1
0
mirror of https://github.com/hashcat/hashcat.git synced 2024-10-09 17:38:58 +00:00
hashcat/OpenCL/m10410_a1.cl
jsteube dad03e394d Fixed two major problems
1) SIMD code for all attack-mode

Macro vector_accessible() was not refactored and missing completely.
Had to rename variables rules_cnt, combs_cnt and bfs_cnt into il_cnt which was a good thing anyway as with new SIMD code they all act in the same way.

2) SIMD code for attack-mode 0

With new SIMD code, apply_rules_vect() has to return u32 not u32x.
This has massive impact on all *_a0 kernels.

I've rewritten most of them. Deep testing using test.sh is still required.

Some kernel need more fixes:

- Some are kind of completely incompatible like m10400 but they still use old check_* includes, we should get rid of them as they are no longer neccessary as we have simd.c
- Some have a chance but require additional effort like m11500. We can use commented out "#define NEW_SIMD_CODE" to find them

This change can have negative impact on -a0 performance for device that require vectorization. That is mostly CPU devices. New GPU's are all scalar, so they wont get hurt by this.
This change also proofes that there's no way to efficiently vectorize kernel rules with new SIMD code, but it enables the addition of the rule functions like @ that we were missing for some long time. This is a TODO.
2016-02-27 17:18:54 +01:00

417 lines
12 KiB
Common Lisp

/**
* Authors.....: Jens Steube <jens.steube@gmail.com>
* Gabriele Gristina <matrix@hashcat.net>
*
* License.....: MIT
*/
#define _MD5_
#include "include/constants.h"
#include "include/kernel_vendor.h"
#define DGST_R0 0
#define DGST_R1 1
#define DGST_R2 2
#define DGST_R3 3
#include "include/kernel_functions.c"
#include "OpenCL/types_ocl.c"
#include "OpenCL/common.c"
#define COMPARE_S "OpenCL/check_single_comp4.c"
#define COMPARE_M "OpenCL/check_multi_comp4.c"
__constant u32 padding[8] =
{
0x5e4ebf28,
0x418a754e,
0x564e0064,
0x0801faff,
0xb6002e2e,
0x803e68d0,
0xfea90c2f,
0x7a695364
};
typedef struct
{
u8 S[256];
u32 wtf_its_faster;
} RC4_KEY;
static void swap (__local RC4_KEY *rc4_key, const u8 i, const u8 j)
{
u8 tmp;
tmp = rc4_key->S[i];
rc4_key->S[i] = rc4_key->S[j];
rc4_key->S[j] = tmp;
}
static void rc4_init_16 (__local RC4_KEY *rc4_key, const u32 data[4])
{
u32 v = 0x03020100;
u32 a = 0x04040404;
__local u32 *ptr = (__local u32 *) rc4_key->S;
#pragma unroll
for (u32 i = 0; i < 64; i++)
{
ptr[i] = v; v += a;
}
const u32 d0 = data[0] >> 0;
const u32 d1 = data[0] >> 8;
const u32 d2 = data[0] >> 16;
const u32 d3 = data[0] >> 24;
const u32 d4 = data[1] >> 0;
u32 j = 0;
#pragma unroll
for (u32 i = 0; i < 255; i += 5)
{
j += rc4_key->S[i + 0] + d0; swap (rc4_key, i + 0, j);
j += rc4_key->S[i + 1] + d1; swap (rc4_key, i + 1, j);
j += rc4_key->S[i + 2] + d2; swap (rc4_key, i + 2, j);
j += rc4_key->S[i + 3] + d3; swap (rc4_key, i + 3, j);
j += rc4_key->S[i + 4] + d4; swap (rc4_key, i + 4, j);
}
j += rc4_key->S[255] + d0; swap (rc4_key, 255, j);
}
static u8 rc4_next_16 (__local RC4_KEY *rc4_key, u8 i, u8 j, __constant u32 *in, u32 out[4])
{
for (u32 k = 0; k < 4; k++)
{
u32 xor4 = 0;
u8 idx;
i += 1;
j += rc4_key->S[i];
swap (rc4_key, i, j);
idx = rc4_key->S[i] + rc4_key->S[j];
xor4 |= rc4_key->S[idx] << 0;
i += 1;
j += rc4_key->S[i];
swap (rc4_key, i, j);
idx = rc4_key->S[i] + rc4_key->S[j];
xor4 |= rc4_key->S[idx] << 8;
i += 1;
j += rc4_key->S[i];
swap (rc4_key, i, j);
idx = rc4_key->S[i] + rc4_key->S[j];
xor4 |= rc4_key->S[idx] << 16;
i += 1;
j += rc4_key->S[i];
swap (rc4_key, i, j);
idx = rc4_key->S[i] + rc4_key->S[j];
xor4 |= rc4_key->S[idx] << 24;
out[k] = in[k] ^ xor4;
}
return j;
}
__kernel void m10410_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pdf_t *pdf_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_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 lid = get_local_id (0);
/**
* base
*/
const u32 gid = get_global_id (0);
if (gid >= gid_max) return;
u32 wordl0[4];
wordl0[0] = pws[gid].i[ 0];
wordl0[1] = pws[gid].i[ 1];
wordl0[2] = pws[gid].i[ 2];
wordl0[3] = pws[gid].i[ 3];
u32 wordl1[4];
wordl1[0] = pws[gid].i[ 4];
wordl1[1] = pws[gid].i[ 5];
wordl1[2] = pws[gid].i[ 6];
wordl1[3] = pws[gid].i[ 7];
u32 wordl2[4];
wordl2[0] = 0;
wordl2[1] = 0;
wordl2[2] = 0;
wordl2[3] = 0;
u32 wordl3[4];
wordl3[0] = 0;
wordl3[1] = 0;
wordl3[2] = 0;
wordl3[3] = 0;
const u32 pw_l_len = pws[gid].pw_len;
if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
{
switch_buffer_by_offset_le (wordl0, wordl1, wordl2, wordl3, combs_buf[0].pw_len);
}
/**
* key
*/
__local RC4_KEY rc4_keys[64];
__local RC4_KEY *rc4_key = &rc4_keys[lid];
/**
* loop
*/
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
{
u32 wordr0[4];
wordr0[0] = combs_buf[il_pos].i[0];
wordr0[1] = combs_buf[il_pos].i[1];
wordr0[2] = combs_buf[il_pos].i[2];
wordr0[3] = combs_buf[il_pos].i[3];
u32 wordr1[4];
wordr1[0] = combs_buf[il_pos].i[4];
wordr1[1] = combs_buf[il_pos].i[5];
wordr1[2] = combs_buf[il_pos].i[6];
wordr1[3] = combs_buf[il_pos].i[7];
u32 wordr2[4];
wordr2[0] = 0;
wordr2[1] = 0;
wordr2[2] = 0;
wordr2[3] = 0;
u32 wordr3[4];
wordr3[0] = 0;
wordr3[1] = 0;
wordr3[2] = 0;
wordr3[3] = 0;
if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
{
switch_buffer_by_offset_le (wordr0, wordr1, wordr2, wordr3, pw_l_len);
}
u32 w0[2];
w0[0] = wordl0[0] | wordr0[0];
w0[1] = wordl0[1] | wordr0[1];
// now the RC4 part
u32 key[4];
key[0] = w0[0];
key[1] = w0[1];
key[2] = 0;
key[3] = 0;
rc4_init_16 (rc4_key, key);
u32 out[4];
rc4_next_16 (rc4_key, 0, 0, padding, out);
const u32 r0 = out[0];
const u32 r1 = out[1];
const u32 r2 = out[2];
const u32 r3 = out[3];
#include COMPARE_M
}
}
__kernel void m10410_m08 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pdf_t *pdf_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_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)
{
}
__kernel void m10410_m16 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pdf_t *pdf_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_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)
{
}
__kernel void m10410_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pdf_t *pdf_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_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 lid = get_local_id (0);
/**
* base
*/
const u32 gid = get_global_id (0);
if (gid >= gid_max) return;
u32 wordl0[4];
wordl0[0] = pws[gid].i[ 0];
wordl0[1] = pws[gid].i[ 1];
wordl0[2] = pws[gid].i[ 2];
wordl0[3] = pws[gid].i[ 3];
u32 wordl1[4];
wordl1[0] = pws[gid].i[ 4];
wordl1[1] = pws[gid].i[ 5];
wordl1[2] = pws[gid].i[ 6];
wordl1[3] = pws[gid].i[ 7];
u32 wordl2[4];
wordl2[0] = 0;
wordl2[1] = 0;
wordl2[2] = 0;
wordl2[3] = 0;
u32 wordl3[4];
wordl3[0] = 0;
wordl3[1] = 0;
wordl3[2] = 0;
wordl3[3] = 0;
const u32 pw_l_len = pws[gid].pw_len;
if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
{
switch_buffer_by_offset_le (wordl0, wordl1, wordl2, wordl3, combs_buf[0].pw_len);
}
/**
* digest
*/
const u32 search[4] =
{
digests_buf[digests_offset].digest_buf[DGST_R0],
digests_buf[digests_offset].digest_buf[DGST_R1],
digests_buf[digests_offset].digest_buf[DGST_R2],
digests_buf[digests_offset].digest_buf[DGST_R3]
};
/**
* key
*/
__local RC4_KEY rc4_keys[64];
__local RC4_KEY *rc4_key = &rc4_keys[lid];
/**
* loop
*/
for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
{
u32 wordr0[4];
wordr0[0] = combs_buf[il_pos].i[0];
wordr0[1] = combs_buf[il_pos].i[1];
wordr0[2] = combs_buf[il_pos].i[2];
wordr0[3] = combs_buf[il_pos].i[3];
u32 wordr1[4];
wordr1[0] = combs_buf[il_pos].i[4];
wordr1[1] = combs_buf[il_pos].i[5];
wordr1[2] = combs_buf[il_pos].i[6];
wordr1[3] = combs_buf[il_pos].i[7];
u32 wordr2[4];
wordr2[0] = 0;
wordr2[1] = 0;
wordr2[2] = 0;
wordr2[3] = 0;
u32 wordr3[4];
wordr3[0] = 0;
wordr3[1] = 0;
wordr3[2] = 0;
wordr3[3] = 0;
if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
{
switch_buffer_by_offset_le (wordr0, wordr1, wordr2, wordr3, pw_l_len);
}
u32 w0[2];
w0[0] = wordl0[0] | wordr0[0];
w0[1] = wordl0[1] | wordr0[1];
// now the RC4 part
u32 key[4];
key[0] = w0[0];
key[1] = w0[1];
key[2] = 0;
key[3] = 0;
rc4_init_16 (rc4_key, key);
u32 out[4];
rc4_next_16 (rc4_key, 0, 0, padding, out);
const u32 r0 = out[0];
const u32 r1 = out[1];
const u32 r2 = out[2];
const u32 r3 = out[3];
#include COMPARE_S
}
}
__kernel void m10410_s08 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pdf_t *pdf_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_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)
{
}
__kernel void m10410_s16 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global pdf_t *pdf_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_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)
{
}