From bbcb23b038fda69173e0a4eb983e5b0315d7f1dd Mon Sep 17 00:00:00 2001 From: Gabriele Gristina Date: Sat, 13 Jul 2019 14:43:13 +0200 Subject: [PATCH 1/6] 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 Date: Sat, 13 Jul 2019 15:36:16 +0200 Subject: [PATCH 2/6] 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 Date: Sat, 13 Jul 2019 16:25:31 +0200 Subject: [PATCH 3/6] 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 Date: Sat, 13 Jul 2019 16:36:25 +0200 Subject: [PATCH 4/6] 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) Gabriele "matrix" Gristina (@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, $word); +} + +1; From 1aef49d11be7afa7ee1c0d78a5091801e94e6463 Mon Sep 17 00:00:00 2001 From: Gabriele Gristina Date: Sat, 13 Jul 2019 20:51:38 +0200 Subject: [PATCH 5/6] update readme/changes txt --- docs/changes.txt | 1 + docs/readme.txt | 1 + 2 files changed, 2 insertions(+) diff --git a/docs/changes.txt b/docs/changes.txt index 0bb228187..7062e62af 100644 --- a/docs/changes.txt +++ b/docs/changes.txt @@ -35,6 +35,7 @@ - Added hash-mode: Python passlib pbkdf2-sha256 - Added hash-mode: Python passlib pbkdf2-sha512 - Added hash-mode: Oracle Transportation Management (SHA256) +- Added hash-mode: sha256(md5($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 f2d92d8aec11d8af5e4bf6eedd4cfae342da82d5 Mon Sep 17 00:00:00 2001 From: Gabriele Gristina Date: Tue, 30 Jul 2019 14:44:17 +0200 Subject: [PATCH 6/6] 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) Gabriele "matrix" Gristina (@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