2 * Author......: Jens Steube <jens.steube@gmail.com>
8 #include "include/constants.h"
9 #include "include/kernel_vendor.h"
28 #include "include/kernel_functions.c"
29 #include "types_amd.c"
30 #include "common_amd.c"
33 #define VECT_COMPARE_S "check_single_vect1_comp4.c"
34 #define VECT_COMPARE_M "check_multi_vect1_comp4.c"
38 #define VECT_COMPARE_S "check_single_vect2_comp4.c"
39 #define VECT_COMPARE_M "check_multi_vect2_comp4.c"
43 #define VECT_COMPARE_S "check_single_vect4_comp4.c"
44 #define VECT_COMPARE_M "check_multi_vect4_comp4.c"
47 __constant u64 k_sha512[80] =
49 SHA512C00, SHA512C01, SHA512C02, SHA512C03,
50 SHA512C04, SHA512C05, SHA512C06, SHA512C07,
51 SHA512C08, SHA512C09, SHA512C0a, SHA512C0b,
52 SHA512C0c, SHA512C0d, SHA512C0e, SHA512C0f,
53 SHA512C10, SHA512C11, SHA512C12, SHA512C13,
54 SHA512C14, SHA512C15, SHA512C16, SHA512C17,
55 SHA512C18, SHA512C19, SHA512C1a, SHA512C1b,
56 SHA512C1c, SHA512C1d, SHA512C1e, SHA512C1f,
57 SHA512C20, SHA512C21, SHA512C22, SHA512C23,
58 SHA512C24, SHA512C25, SHA512C26, SHA512C27,
59 SHA512C28, SHA512C29, SHA512C2a, SHA512C2b,
60 SHA512C2c, SHA512C2d, SHA512C2e, SHA512C2f,
61 SHA512C30, SHA512C31, SHA512C32, SHA512C33,
62 SHA512C34, SHA512C35, SHA512C36, SHA512C37,
63 SHA512C38, SHA512C39, SHA512C3a, SHA512C3b,
64 SHA512C3c, SHA512C3d, SHA512C3e, SHA512C3f,
65 SHA512C40, SHA512C41, SHA512C42, SHA512C43,
66 SHA512C44, SHA512C45, SHA512C46, SHA512C47,
67 SHA512C48, SHA512C49, SHA512C4a, SHA512C4b,
68 SHA512C4c, SHA512C4d, SHA512C4e, SHA512C4f,
71 static void sha512_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u64x digest[8])
73 u64x w0_t = hl32_to_64 (w0[0], w0[1]);
74 u64x w1_t = hl32_to_64 (w0[2], w0[3]);
75 u64x w2_t = hl32_to_64 (w1[0], w1[1]);
76 u64x w3_t = hl32_to_64 (w1[2], w1[3]);
77 u64x w4_t = hl32_to_64 (w2[0], w2[1]);
78 u64x w5_t = hl32_to_64 (w2[2], w2[3]);
79 u64x w6_t = hl32_to_64 (w3[0], w3[1]);
88 u64x wf_t = hl32_to_64 (w3[2], w3[3]);
99 #define ROUND_EXPAND() \
101 w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
102 w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
103 w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
104 w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
105 w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
106 w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
107 w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
108 w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
109 w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
110 w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
111 wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
112 wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
113 wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
114 wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
115 we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
116 wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
119 #define ROUND_STEP(i) \
121 SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
122 SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
123 SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
124 SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
125 SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
126 SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
127 SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
128 SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
129 SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
130 SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
131 SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
132 SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
133 SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
134 SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
135 SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
136 SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
142 for (int i = 16; i < 80; i += 16)
144 ROUND_EXPAND (); ROUND_STEP (i);
168 static void m01720m (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], const u32 pw_len, __global pw_t *pws, __global gpu_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset)
174 const u32 gid = get_global_id (0);
175 const u32 lid = get_local_id (0);
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];
190 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
191 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
192 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
193 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
209 const u32 salt_len = salt_bufs[salt_pos].salt_len;
211 const u32 pw_salt_len = pw_len + salt_len;
219 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
221 const u32 w0r = bfs_buf[il_pos].i;
234 w0_t[0] = swap_workaround (w0[0]);
235 w0_t[1] = swap_workaround (w0[1]);
236 w0_t[2] = swap_workaround (w0[2]);
237 w0_t[3] = swap_workaround (w0[3]);
238 w1_t[0] = swap_workaround (w1[0]);
239 w1_t[1] = swap_workaround (w1[1]);
240 w1_t[2] = swap_workaround (w1[2]);
241 w1_t[3] = swap_workaround (w1[3]);
242 w2_t[0] = swap_workaround (w2[0]);
243 w2_t[1] = swap_workaround (w2[1]);
244 w2_t[2] = swap_workaround (w2[2]);
245 w2_t[3] = swap_workaround (w2[3]);
246 w3_t[0] = swap_workaround (w3[0]);
247 w3_t[1] = swap_workaround (w3[1]);
248 w3_t[2] = swap_workaround (w3[2]);
249 w3_t[3] = swap_workaround (w3[3]);
251 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
253 w0_t[0] |= salt_buf0[0];
254 w0_t[1] |= salt_buf0[1];
255 w0_t[2] |= salt_buf0[2];
256 w0_t[3] |= salt_buf0[3];
257 w1_t[0] |= salt_buf1[0];
258 w1_t[1] |= salt_buf1[1];
259 w1_t[2] |= salt_buf1[2];
260 w1_t[3] |= salt_buf1[3];
261 w2_t[0] |= salt_buf2[0];
262 w2_t[1] |= salt_buf2[1];
263 w2_t[2] |= salt_buf2[2];
264 w2_t[3] |= salt_buf2[3];
265 w3_t[0] |= salt_buf3[0];
266 w3_t[1] |= salt_buf3[1];
268 w3_t[3] = pw_salt_len * 8;
274 w0_t[0] = swap_workaround (w0_t[0]);
275 w0_t[1] = swap_workaround (w0_t[1]);
276 w0_t[2] = swap_workaround (w0_t[2]);
277 w0_t[3] = swap_workaround (w0_t[3]);
278 w1_t[0] = swap_workaround (w1_t[0]);
279 w1_t[1] = swap_workaround (w1_t[1]);
280 w1_t[2] = swap_workaround (w1_t[2]);
281 w1_t[3] = swap_workaround (w1_t[3]);
282 w2_t[0] = swap_workaround (w2_t[0]);
283 w2_t[1] = swap_workaround (w2_t[1]);
284 w2_t[2] = swap_workaround (w2_t[2]);
285 w2_t[3] = swap_workaround (w2_t[3]);
286 w3_t[0] = swap_workaround (w3_t[0]);
287 w3_t[1] = swap_workaround (w3_t[1]);
288 //w3_t[2] = swap_workaround (w3_t[2]);
289 //w3_t[3] = swap_workaround (w3_t[3]);
293 digest[0] = SHA512M_A;
294 digest[1] = SHA512M_B;
295 digest[2] = SHA512M_C;
296 digest[3] = SHA512M_D;
297 digest[4] = SHA512M_E;
298 digest[5] = SHA512M_F;
299 digest[6] = SHA512M_G;
300 digest[7] = SHA512M_H;
302 sha512_transform (w0_t, w1_t, w2_t, w3_t, digest);
305 const u32x r0 = l32_from_64 (digest[7]);
306 const u32x r1 = h32_from_64 (digest[7]);
307 const u32x r2 = l32_from_64 (digest[3]);
308 const u32x r3 = h32_from_64 (digest[3]);
310 #include VECT_COMPARE_M
314 static void m01720s (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], const u32 pw_len, __global pw_t *pws, __global gpu_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset)
320 const u32 gid = get_global_id (0);
321 const u32 lid = get_local_id (0);
327 const u32 search[4] =
329 digests_buf[digests_offset].digest_buf[DGST_R0],
330 digests_buf[digests_offset].digest_buf[DGST_R1],
331 digests_buf[digests_offset].digest_buf[DGST_R2],
332 digests_buf[digests_offset].digest_buf[DGST_R3]
341 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
342 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
343 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
344 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
348 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
349 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
350 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
351 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
367 const u32 salt_len = salt_bufs[salt_pos].salt_len;
369 const u32 pw_salt_len = pw_len + salt_len;
377 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
379 const u32 w0r = bfs_buf[il_pos].i;
392 w0_t[0] = swap_workaround (w0[0]);
393 w0_t[1] = swap_workaround (w0[1]);
394 w0_t[2] = swap_workaround (w0[2]);
395 w0_t[3] = swap_workaround (w0[3]);
396 w1_t[0] = swap_workaround (w1[0]);
397 w1_t[1] = swap_workaround (w1[1]);
398 w1_t[2] = swap_workaround (w1[2]);
399 w1_t[3] = swap_workaround (w1[3]);
400 w2_t[0] = swap_workaround (w2[0]);
401 w2_t[1] = swap_workaround (w2[1]);
402 w2_t[2] = swap_workaround (w2[2]);
403 w2_t[3] = swap_workaround (w2[3]);
404 w3_t[0] = swap_workaround (w3[0]);
405 w3_t[1] = swap_workaround (w3[1]);
406 w3_t[2] = swap_workaround (w3[2]);
407 w3_t[3] = swap_workaround (w3[3]);
409 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
411 w0_t[0] |= salt_buf0[0];
412 w0_t[1] |= salt_buf0[1];
413 w0_t[2] |= salt_buf0[2];
414 w0_t[3] |= salt_buf0[3];
415 w1_t[0] |= salt_buf1[0];
416 w1_t[1] |= salt_buf1[1];
417 w1_t[2] |= salt_buf1[2];
418 w1_t[3] |= salt_buf1[3];
419 w2_t[0] |= salt_buf2[0];
420 w2_t[1] |= salt_buf2[1];
421 w2_t[2] |= salt_buf2[2];
422 w2_t[3] |= salt_buf2[3];
423 w3_t[0] |= salt_buf3[0];
424 w3_t[1] |= salt_buf3[1];
426 w3_t[3] = pw_salt_len * 8;
432 w0_t[0] = swap_workaround (w0_t[0]);
433 w0_t[1] = swap_workaround (w0_t[1]);
434 w0_t[2] = swap_workaround (w0_t[2]);
435 w0_t[3] = swap_workaround (w0_t[3]);
436 w1_t[0] = swap_workaround (w1_t[0]);
437 w1_t[1] = swap_workaround (w1_t[1]);
438 w1_t[2] = swap_workaround (w1_t[2]);
439 w1_t[3] = swap_workaround (w1_t[3]);
440 w2_t[0] = swap_workaround (w2_t[0]);
441 w2_t[1] = swap_workaround (w2_t[1]);
442 w2_t[2] = swap_workaround (w2_t[2]);
443 w2_t[3] = swap_workaround (w2_t[3]);
444 w3_t[0] = swap_workaround (w3_t[0]);
445 w3_t[1] = swap_workaround (w3_t[1]);
446 //w3_t[2] = swap_workaround (w3_t[2]);
447 //w3_t[3] = swap_workaround (w3_t[3]);
451 digest[0] = SHA512M_A;
452 digest[1] = SHA512M_B;
453 digest[2] = SHA512M_C;
454 digest[3] = SHA512M_D;
455 digest[4] = SHA512M_E;
456 digest[5] = SHA512M_F;
457 digest[6] = SHA512M_G;
458 digest[7] = SHA512M_H;
460 sha512_transform (w0_t, w1_t, w2_t, w3_t, digest);
463 const u32x r0 = l32_from_64 (digest[7]);
464 const u32x r1 = h32_from_64 (digest[7]);
465 const u32x r2 = l32_from_64 (digest[3]);
466 const u32x r3 = h32_from_64 (digest[3]);
468 #include VECT_COMPARE_S
472 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01720_m04 (__global pw_t *pws, __global gpu_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
478 const u32 gid = get_global_id (0);
480 if (gid >= gid_max) return;
484 w0[0] = pws[gid].i[ 0];
485 w0[1] = pws[gid].i[ 1];
486 w0[2] = pws[gid].i[ 2];
487 w0[3] = pws[gid].i[ 3];
510 const u32 pw_len = pws[gid].pw_len;
516 m01720m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
519 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01720_m08 (__global pw_t *pws, __global gpu_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
525 const u32 gid = get_global_id (0);
527 if (gid >= gid_max) return;
531 w0[0] = pws[gid].i[ 0];
532 w0[1] = pws[gid].i[ 1];
533 w0[2] = pws[gid].i[ 2];
534 w0[3] = pws[gid].i[ 3];
538 w1[0] = pws[gid].i[ 4];
539 w1[1] = pws[gid].i[ 5];
540 w1[2] = pws[gid].i[ 6];
541 w1[3] = pws[gid].i[ 7];
557 const u32 pw_len = pws[gid].pw_len;
563 m01720m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
566 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01720_m16 (__global pw_t *pws, __global gpu_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
572 const u32 gid = get_global_id (0);
574 if (gid >= gid_max) return;
578 w0[0] = pws[gid].i[ 0];
579 w0[1] = pws[gid].i[ 1];
580 w0[2] = pws[gid].i[ 2];
581 w0[3] = pws[gid].i[ 3];
585 w1[0] = pws[gid].i[ 4];
586 w1[1] = pws[gid].i[ 5];
587 w1[2] = pws[gid].i[ 6];
588 w1[3] = pws[gid].i[ 7];
592 w2[0] = pws[gid].i[ 8];
593 w2[1] = pws[gid].i[ 9];
594 w2[2] = pws[gid].i[10];
595 w2[3] = pws[gid].i[11];
599 w3[0] = pws[gid].i[12];
600 w3[1] = pws[gid].i[13];
604 const u32 pw_len = pws[gid].pw_len;
610 m01720m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
613 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01720_s04 (__global pw_t *pws, __global gpu_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
619 const u32 gid = get_global_id (0);
621 if (gid >= gid_max) return;
625 w0[0] = pws[gid].i[ 0];
626 w0[1] = pws[gid].i[ 1];
627 w0[2] = pws[gid].i[ 2];
628 w0[3] = pws[gid].i[ 3];
651 const u32 pw_len = pws[gid].pw_len;
657 m01720s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
660 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01720_s08 (__global pw_t *pws, __global gpu_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
666 const u32 gid = get_global_id (0);
668 if (gid >= gid_max) return;
672 w0[0] = pws[gid].i[ 0];
673 w0[1] = pws[gid].i[ 1];
674 w0[2] = pws[gid].i[ 2];
675 w0[3] = pws[gid].i[ 3];
679 w1[0] = pws[gid].i[ 4];
680 w1[1] = pws[gid].i[ 5];
681 w1[2] = pws[gid].i[ 6];
682 w1[3] = pws[gid].i[ 7];
698 const u32 pw_len = pws[gid].pw_len;
704 m01720s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
707 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01720_s16 (__global pw_t *pws, __global gpu_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
713 const u32 gid = get_global_id (0);
715 if (gid >= gid_max) return;
719 w0[0] = pws[gid].i[ 0];
720 w0[1] = pws[gid].i[ 1];
721 w0[2] = pws[gid].i[ 2];
722 w0[3] = pws[gid].i[ 3];
726 w1[0] = pws[gid].i[ 4];
727 w1[1] = pws[gid].i[ 5];
728 w1[2] = pws[gid].i[ 6];
729 w1[3] = pws[gid].i[ 7];
733 w2[0] = pws[gid].i[ 8];
734 w2[1] = pws[gid].i[ 9];
735 w2[2] = pws[gid].i[10];
736 w2[3] = pws[gid].i[11];
740 w3[0] = pws[gid].i[12];
741 w3[1] = pws[gid].i[13];
745 const u32 pw_len = pws[gid].pw_len;
751 m01720s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);