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 overwrite_at (u32x sw[16], const u32x w0, const u32 salt_len)
51 case 1: sw[0] = (sw[0] & 0xff000000) | (w0 >> 8);
52 sw[1] = (sw[1] & 0x00ffffff) | (w0 << 24);
54 case 2: sw[0] = (sw[0] & 0xffff0000) | (w0 >> 16);
55 sw[1] = (sw[1] & 0x0000ffff) | (w0 << 16);
57 case 3: sw[0] = (sw[0] & 0xffffff00) | (w0 >> 24);
58 sw[1] = (sw[1] & 0x000000ff) | (w0 << 8);
62 case 5: sw[1] = (sw[1] & 0xff000000) | (w0 >> 8);
63 sw[2] = (sw[2] & 0x00ffffff) | (w0 << 24);
65 case 6: sw[1] = (sw[1] & 0xffff0000) | (w0 >> 16);
66 sw[2] = (sw[2] & 0x0000ffff) | (w0 << 16);
68 case 7: sw[1] = (sw[1] & 0xffffff00) | (w0 >> 24);
69 sw[2] = (sw[2] & 0x000000ff) | (w0 << 8);
73 case 9: sw[2] = (sw[2] & 0xff000000) | (w0 >> 8);
74 sw[3] = (sw[3] & 0x00ffffff) | (w0 << 24);
76 case 10: sw[2] = (sw[2] & 0xffff0000) | (w0 >> 16);
77 sw[3] = (sw[3] & 0x0000ffff) | (w0 << 16);
79 case 11: sw[2] = (sw[2] & 0xffffff00) | (w0 >> 24);
80 sw[3] = (sw[3] & 0x000000ff) | (w0 << 8);
84 case 13: sw[3] = (sw[3] & 0xff000000) | (w0 >> 8);
85 sw[4] = (sw[4] & 0x00ffffff) | (w0 << 24);
87 case 14: sw[3] = (sw[3] & 0xffff0000) | (w0 >> 16);
88 sw[4] = (sw[4] & 0x0000ffff) | (w0 << 16);
90 case 15: sw[3] = (sw[3] & 0xffffff00) | (w0 >> 24);
91 sw[4] = (sw[4] & 0x000000ff) | (w0 << 8);
95 case 17: sw[4] = (sw[4] & 0xff000000) | (w0 >> 8);
96 sw[5] = (sw[5] & 0x00ffffff) | (w0 << 24);
98 case 18: sw[4] = (sw[4] & 0xffff0000) | (w0 >> 16);
99 sw[5] = (sw[5] & 0x0000ffff) | (w0 << 16);
101 case 19: sw[4] = (sw[4] & 0xffffff00) | (w0 >> 24);
102 sw[5] = (sw[5] & 0x000000ff) | (w0 << 8);
106 case 21: sw[5] = (sw[5] & 0xff000000) | (w0 >> 8);
107 sw[6] = (sw[6] & 0x00ffffff) | (w0 << 24);
109 case 22: sw[5] = (sw[5] & 0xffff0000) | (w0 >> 16);
110 sw[6] = (sw[6] & 0x0000ffff) | (w0 << 16);
112 case 23: sw[5] = (sw[5] & 0xffffff00) | (w0 >> 24);
113 sw[6] = (sw[6] & 0x000000ff) | (w0 << 8);
117 case 25: sw[6] = (sw[6] & 0xff000000) | (w0 >> 8);
118 sw[7] = (sw[7] & 0x00ffffff) | (w0 << 24);
120 case 26: sw[6] = (sw[6] & 0xffff0000) | (w0 >> 16);
121 sw[7] = (sw[7] & 0x0000ffff) | (w0 << 16);
123 case 27: sw[6] = (sw[6] & 0xffffff00) | (w0 >> 24);
124 sw[7] = (sw[7] & 0x000000ff) | (w0 << 8);
128 case 29: sw[7] = (sw[7] & 0xff000000) | (w0 >> 8);
129 sw[8] = (sw[8] & 0x00ffffff) | (w0 << 24);
131 case 30: sw[7] = (sw[7] & 0xffff0000) | (w0 >> 16);
132 sw[8] = (sw[8] & 0x0000ffff) | (w0 << 16);
134 case 31: sw[7] = (sw[7] & 0xffffff00) | (w0 >> 24);
135 sw[8] = (sw[8] & 0x000000ff) | (w0 << 8);
140 __device__ static void m00120m (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)
146 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
147 const u32 lid = threadIdx.x;
155 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
156 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
157 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
158 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
162 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
163 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
164 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
165 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
181 const u32 salt_len = salt_bufs[salt_pos].salt_len;
183 const u32 pw_salt_len = pw_len + salt_len;
194 w0_t[0] = swap_workaround (w0[0]);
195 w0_t[1] = swap_workaround (w0[1]);
196 w0_t[2] = swap_workaround (w0[2]);
197 w0_t[3] = swap_workaround (w0[3]);
198 w1_t[0] = swap_workaround (w1[0]);
199 w1_t[1] = swap_workaround (w1[1]);
200 w1_t[2] = swap_workaround (w1[2]);
201 w1_t[3] = swap_workaround (w1[3]);
202 w2_t[0] = swap_workaround (w2[0]);
203 w2_t[1] = swap_workaround (w2[1]);
204 w2_t[2] = swap_workaround (w2[2]);
205 w2_t[3] = swap_workaround (w2[3]);
206 w3_t[0] = swap_workaround (w3[0]);
207 w3_t[1] = swap_workaround (w3[1]);
208 w3_t[2] = swap_workaround (w3[2]);
209 w3_t[3] = swap_workaround (w3[3]);
211 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
213 w0_t[0] |= salt_buf0[0];
214 w0_t[1] |= salt_buf0[1];
215 w0_t[2] |= salt_buf0[2];
216 w0_t[3] |= salt_buf0[3];
217 w1_t[0] |= salt_buf1[0];
218 w1_t[1] |= salt_buf1[1];
219 w1_t[2] |= salt_buf1[2];
220 w1_t[3] |= salt_buf1[3];
221 w2_t[0] |= salt_buf2[0];
222 w2_t[1] |= salt_buf2[1];
223 w2_t[2] |= salt_buf2[2];
224 w2_t[3] |= salt_buf2[3];
225 w3_t[0] |= salt_buf3[0];
226 w3_t[1] |= salt_buf3[1];
227 w3_t[2] |= salt_buf3[2];
228 w3_t[3] |= salt_buf3[3];
230 w0_t[0] = swap_workaround (w0_t[0]);
231 w0_t[1] = swap_workaround (w0_t[1]);
232 w0_t[2] = swap_workaround (w0_t[2]);
233 w0_t[3] = swap_workaround (w0_t[3]);
234 w1_t[0] = swap_workaround (w1_t[0]);
235 w1_t[1] = swap_workaround (w1_t[1]);
236 w1_t[2] = swap_workaround (w1_t[2]);
237 w1_t[3] = swap_workaround (w1_t[3]);
238 w2_t[0] = swap_workaround (w2_t[0]);
239 w2_t[1] = swap_workaround (w2_t[1]);
240 w2_t[2] = swap_workaround (w2_t[2]);
241 w2_t[3] = swap_workaround (w2_t[3]);
242 w3_t[0] = swap_workaround (w3_t[0]);
243 w3_t[1] = swap_workaround (w3_t[1]);
244 w3_t[2] = swap_workaround (w3_t[2]);
245 w3_t[3] = swap_workaround (w3_t[3]);
253 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
255 const u32 w0r = c_bfs[il_pos].i;
257 const u32x w0n = w0l | w0r;
278 overwrite_at (wx, w0n, salt_len);
300 w3_t[3] = pw_salt_len * 8;
315 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t[0]);
316 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t[1]);
317 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w0_t[2]);
318 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w0_t[3]);
319 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w1_t[0]);
320 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w1_t[1]);
321 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t[2]);
322 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t[3]);
323 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t[0]);
324 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w2_t[1]);
325 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w2_t[2]);
326 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w2_t[3]);
327 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w3_t[0]);
328 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t[1]);
329 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t[2]);
330 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w3_t[3]);
331 w0_t[0] = rotl32 ((w3_t[1] ^ w2_t[0] ^ w0_t[2] ^ w0_t[0]), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t[0]);
332 w0_t[1] = rotl32 ((w3_t[2] ^ w2_t[1] ^ w0_t[3] ^ w0_t[1]), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w0_t[1]);
333 w0_t[2] = rotl32 ((w3_t[3] ^ w2_t[2] ^ w1_t[0] ^ w0_t[2]), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w0_t[2]);
334 w0_t[3] = rotl32 ((w0_t[0] ^ w2_t[3] ^ w1_t[1] ^ w0_t[3]), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w0_t[3]);
339 w1_t[0] = rotl32 ((w0_t[1] ^ w3_t[0] ^ w1_t[2] ^ w1_t[0]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t[0]);
340 w1_t[1] = rotl32 ((w0_t[2] ^ w3_t[1] ^ w1_t[3] ^ w1_t[1]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w1_t[1]);
341 w1_t[2] = rotl32 ((w0_t[3] ^ w3_t[2] ^ w2_t[0] ^ w1_t[2]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w1_t[2]);
342 w1_t[3] = rotl32 ((w1_t[0] ^ w3_t[3] ^ w2_t[1] ^ w1_t[3]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t[3]);
343 w2_t[0] = rotl32 ((w1_t[1] ^ w0_t[0] ^ w2_t[2] ^ w2_t[0]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t[0]);
344 w2_t[1] = rotl32 ((w1_t[2] ^ w0_t[1] ^ w2_t[3] ^ w2_t[1]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w2_t[1]);
345 w2_t[2] = rotl32 ((w1_t[3] ^ w0_t[2] ^ w3_t[0] ^ w2_t[2]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t[2]);
346 w2_t[3] = rotl32 ((w2_t[0] ^ w0_t[3] ^ w3_t[1] ^ w2_t[3]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w2_t[3]);
347 w3_t[0] = rotl32 ((w2_t[1] ^ w1_t[0] ^ w3_t[2] ^ w3_t[0]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w3_t[0]);
348 w3_t[1] = rotl32 ((w2_t[2] ^ w1_t[1] ^ w3_t[3] ^ w3_t[1]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w3_t[1]);
349 w3_t[2] = rotl32 ((w2_t[3] ^ w1_t[2] ^ w0_t[0] ^ w3_t[2]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t[2]);
350 w3_t[3] = rotl32 ((w3_t[0] ^ w1_t[3] ^ w0_t[1] ^ w3_t[3]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w3_t[3]);
351 w0_t[0] = rotl32 ((w3_t[1] ^ w2_t[0] ^ w0_t[2] ^ w0_t[0]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t[0]);
352 w0_t[1] = rotl32 ((w3_t[2] ^ w2_t[1] ^ w0_t[3] ^ w0_t[1]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w0_t[1]);
353 w0_t[2] = rotl32 ((w3_t[3] ^ w2_t[2] ^ w1_t[0] ^ w0_t[2]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t[2]);
354 w0_t[3] = rotl32 ((w0_t[0] ^ w2_t[3] ^ w1_t[1] ^ w0_t[3]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w0_t[3]);
355 w1_t[0] = rotl32 ((w0_t[1] ^ w3_t[0] ^ w1_t[2] ^ w1_t[0]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w1_t[0]);
356 w1_t[1] = rotl32 ((w0_t[2] ^ w3_t[1] ^ w1_t[3] ^ w1_t[1]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w1_t[1]);
357 w1_t[2] = rotl32 ((w0_t[3] ^ w3_t[2] ^ w2_t[0] ^ w1_t[2]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t[2]);
358 w1_t[3] = rotl32 ((w1_t[0] ^ w3_t[3] ^ w2_t[1] ^ w1_t[3]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w1_t[3]);
363 w2_t[0] = rotl32 ((w1_t[1] ^ w0_t[0] ^ w2_t[2] ^ w2_t[0]), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t[0]);
364 w2_t[1] = rotl32 ((w1_t[2] ^ w0_t[1] ^ w2_t[3] ^ w2_t[1]), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w2_t[1]);
365 w2_t[2] = rotl32 ((w1_t[3] ^ w0_t[2] ^ w3_t[0] ^ w2_t[2]), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w2_t[2]);
366 w2_t[3] = rotl32 ((w2_t[0] ^ w0_t[3] ^ w3_t[1] ^ w2_t[3]), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w2_t[3]);
367 w3_t[0] = rotl32 ((w2_t[1] ^ w1_t[0] ^ w3_t[2] ^ w3_t[0]), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w3_t[0]);
368 w3_t[1] = rotl32 ((w2_t[2] ^ w1_t[1] ^ w3_t[3] ^ w3_t[1]), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w3_t[1]);
369 w3_t[2] = rotl32 ((w2_t[3] ^ w1_t[2] ^ w0_t[0] ^ w3_t[2]), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t[2]);
370 w3_t[3] = rotl32 ((w3_t[0] ^ w1_t[3] ^ w0_t[1] ^ w3_t[3]), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w3_t[3]);
371 w0_t[0] = rotl32 ((w3_t[1] ^ w2_t[0] ^ w0_t[2] ^ w0_t[0]), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t[0]);
372 w0_t[1] = rotl32 ((w3_t[2] ^ w2_t[1] ^ w0_t[3] ^ w0_t[1]), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w0_t[1]);
373 w0_t[2] = rotl32 ((w3_t[3] ^ w2_t[2] ^ w1_t[0] ^ w0_t[2]), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w0_t[2]);
374 w0_t[3] = rotl32 ((w0_t[0] ^ w2_t[3] ^ w1_t[1] ^ w0_t[3]), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w0_t[3]);
375 w1_t[0] = rotl32 ((w0_t[1] ^ w3_t[0] ^ w1_t[2] ^ w1_t[0]), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w1_t[0]);
376 w1_t[1] = rotl32 ((w0_t[2] ^ w3_t[1] ^ w1_t[3] ^ w1_t[1]), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w1_t[1]);
377 w1_t[2] = rotl32 ((w0_t[3] ^ w3_t[2] ^ w2_t[0] ^ w1_t[2]), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t[2]);
378 w1_t[3] = rotl32 ((w1_t[0] ^ w3_t[3] ^ w2_t[1] ^ w1_t[3]), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w1_t[3]);
379 w2_t[0] = rotl32 ((w1_t[1] ^ w0_t[0] ^ w2_t[2] ^ w2_t[0]), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w2_t[0]);
380 w2_t[1] = rotl32 ((w1_t[2] ^ w0_t[1] ^ w2_t[3] ^ w2_t[1]), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w2_t[1]);
381 w2_t[2] = rotl32 ((w1_t[3] ^ w0_t[2] ^ w3_t[0] ^ w2_t[2]), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w2_t[2]);
382 w2_t[3] = rotl32 ((w2_t[0] ^ w0_t[3] ^ w3_t[1] ^ w2_t[3]), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w2_t[3]);
387 w3_t[0] = rotl32 ((w2_t[1] ^ w1_t[0] ^ w3_t[2] ^ w3_t[0]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t[0]);
388 w3_t[1] = rotl32 ((w2_t[2] ^ w1_t[1] ^ w3_t[3] ^ w3_t[1]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w3_t[1]);
389 w3_t[2] = rotl32 ((w2_t[3] ^ w1_t[2] ^ w0_t[0] ^ w3_t[2]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t[2]);
390 w3_t[3] = rotl32 ((w3_t[0] ^ w1_t[3] ^ w0_t[1] ^ w3_t[3]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w3_t[3]);
391 w0_t[0] = rotl32 ((w3_t[1] ^ w2_t[0] ^ w0_t[2] ^ w0_t[0]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t[0]);
392 w0_t[1] = rotl32 ((w3_t[2] ^ w2_t[1] ^ w0_t[3] ^ w0_t[1]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w0_t[1]);
393 w0_t[2] = rotl32 ((w3_t[3] ^ w2_t[2] ^ w1_t[0] ^ w0_t[2]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w0_t[2]);
394 w0_t[3] = rotl32 ((w0_t[0] ^ w2_t[3] ^ w1_t[1] ^ w0_t[3]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t[3]);
395 w1_t[0] = rotl32 ((w0_t[1] ^ w3_t[0] ^ w1_t[2] ^ w1_t[0]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t[0]);
396 w1_t[1] = rotl32 ((w0_t[2] ^ w3_t[1] ^ w1_t[3] ^ w1_t[1]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w1_t[1]);
397 w1_t[2] = rotl32 ((w0_t[3] ^ w3_t[2] ^ w2_t[0] ^ w1_t[2]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t[2]);
398 w1_t[3] = rotl32 ((w1_t[0] ^ w3_t[3] ^ w2_t[1] ^ w1_t[3]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w1_t[3]);
399 w2_t[0] = rotl32 ((w1_t[1] ^ w0_t[0] ^ w2_t[2] ^ w2_t[0]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w2_t[0]);
400 w2_t[1] = rotl32 ((w1_t[2] ^ w0_t[1] ^ w2_t[3] ^ w2_t[1]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w2_t[1]);
401 w2_t[2] = rotl32 ((w1_t[3] ^ w0_t[2] ^ w3_t[0] ^ w2_t[2]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t[2]);
402 w2_t[3] = rotl32 ((w2_t[0] ^ w0_t[3] ^ w3_t[1] ^ w2_t[3]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w2_t[3]);
403 w3_t[0] = rotl32 ((w2_t[1] ^ w1_t[0] ^ w3_t[2] ^ w3_t[0]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w3_t[0]);
404 w3_t[1] = rotl32 ((w2_t[2] ^ w1_t[1] ^ w3_t[3] ^ w3_t[1]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t[1]);
405 w3_t[2] = rotl32 ((w2_t[3] ^ w1_t[2] ^ w0_t[0] ^ w3_t[2]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w3_t[2]);
406 w3_t[3] = rotl32 ((w3_t[0] ^ w1_t[3] ^ w0_t[1] ^ w3_t[3]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w3_t[3]);
413 #include VECT_COMPARE_M
417 __device__ static void m00120s (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)
423 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
424 const u32 lid = threadIdx.x;
430 const u32 search[4] =
432 digests_buf[digests_offset].digest_buf[DGST_R0],
433 digests_buf[digests_offset].digest_buf[DGST_R1],
434 digests_buf[digests_offset].digest_buf[DGST_R2],
435 digests_buf[digests_offset].digest_buf[DGST_R3]
442 const u32 e_rev = rotl32 (search[1], 2u);
450 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
451 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
452 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
453 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
457 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
458 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
459 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
460 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
476 const u32 salt_len = salt_bufs[salt_pos].salt_len;
478 const u32 pw_salt_len = pw_len + salt_len;
489 w0_t[0] = swap_workaround (w0[0]);
490 w0_t[1] = swap_workaround (w0[1]);
491 w0_t[2] = swap_workaround (w0[2]);
492 w0_t[3] = swap_workaround (w0[3]);
493 w1_t[0] = swap_workaround (w1[0]);
494 w1_t[1] = swap_workaround (w1[1]);
495 w1_t[2] = swap_workaround (w1[2]);
496 w1_t[3] = swap_workaround (w1[3]);
497 w2_t[0] = swap_workaround (w2[0]);
498 w2_t[1] = swap_workaround (w2[1]);
499 w2_t[2] = swap_workaround (w2[2]);
500 w2_t[3] = swap_workaround (w2[3]);
501 w3_t[0] = swap_workaround (w3[0]);
502 w3_t[1] = swap_workaround (w3[1]);
503 w3_t[2] = swap_workaround (w3[2]);
504 w3_t[3] = swap_workaround (w3[3]);
506 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, salt_len);
508 w0_t[0] |= salt_buf0[0];
509 w0_t[1] |= salt_buf0[1];
510 w0_t[2] |= salt_buf0[2];
511 w0_t[3] |= salt_buf0[3];
512 w1_t[0] |= salt_buf1[0];
513 w1_t[1] |= salt_buf1[1];
514 w1_t[2] |= salt_buf1[2];
515 w1_t[3] |= salt_buf1[3];
516 w2_t[0] |= salt_buf2[0];
517 w2_t[1] |= salt_buf2[1];
518 w2_t[2] |= salt_buf2[2];
519 w2_t[3] |= salt_buf2[3];
520 w3_t[0] |= salt_buf3[0];
521 w3_t[1] |= salt_buf3[1];
522 w3_t[2] |= salt_buf3[2];
523 w3_t[3] |= salt_buf3[3];
525 w0_t[0] = swap_workaround (w0_t[0]);
526 w0_t[1] = swap_workaround (w0_t[1]);
527 w0_t[2] = swap_workaround (w0_t[2]);
528 w0_t[3] = swap_workaround (w0_t[3]);
529 w1_t[0] = swap_workaround (w1_t[0]);
530 w1_t[1] = swap_workaround (w1_t[1]);
531 w1_t[2] = swap_workaround (w1_t[2]);
532 w1_t[3] = swap_workaround (w1_t[3]);
533 w2_t[0] = swap_workaround (w2_t[0]);
534 w2_t[1] = swap_workaround (w2_t[1]);
535 w2_t[2] = swap_workaround (w2_t[2]);
536 w2_t[3] = swap_workaround (w2_t[3]);
537 w3_t[0] = swap_workaround (w3_t[0]);
538 w3_t[1] = swap_workaround (w3_t[1]);
539 w3_t[2] = swap_workaround (w3_t[2]);
540 w3_t[3] = swap_workaround (w3_t[3]);
548 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
550 const u32 w0r = c_bfs[il_pos].i;
552 const u32x w0n = w0l | w0r;
573 overwrite_at (wx, w0n, salt_len);
595 w3_t[3] = pw_salt_len * 8;
610 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t[0]);
611 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t[1]);
612 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w0_t[2]);
613 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w0_t[3]);
614 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w1_t[0]);
615 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w1_t[1]);
616 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t[2]);
617 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t[3]);
618 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t[0]);
619 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w2_t[1]);
620 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w2_t[2]);
621 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w2_t[3]);
622 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w3_t[0]);
623 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t[1]);
624 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t[2]);
625 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w3_t[3]);
626 w0_t[0] = rotl32 ((w3_t[1] ^ w2_t[0] ^ w0_t[2] ^ w0_t[0]), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t[0]);
627 w0_t[1] = rotl32 ((w3_t[2] ^ w2_t[1] ^ w0_t[3] ^ w0_t[1]), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w0_t[1]);
628 w0_t[2] = rotl32 ((w3_t[3] ^ w2_t[2] ^ w1_t[0] ^ w0_t[2]), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w0_t[2]);
629 w0_t[3] = rotl32 ((w0_t[0] ^ w2_t[3] ^ w1_t[1] ^ w0_t[3]), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w0_t[3]);
634 w1_t[0] = rotl32 ((w0_t[1] ^ w3_t[0] ^ w1_t[2] ^ w1_t[0]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t[0]);
635 w1_t[1] = rotl32 ((w0_t[2] ^ w3_t[1] ^ w1_t[3] ^ w1_t[1]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w1_t[1]);
636 w1_t[2] = rotl32 ((w0_t[3] ^ w3_t[2] ^ w2_t[0] ^ w1_t[2]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w1_t[2]);
637 w1_t[3] = rotl32 ((w1_t[0] ^ w3_t[3] ^ w2_t[1] ^ w1_t[3]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t[3]);
638 w2_t[0] = rotl32 ((w1_t[1] ^ w0_t[0] ^ w2_t[2] ^ w2_t[0]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t[0]);
639 w2_t[1] = rotl32 ((w1_t[2] ^ w0_t[1] ^ w2_t[3] ^ w2_t[1]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w2_t[1]);
640 w2_t[2] = rotl32 ((w1_t[3] ^ w0_t[2] ^ w3_t[0] ^ w2_t[2]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t[2]);
641 w2_t[3] = rotl32 ((w2_t[0] ^ w0_t[3] ^ w3_t[1] ^ w2_t[3]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w2_t[3]);
642 w3_t[0] = rotl32 ((w2_t[1] ^ w1_t[0] ^ w3_t[2] ^ w3_t[0]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w3_t[0]);
643 w3_t[1] = rotl32 ((w2_t[2] ^ w1_t[1] ^ w3_t[3] ^ w3_t[1]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w3_t[1]);
644 w3_t[2] = rotl32 ((w2_t[3] ^ w1_t[2] ^ w0_t[0] ^ w3_t[2]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t[2]);
645 w3_t[3] = rotl32 ((w3_t[0] ^ w1_t[3] ^ w0_t[1] ^ w3_t[3]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w3_t[3]);
646 w0_t[0] = rotl32 ((w3_t[1] ^ w2_t[0] ^ w0_t[2] ^ w0_t[0]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t[0]);
647 w0_t[1] = rotl32 ((w3_t[2] ^ w2_t[1] ^ w0_t[3] ^ w0_t[1]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w0_t[1]);
648 w0_t[2] = rotl32 ((w3_t[3] ^ w2_t[2] ^ w1_t[0] ^ w0_t[2]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t[2]);
649 w0_t[3] = rotl32 ((w0_t[0] ^ w2_t[3] ^ w1_t[1] ^ w0_t[3]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w0_t[3]);
650 w1_t[0] = rotl32 ((w0_t[1] ^ w3_t[0] ^ w1_t[2] ^ w1_t[0]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w1_t[0]);
651 w1_t[1] = rotl32 ((w0_t[2] ^ w3_t[1] ^ w1_t[3] ^ w1_t[1]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w1_t[1]);
652 w1_t[2] = rotl32 ((w0_t[3] ^ w3_t[2] ^ w2_t[0] ^ w1_t[2]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t[2]);
653 w1_t[3] = rotl32 ((w1_t[0] ^ w3_t[3] ^ w2_t[1] ^ w1_t[3]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w1_t[3]);
658 w2_t[0] = rotl32 ((w1_t[1] ^ w0_t[0] ^ w2_t[2] ^ w2_t[0]), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t[0]);
659 w2_t[1] = rotl32 ((w1_t[2] ^ w0_t[1] ^ w2_t[3] ^ w2_t[1]), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w2_t[1]);
660 w2_t[2] = rotl32 ((w1_t[3] ^ w0_t[2] ^ w3_t[0] ^ w2_t[2]), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w2_t[2]);
661 w2_t[3] = rotl32 ((w2_t[0] ^ w0_t[3] ^ w3_t[1] ^ w2_t[3]), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w2_t[3]);
662 w3_t[0] = rotl32 ((w2_t[1] ^ w1_t[0] ^ w3_t[2] ^ w3_t[0]), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w3_t[0]);
663 w3_t[1] = rotl32 ((w2_t[2] ^ w1_t[1] ^ w3_t[3] ^ w3_t[1]), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w3_t[1]);
664 w3_t[2] = rotl32 ((w2_t[3] ^ w1_t[2] ^ w0_t[0] ^ w3_t[2]), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t[2]);
665 w3_t[3] = rotl32 ((w3_t[0] ^ w1_t[3] ^ w0_t[1] ^ w3_t[3]), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w3_t[3]);
666 w0_t[0] = rotl32 ((w3_t[1] ^ w2_t[0] ^ w0_t[2] ^ w0_t[0]), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t[0]);
667 w0_t[1] = rotl32 ((w3_t[2] ^ w2_t[1] ^ w0_t[3] ^ w0_t[1]), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w0_t[1]);
668 w0_t[2] = rotl32 ((w3_t[3] ^ w2_t[2] ^ w1_t[0] ^ w0_t[2]), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w0_t[2]);
669 w0_t[3] = rotl32 ((w0_t[0] ^ w2_t[3] ^ w1_t[1] ^ w0_t[3]), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w0_t[3]);
670 w1_t[0] = rotl32 ((w0_t[1] ^ w3_t[0] ^ w1_t[2] ^ w1_t[0]), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w1_t[0]);
671 w1_t[1] = rotl32 ((w0_t[2] ^ w3_t[1] ^ w1_t[3] ^ w1_t[1]), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w1_t[1]);
672 w1_t[2] = rotl32 ((w0_t[3] ^ w3_t[2] ^ w2_t[0] ^ w1_t[2]), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t[2]);
673 w1_t[3] = rotl32 ((w1_t[0] ^ w3_t[3] ^ w2_t[1] ^ w1_t[3]), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w1_t[3]);
674 w2_t[0] = rotl32 ((w1_t[1] ^ w0_t[0] ^ w2_t[2] ^ w2_t[0]), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w2_t[0]);
675 w2_t[1] = rotl32 ((w1_t[2] ^ w0_t[1] ^ w2_t[3] ^ w2_t[1]), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w2_t[1]);
676 w2_t[2] = rotl32 ((w1_t[3] ^ w0_t[2] ^ w3_t[0] ^ w2_t[2]), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w2_t[2]);
677 w2_t[3] = rotl32 ((w2_t[0] ^ w0_t[3] ^ w3_t[1] ^ w2_t[3]), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w2_t[3]);
682 w3_t[0] = rotl32 ((w2_t[1] ^ w1_t[0] ^ w3_t[2] ^ w3_t[0]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t[0]);
683 w3_t[1] = rotl32 ((w2_t[2] ^ w1_t[1] ^ w3_t[3] ^ w3_t[1]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w3_t[1]);
684 w3_t[2] = rotl32 ((w2_t[3] ^ w1_t[2] ^ w0_t[0] ^ w3_t[2]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t[2]);
685 w3_t[3] = rotl32 ((w3_t[0] ^ w1_t[3] ^ w0_t[1] ^ w3_t[3]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w3_t[3]);
686 w0_t[0] = rotl32 ((w3_t[1] ^ w2_t[0] ^ w0_t[2] ^ w0_t[0]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t[0]);
687 w0_t[1] = rotl32 ((w3_t[2] ^ w2_t[1] ^ w0_t[3] ^ w0_t[1]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w0_t[1]);
688 w0_t[2] = rotl32 ((w3_t[3] ^ w2_t[2] ^ w1_t[0] ^ w0_t[2]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w0_t[2]);
689 w0_t[3] = rotl32 ((w0_t[0] ^ w2_t[3] ^ w1_t[1] ^ w0_t[3]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t[3]);
690 w1_t[0] = rotl32 ((w0_t[1] ^ w3_t[0] ^ w1_t[2] ^ w1_t[0]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t[0]);
691 w1_t[1] = rotl32 ((w0_t[2] ^ w3_t[1] ^ w1_t[3] ^ w1_t[1]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w1_t[1]);
692 w1_t[2] = rotl32 ((w0_t[3] ^ w3_t[2] ^ w2_t[0] ^ w1_t[2]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t[2]);
693 w1_t[3] = rotl32 ((w1_t[0] ^ w3_t[3] ^ w2_t[1] ^ w1_t[3]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w1_t[3]);
694 w2_t[0] = rotl32 ((w1_t[1] ^ w0_t[0] ^ w2_t[2] ^ w2_t[0]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w2_t[0]);
695 w2_t[1] = rotl32 ((w1_t[2] ^ w0_t[1] ^ w2_t[3] ^ w2_t[1]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w2_t[1]);
696 w2_t[2] = rotl32 ((w1_t[3] ^ w0_t[2] ^ w3_t[0] ^ w2_t[2]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t[2]);
697 w2_t[3] = rotl32 ((w2_t[0] ^ w0_t[3] ^ w3_t[1] ^ w2_t[3]), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w2_t[3]);
698 w3_t[0] = rotl32 ((w2_t[1] ^ w1_t[0] ^ w3_t[2] ^ w3_t[0]), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w3_t[0]);
700 if (e != e_rev) continue;
702 w3_t[1] = rotl32 ((w2_t[2] ^ w1_t[1] ^ w3_t[3] ^ w3_t[1]), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t[1]);
703 w3_t[2] = rotl32 ((w2_t[3] ^ w1_t[2] ^ w0_t[0] ^ w3_t[2]), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w3_t[2]);
704 w3_t[3] = rotl32 ((w3_t[0] ^ w1_t[3] ^ w0_t[1] ^ w3_t[3]), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w3_t[3]);
712 #include VECT_COMPARE_S
716 extern "C" __global__ void __launch_bounds__ (256, 1) m00120_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)
722 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
724 if (gid >= gid_max) return;
728 w0[0] = pws[gid].i[ 0];
729 w0[1] = pws[gid].i[ 1];
730 w0[2] = pws[gid].i[ 2];
731 w0[3] = pws[gid].i[ 3];
754 const u32 pw_len = pws[gid].pw_len;
760 m00120m (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);
763 extern "C" __global__ void __launch_bounds__ (256, 1) m00120_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)
769 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
771 if (gid >= gid_max) return;
775 w0[0] = pws[gid].i[ 0];
776 w0[1] = pws[gid].i[ 1];
777 w0[2] = pws[gid].i[ 2];
778 w0[3] = pws[gid].i[ 3];
782 w1[0] = pws[gid].i[ 4];
783 w1[1] = pws[gid].i[ 5];
784 w1[2] = pws[gid].i[ 6];
785 w1[3] = pws[gid].i[ 7];
801 const u32 pw_len = pws[gid].pw_len;
807 m00120m (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);
810 extern "C" __global__ void __launch_bounds__ (256, 1) m00120_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)
816 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
818 if (gid >= gid_max) return;
822 w0[0] = pws[gid].i[ 0];
823 w0[1] = pws[gid].i[ 1];
824 w0[2] = pws[gid].i[ 2];
825 w0[3] = pws[gid].i[ 3];
829 w1[0] = pws[gid].i[ 4];
830 w1[1] = pws[gid].i[ 5];
831 w1[2] = pws[gid].i[ 6];
832 w1[3] = pws[gid].i[ 7];
836 w2[0] = pws[gid].i[ 8];
837 w2[1] = pws[gid].i[ 9];
838 w2[2] = pws[gid].i[10];
839 w2[3] = pws[gid].i[11];
843 w3[0] = pws[gid].i[12];
844 w3[1] = pws[gid].i[13];
848 const u32 pw_len = pws[gid].pw_len;
854 m00120m (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);
857 extern "C" __global__ void __launch_bounds__ (256, 1) m00120_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)
863 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
865 if (gid >= gid_max) return;
869 w0[0] = pws[gid].i[ 0];
870 w0[1] = pws[gid].i[ 1];
871 w0[2] = pws[gid].i[ 2];
872 w0[3] = pws[gid].i[ 3];
895 const u32 pw_len = pws[gid].pw_len;
901 m00120s (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);
904 extern "C" __global__ void __launch_bounds__ (256, 1) m00120_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)
910 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
912 if (gid >= gid_max) return;
916 w0[0] = pws[gid].i[ 0];
917 w0[1] = pws[gid].i[ 1];
918 w0[2] = pws[gid].i[ 2];
919 w0[3] = pws[gid].i[ 3];
923 w1[0] = pws[gid].i[ 4];
924 w1[1] = pws[gid].i[ 5];
925 w1[2] = pws[gid].i[ 6];
926 w1[3] = pws[gid].i[ 7];
942 const u32 pw_len = pws[gid].pw_len;
948 m00120s (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);
951 extern "C" __global__ void __launch_bounds__ (256, 1) m00120_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)
957 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
959 if (gid >= gid_max) return;
963 w0[0] = pws[gid].i[ 0];
964 w0[1] = pws[gid].i[ 1];
965 w0[2] = pws[gid].i[ 2];
966 w0[3] = pws[gid].i[ 3];
970 w1[0] = pws[gid].i[ 4];
971 w1[1] = pws[gid].i[ 5];
972 w1[2] = pws[gid].i[ 6];
973 w1[3] = pws[gid].i[ 7];
977 w2[0] = pws[gid].i[ 8];
978 w2[1] = pws[gid].i[ 9];
979 w2[2] = pws[gid].i[10];
980 w2[3] = pws[gid].i[11];
984 w3[0] = pws[gid].i[12];
985 w3[1] = pws[gid].i[13];
989 const u32 pw_len = pws[gid].pw_len;
995 m00120s (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);