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__ comb_t c_combs[1024];
45 extern "C" __global__ void __launch_bounds__ (256, 1) m00040_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
51 const u32 lid = threadIdx.x;
57 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
59 if (gid >= gid_max) return;
63 wordl0[0] = pws[gid].i[ 0];
64 wordl0[1] = pws[gid].i[ 1];
65 wordl0[2] = pws[gid].i[ 2];
66 wordl0[3] = pws[gid].i[ 3];
70 wordl1[0] = pws[gid].i[ 4];
71 wordl1[1] = pws[gid].i[ 5];
72 wordl1[2] = pws[gid].i[ 6];
73 wordl1[3] = pws[gid].i[ 7];
89 const u32 pw_l_len = pws[gid].pw_len;
91 if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
93 switch_buffer_by_offset (wordl0, wordl1, wordl2, wordl3, c_combs[0].pw_len);
102 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
103 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
104 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
105 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
109 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
110 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[5];
111 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[6];
112 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[7];
114 const u32 salt_len = salt_bufs[salt_pos].salt_len;
120 for (u32 il_pos = 0; il_pos < combs_cnt; il_pos++)
122 const u32 pw_r_len = c_combs[il_pos].pw_len;
124 const u32 pw_len = pw_l_len + pw_r_len;
128 wordr0[0] = c_combs[il_pos].i[0];
129 wordr0[1] = c_combs[il_pos].i[1];
130 wordr0[2] = c_combs[il_pos].i[2];
131 wordr0[3] = c_combs[il_pos].i[3];
135 wordr1[0] = c_combs[il_pos].i[4];
136 wordr1[1] = c_combs[il_pos].i[5];
137 wordr1[2] = c_combs[il_pos].i[6];
138 wordr1[3] = c_combs[il_pos].i[7];
154 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
156 switch_buffer_by_offset (wordr0, wordr1, wordr2, wordr3, pw_l_len);
163 const u32 pw_salt_len = (pw_len * 2) + salt_len;
170 w0[0] = wordl0[0] | wordr0[0];
171 w0[1] = wordl0[1] | wordr0[1];
172 w0[2] = wordl0[2] | wordr0[2];
173 w0[3] = wordl0[3] | wordr0[3];
174 w1[0] = wordl1[0] | wordr1[0];
175 w1[1] = wordl1[1] | wordr1[1];
176 w1[2] = wordl1[2] | wordr1[2];
177 w1[3] = wordl1[3] | wordr1[3];
192 make_unicode (w0, w0_t, w1_t);
193 make_unicode (w1, w2_t, w3_t);
195 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
197 w0_t[0] |= salt_buf0[0];
198 w0_t[1] |= salt_buf0[1];
199 w0_t[2] |= salt_buf0[2];
200 w0_t[3] |= salt_buf0[3];
201 w1_t[0] |= salt_buf1[0];
202 w1_t[1] |= salt_buf1[1];
203 w1_t[2] |= salt_buf1[2];
204 w1_t[3] |= salt_buf1[3];
206 append_0x80_4 (w0_t, w1_t, w2_t, w3_t, pw_salt_len);
208 w3_t[2] = pw_salt_len * 8;
219 MD5_STEP (MD5_Fo, a, b, c, d, w0_t[0], MD5C00, MD5S00);
220 MD5_STEP (MD5_Fo, d, a, b, c, w0_t[1], MD5C01, MD5S01);
221 MD5_STEP (MD5_Fo, c, d, a, b, w0_t[2], MD5C02, MD5S02);
222 MD5_STEP (MD5_Fo, b, c, d, a, w0_t[3], MD5C03, MD5S03);
223 MD5_STEP (MD5_Fo, a, b, c, d, w1_t[0], MD5C04, MD5S00);
224 MD5_STEP (MD5_Fo, d, a, b, c, w1_t[1], MD5C05, MD5S01);
225 MD5_STEP (MD5_Fo, c, d, a, b, w1_t[2], MD5C06, MD5S02);
226 MD5_STEP (MD5_Fo, b, c, d, a, w1_t[3], MD5C07, MD5S03);
227 MD5_STEP (MD5_Fo, a, b, c, d, w2_t[0], MD5C08, MD5S00);
228 MD5_STEP (MD5_Fo, d, a, b, c, w2_t[1], MD5C09, MD5S01);
229 MD5_STEP (MD5_Fo, c, d, a, b, w2_t[2], MD5C0a, MD5S02);
230 MD5_STEP (MD5_Fo, b, c, d, a, w2_t[3], MD5C0b, MD5S03);
231 MD5_STEP (MD5_Fo, a, b, c, d, w3_t[0], MD5C0c, MD5S00);
232 MD5_STEP (MD5_Fo, d, a, b, c, w3_t[1], MD5C0d, MD5S01);
233 MD5_STEP (MD5_Fo, c, d, a, b, w3_t[2], MD5C0e, MD5S02);
234 MD5_STEP (MD5_Fo, b, c, d, a, w3_t[3], MD5C0f, MD5S03);
236 MD5_STEP (MD5_Go, a, b, c, d, w0_t[1], MD5C10, MD5S10);
237 MD5_STEP (MD5_Go, d, a, b, c, w1_t[2], MD5C11, MD5S11);
238 MD5_STEP (MD5_Go, c, d, a, b, w2_t[3], MD5C12, MD5S12);
239 MD5_STEP (MD5_Go, b, c, d, a, w0_t[0], MD5C13, MD5S13);
240 MD5_STEP (MD5_Go, a, b, c, d, w1_t[1], MD5C14, MD5S10);
241 MD5_STEP (MD5_Go, d, a, b, c, w2_t[2], MD5C15, MD5S11);
242 MD5_STEP (MD5_Go, c, d, a, b, w3_t[3], MD5C16, MD5S12);
243 MD5_STEP (MD5_Go, b, c, d, a, w1_t[0], MD5C17, MD5S13);
244 MD5_STEP (MD5_Go, a, b, c, d, w2_t[1], MD5C18, MD5S10);
245 MD5_STEP (MD5_Go, d, a, b, c, w3_t[2], MD5C19, MD5S11);
246 MD5_STEP (MD5_Go, c, d, a, b, w0_t[3], MD5C1a, MD5S12);
247 MD5_STEP (MD5_Go, b, c, d, a, w2_t[0], MD5C1b, MD5S13);
248 MD5_STEP (MD5_Go, a, b, c, d, w3_t[1], MD5C1c, MD5S10);
249 MD5_STEP (MD5_Go, d, a, b, c, w0_t[2], MD5C1d, MD5S11);
250 MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
251 MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
253 MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
254 MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
255 MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
256 MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
257 MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
258 MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
259 MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
260 MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
261 MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
262 MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
263 MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
264 MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
265 MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
266 MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
267 MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
268 MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
270 MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
271 MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
272 MD5_STEP (MD5_I , c, d, a, b, w3_t[2], MD5C32, MD5S32);
273 MD5_STEP (MD5_I , b, c, d, a, w1_t[1], MD5C33, MD5S33);
274 MD5_STEP (MD5_I , a, b, c, d, w3_t[0], MD5C34, MD5S30);
275 MD5_STEP (MD5_I , d, a, b, c, w0_t[3], MD5C35, MD5S31);
276 MD5_STEP (MD5_I , c, d, a, b, w2_t[2], MD5C36, MD5S32);
277 MD5_STEP (MD5_I , b, c, d, a, w0_t[1], MD5C37, MD5S33);
278 MD5_STEP (MD5_I , a, b, c, d, w2_t[0], MD5C38, MD5S30);
279 MD5_STEP (MD5_I , d, a, b, c, w3_t[3], MD5C39, MD5S31);
280 MD5_STEP (MD5_I , c, d, a, b, w1_t[2], MD5C3a, MD5S32);
281 MD5_STEP (MD5_I , b, c, d, a, w3_t[1], MD5C3b, MD5S33);
282 MD5_STEP (MD5_I , a, b, c, d, w1_t[0], MD5C3c, MD5S30);
283 MD5_STEP (MD5_I , d, a, b, c, w2_t[3], MD5C3d, MD5S31);
284 MD5_STEP (MD5_I , c, d, a, b, w0_t[2], MD5C3e, MD5S32);
285 MD5_STEP (MD5_I , b, c, d, a, w2_t[1], MD5C3f, MD5S33);
293 #include VECT_COMPARE_M
297 extern "C" __global__ void __launch_bounds__ (256, 1) m00040_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
301 extern "C" __global__ void __launch_bounds__ (256, 1) m00040_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
305 extern "C" __global__ void __launch_bounds__ (256, 1) m00040_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
311 const u32 lid = threadIdx.x;
317 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
319 if (gid >= gid_max) return;
323 wordl0[0] = pws[gid].i[ 0];
324 wordl0[1] = pws[gid].i[ 1];
325 wordl0[2] = pws[gid].i[ 2];
326 wordl0[3] = pws[gid].i[ 3];
330 wordl1[0] = pws[gid].i[ 4];
331 wordl1[1] = pws[gid].i[ 5];
332 wordl1[2] = pws[gid].i[ 6];
333 wordl1[3] = pws[gid].i[ 7];
349 const u32 pw_l_len = pws[gid].pw_len;
351 if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
353 switch_buffer_by_offset (wordl0, wordl1, wordl2, wordl3, c_combs[0].pw_len);
362 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
363 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
364 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
365 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
369 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
370 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[5];
371 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[6];
372 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[7];
374 const u32 salt_len = salt_bufs[salt_pos].salt_len;
380 const u32 search[4] =
382 digests_buf[digests_offset].digest_buf[DGST_R0],
383 digests_buf[digests_offset].digest_buf[DGST_R1],
384 digests_buf[digests_offset].digest_buf[DGST_R2],
385 digests_buf[digests_offset].digest_buf[DGST_R3]
392 for (u32 il_pos = 0; il_pos < combs_cnt; il_pos++)
394 const u32 pw_r_len = c_combs[il_pos].pw_len;
396 const u32 pw_len = pw_l_len + pw_r_len;
400 wordr0[0] = c_combs[il_pos].i[0];
401 wordr0[1] = c_combs[il_pos].i[1];
402 wordr0[2] = c_combs[il_pos].i[2];
403 wordr0[3] = c_combs[il_pos].i[3];
407 wordr1[0] = c_combs[il_pos].i[4];
408 wordr1[1] = c_combs[il_pos].i[5];
409 wordr1[2] = c_combs[il_pos].i[6];
410 wordr1[3] = c_combs[il_pos].i[7];
426 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
428 switch_buffer_by_offset (wordr0, wordr1, wordr2, wordr3, pw_l_len);
435 const u32 pw_salt_len = (pw_len * 2) + salt_len;
442 w0[0] = wordl0[0] | wordr0[0];
443 w0[1] = wordl0[1] | wordr0[1];
444 w0[2] = wordl0[2] | wordr0[2];
445 w0[3] = wordl0[3] | wordr0[3];
446 w1[0] = wordl1[0] | wordr1[0];
447 w1[1] = wordl1[1] | wordr1[1];
448 w1[2] = wordl1[2] | wordr1[2];
449 w1[3] = wordl1[3] | wordr1[3];
464 make_unicode (w0, w0_t, w1_t);
465 make_unicode (w1, w2_t, w3_t);
467 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
469 w0_t[0] |= salt_buf0[0];
470 w0_t[1] |= salt_buf0[1];
471 w0_t[2] |= salt_buf0[2];
472 w0_t[3] |= salt_buf0[3];
473 w1_t[0] |= salt_buf1[0];
474 w1_t[1] |= salt_buf1[1];
475 w1_t[2] |= salt_buf1[2];
476 w1_t[3] |= salt_buf1[3];
478 append_0x80_4 (w0_t, w1_t, w2_t, w3_t, pw_salt_len);
480 w3_t[2] = pw_salt_len * 8;
491 MD5_STEP (MD5_Fo, a, b, c, d, w0_t[0], MD5C00, MD5S00);
492 MD5_STEP (MD5_Fo, d, a, b, c, w0_t[1], MD5C01, MD5S01);
493 MD5_STEP (MD5_Fo, c, d, a, b, w0_t[2], MD5C02, MD5S02);
494 MD5_STEP (MD5_Fo, b, c, d, a, w0_t[3], MD5C03, MD5S03);
495 MD5_STEP (MD5_Fo, a, b, c, d, w1_t[0], MD5C04, MD5S00);
496 MD5_STEP (MD5_Fo, d, a, b, c, w1_t[1], MD5C05, MD5S01);
497 MD5_STEP (MD5_Fo, c, d, a, b, w1_t[2], MD5C06, MD5S02);
498 MD5_STEP (MD5_Fo, b, c, d, a, w1_t[3], MD5C07, MD5S03);
499 MD5_STEP (MD5_Fo, a, b, c, d, w2_t[0], MD5C08, MD5S00);
500 MD5_STEP (MD5_Fo, d, a, b, c, w2_t[1], MD5C09, MD5S01);
501 MD5_STEP (MD5_Fo, c, d, a, b, w2_t[2], MD5C0a, MD5S02);
502 MD5_STEP (MD5_Fo, b, c, d, a, w2_t[3], MD5C0b, MD5S03);
503 MD5_STEP (MD5_Fo, a, b, c, d, w3_t[0], MD5C0c, MD5S00);
504 MD5_STEP (MD5_Fo, d, a, b, c, w3_t[1], MD5C0d, MD5S01);
505 MD5_STEP (MD5_Fo, c, d, a, b, w3_t[2], MD5C0e, MD5S02);
506 MD5_STEP (MD5_Fo, b, c, d, a, w3_t[3], MD5C0f, MD5S03);
508 MD5_STEP (MD5_Go, a, b, c, d, w0_t[1], MD5C10, MD5S10);
509 MD5_STEP (MD5_Go, d, a, b, c, w1_t[2], MD5C11, MD5S11);
510 MD5_STEP (MD5_Go, c, d, a, b, w2_t[3], MD5C12, MD5S12);
511 MD5_STEP (MD5_Go, b, c, d, a, w0_t[0], MD5C13, MD5S13);
512 MD5_STEP (MD5_Go, a, b, c, d, w1_t[1], MD5C14, MD5S10);
513 MD5_STEP (MD5_Go, d, a, b, c, w2_t[2], MD5C15, MD5S11);
514 MD5_STEP (MD5_Go, c, d, a, b, w3_t[3], MD5C16, MD5S12);
515 MD5_STEP (MD5_Go, b, c, d, a, w1_t[0], MD5C17, MD5S13);
516 MD5_STEP (MD5_Go, a, b, c, d, w2_t[1], MD5C18, MD5S10);
517 MD5_STEP (MD5_Go, d, a, b, c, w3_t[2], MD5C19, MD5S11);
518 MD5_STEP (MD5_Go, c, d, a, b, w0_t[3], MD5C1a, MD5S12);
519 MD5_STEP (MD5_Go, b, c, d, a, w2_t[0], MD5C1b, MD5S13);
520 MD5_STEP (MD5_Go, a, b, c, d, w3_t[1], MD5C1c, MD5S10);
521 MD5_STEP (MD5_Go, d, a, b, c, w0_t[2], MD5C1d, MD5S11);
522 MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
523 MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
525 MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
526 MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
527 MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
528 MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
529 MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
530 MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
531 MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
532 MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
533 MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
534 MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
535 MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
536 MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
537 MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
538 MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
539 MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
540 MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
542 MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
543 MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
544 MD5_STEP (MD5_I , c, d, a, b, w3_t[2], MD5C32, MD5S32);
545 MD5_STEP (MD5_I , b, c, d, a, w1_t[1], MD5C33, MD5S33);
546 MD5_STEP (MD5_I , a, b, c, d, w3_t[0], MD5C34, MD5S30);
547 MD5_STEP (MD5_I , d, a, b, c, w0_t[3], MD5C35, MD5S31);
548 MD5_STEP (MD5_I , c, d, a, b, w2_t[2], MD5C36, MD5S32);
549 MD5_STEP (MD5_I , b, c, d, a, w0_t[1], MD5C37, MD5S33);
550 MD5_STEP (MD5_I , a, b, c, d, w2_t[0], MD5C38, MD5S30);
551 MD5_STEP (MD5_I , d, a, b, c, w3_t[3], MD5C39, MD5S31);
552 MD5_STEP (MD5_I , c, d, a, b, w1_t[2], MD5C3a, MD5S32);
553 MD5_STEP (MD5_I , b, c, d, a, w3_t[1], MD5C3b, MD5S33);
554 MD5_STEP (MD5_I , a, b, c, d, w1_t[0], MD5C3c, MD5S30);
556 bool q_cond = (search[0] != a);
558 if (q_cond) continue;
560 MD5_STEP (MD5_I , d, a, b, c, w2_t[3], MD5C3d, MD5S31);
561 MD5_STEP (MD5_I , c, d, a, b, w0_t[2], MD5C3e, MD5S32);
562 MD5_STEP (MD5_I , b, c, d, a, w2_t[1], MD5C3f, MD5S33);
570 #include VECT_COMPARE_S
574 extern "C" __global__ void __launch_bounds__ (256, 1) m00040_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
578 extern "C" __global__ void __launch_bounds__ (256, 1) m00040_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)