2 * Author......: Jens Steube <jens.steube@gmail.com>
10 #include "include/constants.h"
11 #include "include/kernel_vendor.h"
18 #include "include/kernel_functions.c"
19 #include "OpenCL/types_ocl.c"
20 #include "OpenCL/common.c"
21 #include "OpenCL/simd.c"
23 __constant u64 k_sha512[80] =
25 SHA512C00, SHA512C01, SHA512C02, SHA512C03,
26 SHA512C04, SHA512C05, SHA512C06, SHA512C07,
27 SHA512C08, SHA512C09, SHA512C0a, SHA512C0b,
28 SHA512C0c, SHA512C0d, SHA512C0e, SHA512C0f,
29 SHA512C10, SHA512C11, SHA512C12, SHA512C13,
30 SHA512C14, SHA512C15, SHA512C16, SHA512C17,
31 SHA512C18, SHA512C19, SHA512C1a, SHA512C1b,
32 SHA512C1c, SHA512C1d, SHA512C1e, SHA512C1f,
33 SHA512C20, SHA512C21, SHA512C22, SHA512C23,
34 SHA512C24, SHA512C25, SHA512C26, SHA512C27,
35 SHA512C28, SHA512C29, SHA512C2a, SHA512C2b,
36 SHA512C2c, SHA512C2d, SHA512C2e, SHA512C2f,
37 SHA512C30, SHA512C31, SHA512C32, SHA512C33,
38 SHA512C34, SHA512C35, SHA512C36, SHA512C37,
39 SHA512C38, SHA512C39, SHA512C3a, SHA512C3b,
40 SHA512C3c, SHA512C3d, SHA512C3e, SHA512C3f,
41 SHA512C40, SHA512C41, SHA512C42, SHA512C43,
42 SHA512C44, SHA512C45, SHA512C46, SHA512C47,
43 SHA512C48, SHA512C49, SHA512C4a, SHA512C4b,
44 SHA512C4c, SHA512C4d, SHA512C4e, SHA512C4f,
47 void sha512_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u64x digest[8])
49 u64x w0_t = hl32_to_64 (w0[0], w0[1]);
50 u64x w1_t = hl32_to_64 (w0[2], w0[3]);
51 u64x w2_t = hl32_to_64 (w1[0], w1[1]);
52 u64x w3_t = hl32_to_64 (w1[2], w1[3]);
53 u64x w4_t = hl32_to_64 (w2[0], w2[1]);
54 u64x w5_t = hl32_to_64 (w2[2], w2[3]);
55 u64x w6_t = hl32_to_64 (w3[0], w3[1]);
64 u64x wf_t = hl32_to_64 (w3[2], w3[3]);
75 #define ROUND_EXPAND() \
77 w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
78 w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
79 w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
80 w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
81 w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
82 w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
83 w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
84 w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
85 w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
86 w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
87 wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
88 wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
89 wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
90 wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
91 we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
92 wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
95 #define ROUND_STEP(i) \
97 SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
98 SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
99 SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
100 SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
101 SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
102 SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
103 SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
104 SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
105 SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
106 SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
107 SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
108 SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
109 SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
110 SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
111 SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
112 SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
118 for (int i = 16; i < 80; i += 16)
120 ROUND_EXPAND (); ROUND_STEP (i);
144 __kernel void m01710_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)
150 const u32 lid = get_local_id (0);
156 const u32 gid = get_global_id (0);
158 if (gid >= gid_max) return;
163 pw_buf0[0] = pws[gid].i[0];
164 pw_buf0[1] = pws[gid].i[1];
165 pw_buf0[2] = pws[gid].i[2];
166 pw_buf0[3] = pws[gid].i[3];
167 pw_buf1[0] = pws[gid].i[4];
168 pw_buf1[1] = pws[gid].i[5];
169 pw_buf1[2] = pws[gid].i[6];
170 pw_buf1[3] = pws[gid].i[7];
172 const u32 pw_l_len = pws[gid].pw_len;
183 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
184 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
185 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
186 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
187 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
188 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
189 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
190 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
191 salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
192 salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
193 salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
194 salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
195 salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
196 salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
197 salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
198 salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
200 const u32 salt_len = salt_bufs[salt_pos].salt_len;
206 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
208 const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
210 const u32x pw_len = pw_l_len + pw_r_len;
213 * concat password candidate
216 u32x wordl0[4] = { 0 };
217 u32x wordl1[4] = { 0 };
218 u32x wordl2[4] = { 0 };
219 u32x wordl3[4] = { 0 };
221 wordl0[0] = pw_buf0[0];
222 wordl0[1] = pw_buf0[1];
223 wordl0[2] = pw_buf0[2];
224 wordl0[3] = pw_buf0[3];
225 wordl1[0] = pw_buf1[0];
226 wordl1[1] = pw_buf1[1];
227 wordl1[2] = pw_buf1[2];
228 wordl1[3] = pw_buf1[3];
230 u32x wordr0[4] = { 0 };
231 u32x wordr1[4] = { 0 };
232 u32x wordr2[4] = { 0 };
233 u32x wordr3[4] = { 0 };
235 wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
236 wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
237 wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
238 wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
239 wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
240 wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
241 wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
242 wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
244 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
246 switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
250 switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
258 w0[0] = wordl0[0] | wordr0[0];
259 w0[1] = wordl0[1] | wordr0[1];
260 w0[2] = wordl0[2] | wordr0[2];
261 w0[3] = wordl0[3] | wordr0[3];
262 w1[0] = wordl1[0] | wordr1[0];
263 w1[1] = wordl1[1] | wordr1[1];
264 w1[2] = wordl1[2] | wordr1[2];
265 w1[3] = wordl1[3] | wordr1[3];
266 w2[0] = wordl2[0] | wordr2[0];
267 w2[1] = wordl2[1] | wordr2[1];
268 w2[2] = wordl2[2] | wordr2[2];
269 w2[3] = wordl2[3] | wordr2[3];
270 w3[0] = wordl3[0] | wordr3[0];
271 w3[1] = wordl3[1] | wordr3[1];
272 w3[2] = wordl3[2] | wordr3[2];
273 w3[3] = wordl3[3] | wordr3[3];
284 s0[0] = salt_buf0[0];
285 s0[1] = salt_buf0[1];
286 s0[2] = salt_buf0[2];
287 s0[3] = salt_buf0[3];
288 s1[0] = salt_buf1[0];
289 s1[1] = salt_buf1[1];
290 s1[2] = salt_buf1[2];
291 s1[3] = salt_buf1[3];
292 s2[0] = salt_buf2[0];
293 s2[1] = salt_buf2[1];
294 s2[2] = salt_buf2[2];
295 s2[3] = salt_buf2[3];
296 s3[0] = salt_buf3[0];
297 s3[1] = salt_buf3[1];
298 s3[2] = salt_buf3[2];
299 s3[3] = salt_buf3[3];
301 switch_buffer_by_offset_le_VV (s0, s1, s2, s3, pw_len);
303 const u32x pw_salt_len = pw_len + salt_len;
331 w0_t[0] = swap32 (w0[0]);
332 w0_t[1] = swap32 (w0[1]);
333 w0_t[2] = swap32 (w0[2]);
334 w0_t[3] = swap32 (w0[3]);
335 w1_t[0] = swap32 (w1[0]);
336 w1_t[1] = swap32 (w1[1]);
337 w1_t[2] = swap32 (w1[2]);
338 w1_t[3] = swap32 (w1[3]);
339 w2_t[0] = swap32 (w2[0]);
340 w2_t[1] = swap32 (w2[1]);
341 w2_t[2] = swap32 (w2[2]);
342 w2_t[3] = swap32 (w2[3]);
343 w3_t[0] = swap32 (w3[0]);
344 w3_t[1] = swap32 (w3[1]);
346 w3_t[3] = pw_salt_len * 8;
350 digest[0] = SHA512M_A;
351 digest[1] = SHA512M_B;
352 digest[2] = SHA512M_C;
353 digest[3] = SHA512M_D;
354 digest[4] = SHA512M_E;
355 digest[5] = SHA512M_F;
356 digest[6] = SHA512M_G;
357 digest[7] = SHA512M_H;
359 sha512_transform (w0_t, w1_t, w2_t, w3_t, digest);
361 const u32x r0 = l32_from_64 (digest[7]);
362 const u32x r1 = h32_from_64 (digest[7]);
363 const u32x r2 = l32_from_64 (digest[3]);
364 const u32x r3 = h32_from_64 (digest[3]);
366 COMPARE_M_SIMD (r0, r1, r2, r3);
370 __kernel void m01710_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)
374 __kernel void m01710_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)
378 __kernel void m01710_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)
384 const u32 lid = get_local_id (0);
390 const u32 gid = get_global_id (0);
392 if (gid >= gid_max) return;
397 pw_buf0[0] = pws[gid].i[0];
398 pw_buf0[1] = pws[gid].i[1];
399 pw_buf0[2] = pws[gid].i[2];
400 pw_buf0[3] = pws[gid].i[3];
401 pw_buf1[0] = pws[gid].i[4];
402 pw_buf1[1] = pws[gid].i[5];
403 pw_buf1[2] = pws[gid].i[6];
404 pw_buf1[3] = pws[gid].i[7];
406 const u32 pw_l_len = pws[gid].pw_len;
417 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
418 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
419 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
420 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
421 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
422 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
423 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
424 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
425 salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
426 salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
427 salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
428 salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
429 salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
430 salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
431 salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
432 salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
434 const u32 salt_len = salt_bufs[salt_pos].salt_len;
440 const u32 search[4] =
442 digests_buf[digests_offset].digest_buf[DGST_R0],
443 digests_buf[digests_offset].digest_buf[DGST_R1],
444 digests_buf[digests_offset].digest_buf[DGST_R2],
445 digests_buf[digests_offset].digest_buf[DGST_R3]
452 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
454 const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
456 const u32x pw_len = pw_l_len + pw_r_len;
459 * concat password candidate
462 u32x wordl0[4] = { 0 };
463 u32x wordl1[4] = { 0 };
464 u32x wordl2[4] = { 0 };
465 u32x wordl3[4] = { 0 };
467 wordl0[0] = pw_buf0[0];
468 wordl0[1] = pw_buf0[1];
469 wordl0[2] = pw_buf0[2];
470 wordl0[3] = pw_buf0[3];
471 wordl1[0] = pw_buf1[0];
472 wordl1[1] = pw_buf1[1];
473 wordl1[2] = pw_buf1[2];
474 wordl1[3] = pw_buf1[3];
476 u32x wordr0[4] = { 0 };
477 u32x wordr1[4] = { 0 };
478 u32x wordr2[4] = { 0 };
479 u32x wordr3[4] = { 0 };
481 wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
482 wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
483 wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
484 wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
485 wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
486 wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
487 wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
488 wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
490 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
492 switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
496 switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
504 w0[0] = wordl0[0] | wordr0[0];
505 w0[1] = wordl0[1] | wordr0[1];
506 w0[2] = wordl0[2] | wordr0[2];
507 w0[3] = wordl0[3] | wordr0[3];
508 w1[0] = wordl1[0] | wordr1[0];
509 w1[1] = wordl1[1] | wordr1[1];
510 w1[2] = wordl1[2] | wordr1[2];
511 w1[3] = wordl1[3] | wordr1[3];
512 w2[0] = wordl2[0] | wordr2[0];
513 w2[1] = wordl2[1] | wordr2[1];
514 w2[2] = wordl2[2] | wordr2[2];
515 w2[3] = wordl2[3] | wordr2[3];
516 w3[0] = wordl3[0] | wordr3[0];
517 w3[1] = wordl3[1] | wordr3[1];
518 w3[2] = wordl3[2] | wordr3[2];
519 w3[3] = wordl3[3] | wordr3[3];
530 s0[0] = salt_buf0[0];
531 s0[1] = salt_buf0[1];
532 s0[2] = salt_buf0[2];
533 s0[3] = salt_buf0[3];
534 s1[0] = salt_buf1[0];
535 s1[1] = salt_buf1[1];
536 s1[2] = salt_buf1[2];
537 s1[3] = salt_buf1[3];
538 s2[0] = salt_buf2[0];
539 s2[1] = salt_buf2[1];
540 s2[2] = salt_buf2[2];
541 s2[3] = salt_buf2[3];
542 s3[0] = salt_buf3[0];
543 s3[1] = salt_buf3[1];
544 s3[2] = salt_buf3[2];
545 s3[3] = salt_buf3[3];
547 switch_buffer_by_offset_le_VV (s0, s1, s2, s3, pw_len);
549 const u32x pw_salt_len = pw_len + salt_len;
577 w0_t[0] = swap32 (w0[0]);
578 w0_t[1] = swap32 (w0[1]);
579 w0_t[2] = swap32 (w0[2]);
580 w0_t[3] = swap32 (w0[3]);
581 w1_t[0] = swap32 (w1[0]);
582 w1_t[1] = swap32 (w1[1]);
583 w1_t[2] = swap32 (w1[2]);
584 w1_t[3] = swap32 (w1[3]);
585 w2_t[0] = swap32 (w2[0]);
586 w2_t[1] = swap32 (w2[1]);
587 w2_t[2] = swap32 (w2[2]);
588 w2_t[3] = swap32 (w2[3]);
589 w3_t[0] = swap32 (w3[0]);
590 w3_t[1] = swap32 (w3[1]);
592 w3_t[3] = pw_salt_len * 8;
596 digest[0] = SHA512M_A;
597 digest[1] = SHA512M_B;
598 digest[2] = SHA512M_C;
599 digest[3] = SHA512M_D;
600 digest[4] = SHA512M_E;
601 digest[5] = SHA512M_F;
602 digest[6] = SHA512M_G;
603 digest[7] = SHA512M_H;
605 sha512_transform (w0_t, w1_t, w2_t, w3_t, digest);
607 const u32x r0 = l32_from_64 (digest[7]);
608 const u32x r1 = h32_from_64 (digest[7]);
609 const u32x r2 = l32_from_64 (digest[3]);
610 const u32x r3 = h32_from_64 (digest[3]);
612 COMPARE_S_SIMD (r0, r1, r2, r3);
616 __kernel void m01710_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)
620 __kernel void m01710_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)