on brain server
+- Add new option --brain-password to specify the brain server authentication password
+- Add new option --brain-client-features which allows enable and disable certain features of the hashcat brain
diff --git a/docs/slow-candidates-mode.md b/docs/slow-candidates-mode.md
index 273cdb1d7..4dbf363ff 100644
--- a/docs/slow-candidates-mode.md
+++ b/docs/slow-candidates-mode.md
@@ -1,4 +1,4 @@
-## Hashcat has a new generic password candidate interface called "slow candidates" ##
+## Generic password candidate interface, aka "slow candidates" mode ##
The first goal of this new interface is to allow attachment of advanced password candidate generators in the future (for example hashcat's table attack, kwprocessor, OMEN, PassGAN, PCFG, princeprocessor, etc.). At this time, the only attack modes that have been added are hashcat's straight attack (including rules engine), combinator attack, and mask attack (AKA brute-force with Markov optimizer). You can enable this new general password-candidate interface by using the new -S/--slow-candidates option.
From 7c327e314a347f445c97fbffbc81cb97f889c20c Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Wed, 14 Aug 2019 12:35:23 +0200
Subject: [PATCH 109/113] Update changes.txt, add entry on documentations
---
docs/changes.txt | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/docs/changes.txt b/docs/changes.txt
index f22cc8768..42bb6124b 100644
--- a/docs/changes.txt
+++ b/docs/changes.txt
@@ -6,11 +6,12 @@
- Fully modularized hash-mode integration via plugin interface and converted all existing hash-modes
- Refactor hashcat backend interface to allow adding compute API other than OpenCL
-- Add CUDA as a new compute API to hashcat backend (enables hashcat to run on NVIDIA Jetson or IBM POWER9)
+- Added CUDA as a new compute API to hashcat backend (enables hashcat to run on NVIDIA Jetson or IBM POWER9)
- Support use of all available GPU memory using CUDA backend
- Support on-the-fly loading of compressed wordlists in zip and gzip format
- Support for inline VeraCrypt PIM Brute-Force
- Support deflate decompression for the 7-Zip hash-mode using zlib hook
+- Added documentation on hashcat brain, slow-candidate and keyboard-layout mapping features
##
## Algorithms
From 8ae3b49062f9227d288afa26d3e007cdcfd84873 Mon Sep 17 00:00:00 2001
From: Royce Williams <royce@techsolvency.com>
Date: Wed, 14 Aug 2019 06:40:36 -0800
Subject: [PATCH 110/113] brain doc tweaks
---
docs/hashcat-brain.md | 30 +++++++++++++++---------------
1 file changed, 15 insertions(+), 15 deletions(-)
diff --git a/docs/hashcat-brain.md b/docs/hashcat-brain.md
index 87f194ff3..406793a07 100644
--- a/docs/hashcat-brain.md
+++ b/docs/hashcat-brain.md
@@ -208,14 +208,14 @@ Lookup times are pretty good. The hashcat brain uses two binary trees, which mea
## Technical details on the hashcat brain server ##
-The hashcat brain server saves the long-term memory to disc every 5 minutes automatically
-The server also saves the long-term memory if the hashcat brain server is killed using Ctrl-C
-There's no mitigation against database poisoning - this would cost too many resources
-There's currently no mitigation against an evil client requesting the server to allocate too much memory
-Make sure your hashcat brain server is protected with a good password, because you have to trust your clients
-I'll add a standalone hashcat brain seeding tool later which enables you to easily push all the words from an entire wordlist or a mask very fast. At this time you can use the --hashcat-session option to do so with hashcat itself
-You can use --brain-server-whitelist in order to force the clients to use a specific hashlist
-The protocol used is pretty simple and does not contain hashcat specific information, which should make it possible for other cracking tools to utilize the server, too
+* The hashcat brain server saves the long-term memory to disk every 5 minutes automatically
+* The server also saves the long-term memory if the hashcat brain server is killed using Ctrl-C
+* There's no mitigation against database poisoning - this would cost too many resources
+* There's currently no mitigation against an evil client requesting the server to allocate too much memory
+* Make sure your hashcat brain server is protected with a good password, because you have to trust your clients
+* I'll add a standalone hashcat brain seeding tool later which enables you to easily push all the words from an entire wordlist or a mask very fast. At this time you can use the --hashcat-session option to do so with hashcat itself
+* You can use --brain-server-whitelist in order to force the clients to use a specific hashlist
+* The protocol used is pretty simple and does not contain hashcat specific information, which should make it possible for other cracking tools to utilize the server, too
## Technical details on the hashcat brain client ##
@@ -294,10 +294,10 @@ If you think that this new feature is a nice way to get a native hashcat multi-s
Most of the commands are self-explaining. I'm just adding them here to inform you which ones exist:
-- Add new option --brain-server to start a hashcat brain server
-- Add new option --brain-client to start a hashcat brain client, automatically activates --slow-candidates
-- Add new option --brain-host and --brain-port to specify ip and port of brain server, both listening and connecting
-- Add new option --brain-session to override automatically calculated brain session ID
-- Add new option --brain-session-whitelist to allow only explicit written session ID on brain server
-- Add new option --brain-password to specify the brain server authentication password
-- Add new option --brain-client-features which allows enable and disable certain features of the hashcat brain
+- `--brain-server` to start a hashcat brain server
+- `--brain-client` to start a hashcat brain client, automatically activates --slow-candidates
+- `--brain-host` and `--brain-port` to specify ip and port of brain server, both listening and connecting
+- `--brain-session` to override automatically calculated brain session ID
+- `--brain-session-whitelist` to allow only explicit written session ID on brain server
+- `--brain-password` to specify the brain server authentication password
+- `--brain-client-features` which allows enable and disable certain features of the hashcat brain
From 0063bc7245748de118cfa04b9d933cf77132a603 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Wed, 21 Aug 2019 14:57:41 +0200
Subject: [PATCH 111/113] Fix uninitialized buffer in maskfile iteration
---
include/types.h | 8 ++++----
src/mpsp.c | 23 +++++++++++++----------
2 files changed, 17 insertions(+), 14 deletions(-)
diff --git a/include/types.h b/include/types.h
index 0bc8ac636..0f754aa71 100644
--- a/include/types.h
+++ b/include/types.h
@@ -2046,12 +2046,12 @@ typedef struct mask_ctx
{
bool enabled;
- cs_t mp_sys[8];
- cs_t mp_usr[4];
+ cs_t *mp_sys;
+ cs_t *mp_usr;
u64 bfs_cnt;
- cs_t css_buf[256];
+ cs_t *css_buf;
u32 css_cnt;
hcstat_table_t *root_table_buf;
@@ -2067,7 +2067,7 @@ typedef struct mask_ctx
u32 masks_cnt;
u32 masks_avail;
- char *mask;
+ char *mask;
mf_t *mfs;
diff --git a/src/mpsp.c b/src/mpsp.c
index fc85a31e1..f69f14fba 100644
--- a/src/mpsp.c
+++ b/src/mpsp.c
@@ -364,6 +364,8 @@ static int mp_gen_css (hashcat_ctx_t *hashcat_ctx, char *mask_buf, size_t mask_l
{
const user_options_t *user_options = hashcat_ctx->user_options;
+ memset (css_buf, 0, 256 * sizeof (cs_t));
+
size_t mask_pos;
size_t css_pos;
@@ -1182,6 +1184,7 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
user_options_extra_t *user_options_extra = hashcat_ctx->user_options_extra;
user_options_t *user_options = hashcat_ctx->user_options;
+
if (user_options_extra->attack_kern == ATTACK_KERN_COMBI)
{
if (user_options->attack_mode == ATTACK_MODE_COMBI)
@@ -1196,8 +1199,6 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
if (mask_ctx_parse_maskfile (hashcat_ctx) == -1) return -1;
- //mask_ctx->css_buf = (cs_t *) hccalloc (256, sizeof (cs_t));
-
if (mp_gen_css (hashcat_ctx, mask_ctx->mask, strlen (mask_ctx->mask), mask_ctx->mp_sys, mask_ctx->mp_usr, mask_ctx->css_buf, &mask_ctx->css_cnt) == -1) return -1;
u32 uniq_tbls[SP_PW_MAX][CHARSIZ] = { { 0 } };
@@ -1221,8 +1222,6 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
if (mask_ctx_parse_maskfile (hashcat_ctx) == -1) return -1;
- //mask_ctx->css_buf = (cs_t *) hccalloc (256, sizeof (cs_t));
-
if (mp_gen_css (hashcat_ctx, mask_ctx->mask, strlen (mask_ctx->mask), mask_ctx->mp_sys, mask_ctx->mp_usr, mask_ctx->css_buf, &mask_ctx->css_cnt) == -1) return -1;
u32 uniq_tbls[SP_PW_MAX][CHARSIZ] = { { 0 } };
@@ -1252,8 +1251,6 @@ int mask_ctx_update_loop (hashcat_ctx_t *hashcat_ctx)
if (user_options->attack_mode == ATTACK_MODE_BF) // always true
{
- //mask_ctx->css_buf = (cs_t *) hccalloc (256, sizeof (cs_t));
-
if (mp_gen_css (hashcat_ctx, mask_ctx->mask, strlen (mask_ctx->mask), mask_ctx->mp_sys, mask_ctx->mp_usr, mask_ctx->css_buf, &mask_ctx->css_cnt) == -1) return -1;
// special case for benchmark
@@ -1372,6 +1369,12 @@ int mask_ctx_init (hashcat_ctx_t *hashcat_ctx)
mask_ctx->enabled = true;
+ mask_ctx->mp_sys = (cs_t *) hccalloc (8, sizeof (cs_t));
+ mask_ctx->mp_usr = (cs_t *) hccalloc (4, sizeof (cs_t));
+
+ mask_ctx->css_buf = (cs_t *) hccalloc (256, sizeof (cs_t));
+ mask_ctx->css_cnt = 0;
+
mask_ctx->root_table_buf = (hcstat_table_t *) hccalloc (SP_ROOT_CNT, sizeof (hcstat_table_t));
mask_ctx->markov_table_buf = (hcstat_table_t *) hccalloc (SP_MARKOV_CNT, sizeof (hcstat_table_t));
@@ -1380,9 +1383,6 @@ int mask_ctx_init (hashcat_ctx_t *hashcat_ctx)
mask_ctx->root_css_buf = (cs_t *) hccalloc (SP_PW_MAX, sizeof (cs_t));
mask_ctx->markov_css_buf = (cs_t *) hccalloc (SP_PW_MAX * CHARSIZ, sizeof (cs_t));
- mask_ctx->css_cnt = 0;
- //mask_ctx->css_buf = NULL;
-
mask_ctx->mask_from_file = false;
mask_ctx->masks = NULL;
@@ -1646,7 +1646,10 @@ void mask_ctx_destroy (hashcat_ctx_t *hashcat_ctx)
if (mask_ctx->enabled == false) return;
- //hcfree (mask_ctx->css_buf);
+ hcfree (mask_ctx->mp_sys);
+ hcfree (mask_ctx->mp_usr);
+
+ hcfree (mask_ctx->css_buf);
hcfree (mask_ctx->root_css_buf);
hcfree (mask_ctx->markov_css_buf);
From d9b22b86e48d53e80c8992df72647f0e1cb29a50 Mon Sep 17 00:00:00 2001
From: philsmd <921533+philsmd@users.noreply.github.com>
Date: Thu, 22 Aug 2019 09:45:35 +0200
Subject: [PATCH 112/113] wrong separator used in SipHash (-m 10100)
---
src/modules/module_10100.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/src/modules/module_10100.c b/src/modules/module_10100.c
index d0cd31e78..ece43c009 100644
--- a/src/modules/module_10100.c
+++ b/src/modules/module_10100.c
@@ -68,10 +68,9 @@ int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSE
token.attr[2] = TOKEN_ATTR_VERIFY_LENGTH
| TOKEN_ATTR_VERIFY_DIGIT;
- token.sep[3] = '$';
- token.len_min[3] = 32;
- token.len_max[3] = 32;
- token.attr[3] = TOKEN_ATTR_VERIFY_LENGTH;
+ token.len[3] = 32;
+ token.attr[3] = TOKEN_ATTR_FIXED_LENGTH
+ | TOKEN_ATTR_VERIFY_HEX;
const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
From f3fd54f8b47325863f59cc7097314b483357acd3 Mon Sep 17 00:00:00 2001
From: Jens Steube <jens.steube@gmail.com>
Date: Thu, 22 Aug 2019 14:26:48 +0200
Subject: [PATCH 113/113] Fix cracking of -m 97xx hashes in -a 3 mode of
passwords of length between 8-15
---
OpenCL/m09700_a3-optimized.cl | 90 +++++++++++++++++++++++++++++++++++
OpenCL/m09720_a3-optimized.cl | 86 +++++++++++++++++++++++++++++++++
2 files changed, 176 insertions(+)
diff --git a/OpenCL/m09700_a3-optimized.cl b/OpenCL/m09700_a3-optimized.cl
index 40e3b73f3..38819cc95 100644
--- a/OpenCL/m09700_a3-optimized.cl
+++ b/OpenCL/m09700_a3-optimized.cl
@@ -1019,6 +1019,51 @@ KERNEL_FQ void m09700_m04 (KERN_ATTR_ESALT (oldoffice01_t))
KERNEL_FQ void m09700_m08 (KERN_ATTR_ESALT (oldoffice01_t))
{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ LOCAL_VK RC4_KEY rc4_keys[64];
+
+ m09700m (rc4_keys, w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
KERNEL_FQ void m09700_m16 (KERN_ATTR_ESALT (oldoffice01_t))
@@ -1076,6 +1121,51 @@ KERNEL_FQ void m09700_s04 (KERN_ATTR_ESALT (oldoffice01_t))
KERNEL_FQ void m09700_s08 (KERN_ATTR_ESALT (oldoffice01_t))
{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ LOCAL_VK RC4_KEY rc4_keys[64];
+
+ m09700s (rc4_keys, w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
KERNEL_FQ void m09700_s16 (KERN_ATTR_ESALT (oldoffice01_t))
diff --git a/OpenCL/m09720_a3-optimized.cl b/OpenCL/m09720_a3-optimized.cl
index b0a0376e5..7da20ed6f 100644
--- a/OpenCL/m09720_a3-optimized.cl
+++ b/OpenCL/m09720_a3-optimized.cl
@@ -608,6 +608,49 @@ KERNEL_FQ void m09720_m04 (KERN_ATTR_ESALT (oldoffice01_t))
KERNEL_FQ void m09720_m08 (KERN_ATTR_ESALT (oldoffice01_t))
{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m09720m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
KERNEL_FQ void m09720_m16 (KERN_ATTR_ESALT (oldoffice01_t))
@@ -663,6 +706,49 @@ KERNEL_FQ void m09720_s04 (KERN_ATTR_ESALT (oldoffice01_t))
KERNEL_FQ void m09720_s08 (KERN_ATTR_ESALT (oldoffice01_t))
{
+ /**
+ * base
+ */
+
+ const u64 gid = get_global_id (0);
+
+ if (gid >= gid_max) return;
+
+ u32 w0[4];
+
+ w0[0] = pws[gid].i[ 0];
+ w0[1] = pws[gid].i[ 1];
+ w0[2] = pws[gid].i[ 2];
+ w0[3] = pws[gid].i[ 3];
+
+ u32 w1[4];
+
+ w1[0] = pws[gid].i[ 4];
+ w1[1] = pws[gid].i[ 5];
+ w1[2] = pws[gid].i[ 6];
+ w1[3] = pws[gid].i[ 7];
+
+ u32 w2[4];
+
+ w2[0] = 0;
+ w2[1] = 0;
+ w2[2] = 0;
+ w2[3] = 0;
+
+ u32 w3[4];
+
+ w3[0] = 0;
+ w3[1] = 0;
+ w3[2] = 0;
+ w3[3] = 0;
+
+ const u32 pw_len = pws[gid].pw_len & 63;
+
+ /**
+ * main
+ */
+
+ m09720s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset, combs_mode, gid_max);
}
KERNEL_FQ void m09720_s16 (KERN_ATTR_ESALT (oldoffice01_t))