2 * Author......: Jens Steube <jens.steube@gmail.com>
10 #include "inc_vendor.cl"
11 #include "inc_hash_constants.h"
12 #include "inc_hash_functions.cl"
13 #include "inc_types.cl"
14 #include "inc_common.cl"
17 #include "inc_simd.cl"
19 __constant u64 k_sha512[80] =
21 SHA512C00, SHA512C01, SHA512C02, SHA512C03,
22 SHA512C04, SHA512C05, SHA512C06, SHA512C07,
23 SHA512C08, SHA512C09, SHA512C0a, SHA512C0b,
24 SHA512C0c, SHA512C0d, SHA512C0e, SHA512C0f,
25 SHA512C10, SHA512C11, SHA512C12, SHA512C13,
26 SHA512C14, SHA512C15, SHA512C16, SHA512C17,
27 SHA512C18, SHA512C19, SHA512C1a, SHA512C1b,
28 SHA512C1c, SHA512C1d, SHA512C1e, SHA512C1f,
29 SHA512C20, SHA512C21, SHA512C22, SHA512C23,
30 SHA512C24, SHA512C25, SHA512C26, SHA512C27,
31 SHA512C28, SHA512C29, SHA512C2a, SHA512C2b,
32 SHA512C2c, SHA512C2d, SHA512C2e, SHA512C2f,
33 SHA512C30, SHA512C31, SHA512C32, SHA512C33,
34 SHA512C34, SHA512C35, SHA512C36, SHA512C37,
35 SHA512C38, SHA512C39, SHA512C3a, SHA512C3b,
36 SHA512C3c, SHA512C3d, SHA512C3e, SHA512C3f,
37 SHA512C40, SHA512C41, SHA512C42, SHA512C43,
38 SHA512C44, SHA512C45, SHA512C46, SHA512C47,
39 SHA512C48, SHA512C49, SHA512C4a, SHA512C4b,
40 SHA512C4c, SHA512C4d, SHA512C4e, SHA512C4f,
43 void sha512_transform (const u64x w0[4], const u64x w1[4], const u64x w2[4], const u64x w3[4], u64x digest[8])
71 #define ROUND_EXPAND() \
73 w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
74 w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
75 w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
76 w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
77 w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
78 w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
79 w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
80 w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
81 w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
82 w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
83 wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
84 wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
85 wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
86 wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
87 we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
88 wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
91 #define ROUND_STEP(i) \
93 SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
94 SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
95 SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
96 SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
97 SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
98 SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
99 SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
100 SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
101 SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
102 SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
103 SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
104 SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
105 SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
106 SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
107 SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
108 SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
116 for (int i = 16; i < 80; i += 16)
118 ROUND_EXPAND (); ROUND_STEP (i);
131 void hmac_sha512_pad (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u64x ipad[8], u64x opad[8])
138 w0_t[0] = hl32_to_64 (w0[0], w0[1]) ^ (u64x) 0x3636363636363636;
139 w0_t[1] = hl32_to_64 (w0[2], w0[3]) ^ (u64x) 0x3636363636363636;
140 w0_t[2] = hl32_to_64 (w1[0], w1[1]) ^ (u64x) 0x3636363636363636;
141 w0_t[3] = hl32_to_64 (w1[2], w1[3]) ^ (u64x) 0x3636363636363636;
142 w1_t[0] = hl32_to_64 (w2[0], w2[1]) ^ (u64x) 0x3636363636363636;
143 w1_t[1] = hl32_to_64 (w2[2], w2[3]) ^ (u64x) 0x3636363636363636;
144 w1_t[2] = hl32_to_64 (w3[0], w3[1]) ^ (u64x) 0x3636363636363636;
145 w1_t[3] = hl32_to_64 (w3[2], w3[3]) ^ (u64x) 0x3636363636363636;
146 w2_t[0] = (u64x) 0x3636363636363636;
147 w2_t[1] = (u64x) 0x3636363636363636;
148 w2_t[2] = (u64x) 0x3636363636363636;
149 w2_t[3] = (u64x) 0x3636363636363636;
150 w3_t[0] = (u64x) 0x3636363636363636;
151 w3_t[1] = (u64x) 0x3636363636363636;
152 w3_t[2] = (u64x) 0x3636363636363636;
153 w3_t[3] = (u64x) 0x3636363636363636;
164 sha512_transform (w0_t, w1_t, w2_t, w3_t, ipad);
166 w0_t[0] = hl32_to_64 (w0[0], w0[1]) ^ (u64x) 0x5c5c5c5c5c5c5c5c;
167 w0_t[1] = hl32_to_64 (w0[2], w0[3]) ^ (u64x) 0x5c5c5c5c5c5c5c5c;
168 w0_t[2] = hl32_to_64 (w1[0], w1[1]) ^ (u64x) 0x5c5c5c5c5c5c5c5c;
169 w0_t[3] = hl32_to_64 (w1[2], w1[3]) ^ (u64x) 0x5c5c5c5c5c5c5c5c;
170 w1_t[0] = hl32_to_64 (w2[0], w2[1]) ^ (u64x) 0x5c5c5c5c5c5c5c5c;
171 w1_t[1] = hl32_to_64 (w2[2], w2[3]) ^ (u64x) 0x5c5c5c5c5c5c5c5c;
172 w1_t[2] = hl32_to_64 (w3[0], w3[1]) ^ (u64x) 0x5c5c5c5c5c5c5c5c;
173 w1_t[3] = hl32_to_64 (w3[2], w3[3]) ^ (u64x) 0x5c5c5c5c5c5c5c5c;
174 w2_t[0] = (u64x) 0x5c5c5c5c5c5c5c5c;
175 w2_t[1] = (u64x) 0x5c5c5c5c5c5c5c5c;
176 w2_t[2] = (u64x) 0x5c5c5c5c5c5c5c5c;
177 w2_t[3] = (u64x) 0x5c5c5c5c5c5c5c5c;
178 w3_t[0] = (u64x) 0x5c5c5c5c5c5c5c5c;
179 w3_t[1] = (u64x) 0x5c5c5c5c5c5c5c5c;
180 w3_t[2] = (u64x) 0x5c5c5c5c5c5c5c5c;
181 w3_t[3] = (u64x) 0x5c5c5c5c5c5c5c5c;
192 sha512_transform (w0_t, w1_t, w2_t, w3_t, opad);
195 void hmac_sha512_run (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u64x ipad[8], u64x opad[8], u64x digest[8])
202 w0_t[0] = hl32_to_64 (w0[0], w0[1]);
203 w0_t[1] = hl32_to_64 (w0[2], w0[3]);
204 w0_t[2] = hl32_to_64 (w1[0], w1[1]);
205 w0_t[3] = hl32_to_64 (w1[2], w1[3]);
206 w1_t[0] = hl32_to_64 (w2[0], w2[1]);
207 w1_t[1] = hl32_to_64 (w2[2], w2[3]);
208 w1_t[2] = hl32_to_64 (w3[0], w3[1]);
217 w3_t[3] = hl32_to_64 (w3[2], w3[3]);
228 sha512_transform (w0_t, w1_t, w2_t, w3_t, digest);
238 w2_t[0] = 0x8000000000000000;
245 w3_t[3] = (128 + 64) * 8;
256 sha512_transform (w0_t, w1_t, w2_t, w3_t, digest);
259 __kernel void m01760_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)
265 const u32 lid = get_local_id (0);
271 const u32 gid = get_global_id (0);
273 if (gid >= gid_max) return;
278 pw_buf0[0] = pws[gid].i[0];
279 pw_buf0[1] = pws[gid].i[1];
280 pw_buf0[2] = pws[gid].i[2];
281 pw_buf0[3] = pws[gid].i[3];
282 pw_buf1[0] = pws[gid].i[4];
283 pw_buf1[1] = pws[gid].i[5];
284 pw_buf1[2] = pws[gid].i[6];
285 pw_buf1[3] = pws[gid].i[7];
287 const u32 pw_len = pws[gid].pw_len;
298 salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
299 salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
300 salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
301 salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
302 salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
303 salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
304 salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
305 salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
306 salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
307 salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
308 salt_buf2[2] = swap32_S (salt_bufs[salt_pos].salt_buf[10]);
309 salt_buf2[3] = swap32_S (salt_bufs[salt_pos].salt_buf[11]);
310 salt_buf3[0] = swap32_S (salt_bufs[salt_pos].salt_buf[12]);
311 salt_buf3[1] = swap32_S (salt_bufs[salt_pos].salt_buf[13]);
312 salt_buf3[2] = swap32_S (salt_bufs[salt_pos].salt_buf[14]);
313 salt_buf3[3] = swap32_S (salt_bufs[salt_pos].salt_buf[15]);
315 const u32 salt_len = salt_bufs[salt_pos].salt_len;
326 w0_t[0] = salt_buf0[0];
327 w0_t[1] = salt_buf0[1];
328 w0_t[2] = salt_buf0[2];
329 w0_t[3] = salt_buf0[3];
330 w1_t[0] = salt_buf1[0];
331 w1_t[1] = salt_buf1[1];
332 w1_t[2] = salt_buf1[2];
333 w1_t[3] = salt_buf1[3];
334 w2_t[0] = salt_buf2[0];
335 w2_t[1] = salt_buf2[1];
336 w2_t[2] = salt_buf2[2];
337 w2_t[3] = salt_buf2[3];
338 w3_t[0] = salt_buf3[0];
339 w3_t[1] = salt_buf3[1];
340 w3_t[2] = salt_buf3[2];
341 w3_t[3] = salt_buf3[3];
346 hmac_sha512_pad (w0_t, w1_t, w2_t, w3_t, ipad, opad);
352 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
359 const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
361 append_0x80_2x4_VV (w0, w1, out_len);
363 w0_t[0] = swap32 (w0[0]);
364 w0_t[1] = swap32 (w0[1]);
365 w0_t[2] = swap32 (w0[2]);
366 w0_t[3] = swap32 (w0[3]);
367 w1_t[0] = swap32 (w1[0]);
368 w1_t[1] = swap32 (w1[1]);
369 w1_t[2] = swap32 (w1[2]);
370 w1_t[3] = swap32 (w1[3]);
378 w3_t[3] = (128 + out_len) * 8;
382 hmac_sha512_run (w0_t, w1_t, w2_t, w3_t, ipad, opad, digest);
384 const u32x r0 = l32_from_64 (digest[7]);
385 const u32x r1 = h32_from_64 (digest[7]);
386 const u32x r2 = l32_from_64 (digest[3]);
387 const u32x r3 = h32_from_64 (digest[3]);
389 COMPARE_M_SIMD (r0, r1, r2, r3);
393 __kernel void m01760_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)
397 __kernel void m01760_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)
401 __kernel void m01760_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)
407 const u32 lid = get_local_id (0);
413 const u32 gid = get_global_id (0);
415 if (gid >= gid_max) return;
420 pw_buf0[0] = pws[gid].i[0];
421 pw_buf0[1] = pws[gid].i[1];
422 pw_buf0[2] = pws[gid].i[2];
423 pw_buf0[3] = pws[gid].i[3];
424 pw_buf1[0] = pws[gid].i[4];
425 pw_buf1[1] = pws[gid].i[5];
426 pw_buf1[2] = pws[gid].i[6];
427 pw_buf1[3] = pws[gid].i[7];
429 const u32 pw_len = pws[gid].pw_len;
440 salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
441 salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
442 salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
443 salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
444 salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
445 salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
446 salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
447 salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
448 salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
449 salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
450 salt_buf2[2] = swap32_S (salt_bufs[salt_pos].salt_buf[10]);
451 salt_buf2[3] = swap32_S (salt_bufs[salt_pos].salt_buf[11]);
452 salt_buf3[0] = swap32_S (salt_bufs[salt_pos].salt_buf[12]);
453 salt_buf3[1] = swap32_S (salt_bufs[salt_pos].salt_buf[13]);
454 salt_buf3[2] = swap32_S (salt_bufs[salt_pos].salt_buf[14]);
455 salt_buf3[3] = swap32_S (salt_bufs[salt_pos].salt_buf[15]);
457 const u32 salt_len = salt_bufs[salt_pos].salt_len;
468 w0_t[0] = salt_buf0[0];
469 w0_t[1] = salt_buf0[1];
470 w0_t[2] = salt_buf0[2];
471 w0_t[3] = salt_buf0[3];
472 w1_t[0] = salt_buf1[0];
473 w1_t[1] = salt_buf1[1];
474 w1_t[2] = salt_buf1[2];
475 w1_t[3] = salt_buf1[3];
476 w2_t[0] = salt_buf2[0];
477 w2_t[1] = salt_buf2[1];
478 w2_t[2] = salt_buf2[2];
479 w2_t[3] = salt_buf2[3];
480 w3_t[0] = salt_buf3[0];
481 w3_t[1] = salt_buf3[1];
482 w3_t[2] = salt_buf3[2];
483 w3_t[3] = salt_buf3[3];
488 hmac_sha512_pad (w0_t, w1_t, w2_t, w3_t, ipad, opad);
494 const u32 search[4] =
496 digests_buf[digests_offset].digest_buf[DGST_R0],
497 digests_buf[digests_offset].digest_buf[DGST_R1],
498 digests_buf[digests_offset].digest_buf[DGST_R2],
499 digests_buf[digests_offset].digest_buf[DGST_R3]
506 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
513 const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
515 append_0x80_2x4_VV (w0, w1, out_len);
517 w0_t[0] = swap32 (w0[0]);
518 w0_t[1] = swap32 (w0[1]);
519 w0_t[2] = swap32 (w0[2]);
520 w0_t[3] = swap32 (w0[3]);
521 w1_t[0] = swap32 (w1[0]);
522 w1_t[1] = swap32 (w1[1]);
523 w1_t[2] = swap32 (w1[2]);
524 w1_t[3] = swap32 (w1[3]);
532 w3_t[3] = (128 + out_len) * 8;
536 hmac_sha512_run (w0_t, w1_t, w2_t, w3_t, ipad, opad, digest);
538 const u32x r0 = l32_from_64 (digest[7]);
539 const u32x r1 = h32_from_64 (digest[7]);
540 const u32x r2 = l32_from_64 (digest[3]);
541 const u32x r3 = h32_from_64 (digest[3]);
543 COMPARE_S_SIMD (r0, r1, r2, r3);
547 __kernel void m01760_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)
551 __kernel void m01760_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)