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 m04900m (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;
60 salt_buf0_t[0] = salt_bufs[salt_pos].salt_buf[0];
61 salt_buf0_t[1] = salt_bufs[salt_pos].salt_buf[1];
62 salt_buf0_t[2] = salt_bufs[salt_pos].salt_buf[2];
63 salt_buf0_t[3] = salt_bufs[salt_pos].salt_buf[3];
67 salt_buf1_t[0] = salt_bufs[salt_pos].salt_buf[4];
68 salt_buf1_t[1] = salt_bufs[salt_pos].salt_buf[5];
69 salt_buf1_t[2] = salt_bufs[salt_pos].salt_buf[6];
70 salt_buf1_t[3] = salt_bufs[salt_pos].salt_buf[7];
86 const u32 salt_len = salt_bufs[salt_pos].salt_len;
88 const u32 pw_salt_len = salt_len + pw_len + salt_len;
90 // first we need to switch the right-hand salt to the correct position (2nd salt)
92 switch_buffer_by_offset (salt_buf0_t, salt_buf1_t, salt_buf2_t, salt_buf3_t, salt_len + pw_len);
96 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
97 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
98 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
99 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
103 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
104 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[5];
105 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[6];
106 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[7];
122 // concatenate the 1st and 2nd instance of the salt
124 salt_buf0[0] |= salt_buf0_t[0];
125 salt_buf0[1] |= salt_buf0_t[1];
126 salt_buf0[2] |= salt_buf0_t[2];
127 salt_buf0[3] |= salt_buf0_t[3];
129 salt_buf1[0] |= salt_buf1_t[0];
130 salt_buf1[1] |= salt_buf1_t[1];
131 salt_buf1[2] |= salt_buf1_t[2];
132 salt_buf1[3] |= salt_buf1_t[3];
134 salt_buf2[0] |= salt_buf2_t[0];
135 salt_buf2[1] |= salt_buf2_t[1];
136 salt_buf2[2] |= salt_buf2_t[2];
137 salt_buf2[3] |= salt_buf2_t[3];
139 salt_buf3[0] |= salt_buf3_t[0];
140 salt_buf3[1] |= salt_buf3_t[1];
141 salt_buf3[2] |= salt_buf3_t[2];
142 salt_buf3[3] |= salt_buf3_t[3];
144 append_0x80_4 (salt_buf0, salt_buf1, salt_buf2, salt_buf3, pw_salt_len);
152 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
154 const u32 w0r = c_bfs[il_pos].i;
187 * put the password after the first salt but before the second salt
190 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
192 w0_t[0] |= salt_buf0[0];
193 w0_t[1] |= salt_buf0[1];
194 w0_t[2] |= salt_buf0[2];
195 w0_t[3] |= salt_buf0[3];
196 w1_t[0] |= salt_buf1[0];
197 w1_t[1] |= salt_buf1[1];
198 w1_t[2] |= salt_buf1[2];
199 w1_t[3] |= salt_buf1[3];
200 w2_t[0] |= salt_buf2[0];
201 w2_t[1] |= salt_buf2[1];
202 w2_t[2] |= salt_buf2[2];
203 w2_t[3] |= salt_buf2[3];
204 w3_t[0] |= salt_buf3[0];
205 w3_t[1] |= salt_buf3[1];
206 w3_t[2] |= salt_buf3[2];
208 u32x w0 = swap_workaround (w0_t[0]);
209 u32x w1 = swap_workaround (w0_t[1]);
210 u32x w2 = swap_workaround (w0_t[2]);
211 u32x w3 = swap_workaround (w0_t[3]);
212 u32x w4 = swap_workaround (w1_t[0]);
213 u32x w5 = swap_workaround (w1_t[1]);
214 u32x w6 = swap_workaround (w1_t[2]);
215 u32x w7 = swap_workaround (w1_t[3]);
216 u32x w8 = swap_workaround (w2_t[0]);
217 u32x w9 = swap_workaround (w2_t[1]);
218 u32x wa = swap_workaround (w2_t[2]);
219 u32x wb = swap_workaround (w2_t[3]);
220 u32x wc = swap_workaround (w3_t[0]);
221 u32x wd = swap_workaround (w3_t[1]);
222 u32x we = swap_workaround (w3_t[2]);
223 u32x wf = pw_salt_len * 8;
238 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0);
239 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1);
240 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2);
241 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3);
242 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4);
243 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5);
244 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6);
245 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7);
246 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8);
247 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9);
248 SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa);
249 SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb);
250 SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc);
251 SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd);
252 SHA1_STEP (SHA1_F0o, b, c, d, e, a, we);
253 SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf);
254 w0 = rotl32 ((wd ^ w8 ^ w2 ^ w0), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0);
255 w1 = rotl32 ((we ^ w9 ^ w3 ^ w1), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1);
256 w2 = rotl32 ((wf ^ wa ^ w4 ^ w2), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2);
257 w3 = rotl32 ((w0 ^ wb ^ w5 ^ w3), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3);
262 w4 = rotl32 ((w1 ^ wc ^ w6 ^ w4), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4);
263 w5 = rotl32 ((w2 ^ wd ^ w7 ^ w5), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5);
264 w6 = rotl32 ((w3 ^ we ^ w8 ^ w6), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6);
265 w7 = rotl32 ((w4 ^ wf ^ w9 ^ w7), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7);
266 w8 = rotl32 ((w5 ^ w0 ^ wa ^ w8), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8);
267 w9 = rotl32 ((w6 ^ w1 ^ wb ^ w9), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9);
268 wa = rotl32 ((w7 ^ w2 ^ wc ^ wa), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa);
269 wb = rotl32 ((w8 ^ w3 ^ wd ^ wb), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb);
270 wc = rotl32 ((w9 ^ w4 ^ we ^ wc), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc);
271 wd = rotl32 ((wa ^ w5 ^ wf ^ wd), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd);
272 we = rotl32 ((wb ^ w6 ^ w0 ^ we), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we);
273 wf = rotl32 ((wc ^ w7 ^ w1 ^ wf), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf);
274 w0 = rotl32 ((wd ^ w8 ^ w2 ^ w0), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0);
275 w1 = rotl32 ((we ^ w9 ^ w3 ^ w1), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1);
276 w2 = rotl32 ((wf ^ wa ^ w4 ^ w2), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2);
277 w3 = rotl32 ((w0 ^ wb ^ w5 ^ w3), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3);
278 w4 = rotl32 ((w1 ^ wc ^ w6 ^ w4), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4);
279 w5 = rotl32 ((w2 ^ wd ^ w7 ^ w5), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5);
280 w6 = rotl32 ((w3 ^ we ^ w8 ^ w6), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6);
281 w7 = rotl32 ((w4 ^ wf ^ w9 ^ w7), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7);
286 w8 = rotl32 ((w5 ^ w0 ^ wa ^ w8), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8);
287 w9 = rotl32 ((w6 ^ w1 ^ wb ^ w9), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9);
288 wa = rotl32 ((w7 ^ w2 ^ wc ^ wa), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa);
289 wb = rotl32 ((w8 ^ w3 ^ wd ^ wb), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb);
290 wc = rotl32 ((w9 ^ w4 ^ we ^ wc), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc);
291 wd = rotl32 ((wa ^ w5 ^ wf ^ wd), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd);
292 we = rotl32 ((wb ^ w6 ^ w0 ^ we), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we);
293 wf = rotl32 ((wc ^ w7 ^ w1 ^ wf), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf);
294 w0 = rotl32 ((wd ^ w8 ^ w2 ^ w0), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0);
295 w1 = rotl32 ((we ^ w9 ^ w3 ^ w1), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1);
296 w2 = rotl32 ((wf ^ wa ^ w4 ^ w2), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2);
297 w3 = rotl32 ((w0 ^ wb ^ w5 ^ w3), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3);
298 w4 = rotl32 ((w1 ^ wc ^ w6 ^ w4), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4);
299 w5 = rotl32 ((w2 ^ wd ^ w7 ^ w5), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5);
300 w6 = rotl32 ((w3 ^ we ^ w8 ^ w6), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6);
301 w7 = rotl32 ((w4 ^ wf ^ w9 ^ w7), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7);
302 w8 = rotl32 ((w5 ^ w0 ^ wa ^ w8), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8);
303 w9 = rotl32 ((w6 ^ w1 ^ wb ^ w9), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9);
304 wa = rotl32 ((w7 ^ w2 ^ wc ^ wa), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa);
305 wb = rotl32 ((w8 ^ w3 ^ wd ^ wb), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb);
310 wc = rotl32 ((w9 ^ w4 ^ we ^ wc), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc);
311 wd = rotl32 ((wa ^ w5 ^ wf ^ wd), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd);
312 we = rotl32 ((wb ^ w6 ^ w0 ^ we), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we);
313 wf = rotl32 ((wc ^ w7 ^ w1 ^ wf), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf);
314 w0 = rotl32 ((wd ^ w8 ^ w2 ^ w0), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0);
315 w1 = rotl32 ((we ^ w9 ^ w3 ^ w1), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1);
316 w2 = rotl32 ((wf ^ wa ^ w4 ^ w2), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2);
317 w3 = rotl32 ((w0 ^ wb ^ w5 ^ w3), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3);
318 w4 = rotl32 ((w1 ^ wc ^ w6 ^ w4), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4);
319 w5 = rotl32 ((w2 ^ wd ^ w7 ^ w5), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5);
320 w6 = rotl32 ((w3 ^ we ^ w8 ^ w6), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6);
321 w7 = rotl32 ((w4 ^ wf ^ w9 ^ w7), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7);
322 w8 = rotl32 ((w5 ^ w0 ^ wa ^ w8), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8);
323 w9 = rotl32 ((w6 ^ w1 ^ wb ^ w9), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9);
324 wa = rotl32 ((w7 ^ w2 ^ wc ^ wa), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa);
325 wb = rotl32 ((w8 ^ w3 ^ wd ^ wb), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb);
326 wc = rotl32 ((w9 ^ w4 ^ we ^ wc), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc);
327 wd = rotl32 ((wa ^ w5 ^ wf ^ wd), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd);
328 we = rotl32 ((wb ^ w6 ^ w0 ^ we), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we);
329 wf = rotl32 ((wc ^ w7 ^ w1 ^ wf), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf);
336 #include VECT_COMPARE_M
340 __device__ static void m04900s (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)
346 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
347 const u32 lid = threadIdx.x;
353 const u32 search[4] =
355 digests_buf[digests_offset].digest_buf[DGST_R0],
356 digests_buf[digests_offset].digest_buf[DGST_R1],
357 digests_buf[digests_offset].digest_buf[DGST_R2],
358 digests_buf[digests_offset].digest_buf[DGST_R3]
365 const u32 e_rev = rotl32 (search[1], 2u);
373 salt_buf0_t[0] = salt_bufs[salt_pos].salt_buf[0];
374 salt_buf0_t[1] = salt_bufs[salt_pos].salt_buf[1];
375 salt_buf0_t[2] = salt_bufs[salt_pos].salt_buf[2];
376 salt_buf0_t[3] = salt_bufs[salt_pos].salt_buf[3];
380 salt_buf1_t[0] = salt_bufs[salt_pos].salt_buf[4];
381 salt_buf1_t[1] = salt_bufs[salt_pos].salt_buf[5];
382 salt_buf1_t[2] = salt_bufs[salt_pos].salt_buf[6];
383 salt_buf1_t[3] = salt_bufs[salt_pos].salt_buf[7];
399 const u32 salt_len = salt_bufs[salt_pos].salt_len;
401 const u32 pw_salt_len = salt_len + pw_len + salt_len;
403 // first we need to switch the right-hand salt to the correct position (2nd salt)
405 switch_buffer_by_offset (salt_buf0_t, salt_buf1_t, salt_buf2_t, salt_buf3_t, salt_len + pw_len);
409 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
410 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
411 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
412 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
416 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
417 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[5];
418 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[6];
419 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[7];
435 // concatenate the 1st and 2nd instance of the salt
437 salt_buf0[0] |= salt_buf0_t[0];
438 salt_buf0[1] |= salt_buf0_t[1];
439 salt_buf0[2] |= salt_buf0_t[2];
440 salt_buf0[3] |= salt_buf0_t[3];
442 salt_buf1[0] |= salt_buf1_t[0];
443 salt_buf1[1] |= salt_buf1_t[1];
444 salt_buf1[2] |= salt_buf1_t[2];
445 salt_buf1[3] |= salt_buf1_t[3];
447 salt_buf2[0] |= salt_buf2_t[0];
448 salt_buf2[1] |= salt_buf2_t[1];
449 salt_buf2[2] |= salt_buf2_t[2];
450 salt_buf2[3] |= salt_buf2_t[3];
452 salt_buf3[0] |= salt_buf3_t[0];
453 salt_buf3[1] |= salt_buf3_t[1];
454 salt_buf3[2] |= salt_buf3_t[2];
455 salt_buf3[3] |= salt_buf3_t[3];
457 append_0x80_4 (salt_buf0, salt_buf1, salt_buf2, salt_buf3, pw_salt_len);
465 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
467 const u32 w0r = c_bfs[il_pos].i;
500 * put the password after the first salt but before the second salt
503 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
505 w0_t[0] |= salt_buf0[0];
506 w0_t[1] |= salt_buf0[1];
507 w0_t[2] |= salt_buf0[2];
508 w0_t[3] |= salt_buf0[3];
509 w1_t[0] |= salt_buf1[0];
510 w1_t[1] |= salt_buf1[1];
511 w1_t[2] |= salt_buf1[2];
512 w1_t[3] |= salt_buf1[3];
513 w2_t[0] |= salt_buf2[0];
514 w2_t[1] |= salt_buf2[1];
515 w2_t[2] |= salt_buf2[2];
516 w2_t[3] |= salt_buf2[3];
517 w3_t[0] |= salt_buf3[0];
518 w3_t[1] |= salt_buf3[1];
519 w3_t[2] |= salt_buf3[2];
521 u32x w0 = swap_workaround (w0_t[0]);
522 u32x w1 = swap_workaround (w0_t[1]);
523 u32x w2 = swap_workaround (w0_t[2]);
524 u32x w3 = swap_workaround (w0_t[3]);
525 u32x w4 = swap_workaround (w1_t[0]);
526 u32x w5 = swap_workaround (w1_t[1]);
527 u32x w6 = swap_workaround (w1_t[2]);
528 u32x w7 = swap_workaround (w1_t[3]);
529 u32x w8 = swap_workaround (w2_t[0]);
530 u32x w9 = swap_workaround (w2_t[1]);
531 u32x wa = swap_workaround (w2_t[2]);
532 u32x wb = swap_workaround (w2_t[3]);
533 u32x wc = swap_workaround (w3_t[0]);
534 u32x wd = swap_workaround (w3_t[1]);
535 u32x we = swap_workaround (w3_t[2]);
536 u32x wf = pw_salt_len * 8;
551 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0);
552 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1);
553 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2);
554 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3);
555 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4);
556 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5);
557 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6);
558 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7);
559 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8);
560 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9);
561 SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa);
562 SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb);
563 SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc);
564 SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd);
565 SHA1_STEP (SHA1_F0o, b, c, d, e, a, we);
566 SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf);
567 w0 = rotl32 ((wd ^ w8 ^ w2 ^ w0), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0);
568 w1 = rotl32 ((we ^ w9 ^ w3 ^ w1), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1);
569 w2 = rotl32 ((wf ^ wa ^ w4 ^ w2), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2);
570 w3 = rotl32 ((w0 ^ wb ^ w5 ^ w3), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3);
575 w4 = rotl32 ((w1 ^ wc ^ w6 ^ w4), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4);
576 w5 = rotl32 ((w2 ^ wd ^ w7 ^ w5), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5);
577 w6 = rotl32 ((w3 ^ we ^ w8 ^ w6), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6);
578 w7 = rotl32 ((w4 ^ wf ^ w9 ^ w7), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7);
579 w8 = rotl32 ((w5 ^ w0 ^ wa ^ w8), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8);
580 w9 = rotl32 ((w6 ^ w1 ^ wb ^ w9), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9);
581 wa = rotl32 ((w7 ^ w2 ^ wc ^ wa), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa);
582 wb = rotl32 ((w8 ^ w3 ^ wd ^ wb), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb);
583 wc = rotl32 ((w9 ^ w4 ^ we ^ wc), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc);
584 wd = rotl32 ((wa ^ w5 ^ wf ^ wd), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd);
585 we = rotl32 ((wb ^ w6 ^ w0 ^ we), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we);
586 wf = rotl32 ((wc ^ w7 ^ w1 ^ wf), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf);
587 w0 = rotl32 ((wd ^ w8 ^ w2 ^ w0), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0);
588 w1 = rotl32 ((we ^ w9 ^ w3 ^ w1), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1);
589 w2 = rotl32 ((wf ^ wa ^ w4 ^ w2), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2);
590 w3 = rotl32 ((w0 ^ wb ^ w5 ^ w3), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3);
591 w4 = rotl32 ((w1 ^ wc ^ w6 ^ w4), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4);
592 w5 = rotl32 ((w2 ^ wd ^ w7 ^ w5), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5);
593 w6 = rotl32 ((w3 ^ we ^ w8 ^ w6), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6);
594 w7 = rotl32 ((w4 ^ wf ^ w9 ^ w7), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7);
599 w8 = rotl32 ((w5 ^ w0 ^ wa ^ w8), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8);
600 w9 = rotl32 ((w6 ^ w1 ^ wb ^ w9), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9);
601 wa = rotl32 ((w7 ^ w2 ^ wc ^ wa), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa);
602 wb = rotl32 ((w8 ^ w3 ^ wd ^ wb), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb);
603 wc = rotl32 ((w9 ^ w4 ^ we ^ wc), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc);
604 wd = rotl32 ((wa ^ w5 ^ wf ^ wd), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd);
605 we = rotl32 ((wb ^ w6 ^ w0 ^ we), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we);
606 wf = rotl32 ((wc ^ w7 ^ w1 ^ wf), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf);
607 w0 = rotl32 ((wd ^ w8 ^ w2 ^ w0), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0);
608 w1 = rotl32 ((we ^ w9 ^ w3 ^ w1), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1);
609 w2 = rotl32 ((wf ^ wa ^ w4 ^ w2), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2);
610 w3 = rotl32 ((w0 ^ wb ^ w5 ^ w3), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3);
611 w4 = rotl32 ((w1 ^ wc ^ w6 ^ w4), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4);
612 w5 = rotl32 ((w2 ^ wd ^ w7 ^ w5), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5);
613 w6 = rotl32 ((w3 ^ we ^ w8 ^ w6), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6);
614 w7 = rotl32 ((w4 ^ wf ^ w9 ^ w7), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7);
615 w8 = rotl32 ((w5 ^ w0 ^ wa ^ w8), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8);
616 w9 = rotl32 ((w6 ^ w1 ^ wb ^ w9), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9);
617 wa = rotl32 ((w7 ^ w2 ^ wc ^ wa), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa);
618 wb = rotl32 ((w8 ^ w3 ^ wd ^ wb), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb);
623 wc = rotl32 ((w9 ^ w4 ^ we ^ wc), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc);
624 wd = rotl32 ((wa ^ w5 ^ wf ^ wd), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd);
625 we = rotl32 ((wb ^ w6 ^ w0 ^ we), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we);
626 wf = rotl32 ((wc ^ w7 ^ w1 ^ wf), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf);
627 w0 = rotl32 ((wd ^ w8 ^ w2 ^ w0), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0);
628 w1 = rotl32 ((we ^ w9 ^ w3 ^ w1), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1);
629 w2 = rotl32 ((wf ^ wa ^ w4 ^ w2), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2);
630 w3 = rotl32 ((w0 ^ wb ^ w5 ^ w3), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3);
631 w4 = rotl32 ((w1 ^ wc ^ w6 ^ w4), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4);
632 w5 = rotl32 ((w2 ^ wd ^ w7 ^ w5), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5);
633 w6 = rotl32 ((w3 ^ we ^ w8 ^ w6), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6);
634 w7 = rotl32 ((w4 ^ wf ^ w9 ^ w7), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7);
635 w8 = rotl32 ((w5 ^ w0 ^ wa ^ w8), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8);
636 w9 = rotl32 ((w6 ^ w1 ^ wb ^ w9), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9);
637 wa = rotl32 ((w7 ^ w2 ^ wc ^ wa), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa);
638 wb = rotl32 ((w8 ^ w3 ^ wd ^ wb), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb);
640 if (e != e_rev) continue;
642 wc = rotl32 ((w9 ^ w4 ^ we ^ wc), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc);
643 wd = rotl32 ((wa ^ w5 ^ wf ^ wd), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd);
644 we = rotl32 ((wb ^ w6 ^ w0 ^ we), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we);
645 wf = rotl32 ((wc ^ w7 ^ w1 ^ wf), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf);
652 #include VECT_COMPARE_S
656 extern "C" __global__ void __launch_bounds__ (256, 1) m04900_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)
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];
691 w3[2] = pws[gid].i[14];
694 const u32 pw_len = pws[gid].pw_len;
700 m04900m (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) m04900_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)
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];
722 w1[0] = pws[gid].i[ 4];
723 w1[1] = pws[gid].i[ 5];
724 w1[2] = pws[gid].i[ 6];
725 w1[3] = pws[gid].i[ 7];
738 w3[2] = pws[gid].i[14];
741 const u32 pw_len = pws[gid].pw_len;
747 m04900m (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) m04900_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)
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];
776 w2[0] = pws[gid].i[ 8];
777 w2[1] = pws[gid].i[ 9];
778 w2[2] = pws[gid].i[10];
779 w2[3] = pws[gid].i[11];
783 w3[0] = pws[gid].i[12];
784 w3[1] = pws[gid].i[13];
785 w3[2] = pws[gid].i[14];
786 w3[3] = pws[gid].i[15];
788 const u32 pw_len = pws[gid].pw_len;
794 m04900m (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) m04900_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)
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];
832 w3[2] = pws[gid].i[14];
835 const u32 pw_len = pws[gid].pw_len;
841 m04900s (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);
844 extern "C" __global__ void __launch_bounds__ (256, 1) m04900_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)
850 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
852 if (gid >= gid_max) return;
856 w0[0] = pws[gid].i[ 0];
857 w0[1] = pws[gid].i[ 1];
858 w0[2] = pws[gid].i[ 2];
859 w0[3] = pws[gid].i[ 3];
863 w1[0] = pws[gid].i[ 4];
864 w1[1] = pws[gid].i[ 5];
865 w1[2] = pws[gid].i[ 6];
866 w1[3] = pws[gid].i[ 7];
879 w3[2] = pws[gid].i[14];
882 const u32 pw_len = pws[gid].pw_len;
888 m04900s (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);
891 extern "C" __global__ void __launch_bounds__ (256, 1) m04900_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)
897 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
899 if (gid >= gid_max) return;
903 w0[0] = pws[gid].i[ 0];
904 w0[1] = pws[gid].i[ 1];
905 w0[2] = pws[gid].i[ 2];
906 w0[3] = pws[gid].i[ 3];
910 w1[0] = pws[gid].i[ 4];
911 w1[1] = pws[gid].i[ 5];
912 w1[2] = pws[gid].i[ 6];
913 w1[3] = pws[gid].i[ 7];
917 w2[0] = pws[gid].i[ 8];
918 w2[1] = pws[gid].i[ 9];
919 w2[2] = pws[gid].i[10];
920 w2[3] = pws[gid].i[11];
924 w3[0] = pws[gid].i[12];
925 w3[1] = pws[gid].i[13];
926 w3[2] = pws[gid].i[14];
927 w3[3] = pws[gid].i[15];
929 const u32 pw_len = pws[gid].pw_len;
935 m04900s (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);