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__ static void m03800m (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)
51 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
52 const u32 lid = threadIdx.x;
64 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
65 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
66 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
67 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
71 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
72 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
73 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
74 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
90 const u32 salt_len = salt_bufs[salt_pos].salt_len;
92 const u32 pw_salt_len = salt_len + pw_len + salt_len;
100 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
102 const u32 w0r = c_bfs[il_pos].i;
139 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
141 w0_t[0] |= salt_buf0[0];
142 w0_t[1] |= salt_buf0[1];
143 w0_t[2] |= salt_buf0[2];
144 w0_t[3] |= salt_buf0[3];
145 w1_t[0] |= salt_buf1[0];
146 w1_t[1] |= salt_buf1[1];
147 w1_t[2] |= salt_buf1[2];
148 w1_t[3] |= salt_buf1[3];
149 w2_t[0] |= salt_buf2[0];
150 w2_t[1] |= salt_buf2[1];
151 w2_t[2] |= salt_buf2[2];
152 w2_t[3] |= salt_buf2[3];
153 w3_t[0] |= salt_buf3[0];
154 w3_t[1] |= salt_buf3[1];
155 w3_t[2] |= salt_buf3[2];
156 w3_t[3] |= salt_buf3[3];
164 s0[0] = salt_buf0[0];
165 s0[1] = salt_buf0[1];
166 s0[2] = salt_buf0[2];
167 s0[3] = salt_buf0[3];
171 s1[0] = salt_buf1[0];
172 s1[1] = salt_buf1[1];
173 s1[2] = salt_buf1[2];
174 s1[3] = salt_buf1[3];
190 switch_buffer_by_offset (s0, s1, s2, s3, salt_len + pw_len);
209 append_0x80_4 (w0_t, w1_t, w2_t, w3_t, pw_salt_len);
211 w3_t[2] = pw_salt_len * 8;
222 MD5_STEP (MD5_Fo, a, b, c, d, w0_t[0], MD5C00, MD5S00);
223 MD5_STEP (MD5_Fo, d, a, b, c, w0_t[1], MD5C01, MD5S01);
224 MD5_STEP (MD5_Fo, c, d, a, b, w0_t[2], MD5C02, MD5S02);
225 MD5_STEP (MD5_Fo, b, c, d, a, w0_t[3], MD5C03, MD5S03);
226 MD5_STEP (MD5_Fo, a, b, c, d, w1_t[0], MD5C04, MD5S00);
227 MD5_STEP (MD5_Fo, d, a, b, c, w1_t[1], MD5C05, MD5S01);
228 MD5_STEP (MD5_Fo, c, d, a, b, w1_t[2], MD5C06, MD5S02);
229 MD5_STEP (MD5_Fo, b, c, d, a, w1_t[3], MD5C07, MD5S03);
230 MD5_STEP (MD5_Fo, a, b, c, d, w2_t[0], MD5C08, MD5S00);
231 MD5_STEP (MD5_Fo, d, a, b, c, w2_t[1], MD5C09, MD5S01);
232 MD5_STEP (MD5_Fo, c, d, a, b, w2_t[2], MD5C0a, MD5S02);
233 MD5_STEP (MD5_Fo, b, c, d, a, w2_t[3], MD5C0b, MD5S03);
234 MD5_STEP (MD5_Fo, a, b, c, d, w3_t[0], MD5C0c, MD5S00);
235 MD5_STEP (MD5_Fo, d, a, b, c, w3_t[1], MD5C0d, MD5S01);
236 MD5_STEP (MD5_Fo, c, d, a, b, w3_t[2], MD5C0e, MD5S02);
237 MD5_STEP (MD5_Fo, b, c, d, a, w3_t[3], MD5C0f, MD5S03);
239 MD5_STEP (MD5_Go, a, b, c, d, w0_t[1], MD5C10, MD5S10);
240 MD5_STEP (MD5_Go, d, a, b, c, w1_t[2], MD5C11, MD5S11);
241 MD5_STEP (MD5_Go, c, d, a, b, w2_t[3], MD5C12, MD5S12);
242 MD5_STEP (MD5_Go, b, c, d, a, w0_t[0], MD5C13, MD5S13);
243 MD5_STEP (MD5_Go, a, b, c, d, w1_t[1], MD5C14, MD5S10);
244 MD5_STEP (MD5_Go, d, a, b, c, w2_t[2], MD5C15, MD5S11);
245 MD5_STEP (MD5_Go, c, d, a, b, w3_t[3], MD5C16, MD5S12);
246 MD5_STEP (MD5_Go, b, c, d, a, w1_t[0], MD5C17, MD5S13);
247 MD5_STEP (MD5_Go, a, b, c, d, w2_t[1], MD5C18, MD5S10);
248 MD5_STEP (MD5_Go, d, a, b, c, w3_t[2], MD5C19, MD5S11);
249 MD5_STEP (MD5_Go, c, d, a, b, w0_t[3], MD5C1a, MD5S12);
250 MD5_STEP (MD5_Go, b, c, d, a, w2_t[0], MD5C1b, MD5S13);
251 MD5_STEP (MD5_Go, a, b, c, d, w3_t[1], MD5C1c, MD5S10);
252 MD5_STEP (MD5_Go, d, a, b, c, w0_t[2], MD5C1d, MD5S11);
253 MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
254 MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
256 MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
257 MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
258 MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
259 MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
260 MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
261 MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
262 MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
263 MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
264 MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
265 MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
266 MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
267 MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
268 MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
269 MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
270 MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
271 MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
273 MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
274 MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
275 MD5_STEP (MD5_I , c, d, a, b, w3_t[2], MD5C32, MD5S32);
276 MD5_STEP (MD5_I , b, c, d, a, w1_t[1], MD5C33, MD5S33);
277 MD5_STEP (MD5_I , a, b, c, d, w3_t[0], MD5C34, MD5S30);
278 MD5_STEP (MD5_I , d, a, b, c, w0_t[3], MD5C35, MD5S31);
279 MD5_STEP (MD5_I , c, d, a, b, w2_t[2], MD5C36, MD5S32);
280 MD5_STEP (MD5_I , b, c, d, a, w0_t[1], MD5C37, MD5S33);
281 MD5_STEP (MD5_I , a, b, c, d, w2_t[0], MD5C38, MD5S30);
282 MD5_STEP (MD5_I , d, a, b, c, w3_t[3], MD5C39, MD5S31);
283 MD5_STEP (MD5_I , c, d, a, b, w1_t[2], MD5C3a, MD5S32);
284 MD5_STEP (MD5_I , b, c, d, a, w3_t[1], MD5C3b, MD5S33);
285 MD5_STEP (MD5_I , a, b, c, d, w1_t[0], MD5C3c, MD5S30);
287 MD5_STEP (MD5_I , d, a, b, c, w2_t[3], MD5C3d, MD5S31);
288 MD5_STEP (MD5_I , c, d, a, b, w0_t[2], MD5C3e, MD5S32);
289 MD5_STEP (MD5_I , b, c, d, a, w2_t[1], MD5C3f, MD5S33);
296 #include VECT_COMPARE_M
300 __device__ static void m03800s (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)
306 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
307 const u32 lid = threadIdx.x;
313 const u32 search[4] =
315 digests_buf[digests_offset].digest_buf[DGST_R0],
316 digests_buf[digests_offset].digest_buf[DGST_R1],
317 digests_buf[digests_offset].digest_buf[DGST_R2],
318 digests_buf[digests_offset].digest_buf[DGST_R3]
327 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
328 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
329 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
330 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
334 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
335 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
336 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
337 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
353 const u32 salt_len = salt_bufs[salt_pos].salt_len;
355 const u32 pw_salt_len = salt_len + pw_len + salt_len;
363 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
365 const u32 w0r = c_bfs[il_pos].i;
402 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
404 w0_t[0] |= salt_buf0[0];
405 w0_t[1] |= salt_buf0[1];
406 w0_t[2] |= salt_buf0[2];
407 w0_t[3] |= salt_buf0[3];
408 w1_t[0] |= salt_buf1[0];
409 w1_t[1] |= salt_buf1[1];
410 w1_t[2] |= salt_buf1[2];
411 w1_t[3] |= salt_buf1[3];
412 w2_t[0] |= salt_buf2[0];
413 w2_t[1] |= salt_buf2[1];
414 w2_t[2] |= salt_buf2[2];
415 w2_t[3] |= salt_buf2[3];
416 w3_t[0] |= salt_buf3[0];
417 w3_t[1] |= salt_buf3[1];
418 w3_t[2] |= salt_buf3[2];
419 w3_t[3] |= salt_buf3[3];
427 s0[0] = salt_buf0[0];
428 s0[1] = salt_buf0[1];
429 s0[2] = salt_buf0[2];
430 s0[3] = salt_buf0[3];
434 s1[0] = salt_buf1[0];
435 s1[1] = salt_buf1[1];
436 s1[2] = salt_buf1[2];
437 s1[3] = salt_buf1[3];
453 switch_buffer_by_offset (s0, s1, s2, s3, salt_len + pw_len);
472 append_0x80_4 (w0_t, w1_t, w2_t, w3_t, pw_salt_len);
474 w3_t[2] = pw_salt_len * 8;
485 MD5_STEP (MD5_Fo, a, b, c, d, w0_t[0], MD5C00, MD5S00);
486 MD5_STEP (MD5_Fo, d, a, b, c, w0_t[1], MD5C01, MD5S01);
487 MD5_STEP (MD5_Fo, c, d, a, b, w0_t[2], MD5C02, MD5S02);
488 MD5_STEP (MD5_Fo, b, c, d, a, w0_t[3], MD5C03, MD5S03);
489 MD5_STEP (MD5_Fo, a, b, c, d, w1_t[0], MD5C04, MD5S00);
490 MD5_STEP (MD5_Fo, d, a, b, c, w1_t[1], MD5C05, MD5S01);
491 MD5_STEP (MD5_Fo, c, d, a, b, w1_t[2], MD5C06, MD5S02);
492 MD5_STEP (MD5_Fo, b, c, d, a, w1_t[3], MD5C07, MD5S03);
493 MD5_STEP (MD5_Fo, a, b, c, d, w2_t[0], MD5C08, MD5S00);
494 MD5_STEP (MD5_Fo, d, a, b, c, w2_t[1], MD5C09, MD5S01);
495 MD5_STEP (MD5_Fo, c, d, a, b, w2_t[2], MD5C0a, MD5S02);
496 MD5_STEP (MD5_Fo, b, c, d, a, w2_t[3], MD5C0b, MD5S03);
497 MD5_STEP (MD5_Fo, a, b, c, d, w3_t[0], MD5C0c, MD5S00);
498 MD5_STEP (MD5_Fo, d, a, b, c, w3_t[1], MD5C0d, MD5S01);
499 MD5_STEP (MD5_Fo, c, d, a, b, w3_t[2], MD5C0e, MD5S02);
500 MD5_STEP (MD5_Fo, b, c, d, a, w3_t[3], MD5C0f, MD5S03);
502 MD5_STEP (MD5_Go, a, b, c, d, w0_t[1], MD5C10, MD5S10);
503 MD5_STEP (MD5_Go, d, a, b, c, w1_t[2], MD5C11, MD5S11);
504 MD5_STEP (MD5_Go, c, d, a, b, w2_t[3], MD5C12, MD5S12);
505 MD5_STEP (MD5_Go, b, c, d, a, w0_t[0], MD5C13, MD5S13);
506 MD5_STEP (MD5_Go, a, b, c, d, w1_t[1], MD5C14, MD5S10);
507 MD5_STEP (MD5_Go, d, a, b, c, w2_t[2], MD5C15, MD5S11);
508 MD5_STEP (MD5_Go, c, d, a, b, w3_t[3], MD5C16, MD5S12);
509 MD5_STEP (MD5_Go, b, c, d, a, w1_t[0], MD5C17, MD5S13);
510 MD5_STEP (MD5_Go, a, b, c, d, w2_t[1], MD5C18, MD5S10);
511 MD5_STEP (MD5_Go, d, a, b, c, w3_t[2], MD5C19, MD5S11);
512 MD5_STEP (MD5_Go, c, d, a, b, w0_t[3], MD5C1a, MD5S12);
513 MD5_STEP (MD5_Go, b, c, d, a, w2_t[0], MD5C1b, MD5S13);
514 MD5_STEP (MD5_Go, a, b, c, d, w3_t[1], MD5C1c, MD5S10);
515 MD5_STEP (MD5_Go, d, a, b, c, w0_t[2], MD5C1d, MD5S11);
516 MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
517 MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
519 MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
520 MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
521 MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
522 MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
523 MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
524 MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
525 MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
526 MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
527 MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
528 MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
529 MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
530 MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
531 MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
532 MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
533 MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
534 MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
536 MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
537 MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
538 MD5_STEP (MD5_I , c, d, a, b, w3_t[2], MD5C32, MD5S32);
539 MD5_STEP (MD5_I , b, c, d, a, w1_t[1], MD5C33, MD5S33);
540 MD5_STEP (MD5_I , a, b, c, d, w3_t[0], MD5C34, MD5S30);
541 MD5_STEP (MD5_I , d, a, b, c, w0_t[3], MD5C35, MD5S31);
542 MD5_STEP (MD5_I , c, d, a, b, w2_t[2], MD5C36, MD5S32);
543 MD5_STEP (MD5_I , b, c, d, a, w0_t[1], MD5C37, MD5S33);
544 MD5_STEP (MD5_I , a, b, c, d, w2_t[0], MD5C38, MD5S30);
545 MD5_STEP (MD5_I , d, a, b, c, w3_t[3], MD5C39, MD5S31);
546 MD5_STEP (MD5_I , c, d, a, b, w1_t[2], MD5C3a, MD5S32);
547 MD5_STEP (MD5_I , b, c, d, a, w3_t[1], MD5C3b, MD5S33);
548 MD5_STEP (MD5_I , a, b, c, d, w1_t[0], MD5C3c, MD5S30);
549 MD5_STEP (MD5_I , d, a, b, c, w2_t[3], MD5C3d, MD5S31);
550 MD5_STEP (MD5_I , c, d, a, b, w0_t[2], MD5C3e, MD5S32);
551 MD5_STEP (MD5_I , b, c, d, a, w2_t[1], MD5C3f, MD5S33);
558 #include VECT_COMPARE_S
562 extern "C" __global__ void __launch_bounds__ (256, 1) m03800_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)
568 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
570 if (gid >= gid_max) return;
574 w0[0] = pws[gid].i[ 0];
575 w0[1] = pws[gid].i[ 1];
576 w0[2] = pws[gid].i[ 2];
577 w0[3] = pws[gid].i[ 3];
597 w3[2] = pws[gid].i[14];
600 const u32 pw_len = pws[gid].pw_len;
606 m03800m (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);
609 extern "C" __global__ void __launch_bounds__ (256, 1) m03800_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)
615 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
617 if (gid >= gid_max) return;
621 w0[0] = pws[gid].i[ 0];
622 w0[1] = pws[gid].i[ 1];
623 w0[2] = pws[gid].i[ 2];
624 w0[3] = pws[gid].i[ 3];
628 w1[0] = pws[gid].i[ 4];
629 w1[1] = pws[gid].i[ 5];
630 w1[2] = pws[gid].i[ 6];
631 w1[3] = pws[gid].i[ 7];
644 w3[2] = pws[gid].i[14];
647 const u32 pw_len = pws[gid].pw_len;
653 m03800m (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);
656 extern "C" __global__ void __launch_bounds__ (256, 1) m03800_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)
662 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
664 if (gid >= gid_max) return;
668 w0[0] = pws[gid].i[ 0];
669 w0[1] = pws[gid].i[ 1];
670 w0[2] = pws[gid].i[ 2];
671 w0[3] = pws[gid].i[ 3];
675 w1[0] = pws[gid].i[ 4];
676 w1[1] = pws[gid].i[ 5];
677 w1[2] = pws[gid].i[ 6];
678 w1[3] = pws[gid].i[ 7];
682 w2[0] = pws[gid].i[ 8];
683 w2[1] = pws[gid].i[ 9];
684 w2[2] = pws[gid].i[10];
685 w2[3] = pws[gid].i[11];
689 w3[0] = pws[gid].i[12];
690 w3[1] = pws[gid].i[13];
691 w3[2] = pws[gid].i[14];
692 w3[3] = pws[gid].i[15];
694 const u32 pw_len = pws[gid].pw_len;
700 m03800m (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);
703 extern "C" __global__ void __launch_bounds__ (256, 1) m03800_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)
709 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
711 if (gid >= gid_max) return;
715 w0[0] = pws[gid].i[ 0];
716 w0[1] = pws[gid].i[ 1];
717 w0[2] = pws[gid].i[ 2];
718 w0[3] = pws[gid].i[ 3];
738 w3[2] = pws[gid].i[14];
741 const u32 pw_len = pws[gid].pw_len;
747 m03800s (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);
750 extern "C" __global__ void __launch_bounds__ (256, 1) m03800_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)
756 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
758 if (gid >= gid_max) return;
762 w0[0] = pws[gid].i[ 0];
763 w0[1] = pws[gid].i[ 1];
764 w0[2] = pws[gid].i[ 2];
765 w0[3] = pws[gid].i[ 3];
769 w1[0] = pws[gid].i[ 4];
770 w1[1] = pws[gid].i[ 5];
771 w1[2] = pws[gid].i[ 6];
772 w1[3] = pws[gid].i[ 7];
785 w3[2] = pws[gid].i[14];
788 const u32 pw_len = pws[gid].pw_len;
794 m03800s (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);
797 extern "C" __global__ void __launch_bounds__ (256, 1) m03800_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)
803 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
805 if (gid >= gid_max) return;
809 w0[0] = pws[gid].i[ 0];
810 w0[1] = pws[gid].i[ 1];
811 w0[2] = pws[gid].i[ 2];
812 w0[3] = pws[gid].i[ 3];
816 w1[0] = pws[gid].i[ 4];
817 w1[1] = pws[gid].i[ 5];
818 w1[2] = pws[gid].i[ 6];
819 w1[3] = pws[gid].i[ 7];
823 w2[0] = pws[gid].i[ 8];
824 w2[1] = pws[gid].i[ 9];
825 w2[2] = pws[gid].i[10];
826 w2[3] = pws[gid].i[11];
830 w3[0] = pws[gid].i[12];
831 w3[1] = pws[gid].i[13];
832 w3[2] = pws[gid].i[14];
833 w3[3] = pws[gid].i[15];
835 const u32 pw_len = pws[gid].pw_len;
841 m03800s (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);