2 * Authors.....: Jens Steube <jens.steube@gmail.com>
3 * Gabriele Gristina <matrix@hashcat.net>
12 #include "inc_vendor.cl"
13 #include "inc_hash_constants.h"
14 #include "inc_hash_functions.cl"
15 #include "inc_types.cl"
16 #include "inc_common.cl"
19 #include "inc_simd.cl"
21 __constant u32 k_sha256[64] =
23 SHA256C00, SHA256C01, SHA256C02, SHA256C03,
24 SHA256C04, SHA256C05, SHA256C06, SHA256C07,
25 SHA256C08, SHA256C09, SHA256C0a, SHA256C0b,
26 SHA256C0c, SHA256C0d, SHA256C0e, SHA256C0f,
27 SHA256C10, SHA256C11, SHA256C12, SHA256C13,
28 SHA256C14, SHA256C15, SHA256C16, SHA256C17,
29 SHA256C18, SHA256C19, SHA256C1a, SHA256C1b,
30 SHA256C1c, SHA256C1d, SHA256C1e, SHA256C1f,
31 SHA256C20, SHA256C21, SHA256C22, SHA256C23,
32 SHA256C24, SHA256C25, SHA256C26, SHA256C27,
33 SHA256C28, SHA256C29, SHA256C2a, SHA256C2b,
34 SHA256C2c, SHA256C2d, SHA256C2e, SHA256C2f,
35 SHA256C30, SHA256C31, SHA256C32, SHA256C33,
36 SHA256C34, SHA256C35, SHA256C36, SHA256C37,
37 SHA256C38, SHA256C39, SHA256C3a, SHA256C3b,
38 SHA256C3c, SHA256C3d, SHA256C3e, SHA256C3f,
41 #define SHA256_S0_S(x) (rotl32_S ((x), 25u) ^ rotl32_S ((x), 14u) ^ SHIFT_RIGHT_32 ((x), 3u))
42 #define SHA256_S1_S(x) (rotl32_S ((x), 15u) ^ rotl32_S ((x), 13u) ^ SHIFT_RIGHT_32 ((x), 10u))
44 #define SHA256_EXPAND_S(x,y,z,w) (SHA256_S1_S (x) + y + SHA256_S0_S (z) + w)
46 void sha256_transform (u32x digest[8], const u32x w[16])
74 #define ROUND_EXPAND() \
76 w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); \
77 w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); \
78 w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); \
79 w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); \
80 w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); \
81 w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); \
82 w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); \
83 w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); \
84 w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); \
85 w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); \
86 wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); \
87 wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); \
88 wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); \
89 wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); \
90 we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); \
91 wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); \
94 #define ROUND_STEP(i) \
96 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha256[i + 0]); \
97 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha256[i + 1]); \
98 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha256[i + 2]); \
99 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha256[i + 3]); \
100 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha256[i + 4]); \
101 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha256[i + 5]); \
102 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha256[i + 6]); \
103 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha256[i + 7]); \
104 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha256[i + 8]); \
105 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha256[i + 9]); \
106 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha256[i + 10]); \
107 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha256[i + 11]); \
108 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha256[i + 12]); \
109 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha256[i + 13]); \
110 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, k_sha256[i + 14]); \
111 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha256[i + 15]); \
119 for (int i = 16; i < 64; i += 16)
121 ROUND_EXPAND (); ROUND_STEP (i);
134 void sha256_transform_z (u32x digest[8])
145 #define ROUND_STEP_Z(i) \
147 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, 0, k_sha256[i + 0]); \
148 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, 0, k_sha256[i + 1]); \
149 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, 0, k_sha256[i + 2]); \
150 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, 0, k_sha256[i + 3]); \
151 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, 0, k_sha256[i + 4]); \
152 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, 0, k_sha256[i + 5]); \
153 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, 0, k_sha256[i + 6]); \
154 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, 0, k_sha256[i + 7]); \
155 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, 0, k_sha256[i + 8]); \
156 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, 0, k_sha256[i + 9]); \
157 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, 0, k_sha256[i + 10]); \
158 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, 0, k_sha256[i + 11]); \
159 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, 0, k_sha256[i + 12]); \
160 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, 0, k_sha256[i + 13]); \
161 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, 0, k_sha256[i + 14]); \
162 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, 0, k_sha256[i + 15]); \
170 for (int i = 16; i < 64; i += 16)
185 void sha256_transform_s (u32x digest[8], __local u32 *w)
196 #define ROUND_STEP_S(i) \
198 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w[i + 0], k_sha256[i + 0]); \
199 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w[i + 1], k_sha256[i + 1]); \
200 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w[i + 2], k_sha256[i + 2]); \
201 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w[i + 3], k_sha256[i + 3]); \
202 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w[i + 4], k_sha256[i + 4]); \
203 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w[i + 5], k_sha256[i + 5]); \
204 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w[i + 6], k_sha256[i + 6]); \
205 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w[i + 7], k_sha256[i + 7]); \
206 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w[i + 8], k_sha256[i + 8]); \
207 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w[i + 9], k_sha256[i + 9]); \
208 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w[i + 10], k_sha256[i + 10]); \
209 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w[i + 11], k_sha256[i + 11]); \
210 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w[i + 12], k_sha256[i + 12]); \
211 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w[i + 13], k_sha256[i + 13]); \
212 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w[i + 14], k_sha256[i + 14]); \
213 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w[i + 15], k_sha256[i + 15]); \
221 for (int i = 16; i < 64; i += 16)
236 __kernel void m08000_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_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)
242 const u32 gid = get_global_id (0);
243 const u32 lid = get_local_id (0);
244 const u32 lsz = get_local_size (0);
250 const u32 salt_buf0 = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
251 const u32 salt_buf1 = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
252 const u32 salt_buf2 = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]); // 0x80
255 * precompute final msg blocks
258 __local u32 w_s1[64];
259 __local u32 w_s2[64];
261 for (u32 i = lid; i < 64; i += lsz)
267 barrier (CLK_LOCAL_MEM_FENCE);
271 w_s1[15] = 0 | salt_buf0 >> 16;
276 for (int i = 16; i < 64; i++)
278 w_s1[i] = SHA256_EXPAND_S (w_s1[i - 2], w_s1[i - 7], w_s1[i - 15], w_s1[i - 16]);
281 w_s2[ 0] = salt_buf0 << 16 | salt_buf1 >> 16;
282 w_s2[ 1] = salt_buf1 << 16 | salt_buf2 >> 16;
283 w_s2[ 2] = salt_buf2 << 16 | 0;
284 w_s2[15] = (510 + 8) * 8;
289 for (int i = 16; i < 64; i++)
291 w_s2[i] = SHA256_EXPAND_S (w_s2[i - 2], w_s2[i - 7], w_s2[i - 15], w_s2[i - 16]);
295 barrier (CLK_LOCAL_MEM_FENCE);
297 if (gid >= gid_max) return;
306 pw_buf0[0] = pws[gid].i[ 0];
307 pw_buf0[1] = pws[gid].i[ 1];
308 pw_buf0[2] = pws[gid].i[ 2];
309 pw_buf0[3] = pws[gid].i[ 3];
310 pw_buf1[0] = pws[gid].i[ 4];
311 pw_buf1[1] = pws[gid].i[ 5];
312 pw_buf1[2] = pws[gid].i[ 6];
313 pw_buf1[3] = pws[gid].i[ 7];
315 const u32 pw_len = pws[gid].pw_len;
321 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
328 apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
335 make_unicode (w0, w0_t, w1_t);
336 make_unicode (w1, w2_t, w3_t);
340 w_t[ 0] = swap32 (w0_t[0]);
341 w_t[ 1] = swap32 (w0_t[1]);
342 w_t[ 2] = swap32 (w0_t[2]);
343 w_t[ 3] = swap32 (w0_t[3]);
344 w_t[ 4] = swap32 (w1_t[0]);
345 w_t[ 5] = swap32 (w1_t[1]);
346 w_t[ 6] = swap32 (w1_t[2]);
347 w_t[ 7] = swap32 (w1_t[3]);
348 w_t[ 8] = swap32 (w2_t[0]);
349 w_t[ 9] = swap32 (w2_t[1]);
350 w_t[10] = swap32 (w2_t[2]);
351 w_t[11] = swap32 (w2_t[3]);
352 w_t[12] = swap32 (w3_t[0]);
353 w_t[13] = swap32 (w3_t[1]);
354 w_t[14] = swap32 (w3_t[2]);
355 w_t[15] = swap32 (w3_t[3]);
357 w_t[ 0] = w_t[ 0] >> 8;
358 w_t[ 1] = w_t[ 1] >> 8;
359 w_t[ 2] = w_t[ 2] >> 8;
360 w_t[ 3] = w_t[ 3] >> 8;
361 w_t[ 4] = w_t[ 4] >> 8;
362 w_t[ 5] = w_t[ 5] >> 8;
363 w_t[ 6] = w_t[ 6] >> 8;
364 w_t[ 7] = w_t[ 7] >> 8;
365 w_t[ 8] = w_t[ 8] >> 8;
366 w_t[ 9] = w_t[ 9] >> 8;
367 w_t[10] = w_t[10] >> 8;
368 w_t[11] = w_t[11] >> 8;
369 w_t[12] = w_t[12] >> 8;
370 w_t[13] = w_t[13] >> 8;
371 w_t[14] = w_t[14] >> 8;
372 w_t[15] = w_t[15] >> 8;
376 digest[0] = SHA256M_A;
377 digest[1] = SHA256M_B;
378 digest[2] = SHA256M_C;
379 digest[3] = SHA256M_D;
380 digest[4] = SHA256M_E;
381 digest[5] = SHA256M_F;
382 digest[6] = SHA256M_G;
383 digest[7] = SHA256M_H;
385 sha256_transform (digest, w_t); // 0 - 64
386 sha256_transform_z (digest); // 64 - 128
387 sha256_transform_z (digest); // 128 - 192
388 sha256_transform_z (digest); // 192 - 256
389 sha256_transform_z (digest); // 256 - 320
390 sha256_transform_z (digest); // 320 - 384
391 sha256_transform_z (digest); // 384 - 448
392 sha256_transform_s (digest, w_s1); // 448 - 512
393 sha256_transform_s (digest, w_s2); // 512 - 576
395 COMPARE_M_SIMD (digest[3], digest[7], digest[2], digest[6]);
399 __kernel void m08000_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_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)
403 __kernel void m08000_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_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)
407 __kernel void m08000_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_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)
413 const u32 gid = get_global_id (0);
414 const u32 lid = get_local_id (0);
415 const u32 lsz = get_local_size (0);
421 const u32 salt_buf0 = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
422 const u32 salt_buf1 = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
423 const u32 salt_buf2 = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]); // 0x80
426 * precompute final msg blocks
429 __local u32 w_s1[64];
430 __local u32 w_s2[64];
432 for (u32 i = lid; i < 64; i += lsz)
438 barrier (CLK_LOCAL_MEM_FENCE);
442 w_s1[15] = 0 | salt_buf0 >> 16;
447 for (int i = 16; i < 64; i++)
449 w_s1[i] = SHA256_EXPAND_S (w_s1[i - 2], w_s1[i - 7], w_s1[i - 15], w_s1[i - 16]);
452 w_s2[ 0] = salt_buf0 << 16 | salt_buf1 >> 16;
453 w_s2[ 1] = salt_buf1 << 16 | salt_buf2 >> 16;
454 w_s2[ 2] = salt_buf2 << 16 | 0;
455 w_s2[15] = (510 + 8) * 8;
460 for (int i = 16; i < 64; i++)
462 w_s2[i] = SHA256_EXPAND_S (w_s2[i - 2], w_s2[i - 7], w_s2[i - 15], w_s2[i - 16]);
466 barrier (CLK_LOCAL_MEM_FENCE);
468 if (gid >= gid_max) return;
477 pw_buf0[0] = pws[gid].i[ 0];
478 pw_buf0[1] = pws[gid].i[ 1];
479 pw_buf0[2] = pws[gid].i[ 2];
480 pw_buf0[3] = pws[gid].i[ 3];
481 pw_buf1[0] = pws[gid].i[ 4];
482 pw_buf1[1] = pws[gid].i[ 5];
483 pw_buf1[2] = pws[gid].i[ 6];
484 pw_buf1[3] = pws[gid].i[ 7];
486 const u32 pw_len = pws[gid].pw_len;
492 const u32 search[4] =
494 digests_buf[digests_offset].digest_buf[DGST_R0],
495 digests_buf[digests_offset].digest_buf[DGST_R1],
496 digests_buf[digests_offset].digest_buf[DGST_R2],
497 digests_buf[digests_offset].digest_buf[DGST_R3]
504 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
511 apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
518 make_unicode (w0, w0_t, w1_t);
519 make_unicode (w1, w2_t, w3_t);
523 w_t[ 0] = swap32 (w0_t[0]);
524 w_t[ 1] = swap32 (w0_t[1]);
525 w_t[ 2] = swap32 (w0_t[2]);
526 w_t[ 3] = swap32 (w0_t[3]);
527 w_t[ 4] = swap32 (w1_t[0]);
528 w_t[ 5] = swap32 (w1_t[1]);
529 w_t[ 6] = swap32 (w1_t[2]);
530 w_t[ 7] = swap32 (w1_t[3]);
531 w_t[ 8] = swap32 (w2_t[0]);
532 w_t[ 9] = swap32 (w2_t[1]);
533 w_t[10] = swap32 (w2_t[2]);
534 w_t[11] = swap32 (w2_t[3]);
535 w_t[12] = swap32 (w3_t[0]);
536 w_t[13] = swap32 (w3_t[1]);
537 w_t[14] = swap32 (w3_t[2]);
538 w_t[15] = swap32 (w3_t[3]);
540 w_t[ 0] = w_t[ 0] >> 8;
541 w_t[ 1] = w_t[ 1] >> 8;
542 w_t[ 2] = w_t[ 2] >> 8;
543 w_t[ 3] = w_t[ 3] >> 8;
544 w_t[ 4] = w_t[ 4] >> 8;
545 w_t[ 5] = w_t[ 5] >> 8;
546 w_t[ 6] = w_t[ 6] >> 8;
547 w_t[ 7] = w_t[ 7] >> 8;
548 w_t[ 8] = w_t[ 8] >> 8;
549 w_t[ 9] = w_t[ 9] >> 8;
550 w_t[10] = w_t[10] >> 8;
551 w_t[11] = w_t[11] >> 8;
552 w_t[12] = w_t[12] >> 8;
553 w_t[13] = w_t[13] >> 8;
554 w_t[14] = w_t[14] >> 8;
555 w_t[15] = w_t[15] >> 8;
559 digest[0] = SHA256M_A;
560 digest[1] = SHA256M_B;
561 digest[2] = SHA256M_C;
562 digest[3] = SHA256M_D;
563 digest[4] = SHA256M_E;
564 digest[5] = SHA256M_F;
565 digest[6] = SHA256M_G;
566 digest[7] = SHA256M_H;
568 sha256_transform (digest, w_t); // 0 - 64
569 sha256_transform_z (digest); // 64 - 128
570 sha256_transform_z (digest); // 128 - 192
571 sha256_transform_z (digest); // 192 - 256
572 sha256_transform_z (digest); // 256 - 320
573 sha256_transform_z (digest); // 320 - 384
574 sha256_transform_z (digest); // 384 - 448
575 sha256_transform_s (digest, w_s1); // 448 - 512
576 sha256_transform_s (digest, w_s2); // 512 - 576
578 COMPARE_S_SIMD (digest[3], digest[7], digest[2], digest[6]);
582 __kernel void m08000_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_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)
586 __kernel void m08000_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_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)