2 * Author......: Jens Steube <jens.steube@gmail.com>
8 #include "include/constants.h"
9 #include "include/kernel_vendor.h"
24 #include "include/kernel_functions.c"
26 #include "common_nv.c"
29 #define VECT_COMPARE_S "check_single_vect1_comp4.c"
30 #define VECT_COMPARE_M "check_multi_vect1_comp4.c"
34 #define VECT_COMPARE_S "check_single_vect2_comp4.c"
35 #define VECT_COMPARE_M "check_multi_vect2_comp4.c"
39 #define VECT_COMPARE_S "check_single_vect4_comp4.c"
40 #define VECT_COMPARE_M "check_multi_vect4_comp4.c"
43 __device__ __constant__ bf_t c_bfs[1024];
45 __device__ __constant__ u64 k_sha512[80] =
47 SHA512C00, SHA512C01, SHA512C02, SHA512C03,
48 SHA512C04, SHA512C05, SHA512C06, SHA512C07,
49 SHA512C08, SHA512C09, SHA512C0a, SHA512C0b,
50 SHA512C0c, SHA512C0d, SHA512C0e, SHA512C0f,
51 SHA512C10, SHA512C11, SHA512C12, SHA512C13,
52 SHA512C14, SHA512C15, SHA512C16, SHA512C17,
53 SHA512C18, SHA512C19, SHA512C1a, SHA512C1b,
54 SHA512C1c, SHA512C1d, SHA512C1e, SHA512C1f,
55 SHA512C20, SHA512C21, SHA512C22, SHA512C23,
56 SHA512C24, SHA512C25, SHA512C26, SHA512C27,
57 SHA512C28, SHA512C29, SHA512C2a, SHA512C2b,
58 SHA512C2c, SHA512C2d, SHA512C2e, SHA512C2f,
59 SHA512C30, SHA512C31, SHA512C32, SHA512C33,
60 SHA512C34, SHA512C35, SHA512C36, SHA512C37,
61 SHA512C38, SHA512C39, SHA512C3a, SHA512C3b,
62 SHA512C3c, SHA512C3d, SHA512C3e, SHA512C3f,
63 SHA512C40, SHA512C41, SHA512C42, SHA512C43,
64 SHA512C44, SHA512C45, SHA512C46, SHA512C47,
65 SHA512C48, SHA512C49, SHA512C4a, SHA512C4b,
66 SHA512C4c, SHA512C4d, SHA512C4e, SHA512C4f,
69 __device__ static void sha512_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u64x digest[8])
71 u64x w0_t = hl32_to_64 (w0[0], w0[1]);
72 u64x w1_t = hl32_to_64 (w0[2], w0[3]);
73 u64x w2_t = hl32_to_64 (w1[0], w1[1]);
74 u64x w3_t = hl32_to_64 (w1[2], w1[3]);
75 u64x w4_t = hl32_to_64 (w2[0], w2[1]);
76 u64x w5_t = hl32_to_64 (w2[2], w2[3]);
77 u64x w6_t = hl32_to_64 (w3[0], w3[1]);
86 u64x wf_t = hl32_to_64 (w3[2], w3[3]);
97 #define ROUND_EXPAND() \
99 w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
100 w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
101 w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
102 w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
103 w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
104 w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
105 w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
106 w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
107 w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
108 w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
109 wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
110 wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
111 wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
112 wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
113 we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
114 wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
117 #define ROUND_STEP(i) \
119 SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
120 SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
121 SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
122 SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
123 SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
124 SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
125 SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
126 SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
127 SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
128 SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
129 SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
130 SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
131 SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
132 SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
133 SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
134 SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
139 for (int i = 16; i < 80; i += 16)
141 ROUND_EXPAND (); ROUND_STEP (i);
165 __device__ static void m01740m (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], const u32 pw_len, const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
171 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
172 const u32 lid = threadIdx.x;
180 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
181 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
182 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
183 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];
206 const u32 salt_len = salt_bufs[salt_pos].salt_len;
208 const u32 pw_salt_len = pw_len + salt_len;
216 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
218 const u32 w0r = c_bfs[il_pos].i;
231 w0_t[0] = swap_workaround (w0[0]);
232 w0_t[1] = swap_workaround (w0[1]);
233 w0_t[2] = swap_workaround (w0[2]);
234 w0_t[3] = swap_workaround (w0[3]);
235 w1_t[0] = swap_workaround (w1[0]);
236 w1_t[1] = swap_workaround (w1[1]);
237 w1_t[2] = swap_workaround (w1[2]);
238 w1_t[3] = swap_workaround (w1[3]);
239 w2_t[0] = swap_workaround (w2[0]);
240 w2_t[1] = swap_workaround (w2[1]);
241 w2_t[2] = swap_workaround (w2[2]);
242 w2_t[3] = swap_workaround (w2[3]);
243 w3_t[0] = swap_workaround (w3[0]);
244 w3_t[1] = swap_workaround (w3[1]);
245 w3_t[2] = swap_workaround (w3[2]);
246 w3_t[3] = swap_workaround (w3[3]);
248 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
250 w0_t[0] |= salt_buf0[0];
251 w0_t[1] |= salt_buf0[1];
252 w0_t[2] |= salt_buf0[2];
253 w0_t[3] |= salt_buf0[3];
254 w1_t[0] |= salt_buf1[0];
255 w1_t[1] |= salt_buf1[1];
256 w1_t[2] |= salt_buf1[2];
257 w1_t[3] |= salt_buf1[3];
258 w2_t[0] |= salt_buf2[0];
259 w2_t[1] |= salt_buf2[1];
260 w2_t[2] |= salt_buf2[2];
261 w2_t[3] |= salt_buf2[3];
262 w3_t[0] |= salt_buf3[0];
263 w3_t[1] |= salt_buf3[1];
265 w3_t[3] = pw_salt_len * 8;
271 w0_t[0] = swap_workaround (w0_t[0]);
272 w0_t[1] = swap_workaround (w0_t[1]);
273 w0_t[2] = swap_workaround (w0_t[2]);
274 w0_t[3] = swap_workaround (w0_t[3]);
275 w1_t[0] = swap_workaround (w1_t[0]);
276 w1_t[1] = swap_workaround (w1_t[1]);
277 w1_t[2] = swap_workaround (w1_t[2]);
278 w1_t[3] = swap_workaround (w1_t[3]);
279 w2_t[0] = swap_workaround (w2_t[0]);
280 w2_t[1] = swap_workaround (w2_t[1]);
281 w2_t[2] = swap_workaround (w2_t[2]);
282 w2_t[3] = swap_workaround (w2_t[3]);
283 w3_t[0] = swap_workaround (w3_t[0]);
284 w3_t[1] = swap_workaround (w3_t[1]);
285 //w3_t[2] = swap_workaround (w3_t[2]);
286 //w3_t[3] = swap_workaround (w3_t[3]);
290 digest[0] = SHA512M_A;
291 digest[1] = SHA512M_B;
292 digest[2] = SHA512M_C;
293 digest[3] = SHA512M_D;
294 digest[4] = SHA512M_E;
295 digest[5] = SHA512M_F;
296 digest[6] = SHA512M_G;
297 digest[7] = SHA512M_H;
299 sha512_transform (w0_t, w1_t, w2_t, w3_t, digest);
302 const u32x r0 = l32_from_64 (digest[7]);
303 const u32x r1 = h32_from_64 (digest[7]);
304 const u32x r2 = l32_from_64 (digest[3]);
305 const u32x r3 = h32_from_64 (digest[3]);
307 #include VECT_COMPARE_M
311 __device__ static void m01740s (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], const u32 pw_len, const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
317 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
318 const u32 lid = threadIdx.x;
324 const u32 search[4] =
326 digests_buf[digests_offset].digest_buf[DGST_R0],
327 digests_buf[digests_offset].digest_buf[DGST_R1],
328 digests_buf[digests_offset].digest_buf[DGST_R2],
329 digests_buf[digests_offset].digest_buf[DGST_R3]
338 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
339 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
340 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
341 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
345 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
346 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
347 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
348 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
364 const u32 salt_len = salt_bufs[salt_pos].salt_len;
366 const u32 pw_salt_len = pw_len + salt_len;
374 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
376 const u32 w0r = c_bfs[il_pos].i;
389 w0_t[0] = swap_workaround (w0[0]);
390 w0_t[1] = swap_workaround (w0[1]);
391 w0_t[2] = swap_workaround (w0[2]);
392 w0_t[3] = swap_workaround (w0[3]);
393 w1_t[0] = swap_workaround (w1[0]);
394 w1_t[1] = swap_workaround (w1[1]);
395 w1_t[2] = swap_workaround (w1[2]);
396 w1_t[3] = swap_workaround (w1[3]);
397 w2_t[0] = swap_workaround (w2[0]);
398 w2_t[1] = swap_workaround (w2[1]);
399 w2_t[2] = swap_workaround (w2[2]);
400 w2_t[3] = swap_workaround (w2[3]);
401 w3_t[0] = swap_workaround (w3[0]);
402 w3_t[1] = swap_workaround (w3[1]);
403 w3_t[2] = swap_workaround (w3[2]);
404 w3_t[3] = swap_workaround (w3[3]);
406 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
408 w0_t[0] |= salt_buf0[0];
409 w0_t[1] |= salt_buf0[1];
410 w0_t[2] |= salt_buf0[2];
411 w0_t[3] |= salt_buf0[3];
412 w1_t[0] |= salt_buf1[0];
413 w1_t[1] |= salt_buf1[1];
414 w1_t[2] |= salt_buf1[2];
415 w1_t[3] |= salt_buf1[3];
416 w2_t[0] |= salt_buf2[0];
417 w2_t[1] |= salt_buf2[1];
418 w2_t[2] |= salt_buf2[2];
419 w2_t[3] |= salt_buf2[3];
420 w3_t[0] |= salt_buf3[0];
421 w3_t[1] |= salt_buf3[1];
423 w3_t[3] = pw_salt_len * 8;
429 w0_t[0] = swap_workaround (w0_t[0]);
430 w0_t[1] = swap_workaround (w0_t[1]);
431 w0_t[2] = swap_workaround (w0_t[2]);
432 w0_t[3] = swap_workaround (w0_t[3]);
433 w1_t[0] = swap_workaround (w1_t[0]);
434 w1_t[1] = swap_workaround (w1_t[1]);
435 w1_t[2] = swap_workaround (w1_t[2]);
436 w1_t[3] = swap_workaround (w1_t[3]);
437 w2_t[0] = swap_workaround (w2_t[0]);
438 w2_t[1] = swap_workaround (w2_t[1]);
439 w2_t[2] = swap_workaround (w2_t[2]);
440 w2_t[3] = swap_workaround (w2_t[3]);
441 w3_t[0] = swap_workaround (w3_t[0]);
442 w3_t[1] = swap_workaround (w3_t[1]);
443 //w3_t[2] = swap_workaround (w3_t[2]);
444 //w3_t[3] = swap_workaround (w3_t[3]);
448 digest[0] = SHA512M_A;
449 digest[1] = SHA512M_B;
450 digest[2] = SHA512M_C;
451 digest[3] = SHA512M_D;
452 digest[4] = SHA512M_E;
453 digest[5] = SHA512M_F;
454 digest[6] = SHA512M_G;
455 digest[7] = SHA512M_H;
457 sha512_transform (w0_t, w1_t, w2_t, w3_t, digest);
460 const u32x r0 = l32_from_64 (digest[7]);
461 const u32x r1 = h32_from_64 (digest[7]);
462 const u32x r2 = l32_from_64 (digest[3]);
463 const u32x r3 = h32_from_64 (digest[3]);
465 #include VECT_COMPARE_S
469 extern "C" __global__ void __launch_bounds__ (256, 1) m01740_m04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
475 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
477 if (gid >= gid_max) return;
481 w0[0] = pws[gid].i[ 0];
482 w0[1] = pws[gid].i[ 1];
483 w0[2] = pws[gid].i[ 2];
484 w0[3] = pws[gid].i[ 3];
507 const u32 pw_len = pws[gid].pw_len;
513 m01740m (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);
516 extern "C" __global__ void __launch_bounds__ (256, 1) m01740_m08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
522 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
524 if (gid >= gid_max) return;
528 w0[0] = pws[gid].i[ 0];
529 w0[1] = pws[gid].i[ 1];
530 w0[2] = pws[gid].i[ 2];
531 w0[3] = pws[gid].i[ 3];
535 w1[0] = pws[gid].i[ 4];
536 w1[1] = pws[gid].i[ 5];
537 w1[2] = pws[gid].i[ 6];
538 w1[3] = pws[gid].i[ 7];
554 const u32 pw_len = pws[gid].pw_len;
560 m01740m (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);
563 extern "C" __global__ void __launch_bounds__ (256, 1) m01740_m16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
569 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
571 if (gid >= gid_max) return;
575 w0[0] = pws[gid].i[ 0];
576 w0[1] = pws[gid].i[ 1];
577 w0[2] = pws[gid].i[ 2];
578 w0[3] = pws[gid].i[ 3];
582 w1[0] = pws[gid].i[ 4];
583 w1[1] = pws[gid].i[ 5];
584 w1[2] = pws[gid].i[ 6];
585 w1[3] = pws[gid].i[ 7];
589 w2[0] = pws[gid].i[ 8];
590 w2[1] = pws[gid].i[ 9];
591 w2[2] = pws[gid].i[10];
592 w2[3] = pws[gid].i[11];
596 w3[0] = pws[gid].i[12];
597 w3[1] = pws[gid].i[13];
601 const u32 pw_len = pws[gid].pw_len;
607 m01740m (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);
610 extern "C" __global__ void __launch_bounds__ (256, 1) m01740_s04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
616 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
618 if (gid >= gid_max) return;
622 w0[0] = pws[gid].i[ 0];
623 w0[1] = pws[gid].i[ 1];
624 w0[2] = pws[gid].i[ 2];
625 w0[3] = pws[gid].i[ 3];
648 const u32 pw_len = pws[gid].pw_len;
654 m01740s (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);
657 extern "C" __global__ void __launch_bounds__ (256, 1) m01740_s08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
663 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
665 if (gid >= gid_max) return;
669 w0[0] = pws[gid].i[ 0];
670 w0[1] = pws[gid].i[ 1];
671 w0[2] = pws[gid].i[ 2];
672 w0[3] = pws[gid].i[ 3];
676 w1[0] = pws[gid].i[ 4];
677 w1[1] = pws[gid].i[ 5];
678 w1[2] = pws[gid].i[ 6];
679 w1[3] = pws[gid].i[ 7];
695 const u32 pw_len = pws[gid].pw_len;
701 m01740s (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);
704 extern "C" __global__ void __launch_bounds__ (256, 1) m01740_s16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
710 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
712 if (gid >= gid_max) return;
716 w0[0] = pws[gid].i[ 0];
717 w0[1] = pws[gid].i[ 1];
718 w0[2] = pws[gid].i[ 2];
719 w0[3] = pws[gid].i[ 3];
723 w1[0] = pws[gid].i[ 4];
724 w1[1] = pws[gid].i[ 5];
725 w1[2] = pws[gid].i[ 6];
726 w1[3] = pws[gid].i[ 7];
730 w2[0] = pws[gid].i[ 8];
731 w2[1] = pws[gid].i[ 9];
732 w2[2] = pws[gid].i[10];
733 w2[3] = pws[gid].i[11];
737 w3[0] = pws[gid].i[12];
738 w3[1] = pws[gid].i[13];
742 const u32 pw_len = pws[gid].pw_len;
748 m01740s (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);