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"
49 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00040_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
55 const u32 lid = get_local_id (0);
61 const u32 gid = get_global_id (0);
63 if (gid >= gid_max) return;
67 wordl0[0] = pws[gid].i[ 0];
68 wordl0[1] = pws[gid].i[ 1];
69 wordl0[2] = pws[gid].i[ 2];
70 wordl0[3] = pws[gid].i[ 3];
74 wordl1[0] = pws[gid].i[ 4];
75 wordl1[1] = pws[gid].i[ 5];
76 wordl1[2] = pws[gid].i[ 6];
77 wordl1[3] = pws[gid].i[ 7];
93 const u32 pw_l_len = pws[gid].pw_len;
95 if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
97 switch_buffer_by_offset (wordl0, wordl1, wordl2, wordl3, combs_buf[0].pw_len);
106 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
107 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
108 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
109 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
113 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
114 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[5];
115 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[6];
116 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[7];
118 const u32 salt_len = salt_bufs[salt_pos].salt_len;
124 for (u32 il_pos = 0; il_pos < combs_cnt; il_pos++)
126 const u32 pw_r_len = combs_buf[il_pos].pw_len;
128 const u32 pw_len = pw_l_len + pw_r_len;
132 wordr0[0] = combs_buf[il_pos].i[0];
133 wordr0[1] = combs_buf[il_pos].i[1];
134 wordr0[2] = combs_buf[il_pos].i[2];
135 wordr0[3] = combs_buf[il_pos].i[3];
139 wordr1[0] = combs_buf[il_pos].i[4];
140 wordr1[1] = combs_buf[il_pos].i[5];
141 wordr1[2] = combs_buf[il_pos].i[6];
142 wordr1[3] = combs_buf[il_pos].i[7];
158 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
160 switch_buffer_by_offset (wordr0, wordr1, wordr2, wordr3, pw_l_len);
167 const u32 pw_salt_len = (pw_len * 2) + salt_len;
174 w0[0] = wordl0[0] | wordr0[0];
175 w0[1] = wordl0[1] | wordr0[1];
176 w0[2] = wordl0[2] | wordr0[2];
177 w0[3] = wordl0[3] | wordr0[3];
178 w1[0] = wordl1[0] | wordr1[0];
179 w1[1] = wordl1[1] | wordr1[1];
180 w1[2] = wordl1[2] | wordr1[2];
181 w1[3] = wordl1[3] | wordr1[3];
196 make_unicode (w0, w0_t, w1_t);
197 make_unicode (w1, w2_t, w3_t);
199 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
201 w0_t[0] |= salt_buf0[0];
202 w0_t[1] |= salt_buf0[1];
203 w0_t[2] |= salt_buf0[2];
204 w0_t[3] |= salt_buf0[3];
205 w1_t[0] |= salt_buf1[0];
206 w1_t[1] |= salt_buf1[1];
207 w1_t[2] |= salt_buf1[2];
208 w1_t[3] |= salt_buf1[3];
210 append_0x80_4 (w0_t, w1_t, w2_t, w3_t, pw_salt_len);
212 w3_t[2] = pw_salt_len * 8;
223 MD5_STEP (MD5_Fo, a, b, c, d, w0_t[0], MD5C00, MD5S00);
224 MD5_STEP (MD5_Fo, d, a, b, c, w0_t[1], MD5C01, MD5S01);
225 MD5_STEP (MD5_Fo, c, d, a, b, w0_t[2], MD5C02, MD5S02);
226 MD5_STEP (MD5_Fo, b, c, d, a, w0_t[3], MD5C03, MD5S03);
227 MD5_STEP (MD5_Fo, a, b, c, d, w1_t[0], MD5C04, MD5S00);
228 MD5_STEP (MD5_Fo, d, a, b, c, w1_t[1], MD5C05, MD5S01);
229 MD5_STEP (MD5_Fo, c, d, a, b, w1_t[2], MD5C06, MD5S02);
230 MD5_STEP (MD5_Fo, b, c, d, a, w1_t[3], MD5C07, MD5S03);
231 MD5_STEP (MD5_Fo, a, b, c, d, w2_t[0], MD5C08, MD5S00);
232 MD5_STEP (MD5_Fo, d, a, b, c, w2_t[1], MD5C09, MD5S01);
233 MD5_STEP (MD5_Fo, c, d, a, b, w2_t[2], MD5C0a, MD5S02);
234 MD5_STEP (MD5_Fo, b, c, d, a, w2_t[3], MD5C0b, MD5S03);
235 MD5_STEP (MD5_Fo, a, b, c, d, w3_t[0], MD5C0c, MD5S00);
236 MD5_STEP (MD5_Fo, d, a, b, c, w3_t[1], MD5C0d, MD5S01);
237 MD5_STEP (MD5_Fo, c, d, a, b, w3_t[2], MD5C0e, MD5S02);
238 MD5_STEP (MD5_Fo, b, c, d, a, w3_t[3], MD5C0f, MD5S03);
240 MD5_STEP (MD5_Go, a, b, c, d, w0_t[1], MD5C10, MD5S10);
241 MD5_STEP (MD5_Go, d, a, b, c, w1_t[2], MD5C11, MD5S11);
242 MD5_STEP (MD5_Go, c, d, a, b, w2_t[3], MD5C12, MD5S12);
243 MD5_STEP (MD5_Go, b, c, d, a, w0_t[0], MD5C13, MD5S13);
244 MD5_STEP (MD5_Go, a, b, c, d, w1_t[1], MD5C14, MD5S10);
245 MD5_STEP (MD5_Go, d, a, b, c, w2_t[2], MD5C15, MD5S11);
246 MD5_STEP (MD5_Go, c, d, a, b, w3_t[3], MD5C16, MD5S12);
247 MD5_STEP (MD5_Go, b, c, d, a, w1_t[0], MD5C17, MD5S13);
248 MD5_STEP (MD5_Go, a, b, c, d, w2_t[1], MD5C18, MD5S10);
249 MD5_STEP (MD5_Go, d, a, b, c, w3_t[2], MD5C19, MD5S11);
250 MD5_STEP (MD5_Go, c, d, a, b, w0_t[3], MD5C1a, MD5S12);
251 MD5_STEP (MD5_Go, b, c, d, a, w2_t[0], MD5C1b, MD5S13);
252 MD5_STEP (MD5_Go, a, b, c, d, w3_t[1], MD5C1c, MD5S10);
253 MD5_STEP (MD5_Go, d, a, b, c, w0_t[2], MD5C1d, MD5S11);
254 MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
255 MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
257 MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
258 MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
259 MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
260 MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
261 MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
262 MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
263 MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
264 MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
265 MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
266 MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
267 MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
268 MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
269 MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
270 MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
271 MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
272 MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
274 MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
275 MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
276 MD5_STEP (MD5_I , c, d, a, b, w3_t[2], MD5C32, MD5S32);
277 MD5_STEP (MD5_I , b, c, d, a, w1_t[1], MD5C33, MD5S33);
278 MD5_STEP (MD5_I , a, b, c, d, w3_t[0], MD5C34, MD5S30);
279 MD5_STEP (MD5_I , d, a, b, c, w0_t[3], MD5C35, MD5S31);
280 MD5_STEP (MD5_I , c, d, a, b, w2_t[2], MD5C36, MD5S32);
281 MD5_STEP (MD5_I , b, c, d, a, w0_t[1], MD5C37, MD5S33);
282 MD5_STEP (MD5_I , a, b, c, d, w2_t[0], MD5C38, MD5S30);
283 MD5_STEP (MD5_I , d, a, b, c, w3_t[3], MD5C39, MD5S31);
284 MD5_STEP (MD5_I , c, d, a, b, w1_t[2], MD5C3a, MD5S32);
285 MD5_STEP (MD5_I , b, c, d, a, w3_t[1], MD5C3b, MD5S33);
286 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);
297 #include VECT_COMPARE_M
301 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00040_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
305 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00040_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
309 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00040_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
315 const u32 lid = get_local_id (0);
321 const u32 gid = get_global_id (0);
323 if (gid >= gid_max) return;
327 wordl0[0] = pws[gid].i[ 0];
328 wordl0[1] = pws[gid].i[ 1];
329 wordl0[2] = pws[gid].i[ 2];
330 wordl0[3] = pws[gid].i[ 3];
334 wordl1[0] = pws[gid].i[ 4];
335 wordl1[1] = pws[gid].i[ 5];
336 wordl1[2] = pws[gid].i[ 6];
337 wordl1[3] = pws[gid].i[ 7];
353 const u32 pw_l_len = pws[gid].pw_len;
355 if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
357 switch_buffer_by_offset (wordl0, wordl1, wordl2, wordl3, combs_buf[0].pw_len);
366 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
367 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
368 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
369 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
373 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
374 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[5];
375 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[6];
376 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[7];
378 const u32 salt_len = salt_bufs[salt_pos].salt_len;
384 const u32 search[4] =
386 digests_buf[digests_offset].digest_buf[DGST_R0],
387 digests_buf[digests_offset].digest_buf[DGST_R1],
388 digests_buf[digests_offset].digest_buf[DGST_R2],
389 digests_buf[digests_offset].digest_buf[DGST_R3]
396 for (u32 il_pos = 0; il_pos < combs_cnt; il_pos++)
398 const u32 pw_r_len = combs_buf[il_pos].pw_len;
400 const u32 pw_len = pw_l_len + pw_r_len;
404 wordr0[0] = combs_buf[il_pos].i[0];
405 wordr0[1] = combs_buf[il_pos].i[1];
406 wordr0[2] = combs_buf[il_pos].i[2];
407 wordr0[3] = combs_buf[il_pos].i[3];
411 wordr1[0] = combs_buf[il_pos].i[4];
412 wordr1[1] = combs_buf[il_pos].i[5];
413 wordr1[2] = combs_buf[il_pos].i[6];
414 wordr1[3] = combs_buf[il_pos].i[7];
430 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
432 switch_buffer_by_offset (wordr0, wordr1, wordr2, wordr3, pw_l_len);
439 const u32 pw_salt_len = (pw_len * 2) + salt_len;
446 w0[0] = wordl0[0] | wordr0[0];
447 w0[1] = wordl0[1] | wordr0[1];
448 w0[2] = wordl0[2] | wordr0[2];
449 w0[3] = wordl0[3] | wordr0[3];
450 w1[0] = wordl1[0] | wordr1[0];
451 w1[1] = wordl1[1] | wordr1[1];
452 w1[2] = wordl1[2] | wordr1[2];
453 w1[3] = wordl1[3] | wordr1[3];
468 make_unicode (w0, w0_t, w1_t);
469 make_unicode (w1, w2_t, w3_t);
471 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
473 w0_t[0] |= salt_buf0[0];
474 w0_t[1] |= salt_buf0[1];
475 w0_t[2] |= salt_buf0[2];
476 w0_t[3] |= salt_buf0[3];
477 w1_t[0] |= salt_buf1[0];
478 w1_t[1] |= salt_buf1[1];
479 w1_t[2] |= salt_buf1[2];
480 w1_t[3] |= salt_buf1[3];
482 append_0x80_4 (w0_t, w1_t, w2_t, w3_t, pw_salt_len);
484 w3_t[2] = pw_salt_len * 8;
495 MD5_STEP (MD5_Fo, a, b, c, d, w0_t[0], MD5C00, MD5S00);
496 MD5_STEP (MD5_Fo, d, a, b, c, w0_t[1], MD5C01, MD5S01);
497 MD5_STEP (MD5_Fo, c, d, a, b, w0_t[2], MD5C02, MD5S02);
498 MD5_STEP (MD5_Fo, b, c, d, a, w0_t[3], MD5C03, MD5S03);
499 MD5_STEP (MD5_Fo, a, b, c, d, w1_t[0], MD5C04, MD5S00);
500 MD5_STEP (MD5_Fo, d, a, b, c, w1_t[1], MD5C05, MD5S01);
501 MD5_STEP (MD5_Fo, c, d, a, b, w1_t[2], MD5C06, MD5S02);
502 MD5_STEP (MD5_Fo, b, c, d, a, w1_t[3], MD5C07, MD5S03);
503 MD5_STEP (MD5_Fo, a, b, c, d, w2_t[0], MD5C08, MD5S00);
504 MD5_STEP (MD5_Fo, d, a, b, c, w2_t[1], MD5C09, MD5S01);
505 MD5_STEP (MD5_Fo, c, d, a, b, w2_t[2], MD5C0a, MD5S02);
506 MD5_STEP (MD5_Fo, b, c, d, a, w2_t[3], MD5C0b, MD5S03);
507 MD5_STEP (MD5_Fo, a, b, c, d, w3_t[0], MD5C0c, MD5S00);
508 MD5_STEP (MD5_Fo, d, a, b, c, w3_t[1], MD5C0d, MD5S01);
509 MD5_STEP (MD5_Fo, c, d, a, b, w3_t[2], MD5C0e, MD5S02);
510 MD5_STEP (MD5_Fo, b, c, d, a, w3_t[3], MD5C0f, MD5S03);
512 MD5_STEP (MD5_Go, a, b, c, d, w0_t[1], MD5C10, MD5S10);
513 MD5_STEP (MD5_Go, d, a, b, c, w1_t[2], MD5C11, MD5S11);
514 MD5_STEP (MD5_Go, c, d, a, b, w2_t[3], MD5C12, MD5S12);
515 MD5_STEP (MD5_Go, b, c, d, a, w0_t[0], MD5C13, MD5S13);
516 MD5_STEP (MD5_Go, a, b, c, d, w1_t[1], MD5C14, MD5S10);
517 MD5_STEP (MD5_Go, d, a, b, c, w2_t[2], MD5C15, MD5S11);
518 MD5_STEP (MD5_Go, c, d, a, b, w3_t[3], MD5C16, MD5S12);
519 MD5_STEP (MD5_Go, b, c, d, a, w1_t[0], MD5C17, MD5S13);
520 MD5_STEP (MD5_Go, a, b, c, d, w2_t[1], MD5C18, MD5S10);
521 MD5_STEP (MD5_Go, d, a, b, c, w3_t[2], MD5C19, MD5S11);
522 MD5_STEP (MD5_Go, c, d, a, b, w0_t[3], MD5C1a, MD5S12);
523 MD5_STEP (MD5_Go, b, c, d, a, w2_t[0], MD5C1b, MD5S13);
524 MD5_STEP (MD5_Go, a, b, c, d, w3_t[1], MD5C1c, MD5S10);
525 MD5_STEP (MD5_Go, d, a, b, c, w0_t[2], MD5C1d, MD5S11);
526 MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
527 MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
529 MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
530 MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
531 MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
532 MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
533 MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
534 MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
535 MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
536 MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
537 MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
538 MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
539 MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
540 MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
541 MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
542 MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
543 MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
544 MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
546 MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
547 MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
548 MD5_STEP (MD5_I , c, d, a, b, w3_t[2], MD5C32, MD5S32);
549 MD5_STEP (MD5_I , b, c, d, a, w1_t[1], MD5C33, MD5S33);
550 MD5_STEP (MD5_I , a, b, c, d, w3_t[0], MD5C34, MD5S30);
551 MD5_STEP (MD5_I , d, a, b, c, w0_t[3], MD5C35, MD5S31);
552 MD5_STEP (MD5_I , c, d, a, b, w2_t[2], MD5C36, MD5S32);
553 MD5_STEP (MD5_I , b, c, d, a, w0_t[1], MD5C37, MD5S33);
554 MD5_STEP (MD5_I , a, b, c, d, w2_t[0], MD5C38, MD5S30);
555 MD5_STEP (MD5_I , d, a, b, c, w3_t[3], MD5C39, MD5S31);
556 MD5_STEP (MD5_I , c, d, a, b, w1_t[2], MD5C3a, MD5S32);
557 MD5_STEP (MD5_I , b, c, d, a, w3_t[1], MD5C3b, MD5S33);
558 MD5_STEP (MD5_I , a, b, c, d, w1_t[0], MD5C3c, MD5S30);
560 bool q_cond = allx (search[0] != a);
562 if (q_cond) continue;
564 MD5_STEP (MD5_I , d, a, b, c, w2_t[3], MD5C3d, MD5S31);
565 MD5_STEP (MD5_I , c, d, a, b, w0_t[2], MD5C3e, MD5S32);
566 MD5_STEP (MD5_I , b, c, d, a, w2_t[1], MD5C3f, MD5S33);
574 #include VECT_COMPARE_S
578 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00040_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
582 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00040_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)