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 __device__ __constant__ u32x c_bfs[1024];
46 __device__ static void m00110m (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, 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)
52 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
53 const u32 lid = threadIdx.x;
61 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
62 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
63 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
64 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
68 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
69 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
70 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
71 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
75 salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
87 switch_buffer_by_offset (salt_buf0, salt_buf1, salt_buf2, salt_buf3, pw_len);
89 w[ 0] |= swap_workaround (salt_buf0[0]);
90 w[ 1] |= swap_workaround (salt_buf0[1]);
91 w[ 2] |= swap_workaround (salt_buf0[2]);
92 w[ 3] |= swap_workaround (salt_buf0[3]);
93 w[ 4] |= swap_workaround (salt_buf1[0]);
94 w[ 5] |= swap_workaround (salt_buf1[1]);
95 w[ 6] |= swap_workaround (salt_buf1[2]);
96 w[ 7] |= swap_workaround (salt_buf1[3]);
97 w[ 8] |= swap_workaround (salt_buf2[0]);
98 w[ 9] |= swap_workaround (salt_buf2[1]);
99 w[10] |= swap_workaround (salt_buf2[2]);
100 w[11] |= swap_workaround (salt_buf2[3]);
101 w[12] |= swap_workaround (salt_buf3[0]);
102 w[13] |= swap_workaround (salt_buf3[1]);
103 w[14] |= swap_workaround (salt_buf3[2]);
104 w[15] |= swap_workaround (salt_buf3[3]);
106 const u32 salt_len = salt_bufs[salt_pos].salt_len;
108 const u32 pw_salt_len = pw_len + salt_len;
110 w[15] = pw_salt_len * 8;
116 const u32 c_16s = rotl32 ((w[13] ^ w[ 8] ^ w[ 2] ), 1u);
117 const u32 c_17s = rotl32 ((w[14] ^ w[ 9] ^ w[ 3] ^ w[ 1]), 1u);
118 const u32 c_18s = rotl32 ((w[15] ^ w[10] ^ w[ 4] ^ w[ 2]), 1u);
119 const u32 c_19s = rotl32 ((c_16s ^ w[11] ^ w[ 5] ^ w[ 3]), 1u);
120 const u32 c_20s = rotl32 ((c_17s ^ w[12] ^ w[ 6] ^ w[ 4]), 1u);
121 const u32 c_21s = rotl32 ((c_18s ^ w[13] ^ w[ 7] ^ w[ 5]), 1u);
122 const u32 c_22s = rotl32 ((c_19s ^ w[14] ^ w[ 8] ^ w[ 6]), 1u);
123 const u32 c_23s = rotl32 ((c_20s ^ w[15] ^ w[ 9] ^ w[ 7]), 1u);
124 const u32 c_24s = rotl32 ((c_21s ^ c_16s ^ w[10] ^ w[ 8]), 1u);
125 const u32 c_25s = rotl32 ((c_22s ^ c_17s ^ w[11] ^ w[ 9]), 1u);
126 const u32 c_26s = rotl32 ((c_23s ^ c_18s ^ w[12] ^ w[10]), 1u);
127 const u32 c_27s = rotl32 ((c_24s ^ c_19s ^ w[13] ^ w[11]), 1u);
128 const u32 c_28s = rotl32 ((c_25s ^ c_20s ^ w[14] ^ w[12]), 1u);
129 const u32 c_29s = rotl32 ((c_26s ^ c_21s ^ w[15] ^ w[13]), 1u);
130 const u32 c_30s = rotl32 ((c_27s ^ c_22s ^ c_16s ^ w[14]), 1u);
131 const u32 c_31s = rotl32 ((c_28s ^ c_23s ^ c_17s ^ w[15]), 1u);
132 const u32 c_32s = rotl32 ((c_29s ^ c_24s ^ c_18s ^ c_16s), 1u);
133 const u32 c_33s = rotl32 ((c_30s ^ c_25s ^ c_19s ^ c_17s), 1u);
134 const u32 c_34s = rotl32 ((c_31s ^ c_26s ^ c_20s ^ c_18s), 1u);
135 const u32 c_35s = rotl32 ((c_32s ^ c_27s ^ c_21s ^ c_19s), 1u);
136 const u32 c_36s = rotl32 ((c_33s ^ c_28s ^ c_22s ^ c_20s), 1u);
137 const u32 c_37s = rotl32 ((c_34s ^ c_29s ^ c_23s ^ c_21s), 1u);
138 const u32 c_38s = rotl32 ((c_35s ^ c_30s ^ c_24s ^ c_22s), 1u);
139 const u32 c_39s = rotl32 ((c_36s ^ c_31s ^ c_25s ^ c_23s), 1u);
140 const u32 c_40s = rotl32 ((c_37s ^ c_32s ^ c_26s ^ c_24s), 1u);
141 const u32 c_41s = rotl32 ((c_38s ^ c_33s ^ c_27s ^ c_25s), 1u);
142 const u32 c_42s = rotl32 ((c_39s ^ c_34s ^ c_28s ^ c_26s), 1u);
143 const u32 c_43s = rotl32 ((c_40s ^ c_35s ^ c_29s ^ c_27s), 1u);
144 const u32 c_44s = rotl32 ((c_41s ^ c_36s ^ c_30s ^ c_28s), 1u);
145 const u32 c_45s = rotl32 ((c_42s ^ c_37s ^ c_31s ^ c_29s), 1u);
146 const u32 c_46s = rotl32 ((c_43s ^ c_38s ^ c_32s ^ c_30s), 1u);
147 const u32 c_47s = rotl32 ((c_44s ^ c_39s ^ c_33s ^ c_31s), 1u);
148 const u32 c_48s = rotl32 ((c_45s ^ c_40s ^ c_34s ^ c_32s), 1u);
149 const u32 c_49s = rotl32 ((c_46s ^ c_41s ^ c_35s ^ c_33s), 1u);
150 const u32 c_50s = rotl32 ((c_47s ^ c_42s ^ c_36s ^ c_34s), 1u);
151 const u32 c_51s = rotl32 ((c_48s ^ c_43s ^ c_37s ^ c_35s), 1u);
152 const u32 c_52s = rotl32 ((c_49s ^ c_44s ^ c_38s ^ c_36s), 1u);
153 const u32 c_53s = rotl32 ((c_50s ^ c_45s ^ c_39s ^ c_37s), 1u);
154 const u32 c_54s = rotl32 ((c_51s ^ c_46s ^ c_40s ^ c_38s), 1u);
155 const u32 c_55s = rotl32 ((c_52s ^ c_47s ^ c_41s ^ c_39s), 1u);
156 const u32 c_56s = rotl32 ((c_53s ^ c_48s ^ c_42s ^ c_40s), 1u);
157 const u32 c_57s = rotl32 ((c_54s ^ c_49s ^ c_43s ^ c_41s), 1u);
158 const u32 c_58s = rotl32 ((c_55s ^ c_50s ^ c_44s ^ c_42s), 1u);
159 const u32 c_59s = rotl32 ((c_56s ^ c_51s ^ c_45s ^ c_43s), 1u);
160 const u32 c_60s = rotl32 ((c_57s ^ c_52s ^ c_46s ^ c_44s), 1u);
161 const u32 c_61s = rotl32 ((c_58s ^ c_53s ^ c_47s ^ c_45s), 1u);
162 const u32 c_62s = rotl32 ((c_59s ^ c_54s ^ c_48s ^ c_46s), 1u);
163 const u32 c_63s = rotl32 ((c_60s ^ c_55s ^ c_49s ^ c_47s), 1u);
164 const u32 c_64s = rotl32 ((c_61s ^ c_56s ^ c_50s ^ c_48s), 1u);
165 const u32 c_65s = rotl32 ((c_62s ^ c_57s ^ c_51s ^ c_49s), 1u);
166 const u32 c_66s = rotl32 ((c_63s ^ c_58s ^ c_52s ^ c_50s), 1u);
167 const u32 c_67s = rotl32 ((c_64s ^ c_59s ^ c_53s ^ c_51s), 1u);
168 const u32 c_68s = rotl32 ((c_65s ^ c_60s ^ c_54s ^ c_52s), 1u);
169 const u32 c_69s = rotl32 ((c_66s ^ c_61s ^ c_55s ^ c_53s), 1u);
170 const u32 c_70s = rotl32 ((c_67s ^ c_62s ^ c_56s ^ c_54s), 1u);
171 const u32 c_71s = rotl32 ((c_68s ^ c_63s ^ c_57s ^ c_55s), 1u);
172 const u32 c_72s = rotl32 ((c_69s ^ c_64s ^ c_58s ^ c_56s), 1u);
173 const u32 c_73s = rotl32 ((c_70s ^ c_65s ^ c_59s ^ c_57s), 1u);
174 const u32 c_74s = rotl32 ((c_71s ^ c_66s ^ c_60s ^ c_58s), 1u);
175 const u32 c_75s = rotl32 ((c_72s ^ c_67s ^ c_61s ^ c_59s), 1u);
176 const u32 c_76s = rotl32 ((c_73s ^ c_68s ^ c_62s ^ c_60s), 1u);
177 const u32 c_77s = rotl32 ((c_74s ^ c_69s ^ c_63s ^ c_61s), 1u);
178 const u32 c_78s = rotl32 ((c_75s ^ c_70s ^ c_64s ^ c_62s), 1u);
179 const u32 c_79s = rotl32 ((c_76s ^ c_71s ^ c_65s ^ c_63s), 1u);
181 const u32 c_17sK = c_17s + SHA1C00;
182 const u32 c_18sK = c_18s + SHA1C00;
183 const u32 c_20sK = c_20s + SHA1C01;
184 const u32 c_21sK = c_21s + SHA1C01;
185 const u32 c_23sK = c_23s + SHA1C01;
186 const u32 c_26sK = c_26s + SHA1C01;
187 const u32 c_27sK = c_27s + SHA1C01;
188 const u32 c_29sK = c_29s + SHA1C01;
189 const u32 c_33sK = c_33s + SHA1C01;
190 const u32 c_39sK = c_39s + SHA1C01;
191 const u32 c_41sK = c_41s + SHA1C02;
192 const u32 c_45sK = c_45s + SHA1C02;
193 const u32 c_53sK = c_53s + SHA1C02;
194 const u32 c_65sK = c_65s + SHA1C03;
195 const u32 c_69sK = c_69s + SHA1C03;
197 const u32 w1 = w[ 1] + SHA1C00;
198 const u32 w2 = w[ 2] + SHA1C00;
199 const u32 w3 = w[ 3] + SHA1C00;
200 const u32 w4 = w[ 4] + SHA1C00;
201 const u32 w5 = w[ 5] + SHA1C00;
202 const u32 w6 = w[ 6] + SHA1C00;
203 const u32 w7 = w[ 7] + SHA1C00;
204 const u32 w8 = w[ 8] + SHA1C00;
205 const u32 w9 = w[ 9] + SHA1C00;
206 const u32 wa = w[10] + SHA1C00;
207 const u32 wb = w[11] + SHA1C00;
208 const u32 wc = w[12] + SHA1C00;
209 const u32 wd = w[13] + SHA1C00;
210 const u32 we = w[14] + SHA1C00;
211 const u32 wf = w[15] + SHA1C00;
217 const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
221 for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
223 const u32x w0r = c_bfs[il_pos];
225 const u32x w0 = w0l | w0r;
227 const u32x w0s01 = rotl32 (w0, 1u);
228 const u32x w0s02 = rotl32 (w0, 2u);
229 const u32x w0s03 = rotl32 (w0, 3u);
230 const u32x w0s04 = rotl32 (w0, 4u);
231 const u32x w0s05 = rotl32 (w0, 5u);
232 const u32x w0s06 = rotl32 (w0, 6u);
233 const u32x w0s07 = rotl32 (w0, 7u);
234 const u32x w0s08 = rotl32 (w0, 8u);
235 const u32x w0s09 = rotl32 (w0, 9u);
236 const u32x w0s10 = rotl32 (w0, 10u);
237 const u32x w0s11 = rotl32 (w0, 11u);
238 const u32x w0s12 = rotl32 (w0, 12u);
239 const u32x w0s13 = rotl32 (w0, 13u);
240 const u32x w0s14 = rotl32 (w0, 14u);
241 const u32x w0s15 = rotl32 (w0, 15u);
242 const u32x w0s16 = rotl32 (w0, 16u);
243 const u32x w0s17 = rotl32 (w0, 17u);
244 const u32x w0s18 = rotl32 (w0, 18u);
245 const u32x w0s19 = rotl32 (w0, 19u);
246 const u32x w0s20 = rotl32 (w0, 20u);
247 const u32x w0s21 = rotl32 (w0, 21u);
248 const u32x w0s22 = rotl32 (w0, 22U);
250 const u32x w0s04___w0s06 = w0s04 ^ w0s06;
251 const u32x w0s04___w0s08 = w0s04 ^ w0s08;
252 const u32x w0s08___w0s12 = w0s08 ^ w0s12;
253 const u32x w0s04___w0s06___w0s07 = w0s04___w0s06 ^ w0s07;
264 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0);
265 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, w1);
266 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, w2);
267 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, w3);
268 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, w4);
269 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, w5);
270 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, w6);
271 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, w7);
272 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, w8);
273 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, w9);
274 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, wa);
275 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, wb);
276 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, wc);
277 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, wd);
278 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, we);
279 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, wf);
281 SHA1_STEP (SHA1_F0o, e, a, b, c, d, (c_16s ^ w0s01));
282 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, (c_17sK));
283 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, (c_18sK));
284 SHA1_STEP (SHA1_F0o, b, c, d, e, a, (c_19s ^ w0s02));
289 SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_20sK));
290 SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_21sK));
291 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_22s ^ w0s03));
292 SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_23sK));
293 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_24s ^ w0s02));
294 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_25s ^ w0s04));
295 SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_26sK));
296 SHA1_STEPX(SHA1_F1 , d, e, a, b, c, (c_27sK));
297 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_28s ^ w0s05));
298 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_29sK));
299 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_30s ^ w0s02 ^ w0s04));
300 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_31s ^ w0s06));
301 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_32s ^ w0s02 ^ w0s03));
302 SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_33sK));
303 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_34s ^ w0s07));
304 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_35s ^ w0s04));
305 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_36s ^ w0s04___w0s06));
306 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_37s ^ w0s08));
307 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_38s ^ w0s04));
308 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_39sK));
313 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_40s ^ w0s04 ^ w0s09));
314 SHA1_STEPX(SHA1_F2o, e, a, b, c, d, (c_41sK));
315 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_42s ^ w0s06 ^ w0s08));
316 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_43s ^ w0s10));
317 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_44s ^ w0s03 ^ w0s06 ^ w0s07));
318 SHA1_STEPX(SHA1_F2o, a, b, c, d, e, (c_45sK));
319 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_46s ^ w0s04 ^ w0s11));
320 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_47s ^ w0s04___w0s08));
321 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_48s ^ w0s03 ^ w0s04___w0s08 ^ w0s05 ^ w0s10));
322 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_49s ^ w0s12));
323 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_50s ^ w0s08));
324 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_51s ^ w0s04___w0s06));
325 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_52s ^ w0s04___w0s08 ^ w0s13));
326 SHA1_STEPX(SHA1_F2o, c, d, e, a, b, (c_53sK));
327 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_54s ^ w0s07 ^ w0s10 ^ w0s12));
328 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_55s ^ w0s14));
329 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_56s ^ w0s04___w0s06___w0s07 ^ w0s10 ^ w0s11));
330 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_57s ^ w0s08));
331 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_58s ^ w0s04___w0s08 ^ w0s15));
332 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_59s ^ w0s08___w0s12));
337 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_60s ^ w0s04 ^ w0s08___w0s12 ^ w0s07 ^ w0s14));
338 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_61s ^ w0s16));
339 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_62s ^ w0s04___w0s06 ^ w0s08___w0s12));
340 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_63s ^ w0s08));
341 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_64s ^ w0s04___w0s06___w0s07 ^ w0s08___w0s12 ^ w0s17));
342 SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_65sK));
343 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_66s ^ w0s14 ^ w0s16));
344 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_67s ^ w0s08 ^ w0s18));
345 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_68s ^ w0s11 ^ w0s14 ^ w0s15));
346 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_69sK));
347 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_70s ^ w0s12 ^ w0s19));
348 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_71s ^ w0s12 ^ w0s16));
349 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_72s ^ w0s05 ^ w0s11 ^ w0s12 ^ w0s13 ^ w0s16 ^ w0s18));
350 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_73s ^ w0s20));
351 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_74s ^ w0s08 ^ w0s16));
352 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_75s ^ w0s06 ^ w0s12 ^ w0s14));
353 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_76s ^ w0s07 ^ w0s08___w0s12 ^ w0s16 ^ w0s21));
354 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_77s));
355 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_78s ^ w0s07 ^ w0s08 ^ w0s15 ^ w0s18 ^ w0s20));
356 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_79s ^ w0s08 ^ w0s22));
364 #include VECT_COMPARE_M
368 __device__ static void m00110s (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, 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)
374 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
375 const u32 lid = threadIdx.x;
381 const u32 c_16s = rotl32 ((w[13] ^ w[ 8] ^ w[ 2] ), 1u);
382 const u32 c_17s = rotl32 ((w[14] ^ w[ 9] ^ w[ 3] ^ w[ 1]), 1u);
383 const u32 c_18s = rotl32 ((w[15] ^ w[10] ^ w[ 4] ^ w[ 2]), 1u);
384 const u32 c_19s = rotl32 ((c_16s ^ w[11] ^ w[ 5] ^ w[ 3]), 1u);
385 const u32 c_20s = rotl32 ((c_17s ^ w[12] ^ w[ 6] ^ w[ 4]), 1u);
386 const u32 c_21s = rotl32 ((c_18s ^ w[13] ^ w[ 7] ^ w[ 5]), 1u);
387 const u32 c_22s = rotl32 ((c_19s ^ w[14] ^ w[ 8] ^ w[ 6]), 1u);
388 const u32 c_23s = rotl32 ((c_20s ^ w[15] ^ w[ 9] ^ w[ 7]), 1u);
389 const u32 c_24s = rotl32 ((c_21s ^ c_16s ^ w[10] ^ w[ 8]), 1u);
390 const u32 c_25s = rotl32 ((c_22s ^ c_17s ^ w[11] ^ w[ 9]), 1u);
391 const u32 c_26s = rotl32 ((c_23s ^ c_18s ^ w[12] ^ w[10]), 1u);
392 const u32 c_27s = rotl32 ((c_24s ^ c_19s ^ w[13] ^ w[11]), 1u);
393 const u32 c_28s = rotl32 ((c_25s ^ c_20s ^ w[14] ^ w[12]), 1u);
394 const u32 c_29s = rotl32 ((c_26s ^ c_21s ^ w[15] ^ w[13]), 1u);
395 const u32 c_30s = rotl32 ((c_27s ^ c_22s ^ c_16s ^ w[14]), 1u);
396 const u32 c_31s = rotl32 ((c_28s ^ c_23s ^ c_17s ^ w[15]), 1u);
397 const u32 c_32s = rotl32 ((c_29s ^ c_24s ^ c_18s ^ c_16s), 1u);
398 const u32 c_33s = rotl32 ((c_30s ^ c_25s ^ c_19s ^ c_17s), 1u);
399 const u32 c_34s = rotl32 ((c_31s ^ c_26s ^ c_20s ^ c_18s), 1u);
400 const u32 c_35s = rotl32 ((c_32s ^ c_27s ^ c_21s ^ c_19s), 1u);
401 const u32 c_36s = rotl32 ((c_33s ^ c_28s ^ c_22s ^ c_20s), 1u);
402 const u32 c_37s = rotl32 ((c_34s ^ c_29s ^ c_23s ^ c_21s), 1u);
403 const u32 c_38s = rotl32 ((c_35s ^ c_30s ^ c_24s ^ c_22s), 1u);
404 const u32 c_39s = rotl32 ((c_36s ^ c_31s ^ c_25s ^ c_23s), 1u);
405 const u32 c_40s = rotl32 ((c_37s ^ c_32s ^ c_26s ^ c_24s), 1u);
406 const u32 c_41s = rotl32 ((c_38s ^ c_33s ^ c_27s ^ c_25s), 1u);
407 const u32 c_42s = rotl32 ((c_39s ^ c_34s ^ c_28s ^ c_26s), 1u);
408 const u32 c_43s = rotl32 ((c_40s ^ c_35s ^ c_29s ^ c_27s), 1u);
409 const u32 c_44s = rotl32 ((c_41s ^ c_36s ^ c_30s ^ c_28s), 1u);
410 const u32 c_45s = rotl32 ((c_42s ^ c_37s ^ c_31s ^ c_29s), 1u);
411 const u32 c_46s = rotl32 ((c_43s ^ c_38s ^ c_32s ^ c_30s), 1u);
412 const u32 c_47s = rotl32 ((c_44s ^ c_39s ^ c_33s ^ c_31s), 1u);
413 const u32 c_48s = rotl32 ((c_45s ^ c_40s ^ c_34s ^ c_32s), 1u);
414 const u32 c_49s = rotl32 ((c_46s ^ c_41s ^ c_35s ^ c_33s), 1u);
415 const u32 c_50s = rotl32 ((c_47s ^ c_42s ^ c_36s ^ c_34s), 1u);
416 const u32 c_51s = rotl32 ((c_48s ^ c_43s ^ c_37s ^ c_35s), 1u);
417 const u32 c_52s = rotl32 ((c_49s ^ c_44s ^ c_38s ^ c_36s), 1u);
418 const u32 c_53s = rotl32 ((c_50s ^ c_45s ^ c_39s ^ c_37s), 1u);
419 const u32 c_54s = rotl32 ((c_51s ^ c_46s ^ c_40s ^ c_38s), 1u);
420 const u32 c_55s = rotl32 ((c_52s ^ c_47s ^ c_41s ^ c_39s), 1u);
421 const u32 c_56s = rotl32 ((c_53s ^ c_48s ^ c_42s ^ c_40s), 1u);
422 const u32 c_57s = rotl32 ((c_54s ^ c_49s ^ c_43s ^ c_41s), 1u);
423 const u32 c_58s = rotl32 ((c_55s ^ c_50s ^ c_44s ^ c_42s), 1u);
424 const u32 c_59s = rotl32 ((c_56s ^ c_51s ^ c_45s ^ c_43s), 1u);
425 const u32 c_60s = rotl32 ((c_57s ^ c_52s ^ c_46s ^ c_44s), 1u);
426 const u32 c_61s = rotl32 ((c_58s ^ c_53s ^ c_47s ^ c_45s), 1u);
427 const u32 c_62s = rotl32 ((c_59s ^ c_54s ^ c_48s ^ c_46s), 1u);
428 const u32 c_63s = rotl32 ((c_60s ^ c_55s ^ c_49s ^ c_47s), 1u);
429 const u32 c_64s = rotl32 ((c_61s ^ c_56s ^ c_50s ^ c_48s), 1u);
430 const u32 c_65s = rotl32 ((c_62s ^ c_57s ^ c_51s ^ c_49s), 1u);
431 const u32 c_66s = rotl32 ((c_63s ^ c_58s ^ c_52s ^ c_50s), 1u);
432 const u32 c_67s = rotl32 ((c_64s ^ c_59s ^ c_53s ^ c_51s), 1u);
433 const u32 c_68s = rotl32 ((c_65s ^ c_60s ^ c_54s ^ c_52s), 1u);
434 const u32 c_69s = rotl32 ((c_66s ^ c_61s ^ c_55s ^ c_53s), 1u);
435 const u32 c_70s = rotl32 ((c_67s ^ c_62s ^ c_56s ^ c_54s), 1u);
436 const u32 c_71s = rotl32 ((c_68s ^ c_63s ^ c_57s ^ c_55s), 1u);
437 const u32 c_72s = rotl32 ((c_69s ^ c_64s ^ c_58s ^ c_56s), 1u);
438 const u32 c_73s = rotl32 ((c_70s ^ c_65s ^ c_59s ^ c_57s), 1u);
439 const u32 c_74s = rotl32 ((c_71s ^ c_66s ^ c_60s ^ c_58s), 1u);
440 const u32 c_75s = rotl32 ((c_72s ^ c_67s ^ c_61s ^ c_59s), 1u);
442 const u32 c_17sK = c_17s + SHA1C00;
443 const u32 c_18sK = c_18s + SHA1C00;
444 const u32 c_20sK = c_20s + SHA1C01;
445 const u32 c_21sK = c_21s + SHA1C01;
446 const u32 c_23sK = c_23s + SHA1C01;
447 const u32 c_26sK = c_26s + SHA1C01;
448 const u32 c_27sK = c_27s + SHA1C01;
449 const u32 c_29sK = c_29s + SHA1C01;
450 const u32 c_33sK = c_33s + SHA1C01;
451 const u32 c_39sK = c_39s + SHA1C01;
452 const u32 c_41sK = c_41s + SHA1C02;
453 const u32 c_45sK = c_45s + SHA1C02;
454 const u32 c_53sK = c_53s + SHA1C02;
455 const u32 c_65sK = c_65s + SHA1C03;
456 const u32 c_69sK = c_69s + SHA1C03;
458 const u32 w1 = w[ 1] + SHA1C00;
459 const u32 w2 = w[ 2] + SHA1C00;
460 const u32 w3 = w[ 3] + SHA1C00;
461 const u32 w4 = w[ 4] + SHA1C00;
462 const u32 w5 = w[ 5] + SHA1C00;
463 const u32 w6 = w[ 6] + SHA1C00;
464 const u32 w7 = w[ 7] + SHA1C00;
465 const u32 w8 = w[ 8] + SHA1C00;
466 const u32 w9 = w[ 9] + SHA1C00;
467 const u32 wa = w[10] + SHA1C00;
468 const u32 wb = w[11] + SHA1C00;
469 const u32 wc = w[12] + SHA1C00;
470 const u32 wd = w[13] + SHA1C00;
471 const u32 we = w[14] + SHA1C00;
472 const u32 wf = w[15] + SHA1C00;
478 const u32 search[4] =
480 digests_buf[digests_offset].digest_buf[DGST_R0],
481 digests_buf[digests_offset].digest_buf[DGST_R1],
482 digests_buf[digests_offset].digest_buf[DGST_R2],
483 digests_buf[digests_offset].digest_buf[DGST_R3]
490 const u32 e_rev = rotl32 (search[1], 2u) - SHA1C03;
496 const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
500 for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
502 const u32x w0r = c_bfs[il_pos];
504 const u32x w0 = w0l | w0r;
506 const u32x w0s01 = rotl32 (w0, 1u);
507 const u32x w0s02 = rotl32 (w0, 2u);
508 const u32x w0s03 = rotl32 (w0, 3u);
509 const u32x w0s04 = rotl32 (w0, 4u);
510 const u32x w0s05 = rotl32 (w0, 5u);
511 const u32x w0s06 = rotl32 (w0, 6u);
512 const u32x w0s07 = rotl32 (w0, 7u);
513 const u32x w0s08 = rotl32 (w0, 8u);
514 const u32x w0s09 = rotl32 (w0, 9u);
515 const u32x w0s10 = rotl32 (w0, 10u);
516 const u32x w0s11 = rotl32 (w0, 11u);
517 const u32x w0s12 = rotl32 (w0, 12u);
518 const u32x w0s13 = rotl32 (w0, 13u);
519 const u32x w0s14 = rotl32 (w0, 14u);
520 const u32x w0s15 = rotl32 (w0, 15u);
521 const u32x w0s16 = rotl32 (w0, 16u);
522 const u32x w0s17 = rotl32 (w0, 17u);
523 const u32x w0s18 = rotl32 (w0, 18u);
524 const u32x w0s19 = rotl32 (w0, 19u);
525 const u32x w0s20 = rotl32 (w0, 20u);
527 const u32x w0s04___w0s06 = w0s04 ^ w0s06;
528 const u32x w0s04___w0s08 = w0s04 ^ w0s08;
529 const u32x w0s08___w0s12 = w0s08 ^ w0s12;
530 const u32x w0s04___w0s06___w0s07 = w0s04___w0s06 ^ w0s07;
541 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0);
542 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, w1);
543 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, w2);
544 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, w3);
545 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, w4);
546 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, w5);
547 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, w6);
548 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, w7);
549 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, w8);
550 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, w9);
551 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, wa);
552 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, wb);
553 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, wc);
554 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, wd);
555 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, we);
556 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, wf);
558 SHA1_STEP (SHA1_F0o, e, a, b, c, d, (c_16s ^ w0s01));
559 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, (c_17sK));
560 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, (c_18sK));
561 SHA1_STEP (SHA1_F0o, b, c, d, e, a, (c_19s ^ w0s02));
566 SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_20sK));
567 SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_21sK));
568 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_22s ^ w0s03));
569 SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_23sK));
570 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_24s ^ w0s02));
571 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_25s ^ w0s04));
572 SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_26sK));
573 SHA1_STEPX(SHA1_F1 , d, e, a, b, c, (c_27sK));
574 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_28s ^ w0s05));
575 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_29sK));
576 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_30s ^ w0s02 ^ w0s04));
577 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_31s ^ w0s06));
578 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_32s ^ w0s02 ^ w0s03));
579 SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_33sK));
580 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_34s ^ w0s07));
581 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_35s ^ w0s04));
582 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_36s ^ w0s04___w0s06));
583 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_37s ^ w0s08));
584 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_38s ^ w0s04));
585 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_39sK));
590 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_40s ^ w0s04 ^ w0s09));
591 SHA1_STEPX(SHA1_F2o, e, a, b, c, d, (c_41sK));
592 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_42s ^ w0s06 ^ w0s08));
593 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_43s ^ w0s10));
594 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_44s ^ w0s03 ^ w0s06 ^ w0s07));
595 SHA1_STEPX(SHA1_F2o, a, b, c, d, e, (c_45sK));
596 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_46s ^ w0s04 ^ w0s11));
597 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_47s ^ w0s04___w0s08));
598 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_48s ^ w0s03 ^ w0s04___w0s08 ^ w0s05 ^ w0s10));
599 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_49s ^ w0s12));
600 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_50s ^ w0s08));
601 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_51s ^ w0s04___w0s06));
602 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_52s ^ w0s04___w0s08 ^ w0s13));
603 SHA1_STEPX(SHA1_F2o, c, d, e, a, b, (c_53sK));
604 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_54s ^ w0s07 ^ w0s10 ^ w0s12));
605 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_55s ^ w0s14));
606 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_56s ^ w0s04___w0s06___w0s07 ^ w0s10 ^ w0s11));
607 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_57s ^ w0s08));
608 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_58s ^ w0s04___w0s08 ^ w0s15));
609 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_59s ^ w0s08___w0s12));
614 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_60s ^ w0s04 ^ w0s08___w0s12 ^ w0s07 ^ w0s14));
615 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_61s ^ w0s16));
616 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_62s ^ w0s04___w0s06 ^ w0s08___w0s12));
617 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_63s ^ w0s08));
618 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_64s ^ w0s04___w0s06___w0s07 ^ w0s08___w0s12 ^ w0s17));
619 SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_65sK));
620 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_66s ^ w0s14 ^ w0s16));
621 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_67s ^ w0s08 ^ w0s18));
622 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_68s ^ w0s11 ^ w0s14 ^ w0s15));
623 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_69sK));
624 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_70s ^ w0s12 ^ w0s19));
625 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_71s ^ w0s12 ^ w0s16));
626 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_72s ^ w0s05 ^ w0s11 ^ w0s12 ^ w0s13 ^ w0s16 ^ w0s18));
627 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_73s ^ w0s20));
628 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_74s ^ w0s08 ^ w0s16));
630 SHA1_STEP_PE (SHA1_F1, a, b, c, d, e, (c_75s ^ w0s06 ^ w0s12 ^ w0s14));
632 bool q_cond = (e_rev != e);
634 if (q_cond) continue;
636 SHA1_STEP_PB (SHA1_F1, a, b, c, d, e, 0);
638 const u32 c_76s = rotl32 ((c_73s ^ c_68s ^ c_62s ^ c_60s), 1u);
639 const u32 c_77s = rotl32 ((c_74s ^ c_69s ^ c_63s ^ c_61s), 1u);
640 const u32 c_78s = rotl32 ((c_75s ^ c_70s ^ c_64s ^ c_62s), 1u);
641 const u32 c_79s = rotl32 ((c_76s ^ c_71s ^ c_65s ^ c_63s), 1u);
643 const u32x w0s21 = rotl32 (w0, 21u);
644 const u32x w0s22 = rotl32 (w0, 22U);
646 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_76s ^ w0s07 ^ w0s08___w0s12 ^ w0s16 ^ w0s21));
647 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_77s));
648 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_78s ^ w0s07 ^ w0s08 ^ w0s15 ^ w0s18 ^ w0s20));
649 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_79s ^ w0s08 ^ w0s22));
657 #include VECT_COMPARE_S
661 extern "C" __global__ void __launch_bounds__ (256, 1) m00110_m04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
667 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
669 if (gid >= gid_max) return;
673 w[ 0] = pws[gid].i[ 0];
674 w[ 1] = pws[gid].i[ 1];
675 w[ 2] = pws[gid].i[ 2];
676 w[ 3] = pws[gid].i[ 3];
688 w[15] = pws[gid].i[15];
690 const u32 pw_len = pws[gid].pw_len;
696 m00110m (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);
699 extern "C" __global__ void __launch_bounds__ (256, 1) m00110_m08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
705 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
707 if (gid >= gid_max) return;
711 w[ 0] = pws[gid].i[ 0];
712 w[ 1] = pws[gid].i[ 1];
713 w[ 2] = pws[gid].i[ 2];
714 w[ 3] = pws[gid].i[ 3];
715 w[ 4] = pws[gid].i[ 4];
716 w[ 5] = pws[gid].i[ 5];
717 w[ 6] = pws[gid].i[ 6];
718 w[ 7] = pws[gid].i[ 7];
726 w[15] = pws[gid].i[15];
728 const u32 pw_len = pws[gid].pw_len;
734 m00110m (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);
737 extern "C" __global__ void __launch_bounds__ (256, 1) m00110_m16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
743 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
745 if (gid >= gid_max) return;
749 w[ 0] = pws[gid].i[ 0];
750 w[ 1] = pws[gid].i[ 1];
751 w[ 2] = pws[gid].i[ 2];
752 w[ 3] = pws[gid].i[ 3];
753 w[ 4] = pws[gid].i[ 4];
754 w[ 5] = pws[gid].i[ 5];
755 w[ 6] = pws[gid].i[ 6];
756 w[ 7] = pws[gid].i[ 7];
757 w[ 8] = pws[gid].i[ 8];
758 w[ 9] = pws[gid].i[ 9];
759 w[10] = pws[gid].i[10];
760 w[11] = pws[gid].i[11];
761 w[12] = pws[gid].i[12];
762 w[13] = pws[gid].i[13];
763 w[14] = pws[gid].i[14];
764 w[15] = pws[gid].i[15];
766 const u32 pw_len = pws[gid].pw_len;
772 m00110m (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);
775 extern "C" __global__ void __launch_bounds__ (256, 1) m00110_s04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
781 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
783 if (gid >= gid_max) return;
787 w[ 0] = pws[gid].i[ 0];
788 w[ 1] = pws[gid].i[ 1];
789 w[ 2] = pws[gid].i[ 2];
790 w[ 3] = pws[gid].i[ 3];
802 w[15] = pws[gid].i[15];
804 const u32 pw_len = pws[gid].pw_len;
810 m00110s (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);
813 extern "C" __global__ void __launch_bounds__ (256, 1) m00110_s08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
819 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
821 if (gid >= gid_max) return;
825 w[ 0] = pws[gid].i[ 0];
826 w[ 1] = pws[gid].i[ 1];
827 w[ 2] = pws[gid].i[ 2];
828 w[ 3] = pws[gid].i[ 3];
829 w[ 4] = pws[gid].i[ 4];
830 w[ 5] = pws[gid].i[ 5];
831 w[ 6] = pws[gid].i[ 6];
832 w[ 7] = pws[gid].i[ 7];
840 w[15] = pws[gid].i[15];
842 const u32 pw_len = pws[gid].pw_len;
848 m00110s (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);
851 extern "C" __global__ void __launch_bounds__ (256, 1) m00110_s16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
857 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
859 if (gid >= gid_max) return;
863 w[ 0] = pws[gid].i[ 0];
864 w[ 1] = pws[gid].i[ 1];
865 w[ 2] = pws[gid].i[ 2];
866 w[ 3] = pws[gid].i[ 3];
867 w[ 4] = pws[gid].i[ 4];
868 w[ 5] = pws[gid].i[ 5];
869 w[ 6] = pws[gid].i[ 6];
870 w[ 7] = pws[gid].i[ 7];
871 w[ 8] = pws[gid].i[ 8];
872 w[ 9] = pws[gid].i[ 9];
873 w[10] = pws[gid].i[10];
874 w[11] = pws[gid].i[11];
875 w[12] = pws[gid].i[12];
876 w[13] = pws[gid].i[13];
877 w[14] = pws[gid].i[14];
878 w[15] = pws[gid].i[15];
880 const u32 pw_len = pws[gid].pw_len;
886 m00110s (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);