mirror of
https://github.com/hashcat/hashcat.git
synced 2024-12-23 07:08:19 +00:00
Add pure kernels for SIP digest authentication (MD5)
This commit is contained in:
parent
b1f9ed4a7c
commit
4f72c8bee6
@ -791,10 +791,10 @@ typedef struct bitcoin_wallet
|
||||
|
||||
typedef struct sip
|
||||
{
|
||||
u32 salt_buf[30];
|
||||
u32 salt_buf[32];
|
||||
u32 salt_len;
|
||||
|
||||
u32 esalt_buf[38];
|
||||
u32 esalt_buf[48];
|
||||
u32 esalt_len;
|
||||
|
||||
} sip_t;
|
||||
|
File diff suppressed because it is too large
Load Diff
254
OpenCL/m11400_a0.cl
Normal file
254
OpenCL/m11400_a0.cl
Normal file
@ -0,0 +1,254 @@
|
||||
/**
|
||||
* Author......: See docs/credits.txt
|
||||
* License.....: MIT
|
||||
*/
|
||||
|
||||
//#define NEW_SIMD_CODE
|
||||
|
||||
#include "inc_vendor.cl"
|
||||
#include "inc_hash_constants.h"
|
||||
#include "inc_hash_functions.cl"
|
||||
#include "inc_types.cl"
|
||||
#include "inc_common.cl"
|
||||
#include "inc_rp.h"
|
||||
#include "inc_rp.cl"
|
||||
#include "inc_scalar.cl"
|
||||
#include "inc_hash_md5.cl"
|
||||
|
||||
#if VECT_SIZE == 1
|
||||
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i)])
|
||||
#elif VECT_SIZE == 2
|
||||
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
|
||||
#elif VECT_SIZE == 4
|
||||
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
|
||||
#elif VECT_SIZE == 8
|
||||
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
|
||||
#elif VECT_SIZE == 16
|
||||
#define uint_to_hex_lower8(i) (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 void m11400_mxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const sip_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u32 gid = get_global_id (0);
|
||||
const u32 lid = get_local_id (0);
|
||||
const u32 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
__local u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
|
||||
}
|
||||
|
||||
barrier (CLK_LOCAL_MEM_FENCE);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len;
|
||||
|
||||
const u32 pw_lenv = ceil ((float) pw_len / 4);
|
||||
|
||||
u32 w[64] = { 0 };
|
||||
|
||||
for (int idx = 0; idx < pw_lenv; idx++)
|
||||
{
|
||||
w[idx] = pws[gid].i[idx];
|
||||
|
||||
barrier (CLK_GLOBAL_MEM_FENCE);
|
||||
}
|
||||
|
||||
md5_ctx_t ctx0;
|
||||
|
||||
md5_init (&ctx0);
|
||||
|
||||
md5_update_global (&ctx0, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
||||
{
|
||||
// todo: add rules engine
|
||||
|
||||
md5_ctx_t ctx1 = ctx0;
|
||||
|
||||
md5_update (&ctx1, w, 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];
|
||||
|
||||
md5_ctx_t ctx;
|
||||
|
||||
md5_init (&ctx);
|
||||
|
||||
ctx.w0[0] = uint_to_hex_lower8 ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((a >> 8) & 255) << 16;
|
||||
ctx.w0[1] = uint_to_hex_lower8 ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((a >> 24) & 255) << 16;
|
||||
ctx.w0[2] = uint_to_hex_lower8 ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((b >> 8) & 255) << 16;
|
||||
ctx.w0[3] = uint_to_hex_lower8 ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((b >> 24) & 255) << 16;
|
||||
ctx.w1[0] = uint_to_hex_lower8 ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((c >> 8) & 255) << 16;
|
||||
ctx.w1[1] = uint_to_hex_lower8 ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((c >> 24) & 255) << 16;
|
||||
ctx.w1[2] = uint_to_hex_lower8 ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((d >> 8) & 255) << 16;
|
||||
ctx.w1[3] = uint_to_hex_lower8 ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((d >> 24) & 255) << 16;
|
||||
|
||||
ctx.len = 32;
|
||||
|
||||
md5_update_global (&ctx, esalt_bufs[digests_offset].esalt_buf, esalt_bufs[digests_offset].esalt_len);
|
||||
|
||||
md5_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
__kernel void m11400_sxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const sip_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u32 gid = get_global_id (0);
|
||||
const u32 lid = get_local_id (0);
|
||||
const u32 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
__local u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
|
||||
}
|
||||
|
||||
barrier (CLK_LOCAL_MEM_FENCE);
|
||||
|
||||
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;
|
||||
|
||||
const u32 pw_lenv = ceil ((float) pw_len / 4);
|
||||
|
||||
u32 w[64] = { 0 };
|
||||
|
||||
for (int idx = 0; idx < pw_lenv; idx++)
|
||||
{
|
||||
w[idx] = pws[gid].i[idx];
|
||||
|
||||
barrier (CLK_GLOBAL_MEM_FENCE);
|
||||
}
|
||||
|
||||
md5_ctx_t ctx0;
|
||||
|
||||
md5_init (&ctx0);
|
||||
|
||||
md5_update_global (&ctx0, salt_bufs[salt_pos].salt_buf, salt_bufs[salt_pos].salt_len);
|
||||
|
||||
/**
|
||||
* loop
|
||||
*/
|
||||
|
||||
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
|
||||
{
|
||||
// todo: add rules engine
|
||||
|
||||
md5_ctx_t ctx1 = ctx0;
|
||||
|
||||
md5_update (&ctx1, w, 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];
|
||||
|
||||
md5_ctx_t ctx;
|
||||
|
||||
md5_init (&ctx);
|
||||
|
||||
ctx.w0[0] = uint_to_hex_lower8 ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((a >> 8) & 255) << 16;
|
||||
ctx.w0[1] = uint_to_hex_lower8 ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((a >> 24) & 255) << 16;
|
||||
ctx.w0[2] = uint_to_hex_lower8 ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((b >> 8) & 255) << 16;
|
||||
ctx.w0[3] = uint_to_hex_lower8 ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((b >> 24) & 255) << 16;
|
||||
ctx.w1[0] = uint_to_hex_lower8 ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((c >> 8) & 255) << 16;
|
||||
ctx.w1[1] = uint_to_hex_lower8 ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((c >> 24) & 255) << 16;
|
||||
ctx.w1[2] = uint_to_hex_lower8 ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((d >> 8) & 255) << 16;
|
||||
ctx.w1[3] = uint_to_hex_lower8 ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((d >> 24) & 255) << 16;
|
||||
|
||||
ctx.len = 32;
|
||||
|
||||
md5_update_global (&ctx, esalt_bufs[digests_offset].esalt_buf, esalt_bufs[digests_offset].esalt_len);
|
||||
|
||||
md5_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
File diff suppressed because it is too large
Load Diff
226
OpenCL/m11400_a1.cl
Normal file
226
OpenCL/m11400_a1.cl
Normal file
@ -0,0 +1,226 @@
|
||||
/**
|
||||
* Author......: See docs/credits.txt
|
||||
* License.....: MIT
|
||||
*/
|
||||
|
||||
//#define NEW_SIMD_CODE
|
||||
|
||||
#include "inc_vendor.cl"
|
||||
#include "inc_hash_constants.h"
|
||||
#include "inc_hash_functions.cl"
|
||||
#include "inc_types.cl"
|
||||
#include "inc_common.cl"
|
||||
#include "inc_scalar.cl"
|
||||
#include "inc_hash_md5.cl"
|
||||
|
||||
#if VECT_SIZE == 1
|
||||
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i)])
|
||||
#elif VECT_SIZE == 2
|
||||
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
|
||||
#elif VECT_SIZE == 4
|
||||
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
|
||||
#elif VECT_SIZE == 8
|
||||
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
|
||||
#elif VECT_SIZE == 16
|
||||
#define uint_to_hex_lower8(i) (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 void m11400_mxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const sip_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u32 gid = get_global_id (0);
|
||||
const u32 lid = get_local_id (0);
|
||||
const u32 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
__local u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
|
||||
}
|
||||
|
||||
barrier (CLK_LOCAL_MEM_FENCE);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
md5_ctx_t ctx0;
|
||||
|
||||
md5_init (&ctx0);
|
||||
|
||||
md5_update_global (&ctx0, esalt_bufs[digests_offset].salt_buf, esalt_bufs[digests_offset].salt_len);
|
||||
|
||||
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];
|
||||
|
||||
md5_ctx_t ctx;
|
||||
|
||||
md5_init (&ctx);
|
||||
|
||||
ctx.w0[0] = uint_to_hex_lower8 ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((a >> 8) & 255) << 16;
|
||||
ctx.w0[1] = uint_to_hex_lower8 ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((a >> 24) & 255) << 16;
|
||||
ctx.w0[2] = uint_to_hex_lower8 ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((b >> 8) & 255) << 16;
|
||||
ctx.w0[3] = uint_to_hex_lower8 ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((b >> 24) & 255) << 16;
|
||||
ctx.w1[0] = uint_to_hex_lower8 ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((c >> 8) & 255) << 16;
|
||||
ctx.w1[1] = uint_to_hex_lower8 ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((c >> 24) & 255) << 16;
|
||||
ctx.w1[2] = uint_to_hex_lower8 ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((d >> 8) & 255) << 16;
|
||||
ctx.w1[3] = uint_to_hex_lower8 ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((d >> 24) & 255) << 16;
|
||||
|
||||
ctx.len = 32;
|
||||
|
||||
md5_update_global (&ctx, esalt_bufs[digests_offset].esalt_buf, esalt_bufs[digests_offset].esalt_len);
|
||||
|
||||
md5_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
__kernel void m11400_sxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global const bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const sip_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u32 gid = get_global_id (0);
|
||||
const u32 lid = get_local_id (0);
|
||||
const u32 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
__local u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
|
||||
}
|
||||
|
||||
barrier (CLK_LOCAL_MEM_FENCE);
|
||||
|
||||
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, esalt_bufs[digests_offset].salt_buf, esalt_bufs[digests_offset].salt_len);
|
||||
|
||||
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];
|
||||
|
||||
md5_ctx_t ctx;
|
||||
|
||||
md5_init (&ctx);
|
||||
|
||||
ctx.w0[0] = uint_to_hex_lower8 ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((a >> 8) & 255) << 16;
|
||||
ctx.w0[1] = uint_to_hex_lower8 ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((a >> 24) & 255) << 16;
|
||||
ctx.w0[2] = uint_to_hex_lower8 ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((b >> 8) & 255) << 16;
|
||||
ctx.w0[3] = uint_to_hex_lower8 ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((b >> 24) & 255) << 16;
|
||||
ctx.w1[0] = uint_to_hex_lower8 ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((c >> 8) & 255) << 16;
|
||||
ctx.w1[1] = uint_to_hex_lower8 ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((c >> 24) & 255) << 16;
|
||||
ctx.w1[2] = uint_to_hex_lower8 ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((d >> 8) & 255) << 16;
|
||||
ctx.w1[3] = uint_to_hex_lower8 ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((d >> 24) & 255) << 16;
|
||||
|
||||
ctx.len = 32;
|
||||
|
||||
md5_update_global (&ctx, esalt_bufs[digests_offset].esalt_buf, esalt_bufs[digests_offset].esalt_len);
|
||||
|
||||
md5_final (&ctx);
|
||||
|
||||
const u32 r0 = ctx.h[DGST_R0];
|
||||
const u32 r1 = ctx.h[DGST_R1];
|
||||
const u32 r2 = ctx.h[DGST_R2];
|
||||
const u32 r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SCALAR (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
File diff suppressed because it is too large
Load Diff
294
OpenCL/m11400_a3.cl
Normal file
294
OpenCL/m11400_a3.cl
Normal file
@ -0,0 +1,294 @@
|
||||
/**
|
||||
* Author......: See docs/credits.txt
|
||||
* License.....: MIT
|
||||
*/
|
||||
|
||||
#define NEW_SIMD_CODE
|
||||
|
||||
#include "inc_vendor.cl"
|
||||
#include "inc_hash_constants.h"
|
||||
#include "inc_hash_functions.cl"
|
||||
#include "inc_types.cl"
|
||||
#include "inc_common.cl"
|
||||
#include "inc_simd.cl"
|
||||
#include "inc_hash_md5.cl"
|
||||
|
||||
#if VECT_SIZE == 1
|
||||
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i)])
|
||||
#elif VECT_SIZE == 2
|
||||
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
|
||||
#elif VECT_SIZE == 4
|
||||
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
|
||||
#elif VECT_SIZE == 8
|
||||
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
|
||||
#elif VECT_SIZE == 16
|
||||
#define uint_to_hex_lower8(i) (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 void m11400_mxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __constant const u32x *words_buf_r, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const sip_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u32 gid = get_global_id (0);
|
||||
const u32 lid = get_local_id (0);
|
||||
const u32 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
__local u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
|
||||
}
|
||||
|
||||
barrier (CLK_LOCAL_MEM_FENCE);
|
||||
|
||||
if (gid >= gid_max) return;
|
||||
|
||||
/**
|
||||
* base
|
||||
*/
|
||||
|
||||
const u32 pw_len = pws[gid].pw_len;
|
||||
|
||||
const u32 pw_lenv = ceil ((float) pw_len / 4);
|
||||
|
||||
u32x w[64] = { 0 };
|
||||
|
||||
for (int idx = 0; idx < pw_lenv; idx++)
|
||||
{
|
||||
w[idx] = pws[gid].i[idx];
|
||||
|
||||
barrier (CLK_GLOBAL_MEM_FENCE);
|
||||
}
|
||||
|
||||
const u32 esalt_len = esalt_bufs[digests_offset].esalt_len;
|
||||
|
||||
const u32 esalt_lenv = ceil ((float) esalt_len / 4);
|
||||
|
||||
u32x esalt_buf[64] = { 0 };
|
||||
|
||||
for (int idx = 0; idx < esalt_lenv; idx++)
|
||||
{
|
||||
esalt_buf[idx] = esalt_bufs[digests_offset].esalt_buf[idx];
|
||||
|
||||
barrier (CLK_GLOBAL_MEM_FENCE);
|
||||
}
|
||||
|
||||
md5_ctx_t ctx0;
|
||||
|
||||
md5_init (&ctx0);
|
||||
|
||||
md5_update_global (&ctx0, esalt_bufs[digests_offset].salt_buf, esalt_bufs[digests_offset].salt_len);
|
||||
|
||||
/**
|
||||
* 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 ctx1;
|
||||
|
||||
md5_init_vector_from_scalar (&ctx1, &ctx0);
|
||||
|
||||
md5_update_vector (&ctx1, w, pw_len);
|
||||
|
||||
md5_final_vector (&ctx1);
|
||||
|
||||
const u32x a = ctx1.h[0];
|
||||
const u32x b = ctx1.h[1];
|
||||
const u32x c = ctx1.h[2];
|
||||
const u32x d = ctx1.h[3];
|
||||
|
||||
md5_ctx_vector_t ctx;
|
||||
|
||||
md5_init_vector (&ctx);
|
||||
|
||||
ctx.w0[0] = uint_to_hex_lower8 ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((a >> 8) & 255) << 16;
|
||||
ctx.w0[1] = uint_to_hex_lower8 ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((a >> 24) & 255) << 16;
|
||||
ctx.w0[2] = uint_to_hex_lower8 ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((b >> 8) & 255) << 16;
|
||||
ctx.w0[3] = uint_to_hex_lower8 ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((b >> 24) & 255) << 16;
|
||||
ctx.w1[0] = uint_to_hex_lower8 ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((c >> 8) & 255) << 16;
|
||||
ctx.w1[1] = uint_to_hex_lower8 ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((c >> 24) & 255) << 16;
|
||||
ctx.w1[2] = uint_to_hex_lower8 ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((d >> 8) & 255) << 16;
|
||||
ctx.w1[3] = uint_to_hex_lower8 ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((d >> 24) & 255) << 16;
|
||||
|
||||
ctx.len = 32;
|
||||
|
||||
md5_update_vector (&ctx, esalt_buf, esalt_len);
|
||||
|
||||
md5_final_vector (&ctx);
|
||||
|
||||
const u32x r0 = ctx.h[DGST_R0];
|
||||
const u32x r1 = ctx.h[DGST_R1];
|
||||
const u32x r2 = ctx.h[DGST_R2];
|
||||
const u32x r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_M_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
||||
|
||||
__kernel void m11400_sxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __constant const u32x *words_buf_r, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const sip_t *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
|
||||
{
|
||||
/**
|
||||
* modifier
|
||||
*/
|
||||
|
||||
const u32 gid = get_global_id (0);
|
||||
const u32 lid = get_local_id (0);
|
||||
const u32 lsz = get_local_size (0);
|
||||
|
||||
/**
|
||||
* bin2asc table
|
||||
*/
|
||||
|
||||
__local u32 l_bin2asc[256];
|
||||
|
||||
for (u32 i = lid; i < 256; i += lsz)
|
||||
{
|
||||
const u32 i0 = (i >> 0) & 15;
|
||||
const u32 i1 = (i >> 4) & 15;
|
||||
|
||||
l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
|
||||
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
|
||||
}
|
||||
|
||||
barrier (CLK_LOCAL_MEM_FENCE);
|
||||
|
||||
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;
|
||||
|
||||
const u32 pw_lenv = ceil ((float) pw_len / 4);
|
||||
|
||||
u32x w[64] = { 0 };
|
||||
|
||||
for (int idx = 0; idx < pw_lenv; idx++)
|
||||
{
|
||||
w[idx] = pws[gid].i[idx];
|
||||
|
||||
barrier (CLK_GLOBAL_MEM_FENCE);
|
||||
}
|
||||
|
||||
const u32 esalt_len = esalt_bufs[digests_offset].esalt_len;
|
||||
|
||||
const u32 esalt_lenv = ceil ((float) esalt_len / 4);
|
||||
|
||||
u32x esalt_buf[64] = { 0 };
|
||||
|
||||
for (int idx = 0; idx < esalt_lenv; idx++)
|
||||
{
|
||||
esalt_buf[idx] = esalt_bufs[digests_offset].esalt_buf[idx];
|
||||
|
||||
barrier (CLK_GLOBAL_MEM_FENCE);
|
||||
}
|
||||
|
||||
md5_ctx_t ctx0;
|
||||
|
||||
md5_init (&ctx0);
|
||||
|
||||
md5_update_global (&ctx0, esalt_bufs[digests_offset].salt_buf, esalt_bufs[digests_offset].salt_len);
|
||||
|
||||
/**
|
||||
* 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 ctx1;
|
||||
|
||||
md5_init_vector_from_scalar (&ctx1, &ctx0);
|
||||
|
||||
md5_update_vector (&ctx1, w, pw_len);
|
||||
|
||||
md5_final_vector (&ctx1);
|
||||
|
||||
const u32x a = ctx1.h[0];
|
||||
const u32x b = ctx1.h[1];
|
||||
const u32x c = ctx1.h[2];
|
||||
const u32x d = ctx1.h[3];
|
||||
|
||||
md5_ctx_vector_t ctx;
|
||||
|
||||
md5_init_vector (&ctx);
|
||||
|
||||
ctx.w0[0] = uint_to_hex_lower8 ((a >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((a >> 8) & 255) << 16;
|
||||
ctx.w0[1] = uint_to_hex_lower8 ((a >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((a >> 24) & 255) << 16;
|
||||
ctx.w0[2] = uint_to_hex_lower8 ((b >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((b >> 8) & 255) << 16;
|
||||
ctx.w0[3] = uint_to_hex_lower8 ((b >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((b >> 24) & 255) << 16;
|
||||
ctx.w1[0] = uint_to_hex_lower8 ((c >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((c >> 8) & 255) << 16;
|
||||
ctx.w1[1] = uint_to_hex_lower8 ((c >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((c >> 24) & 255) << 16;
|
||||
ctx.w1[2] = uint_to_hex_lower8 ((d >> 0) & 255) << 0
|
||||
| uint_to_hex_lower8 ((d >> 8) & 255) << 16;
|
||||
ctx.w1[3] = uint_to_hex_lower8 ((d >> 16) & 255) << 0
|
||||
| uint_to_hex_lower8 ((d >> 24) & 255) << 16;
|
||||
|
||||
ctx.len = 32;
|
||||
|
||||
md5_update_vector (&ctx, esalt_buf, esalt_len);
|
||||
|
||||
md5_final_vector (&ctx);
|
||||
|
||||
const u32x r0 = ctx.h[DGST_R0];
|
||||
const u32x r1 = ctx.h[DGST_R1];
|
||||
const u32x r2 = ctx.h[DGST_R2];
|
||||
const u32x r3 = ctx.h[DGST_R3];
|
||||
|
||||
COMPARE_S_SIMD (r0, r1, r2, r3);
|
||||
}
|
||||
}
|
@ -211,10 +211,10 @@ typedef struct bitcoin_wallet
|
||||
|
||||
typedef struct sip
|
||||
{
|
||||
u32 salt_buf[30];
|
||||
u32 salt_buf[32];
|
||||
u32 salt_len;
|
||||
|
||||
u32 esalt_buf[38];
|
||||
u32 esalt_buf[48];
|
||||
u32 esalt_len;
|
||||
|
||||
} sip_t;
|
||||
|
Loading…
Reference in New Issue
Block a user