1
0
mirror of https://github.com/hashcat/hashcat.git synced 2024-12-23 15:18:16 +00:00
hashcat/OpenCL/m14400_a0-optimized.cl
jsteube beb6ee2061 Add OPTI_TYPE_OPTIMIZED_KERNEL
Rename unconverted fast hash kernels to optimized kernels
Finalize some converted fast hashes to default kernels
2017-07-18 14:45:15 +02:00

800 lines
30 KiB
Common Lisp

/**
* Author......: See docs/credits.txt
* License.....: MIT
*/
#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_simd.cl"
#if VECT_SIZE == 1
#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i)])
#elif VECT_SIZE == 2
#define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
#elif VECT_SIZE == 4
#define uint_to_hex_lower8_le(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_le(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_le(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
void append_4 (const u32 offset, u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 src_r0)
{
u32 tmp[2];
switch (offset & 3)
{
case 0: tmp[0] = src_r0;
tmp[1] = 0;
break;
case 1: tmp[0] = src_r0 << 8;
tmp[1] = src_r0 >> 24;
break;
case 2: tmp[0] = src_r0 << 16;
tmp[1] = src_r0 >> 16;
break;
case 3: tmp[0] = src_r0 << 24;
tmp[1] = src_r0 >> 8;
break;
}
switch (offset / 4)
{
case 0: w0[0] |= tmp[0];
w0[1] = tmp[1];
break;
case 1: w0[1] |= tmp[0];
w0[2] = tmp[1];
break;
case 2: w0[2] |= tmp[0];
w0[3] = tmp[1];
break;
case 3: w0[3] |= tmp[0];
w1[0] = tmp[1];
break;
case 4: w1[0] |= tmp[0];
w1[1] = tmp[1];
break;
case 5: w1[1] |= tmp[0];
w1[2] = tmp[1];
break;
case 6: w1[2] |= tmp[0];
w1[3] = tmp[1];
break;
case 7: w1[3] |= tmp[0];
w2[0] = tmp[1];
break;
case 8: w2[0] |= tmp[0];
w2[1] = tmp[1];
break;
case 9: w2[1] |= tmp[0];
w2[2] = tmp[1];
break;
case 10: w2[2] |= tmp[0];
w2[3] = tmp[1];
break;
case 11: w2[3] |= tmp[0];
w3[0] = tmp[1];
break;
case 12: w3[0] |= tmp[0];
w3[1] = tmp[1];
break;
case 13: w3[1] |= tmp[0];
w3[2] = tmp[1];
break;
case 14: w3[2] |= tmp[0];
w3[3] = tmp[1];
break;
case 15: w3[3] |= tmp[0];
break;
}
}
void shift_2 (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4])
{
w3[3] = w3[2] >> 16 | w3[3] << 16;
w3[2] = w3[1] >> 16 | w3[2] << 16;
w3[1] = w3[0] >> 16 | w3[1] << 16;
w3[0] = w2[3] >> 16 | w3[0] << 16;
w2[3] = w2[2] >> 16 | w2[3] << 16;
w2[2] = w2[1] >> 16 | w2[2] << 16;
w2[1] = w2[0] >> 16 | w2[1] << 16;
w2[0] = w1[3] >> 16 | w2[0] << 16;
w1[3] = w1[2] >> 16 | w1[3] << 16;
w1[2] = w1[1] >> 16 | w1[2] << 16;
w1[1] = w1[0] >> 16 | w1[1] << 16;
w1[0] = w0[3] >> 16 | w1[0] << 16;
w0[3] = w0[2] >> 16 | w0[3] << 16;
w0[2] = w0[1] >> 16 | w0[2] << 16;
w0[1] = w0[0] >> 16 | w0[1] << 16;
w0[0] = 0 | w0[0] << 16;
}
void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5])
{
u32x A = digest[0];
u32x B = digest[1];
u32x C = digest[2];
u32x D = digest[3];
u32x E = digest[4];
u32x w0_t = w0[0];
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];
#undef K
#define K SHA1C00
SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
#undef K
#define K SHA1C01
w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
#undef K
#define K SHA1C02
w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
#undef K
#define K SHA1C03
wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
digest[0] += A;
digest[1] += B;
digest[2] += C;
digest[3] += D;
digest[4] += E;
}
__kernel void m14400_m04 (__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 void *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) << 0
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
}
barrier (CLK_LOCAL_MEM_FENCE);
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;
/**
* salt
*/
const u32 dashes = 0x2d2d2d2d;
u32 salt_buf0[4];
u32 salt_buf1[4];
u32 salt_buf2[4];
u32 salt_buf3[4];
salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
salt_buf1[1] = 0;
salt_buf1[2] = 0;
salt_buf1[3] = 0;
salt_buf2[0] = 0;
salt_buf2[1] = 0;
salt_buf2[2] = 0;
salt_buf2[3] = 0;
salt_buf3[0] = 0;
salt_buf3[1] = 0;
salt_buf3[2] = 0;
salt_buf3[3] = 0;
shift_2 (salt_buf0, salt_buf1, salt_buf2, salt_buf3);
salt_buf0[0] |= dashes >> 16;
salt_buf1[1] |= dashes << 16;
salt_buf0[0] = swap32 (salt_buf0[0]);
salt_buf0[1] = swap32 (salt_buf0[1]);
salt_buf0[2] = swap32 (salt_buf0[2]);
salt_buf0[3] = swap32 (salt_buf0[3]);
salt_buf1[0] = swap32 (salt_buf1[0]);
salt_buf1[1] = swap32 (salt_buf1[1]);
salt_buf1[2] = swap32 (salt_buf1[2]);
salt_buf1[3] = swap32 (salt_buf1[3]);
salt_buf2[0] = swap32 (salt_buf2[0]);
salt_buf2[1] = swap32 (salt_buf2[1]);
salt_buf2[2] = swap32 (salt_buf2[2]);
salt_buf2[3] = swap32 (salt_buf2[3]);
salt_buf3[0] = swap32 (salt_buf3[0]);
salt_buf3[1] = swap32 (salt_buf3[1]);
salt_buf3[2] = swap32 (salt_buf3[2]);
salt_buf3[3] = swap32 (salt_buf3[3]);
const u32 salt_len_orig = salt_bufs[salt_pos].salt_len;
const u32 salt_len_new = 2 + salt_len_orig + 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_orig = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
append_4 (out_len_orig, w0, w1, w2, w3, dashes);
shift_2 (w0, w1, w2, w3);
w0[0] |= dashes >> 16;
const u32x out_len_new = 2 + out_len_orig + 4;
append_0x80_4x4_VV (w0, w1, w2, w3, out_len_new);
w0[0] = swap32 (w0[0]);
w0[1] = swap32 (w0[1]);
w0[2] = swap32 (w0[2]);
w0[3] = swap32 (w0[3]);
w1[0] = swap32 (w1[0]);
w1[1] = swap32 (w1[1]);
w1[2] = swap32 (w1[2]);
w1[3] = swap32 (w1[3]);
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = 0;
/**
* prepend salt
*/
const u32x out_salt_len = salt_len_new + out_len_new;
u32x t0[4];
u32x t1[4];
u32x t2[4];
u32x t3[4];
t0[0] = salt_buf0[0];
t0[1] = salt_buf0[1];
t0[2] = salt_buf0[2];
t0[3] = salt_buf0[3];
t1[0] = salt_buf1[0];
t1[1] = salt_buf1[1];
t1[2] = w0[0];
t1[3] = w0[1];
t2[0] = w0[2];
t2[1] = w0[3];
t2[2] = w1[0];
t2[3] = w1[1];
t3[0] = w1[2];
t3[1] = w1[3];
t3[2] = 0;
t3[3] = out_salt_len * 8;
/**
* sha1
*/
u32x digest[5];
digest[0] = SHA1M_A;
digest[1] = SHA1M_B;
digest[2] = SHA1M_C;
digest[3] = SHA1M_D;
digest[4] = SHA1M_E;
sha1_transform (t0, t1, t2, t3, digest);
for (int i = 1; i < 10; i++)
{
u32 s[10];
s[0] = uint_to_hex_lower8_le ((digest[0] >> 16) & 255) << 0
| uint_to_hex_lower8_le ((digest[0] >> 24) & 255) << 16;
s[1] = uint_to_hex_lower8_le ((digest[0] >> 0) & 255) << 0
| uint_to_hex_lower8_le ((digest[0] >> 8) & 255) << 16;
s[2] = uint_to_hex_lower8_le ((digest[1] >> 16) & 255) << 0
| uint_to_hex_lower8_le ((digest[1] >> 24) & 255) << 16;
s[3] = uint_to_hex_lower8_le ((digest[1] >> 0) & 255) << 0
| uint_to_hex_lower8_le ((digest[1] >> 8) & 255) << 16;
s[4] = uint_to_hex_lower8_le ((digest[2] >> 16) & 255) << 0
| uint_to_hex_lower8_le ((digest[2] >> 24) & 255) << 16;
s[5] = uint_to_hex_lower8_le ((digest[2] >> 0) & 255) << 0
| uint_to_hex_lower8_le ((digest[2] >> 8) & 255) << 16;
s[6] = uint_to_hex_lower8_le ((digest[3] >> 16) & 255) << 0
| uint_to_hex_lower8_le ((digest[3] >> 24) & 255) << 16;
s[7] = uint_to_hex_lower8_le ((digest[3] >> 0) & 255) << 0
| uint_to_hex_lower8_le ((digest[3] >> 8) & 255) << 16;
s[8] = uint_to_hex_lower8_le ((digest[4] >> 16) & 255) << 0
| uint_to_hex_lower8_le ((digest[4] >> 24) & 255) << 16;
s[9] = uint_to_hex_lower8_le ((digest[4] >> 0) & 255) << 0
| uint_to_hex_lower8_le ((digest[4] >> 8) & 255) << 16;
t0[0] = salt_buf0[0];
t0[1] = salt_buf0[1];
t0[2] = salt_buf0[2];
t0[3] = salt_buf0[3];
t1[0] = salt_buf1[0];
t1[1] = salt_buf1[1];
t1[2] = s[0];
t1[3] = s[1];
t2[0] = s[2];
t2[1] = s[3];
t2[2] = s[4];
t2[3] = s[5];
t3[0] = s[6];
t3[1] = s[7];
t3[2] = s[8];
t3[3] = s[9];
digest[0] = SHA1M_A;
digest[1] = SHA1M_B;
digest[2] = SHA1M_C;
digest[3] = SHA1M_D;
digest[4] = SHA1M_E;
sha1_transform (t0, t1, t2, t3, digest);
t0[0] = w0[0];
t0[1] = w0[1];
t0[2] = w0[2];
t0[3] = w0[3];
t1[0] = w1[0];
t1[1] = w1[1];
t1[2] = w1[2];
t1[3] = w1[3];
t2[0] = 0;
t2[1] = 0;
t2[2] = 0;
t2[3] = 0;
t3[0] = 0;
t3[1] = 0;
t3[2] = 0;
t3[3] = (salt_len_new + 40 + out_len_new) * 8;
sha1_transform (t0, t1, t2, t3, digest);
}
const u32x a = digest[0];
const u32x b = digest[1];
const u32x c = digest[2];
const u32x d = digest[3];
const u32x e = digest[4];
COMPARE_M_SIMD (d, e, c, b);
}
}
__kernel void m14400_m08 (__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 void *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)
{
}
__kernel void m14400_m16 (__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 void *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)
{
}
__kernel void m14400_s04 (__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 void *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) << 0
| ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
}
barrier (CLK_LOCAL_MEM_FENCE);
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;
/**
* salt
*/
const u32 dashes = 0x2d2d2d2d;
u32 salt_buf0[4];
u32 salt_buf1[4];
u32 salt_buf2[4];
u32 salt_buf3[4];
salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
salt_buf1[1] = 0;
salt_buf1[2] = 0;
salt_buf1[3] = 0;
salt_buf2[0] = 0;
salt_buf2[1] = 0;
salt_buf2[2] = 0;
salt_buf2[3] = 0;
salt_buf3[0] = 0;
salt_buf3[1] = 0;
salt_buf3[2] = 0;
salt_buf3[3] = 0;
shift_2 (salt_buf0, salt_buf1, salt_buf2, salt_buf3);
salt_buf0[0] |= dashes >> 16;
salt_buf1[1] |= dashes << 16;
salt_buf0[0] = swap32 (salt_buf0[0]);
salt_buf0[1] = swap32 (salt_buf0[1]);
salt_buf0[2] = swap32 (salt_buf0[2]);
salt_buf0[3] = swap32 (salt_buf0[3]);
salt_buf1[0] = swap32 (salt_buf1[0]);
salt_buf1[1] = swap32 (salt_buf1[1]);
salt_buf1[2] = swap32 (salt_buf1[2]);
salt_buf1[3] = swap32 (salt_buf1[3]);
salt_buf2[0] = swap32 (salt_buf2[0]);
salt_buf2[1] = swap32 (salt_buf2[1]);
salt_buf2[2] = swap32 (salt_buf2[2]);
salt_buf2[3] = swap32 (salt_buf2[3]);
salt_buf3[0] = swap32 (salt_buf3[0]);
salt_buf3[1] = swap32 (salt_buf3[1]);
salt_buf3[2] = swap32 (salt_buf3[2]);
salt_buf3[3] = swap32 (salt_buf3[3]);
const u32 salt_len_orig = salt_bufs[salt_pos].salt_len;
const u32 salt_len_new = 2 + salt_len_orig + 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_orig = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
append_4 (out_len_orig, w0, w1, w2, w3, dashes);
shift_2 (w0, w1, w2, w3);
w0[0] |= dashes >> 16;
const u32x out_len_new = 2 + out_len_orig + 4;
append_0x80_4x4_VV (w0, w1, w2, w3, out_len_new);
w0[0] = swap32 (w0[0]);
w0[1] = swap32 (w0[1]);
w0[2] = swap32 (w0[2]);
w0[3] = swap32 (w0[3]);
w1[0] = swap32 (w1[0]);
w1[1] = swap32 (w1[1]);
w1[2] = swap32 (w1[2]);
w1[3] = swap32 (w1[3]);
w2[0] = 0;
w2[1] = 0;
w2[2] = 0;
w2[3] = 0;
w3[0] = 0;
w3[1] = 0;
w3[2] = 0;
w3[3] = 0;
/**
* prepend salt
*/
const u32x out_salt_len = salt_len_new + out_len_new;
u32x t0[4];
u32x t1[4];
u32x t2[4];
u32x t3[4];
t0[0] = salt_buf0[0];
t0[1] = salt_buf0[1];
t0[2] = salt_buf0[2];
t0[3] = salt_buf0[3];
t1[0] = salt_buf1[0];
t1[1] = salt_buf1[1];
t1[2] = w0[0];
t1[3] = w0[1];
t2[0] = w0[2];
t2[1] = w0[3];
t2[2] = w1[0];
t2[3] = w1[1];
t3[0] = w1[2];
t3[1] = w1[3];
t3[2] = 0;
t3[3] = out_salt_len * 8;
/**
* sha1
*/
u32x digest[5];
digest[0] = SHA1M_A;
digest[1] = SHA1M_B;
digest[2] = SHA1M_C;
digest[3] = SHA1M_D;
digest[4] = SHA1M_E;
sha1_transform (t0, t1, t2, t3, digest);
for (int i = 1; i < 10; i++)
{
u32 s[10];
s[0] = uint_to_hex_lower8_le ((digest[0] >> 16) & 255) << 0
| uint_to_hex_lower8_le ((digest[0] >> 24) & 255) << 16;
s[1] = uint_to_hex_lower8_le ((digest[0] >> 0) & 255) << 0
| uint_to_hex_lower8_le ((digest[0] >> 8) & 255) << 16;
s[2] = uint_to_hex_lower8_le ((digest[1] >> 16) & 255) << 0
| uint_to_hex_lower8_le ((digest[1] >> 24) & 255) << 16;
s[3] = uint_to_hex_lower8_le ((digest[1] >> 0) & 255) << 0
| uint_to_hex_lower8_le ((digest[1] >> 8) & 255) << 16;
s[4] = uint_to_hex_lower8_le ((digest[2] >> 16) & 255) << 0
| uint_to_hex_lower8_le ((digest[2] >> 24) & 255) << 16;
s[5] = uint_to_hex_lower8_le ((digest[2] >> 0) & 255) << 0
| uint_to_hex_lower8_le ((digest[2] >> 8) & 255) << 16;
s[6] = uint_to_hex_lower8_le ((digest[3] >> 16) & 255) << 0
| uint_to_hex_lower8_le ((digest[3] >> 24) & 255) << 16;
s[7] = uint_to_hex_lower8_le ((digest[3] >> 0) & 255) << 0
| uint_to_hex_lower8_le ((digest[3] >> 8) & 255) << 16;
s[8] = uint_to_hex_lower8_le ((digest[4] >> 16) & 255) << 0
| uint_to_hex_lower8_le ((digest[4] >> 24) & 255) << 16;
s[9] = uint_to_hex_lower8_le ((digest[4] >> 0) & 255) << 0
| uint_to_hex_lower8_le ((digest[4] >> 8) & 255) << 16;
t0[0] = salt_buf0[0];
t0[1] = salt_buf0[1];
t0[2] = salt_buf0[2];
t0[3] = salt_buf0[3];
t1[0] = salt_buf1[0];
t1[1] = salt_buf1[1];
t1[2] = s[0];
t1[3] = s[1];
t2[0] = s[2];
t2[1] = s[3];
t2[2] = s[4];
t2[3] = s[5];
t3[0] = s[6];
t3[1] = s[7];
t3[2] = s[8];
t3[3] = s[9];
digest[0] = SHA1M_A;
digest[1] = SHA1M_B;
digest[2] = SHA1M_C;
digest[3] = SHA1M_D;
digest[4] = SHA1M_E;
sha1_transform (t0, t1, t2, t3, digest);
t0[0] = w0[0];
t0[1] = w0[1];
t0[2] = w0[2];
t0[3] = w0[3];
t1[0] = w1[0];
t1[1] = w1[1];
t1[2] = w1[2];
t1[3] = w1[3];
t2[0] = 0;
t2[1] = 0;
t2[2] = 0;
t2[3] = 0;
t3[0] = 0;
t3[1] = 0;
t3[2] = 0;
t3[3] = (salt_len_new + 40 + out_len_new) * 8;
sha1_transform (t0, t1, t2, t3, digest);
}
const u32x a = digest[0];
const u32x b = digest[1];
const u32x c = digest[2];
const u32x d = digest[3];
const u32x e = digest[4];
COMPARE_S_SIMD (d, e, c, b);
}
}
__kernel void m14400_s08 (__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 void *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)
{
}
__kernel void m14400_s16 (__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 void *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)
{
}