arno/hashcat
1
0
Fork 0
mirror of https://github.com/hashcat/hashcat.git synced 2024-12-23 15:18:16 +00:00
Code Issues Releases Wiki Activity
5d886658da
hashcat/OpenCL/m10100_a0.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

303 lines
11 KiB
Common Lisp
Raw Blame History

/**
* Author......: Jens Steube <jens.steube@gmail.com>
* License.....: MIT
*/
#define _SIPHASH_
//incompatible to simd
//#define NEW_SIMD_CODE
#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"
#include "include/rp_kernel.h"
#include "OpenCL/rp.c"
#include "OpenCL/simd.c"
#define SIPROUND(v0,v1,v2,v3) \
(v0) += (v1); \
(v1) = rotl64 ((v1), 13); \
(v1) ^= (v0); \
(v0) = rotl64 ((v0), 32); \
(v2) += (v3); \
(v3) = rotl64 ((v3), 16); \
(v3) ^= (v2); \
(v0) += (v3); \
(v3) = rotl64 ((v3), 21); \
(v3) ^= (v0); \
(v2) += (v1); \
(v1) = rotl64 ((v1), 17); \
(v1) ^= (v2); \
(v2) = rotl64 ((v2), 32)
__kernel void m10100_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 void *esalt_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 pw_buf0[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];
u32 pw_buf1[4];
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;
/**
* base
*/
u64x v0p = SIPHASHM_0;
u64x v1p = SIPHASHM_1;
u64x v2p = SIPHASHM_2;
u64x v3p = SIPHASHM_3;
v0p ^= hl32_to_64 (salt_bufs[salt_pos].salt_buf[1], salt_bufs[salt_pos].salt_buf[0]);
v1p ^= hl32_to_64 (salt_bufs[salt_pos].salt_buf[3], salt_bufs[salt_pos].salt_buf[2]);
v2p ^= hl32_to_64 (salt_bufs[salt_pos].salt_buf[1], salt_bufs[salt_pos].salt_buf[0]);
v3p ^= hl32_to_64 (salt_bufs[salt_pos].salt_buf[3], salt_bufs[salt_pos].salt_buf[2]);
/**
* 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 (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
switch (out_len / 8)
{
case 0: w0[1] |= out_len << 24; break;
case 1: w0[3] |= out_len << 24; break;
case 2: w1[1] |= out_len << 24; break;
case 3: w1[3] |= out_len << 24; break;
}
u64x v0 = v0p;
u64x v1 = v1p;
u64x v2 = v2p;
u64x v3 = v3p;
int i;
int j;
for (i = 0, j = 0; i <= out_len && i < 16; i += 8, j += 2)
{
u64x m = hl32_to_64 (w0[j + 1], w0[j + 0]);
v3 ^= m;
SIPROUND (v0, v1, v2, v3);
SIPROUND (v0, v1, v2, v3);
v0 ^= m;
}
for ( j = 0; i <= out_len && i < 32; i += 8, j += 2)
{
u64x m = hl32_to_64 (w1[j + 1], w1[j + 0]);
v3 ^= m;
SIPROUND (v0, v1, v2, v3);
SIPROUND (v0, v1, v2, v3);
v0 ^= m;
}
v2 ^= 0xff;
SIPROUND (v0, v1, v2, v3);
SIPROUND (v0, v1, v2, v3);
SIPROUND (v0, v1, v2, v3);
SIPROUND (v0, v1, v2, v3);
const u64x v = v0 ^ v1 ^ v2 ^ v3;
const u32x a = l32_from_64 (v);
const u32x b = h32_from_64 (v);
const u32x c = 0;
const u32x d = 0;
COMPARE_M_SIMD (a, b, c, d);
}
}
__kernel void m10100_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 void *esalt_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 m10100_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 void *esalt_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 m10100_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 void *esalt_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 pw_buf0[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];
u32 pw_buf1[4];
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;
/**
* base
*/
u64x v0p = SIPHASHM_0;
u64x v1p = SIPHASHM_1;
u64x v2p = SIPHASHM_2;
u64x v3p = SIPHASHM_3;
v0p ^= hl32_to_64 (salt_bufs[salt_pos].salt_buf[1], salt_bufs[salt_pos].salt_buf[0]);
v1p ^= hl32_to_64 (salt_bufs[salt_pos].salt_buf[3], salt_bufs[salt_pos].salt_buf[2]);
v2p ^= hl32_to_64 (salt_bufs[salt_pos].salt_buf[1], salt_bufs[salt_pos].salt_buf[0]);
v3p ^= hl32_to_64 (salt_bufs[salt_pos].salt_buf[3], salt_bufs[salt_pos].salt_buf[2]);
/**
* digest
*/
const u32 search[4] =
{
digests_buf[digests_offset].digest_buf[DGST_R0],
digests_buf[digests_offset].digest_buf[DGST_R1],
digests_buf[digests_offset].digest_buf[DGST_R2],
digests_buf[digests_offset].digest_buf[DGST_R3]
};
/**
* loop
*/
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
{
u32x w0[4] = { 0 };
u32x w1[4] = { 0 };
u32x w2[4] = { 0 };
u32x w3[4] = { 0 };
const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
switch (out_len / 8)
{
case 0: w0[1] |= out_len << 24; break;
case 1: w0[3] |= out_len << 24; break;
case 2: w1[1] |= out_len << 24; break;
case 3: w1[3] |= out_len << 24; break;
}
u64x v0 = v0p;
u64x v1 = v1p;
u64x v2 = v2p;
u64x v3 = v3p;
int i;
int j;
for (i = 0, j = 0; i <= out_len && i < 16; i += 8, j += 2)
{
u64x m = hl32_to_64 (w0[j + 1], w0[j + 0]);
v3 ^= m;
SIPROUND (v0, v1, v2, v3);
SIPROUND (v0, v1, v2, v3);
v0 ^= m;
}
for ( j = 0; i <= out_len && i < 32; i += 8, j += 2)
{
u64x m = hl32_to_64 (w1[j + 1], w1[j + 0]);
v3 ^= m;
SIPROUND (v0, v1, v2, v3);
SIPROUND (v0, v1, v2, v3);
v0 ^= m;
}
v2 ^= 0xff;
SIPROUND (v0, v1, v2, v3);
SIPROUND (v0, v1, v2, v3);
SIPROUND (v0, v1, v2, v3);
SIPROUND (v0, v1, v2, v3);
const u64x v = v0 ^ v1 ^ v2 ^ v3;
const u32x a = l32_from_64 (v);
const u32x b = h32_from_64 (v);
const u32x c = 0;
const u32x d = 0;
COMPARE_S_SIMD (a, b, c, d);
}
}
__kernel void m10100_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 void *esalt_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 m10100_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 void *esalt_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)
{
}
Reference in New Issue View Git Blame Copy Permalink