2 * Author......: Jens Steube <jens.steube@gmail.com>
9 #include "include/constants.h"
10 #include "include/kernel_vendor.h"
25 #include "include/kernel_functions.c"
27 #include "common_nv.c"
30 #define VECT_COMPARE_S "check_single_vect1_comp4_warp.c"
31 #define VECT_COMPARE_M "check_multi_vect1_comp4_warp.c"
35 #define VECT_COMPARE_S "check_single_vect2_comp4_warp.c"
36 #define VECT_COMPARE_M "check_multi_vect2_comp4_warp.c"
40 #define VECT_COMPARE_S "check_single_vect4_comp4_warp.c"
41 #define VECT_COMPARE_M "check_multi_vect4_comp4_warp.c"
44 #define MD4_STEP_REV(f,a,b,c,d,x,t,s) \
52 #define MD4_STEP_REV1(f,a,b,c,d,x,t,s) \
59 __device__ __constant__ u32x c_bfs[1024];
61 __device__ static void m01000m (u32 w[16], const u32 pw_len, const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x * words_buf_r, 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)
67 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
68 const u32 lid = threadIdx.x;
74 const u32 F_w0c00 = 0 + MD4C00;
75 const u32 F_w1c00 = w[ 1] + MD4C00;
76 const u32 F_w2c00 = w[ 2] + MD4C00;
77 const u32 F_w3c00 = w[ 3] + MD4C00;
78 const u32 F_w4c00 = w[ 4] + MD4C00;
79 const u32 F_w5c00 = w[ 5] + MD4C00;
80 const u32 F_w6c00 = w[ 6] + MD4C00;
81 const u32 F_w7c00 = w[ 7] + MD4C00;
82 const u32 F_w8c00 = w[ 8] + MD4C00;
83 const u32 F_w9c00 = w[ 9] + MD4C00;
84 const u32 F_wac00 = w[10] + MD4C00;
85 const u32 F_wbc00 = w[11] + MD4C00;
86 const u32 F_wcc00 = w[12] + MD4C00;
87 const u32 F_wdc00 = w[13] + MD4C00;
88 const u32 F_wec00 = w[14] + MD4C00;
89 const u32 F_wfc00 = w[15] + MD4C00;
91 const u32 G_w0c01 = 0 + MD4C01;
92 const u32 G_w4c01 = w[ 4] + MD4C01;
93 const u32 G_w8c01 = w[ 8] + MD4C01;
94 const u32 G_wcc01 = w[12] + MD4C01;
95 const u32 G_w1c01 = w[ 1] + MD4C01;
96 const u32 G_w5c01 = w[ 5] + MD4C01;
97 const u32 G_w9c01 = w[ 9] + MD4C01;
98 const u32 G_wdc01 = w[13] + MD4C01;
99 const u32 G_w2c01 = w[ 2] + MD4C01;
100 const u32 G_w6c01 = w[ 6] + MD4C01;
101 const u32 G_wac01 = w[10] + MD4C01;
102 const u32 G_wec01 = w[14] + MD4C01;
103 const u32 G_w3c01 = w[ 3] + MD4C01;
104 const u32 G_w7c01 = w[ 7] + MD4C01;
105 const u32 G_wbc01 = w[11] + MD4C01;
106 const u32 G_wfc01 = w[15] + MD4C01;
108 const u32 H_w0c02 = 0 + MD4C02;
109 const u32 H_w8c02 = w[ 8] + MD4C02;
110 const u32 H_w4c02 = w[ 4] + MD4C02;
111 const u32 H_wcc02 = w[12] + MD4C02;
112 const u32 H_w2c02 = w[ 2] + MD4C02;
113 const u32 H_wac02 = w[10] + MD4C02;
114 const u32 H_w6c02 = w[ 6] + MD4C02;
115 const u32 H_wec02 = w[14] + MD4C02;
116 const u32 H_w1c02 = w[ 1] + MD4C02;
117 const u32 H_w9c02 = w[ 9] + MD4C02;
118 const u32 H_w5c02 = w[ 5] + MD4C02;
119 const u32 H_wdc02 = w[13] + MD4C02;
120 const u32 H_w3c02 = w[ 3] + MD4C02;
121 const u32 H_wbc02 = w[11] + MD4C02;
122 const u32 H_w7c02 = w[ 7] + MD4C02;
123 const u32 H_wfc02 = w[15] + MD4C02;
129 const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
133 for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
135 const u32x w0r = c_bfs[il_pos];
137 const u32x w0 = w0l | w0r;
146 MD4_STEP (MD4_Fo, a, b, c, d, w0, F_w0c00, MD4S00);
147 MD4_STEP0(MD4_Fo, d, a, b, c, F_w1c00, MD4S01);
148 MD4_STEP0(MD4_Fo, c, d, a, b, F_w2c00, MD4S02);
149 MD4_STEP0(MD4_Fo, b, c, d, a, F_w3c00, MD4S03);
150 MD4_STEP0(MD4_Fo, a, b, c, d, F_w4c00, MD4S00);
151 MD4_STEP0(MD4_Fo, d, a, b, c, F_w5c00, MD4S01);
152 MD4_STEP0(MD4_Fo, c, d, a, b, F_w6c00, MD4S02);
153 MD4_STEP0(MD4_Fo, b, c, d, a, F_w7c00, MD4S03);
154 MD4_STEP0(MD4_Fo, a, b, c, d, F_w8c00, MD4S00);
155 MD4_STEP0(MD4_Fo, d, a, b, c, F_w9c00, MD4S01);
156 MD4_STEP0(MD4_Fo, c, d, a, b, F_wac00, MD4S02);
157 MD4_STEP0(MD4_Fo, b, c, d, a, F_wbc00, MD4S03);
158 MD4_STEP0(MD4_Fo, a, b, c, d, F_wcc00, MD4S00);
159 MD4_STEP0(MD4_Fo, d, a, b, c, F_wdc00, MD4S01);
160 MD4_STEP0(MD4_Fo, c, d, a, b, F_wec00, MD4S02);
161 MD4_STEP0(MD4_Fo, b, c, d, a, F_wfc00, MD4S03);
163 MD4_STEP (MD4_Go, a, b, c, d, w0, G_w0c01, MD4S10);
164 MD4_STEP0(MD4_Go, d, a, b, c, G_w4c01, MD4S11);
165 MD4_STEP0(MD4_Go, c, d, a, b, G_w8c01, MD4S12);
166 MD4_STEP0(MD4_Go, b, c, d, a, G_wcc01, MD4S13);
167 MD4_STEP0(MD4_Go, a, b, c, d, G_w1c01, MD4S10);
168 MD4_STEP0(MD4_Go, d, a, b, c, G_w5c01, MD4S11);
169 MD4_STEP0(MD4_Go, c, d, a, b, G_w9c01, MD4S12);
170 MD4_STEP0(MD4_Go, b, c, d, a, G_wdc01, MD4S13);
171 MD4_STEP0(MD4_Go, a, b, c, d, G_w2c01, MD4S10);
172 MD4_STEP0(MD4_Go, d, a, b, c, G_w6c01, MD4S11);
173 MD4_STEP0(MD4_Go, c, d, a, b, G_wac01, MD4S12);
174 MD4_STEP0(MD4_Go, b, c, d, a, G_wec01, MD4S13);
175 MD4_STEP0(MD4_Go, a, b, c, d, G_w3c01, MD4S10);
176 MD4_STEP0(MD4_Go, d, a, b, c, G_w7c01, MD4S11);
177 MD4_STEP0(MD4_Go, c, d, a, b, G_wbc01, MD4S12);
178 MD4_STEP0(MD4_Go, b, c, d, a, G_wfc01, MD4S13);
180 MD4_STEP (MD4_H1, a, b, c, d, w0, H_w0c02, MD4S20);
181 MD4_STEP0(MD4_H2, d, a, b, c, H_w8c02, MD4S21);
182 MD4_STEP0(MD4_H1, c, d, a, b, H_w4c02, MD4S22);
183 MD4_STEP0(MD4_H2, b, c, d, a, H_wcc02, MD4S23);
184 MD4_STEP0(MD4_H1, a, b, c, d, H_w2c02, MD4S20);
185 MD4_STEP0(MD4_H2, d, a, b, c, H_wac02, MD4S21);
186 MD4_STEP0(MD4_H1, c, d, a, b, H_w6c02, MD4S22);
187 MD4_STEP0(MD4_H2, b, c, d, a, H_wec02, MD4S23);
188 MD4_STEP0(MD4_H1, a, b, c, d, H_w1c02, MD4S20);
189 MD4_STEP0(MD4_H2, d, a, b, c, H_w9c02, MD4S21);
190 MD4_STEP0(MD4_H1, c, d, a, b, H_w5c02, MD4S22);
191 MD4_STEP0(MD4_H2, b, c, d, a, H_wdc02, MD4S23);
192 MD4_STEP0(MD4_H1, a, b, c, d, H_w3c02, MD4S20);
193 MD4_STEP0(MD4_H2, d, a, b, c, H_wbc02, MD4S21);
194 MD4_STEP0(MD4_H1, c, d, a, b, H_w7c02, MD4S22);
195 MD4_STEP0(MD4_H2, b, c, d, a, H_wfc02, MD4S23);
202 #include VECT_COMPARE_M
206 __device__ static void m01000s (u32 w[16], const u32 pw_len, const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x * words_buf_r, 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)
212 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
213 const u32 lid = threadIdx.x;
219 const u32 F_w0c00 = 0 + MD4C00;
220 const u32 F_w1c00 = w[ 1] + MD4C00;
221 const u32 F_w2c00 = w[ 2] + MD4C00;
222 const u32 F_w3c00 = w[ 3] + MD4C00;
223 const u32 F_w4c00 = w[ 4] + MD4C00;
224 const u32 F_w5c00 = w[ 5] + MD4C00;
225 const u32 F_w6c00 = w[ 6] + MD4C00;
226 const u32 F_w7c00 = w[ 7] + MD4C00;
227 const u32 F_w8c00 = w[ 8] + MD4C00;
228 const u32 F_w9c00 = w[ 9] + MD4C00;
229 const u32 F_wac00 = w[10] + MD4C00;
230 const u32 F_wbc00 = w[11] + MD4C00;
231 const u32 F_wcc00 = w[12] + MD4C00;
232 const u32 F_wdc00 = w[13] + MD4C00;
233 const u32 F_wec00 = w[14] + MD4C00;
234 const u32 F_wfc00 = w[15] + MD4C00;
236 const u32 G_w0c01 = 0 + MD4C01;
237 const u32 G_w4c01 = w[ 4] + MD4C01;
238 const u32 G_w8c01 = w[ 8] + MD4C01;
239 const u32 G_wcc01 = w[12] + MD4C01;
240 const u32 G_w1c01 = w[ 1] + MD4C01;
241 const u32 G_w5c01 = w[ 5] + MD4C01;
242 const u32 G_w9c01 = w[ 9] + MD4C01;
243 const u32 G_wdc01 = w[13] + MD4C01;
244 const u32 G_w2c01 = w[ 2] + MD4C01;
245 const u32 G_w6c01 = w[ 6] + MD4C01;
246 const u32 G_wac01 = w[10] + MD4C01;
247 const u32 G_wec01 = w[14] + MD4C01;
248 const u32 G_w3c01 = w[ 3] + MD4C01;
249 const u32 G_w7c01 = w[ 7] + MD4C01;
250 const u32 G_wbc01 = w[11] + MD4C01;
251 const u32 G_wfc01 = w[15] + MD4C01;
253 const u32 H_w0c02 = 0 + MD4C02;
254 const u32 H_w8c02 = w[ 8] + MD4C02;
255 const u32 H_w4c02 = w[ 4] + MD4C02;
256 const u32 H_wcc02 = w[12] + MD4C02;
257 const u32 H_w2c02 = w[ 2] + MD4C02;
258 const u32 H_wac02 = w[10] + MD4C02;
259 const u32 H_w6c02 = w[ 6] + MD4C02;
260 const u32 H_wec02 = w[14] + MD4C02;
261 const u32 H_w1c02 = w[ 1] + MD4C02;
262 const u32 H_w9c02 = w[ 9] + MD4C02;
263 const u32 H_w5c02 = w[ 5] + MD4C02;
264 const u32 H_wdc02 = w[13] + MD4C02;
265 const u32 H_w3c02 = w[ 3] + MD4C02;
266 const u32 H_wbc02 = w[11] + MD4C02;
267 const u32 H_w7c02 = w[ 7] + MD4C02;
268 const u32 H_wfc02 = w[15] + MD4C02;
274 const u32 search[4] =
276 digests_buf[digests_offset].digest_buf[DGST_R0],
277 digests_buf[digests_offset].digest_buf[DGST_R1],
278 digests_buf[digests_offset].digest_buf[DGST_R2],
279 digests_buf[digests_offset].digest_buf[DGST_R3]
286 u32 a_rev = digests_buf[digests_offset].digest_buf[0];
287 u32 b_rev = digests_buf[digests_offset].digest_buf[1];
288 u32 c_rev = digests_buf[digests_offset].digest_buf[2];
289 u32 d_rev = digests_buf[digests_offset].digest_buf[3];
291 MD4_STEP_REV (MD4_H, b_rev, c_rev, d_rev, a_rev, w[15], MD4C02, MD4S23);
292 MD4_STEP_REV (MD4_H, c_rev, d_rev, a_rev, b_rev, w[ 7], MD4C02, MD4S22);
293 MD4_STEP_REV (MD4_H, d_rev, a_rev, b_rev, c_rev, w[11], MD4C02, MD4S21);
294 MD4_STEP_REV (MD4_H, a_rev, b_rev, c_rev, d_rev, w[ 3], MD4C02, MD4S20);
295 MD4_STEP_REV (MD4_H, b_rev, c_rev, d_rev, a_rev, w[13], MD4C02, MD4S23);
296 MD4_STEP_REV (MD4_H, c_rev, d_rev, a_rev, b_rev, w[ 5], MD4C02, MD4S22);
297 MD4_STEP_REV (MD4_H, d_rev, a_rev, b_rev, c_rev, w[ 9], MD4C02, MD4S21);
298 MD4_STEP_REV (MD4_H, a_rev, b_rev, c_rev, d_rev, w[ 1], MD4C02, MD4S20);
299 MD4_STEP_REV (MD4_H, b_rev, c_rev, d_rev, a_rev, w[14], MD4C02, MD4S23);
300 MD4_STEP_REV (MD4_H, c_rev, d_rev, a_rev, b_rev, w[ 6], MD4C02, MD4S22);
301 MD4_STEP_REV (MD4_H, d_rev, a_rev, b_rev, c_rev, w[10], MD4C02, MD4S21);
302 MD4_STEP_REV (MD4_H, a_rev, b_rev, c_rev, d_rev, w[ 2], MD4C02, MD4S20);
303 MD4_STEP_REV (MD4_H, b_rev, c_rev, d_rev, a_rev, w[12], MD4C02, MD4S23);
304 MD4_STEP_REV (MD4_H, c_rev, d_rev, a_rev, b_rev, w[ 4], MD4C02, MD4S22);
305 MD4_STEP_REV (MD4_H, d_rev, a_rev, b_rev, c_rev, w[ 8], MD4C02, MD4S21);
306 MD4_STEP_REV (MD4_H, a_rev, b_rev, c_rev, d_rev, 0, MD4C02, MD4S20);
308 const u32x sav_c = c_rev;
309 const u32x sav_d = d_rev;
311 MD4_STEP_REV1(MD4_G, b_rev, c_rev, d_rev, a_rev, w[15], MD4C01, MD4S13);
312 MD4_STEP_REV1(MD4_G, c_rev, d_rev, a_rev, b_rev, w[11], MD4C01, MD4S12);
318 const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
322 for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
324 const u32x w0r = c_bfs[il_pos];
326 const u32x w0 = w0l | w0r;
333 pre_b = pre_b - MD4_G (sav_c, sav_d, pre_a);
334 pre_c = pre_c - MD4_G (sav_d, pre_a, pre_b);
343 MD4_STEP (MD4_Fo, a, b, c, d, w0, F_w0c00, MD4S00);
344 MD4_STEP0(MD4_Fo, d, a, b, c, F_w1c00, MD4S01);
345 MD4_STEP0(MD4_Fo, c, d, a, b, F_w2c00, MD4S02);
346 MD4_STEP0(MD4_Fo, b, c, d, a, F_w3c00, MD4S03);
347 MD4_STEP0(MD4_Fo, a, b, c, d, F_w4c00, MD4S00);
348 MD4_STEP0(MD4_Fo, d, a, b, c, F_w5c00, MD4S01);
349 MD4_STEP0(MD4_Fo, c, d, a, b, F_w6c00, MD4S02);
350 MD4_STEP0(MD4_Fo, b, c, d, a, F_w7c00, MD4S03);
351 MD4_STEP0(MD4_Fo, a, b, c, d, F_w8c00, MD4S00);
352 MD4_STEP0(MD4_Fo, d, a, b, c, F_w9c00, MD4S01);
353 MD4_STEP0(MD4_Fo, c, d, a, b, F_wac00, MD4S02);
354 MD4_STEP0(MD4_Fo, b, c, d, a, F_wbc00, MD4S03);
355 MD4_STEP0(MD4_Fo, a, b, c, d, F_wcc00, MD4S00);
356 MD4_STEP0(MD4_Fo, d, a, b, c, F_wdc00, MD4S01);
357 MD4_STEP0(MD4_Fo, c, d, a, b, F_wec00, MD4S02);
358 MD4_STEP0(MD4_Fo, b, c, d, a, F_wfc00, MD4S03);
360 MD4_STEP (MD4_Go, a, b, c, d, w0, G_w0c01, MD4S10);
361 MD4_STEP0(MD4_Go, d, a, b, c, G_w4c01, MD4S11);
362 MD4_STEP0(MD4_Go, c, d, a, b, G_w8c01, MD4S12);
363 MD4_STEP0(MD4_Go, b, c, d, a, G_wcc01, MD4S13);
364 MD4_STEP0(MD4_Go, a, b, c, d, G_w1c01, MD4S10);
365 MD4_STEP0(MD4_Go, d, a, b, c, G_w5c01, MD4S11);
366 MD4_STEP0(MD4_Go, c, d, a, b, G_w9c01, MD4S12);
367 MD4_STEP0(MD4_Go, b, c, d, a, G_wdc01, MD4S13);
368 MD4_STEP0(MD4_Go, a, b, c, d, G_w2c01, MD4S10);
369 MD4_STEP0(MD4_Go, d, a, b, c, G_w6c01, MD4S11);
370 MD4_STEP0(MD4_Go, c, d, a, b, G_wac01, MD4S12);
372 bool q_cond = (pre_c != c);
374 if (q_cond) continue;
376 MD4_STEP0(MD4_Go, b, c, d, a, G_wec01, MD4S13);
377 MD4_STEP0(MD4_Go, a, b, c, d, G_w3c01, MD4S10);
378 MD4_STEP0(MD4_Go, d, a, b, c, G_w7c01, MD4S11);
379 MD4_STEP0(MD4_Go, c, d, a, b, G_wbc01, MD4S12);
380 MD4_STEP0(MD4_Go, b, c, d, a, G_wfc01, MD4S13);
382 MD4_STEP (MD4_H1, a, b, c, d, w0, H_w0c02, MD4S20);
383 MD4_STEP0(MD4_H2, d, a, b, c, H_w8c02, MD4S21);
384 MD4_STEP0(MD4_H1, c, d, a, b, H_w4c02, MD4S22);
385 MD4_STEP0(MD4_H2, b, c, d, a, H_wcc02, MD4S23);
386 MD4_STEP0(MD4_H1, a, b, c, d, H_w2c02, MD4S20);
387 MD4_STEP0(MD4_H2, d, a, b, c, H_wac02, MD4S21);
388 MD4_STEP0(MD4_H1, c, d, a, b, H_w6c02, MD4S22);
389 MD4_STEP0(MD4_H2, b, c, d, a, H_wec02, MD4S23);
390 MD4_STEP0(MD4_H1, a, b, c, d, H_w1c02, MD4S20);
391 MD4_STEP0(MD4_H2, d, a, b, c, H_w9c02, MD4S21);
392 MD4_STEP0(MD4_H1, c, d, a, b, H_w5c02, MD4S22);
393 MD4_STEP0(MD4_H2, b, c, d, a, H_wdc02, MD4S23);
394 MD4_STEP0(MD4_H1, a, b, c, d, H_w3c02, MD4S20);
395 MD4_STEP0(MD4_H2, d, a, b, c, H_wbc02, MD4S21);
396 MD4_STEP0(MD4_H1, c, d, a, b, H_w7c02, MD4S22);
397 MD4_STEP0(MD4_H2, b, c, d, a, H_wfc02, MD4S23);
404 #include VECT_COMPARE_S
408 extern "C" __global__ void __launch_bounds__ (256, 1) m01000_m04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r,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)
414 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
416 if (gid >= gid_max) return;
420 w[ 0] = pws[gid].i[ 0];
421 w[ 1] = pws[gid].i[ 1];
422 w[ 2] = pws[gid].i[ 2];
423 w[ 3] = pws[gid].i[ 3];
434 w[14] = pws[gid].i[14];
437 const u32 pw_len = pws[gid].pw_len;
443 m01000m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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);
446 extern "C" __global__ void __launch_bounds__ (256, 1) m01000_m08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r,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)
452 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
454 if (gid >= gid_max) return;
458 w[ 0] = pws[gid].i[ 0];
459 w[ 1] = pws[gid].i[ 1];
460 w[ 2] = pws[gid].i[ 2];
461 w[ 3] = pws[gid].i[ 3];
462 w[ 4] = pws[gid].i[ 4];
463 w[ 5] = pws[gid].i[ 5];
464 w[ 6] = pws[gid].i[ 6];
465 w[ 7] = pws[gid].i[ 7];
472 w[14] = pws[gid].i[14];
475 const u32 pw_len = pws[gid].pw_len;
481 m01000m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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);
484 extern "C" __global__ void __launch_bounds__ (256, 1) m01000_m16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r,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)
490 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
492 if (gid >= gid_max) return;
496 w[ 0] = pws[gid].i[ 0];
497 w[ 1] = pws[gid].i[ 1];
498 w[ 2] = pws[gid].i[ 2];
499 w[ 3] = pws[gid].i[ 3];
500 w[ 4] = pws[gid].i[ 4];
501 w[ 5] = pws[gid].i[ 5];
502 w[ 6] = pws[gid].i[ 6];
503 w[ 7] = pws[gid].i[ 7];
504 w[ 8] = pws[gid].i[ 8];
505 w[ 9] = pws[gid].i[ 9];
506 w[10] = pws[gid].i[10];
507 w[11] = pws[gid].i[11];
508 w[12] = pws[gid].i[12];
509 w[13] = pws[gid].i[13];
510 w[14] = pws[gid].i[14];
511 w[15] = pws[gid].i[15];
513 const u32 pw_len = pws[gid].pw_len;
519 m01000m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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);
522 extern "C" __global__ void __launch_bounds__ (256, 1) m01000_s04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r,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)
528 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
530 if (gid >= gid_max) return;
534 w[ 0] = pws[gid].i[ 0];
535 w[ 1] = pws[gid].i[ 1];
536 w[ 2] = pws[gid].i[ 2];
537 w[ 3] = pws[gid].i[ 3];
548 w[14] = pws[gid].i[14];
551 const u32 pw_len = pws[gid].pw_len;
557 m01000s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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);
560 extern "C" __global__ void __launch_bounds__ (256, 1) m01000_s08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r,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)
566 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
568 if (gid >= gid_max) return;
572 w[ 0] = pws[gid].i[ 0];
573 w[ 1] = pws[gid].i[ 1];
574 w[ 2] = pws[gid].i[ 2];
575 w[ 3] = pws[gid].i[ 3];
576 w[ 4] = pws[gid].i[ 4];
577 w[ 5] = pws[gid].i[ 5];
578 w[ 6] = pws[gid].i[ 6];
579 w[ 7] = pws[gid].i[ 7];
586 w[14] = pws[gid].i[14];
589 const u32 pw_len = pws[gid].pw_len;
595 m01000s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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);
598 extern "C" __global__ void __launch_bounds__ (256, 1) m01000_s16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r,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)
604 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
606 if (gid >= gid_max) return;
610 w[ 0] = pws[gid].i[ 0];
611 w[ 1] = pws[gid].i[ 1];
612 w[ 2] = pws[gid].i[ 2];
613 w[ 3] = pws[gid].i[ 3];
614 w[ 4] = pws[gid].i[ 4];
615 w[ 5] = pws[gid].i[ 5];
616 w[ 6] = pws[gid].i[ 6];
617 w[ 7] = pws[gid].i[ 7];
618 w[ 8] = pws[gid].i[ 8];
619 w[ 9] = pws[gid].i[ 9];
620 w[10] = pws[gid].i[10];
621 w[11] = pws[gid].i[11];
622 w[12] = pws[gid].i[12];
623 w[13] = pws[gid].i[13];
624 w[14] = pws[gid].i[14];
625 w[15] = pws[gid].i[15];
627 const u32 pw_len = pws[gid].pw_len;
633 m01000s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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);