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 m00100m (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;
59 const u32 c_16s = rotl32 ((w[13] ^ w[ 8] ^ w[ 2] ), 1u);
60 const u32 c_17s = rotl32 ((w[14] ^ w[ 9] ^ w[ 3] ^ w[ 1]), 1u);
61 const u32 c_18s = rotl32 ((w[15] ^ w[10] ^ w[ 4] ^ w[ 2]), 1u);
62 const u32 c_19s = rotl32 ((c_16s ^ w[11] ^ w[ 5] ^ w[ 3]), 1u);
63 const u32 c_20s = rotl32 ((c_17s ^ w[12] ^ w[ 6] ^ w[ 4]), 1u);
64 const u32 c_21s = rotl32 ((c_18s ^ w[13] ^ w[ 7] ^ w[ 5]), 1u);
65 const u32 c_22s = rotl32 ((c_19s ^ w[14] ^ w[ 8] ^ w[ 6]), 1u);
66 const u32 c_23s = rotl32 ((c_20s ^ w[15] ^ w[ 9] ^ w[ 7]), 1u);
67 const u32 c_24s = rotl32 ((c_21s ^ c_16s ^ w[10] ^ w[ 8]), 1u);
68 const u32 c_25s = rotl32 ((c_22s ^ c_17s ^ w[11] ^ w[ 9]), 1u);
69 const u32 c_26s = rotl32 ((c_23s ^ c_18s ^ w[12] ^ w[10]), 1u);
70 const u32 c_27s = rotl32 ((c_24s ^ c_19s ^ w[13] ^ w[11]), 1u);
71 const u32 c_28s = rotl32 ((c_25s ^ c_20s ^ w[14] ^ w[12]), 1u);
72 const u32 c_29s = rotl32 ((c_26s ^ c_21s ^ w[15] ^ w[13]), 1u);
73 const u32 c_30s = rotl32 ((c_27s ^ c_22s ^ c_16s ^ w[14]), 1u);
74 const u32 c_31s = rotl32 ((c_28s ^ c_23s ^ c_17s ^ w[15]), 1u);
75 const u32 c_32s = rotl32 ((c_29s ^ c_24s ^ c_18s ^ c_16s), 1u);
76 const u32 c_33s = rotl32 ((c_30s ^ c_25s ^ c_19s ^ c_17s), 1u);
77 const u32 c_34s = rotl32 ((c_31s ^ c_26s ^ c_20s ^ c_18s), 1u);
78 const u32 c_35s = rotl32 ((c_32s ^ c_27s ^ c_21s ^ c_19s), 1u);
79 const u32 c_36s = rotl32 ((c_33s ^ c_28s ^ c_22s ^ c_20s), 1u);
80 const u32 c_37s = rotl32 ((c_34s ^ c_29s ^ c_23s ^ c_21s), 1u);
81 const u32 c_38s = rotl32 ((c_35s ^ c_30s ^ c_24s ^ c_22s), 1u);
82 const u32 c_39s = rotl32 ((c_36s ^ c_31s ^ c_25s ^ c_23s), 1u);
83 const u32 c_40s = rotl32 ((c_37s ^ c_32s ^ c_26s ^ c_24s), 1u);
84 const u32 c_41s = rotl32 ((c_38s ^ c_33s ^ c_27s ^ c_25s), 1u);
85 const u32 c_42s = rotl32 ((c_39s ^ c_34s ^ c_28s ^ c_26s), 1u);
86 const u32 c_43s = rotl32 ((c_40s ^ c_35s ^ c_29s ^ c_27s), 1u);
87 const u32 c_44s = rotl32 ((c_41s ^ c_36s ^ c_30s ^ c_28s), 1u);
88 const u32 c_45s = rotl32 ((c_42s ^ c_37s ^ c_31s ^ c_29s), 1u);
89 const u32 c_46s = rotl32 ((c_43s ^ c_38s ^ c_32s ^ c_30s), 1u);
90 const u32 c_47s = rotl32 ((c_44s ^ c_39s ^ c_33s ^ c_31s), 1u);
91 const u32 c_48s = rotl32 ((c_45s ^ c_40s ^ c_34s ^ c_32s), 1u);
92 const u32 c_49s = rotl32 ((c_46s ^ c_41s ^ c_35s ^ c_33s), 1u);
93 const u32 c_50s = rotl32 ((c_47s ^ c_42s ^ c_36s ^ c_34s), 1u);
94 const u32 c_51s = rotl32 ((c_48s ^ c_43s ^ c_37s ^ c_35s), 1u);
95 const u32 c_52s = rotl32 ((c_49s ^ c_44s ^ c_38s ^ c_36s), 1u);
96 const u32 c_53s = rotl32 ((c_50s ^ c_45s ^ c_39s ^ c_37s), 1u);
97 const u32 c_54s = rotl32 ((c_51s ^ c_46s ^ c_40s ^ c_38s), 1u);
98 const u32 c_55s = rotl32 ((c_52s ^ c_47s ^ c_41s ^ c_39s), 1u);
99 const u32 c_56s = rotl32 ((c_53s ^ c_48s ^ c_42s ^ c_40s), 1u);
100 const u32 c_57s = rotl32 ((c_54s ^ c_49s ^ c_43s ^ c_41s), 1u);
101 const u32 c_58s = rotl32 ((c_55s ^ c_50s ^ c_44s ^ c_42s), 1u);
102 const u32 c_59s = rotl32 ((c_56s ^ c_51s ^ c_45s ^ c_43s), 1u);
103 const u32 c_60s = rotl32 ((c_57s ^ c_52s ^ c_46s ^ c_44s), 1u);
104 const u32 c_61s = rotl32 ((c_58s ^ c_53s ^ c_47s ^ c_45s), 1u);
105 const u32 c_62s = rotl32 ((c_59s ^ c_54s ^ c_48s ^ c_46s), 1u);
106 const u32 c_63s = rotl32 ((c_60s ^ c_55s ^ c_49s ^ c_47s), 1u);
107 const u32 c_64s = rotl32 ((c_61s ^ c_56s ^ c_50s ^ c_48s), 1u);
108 const u32 c_65s = rotl32 ((c_62s ^ c_57s ^ c_51s ^ c_49s), 1u);
109 const u32 c_66s = rotl32 ((c_63s ^ c_58s ^ c_52s ^ c_50s), 1u);
110 const u32 c_67s = rotl32 ((c_64s ^ c_59s ^ c_53s ^ c_51s), 1u);
111 const u32 c_68s = rotl32 ((c_65s ^ c_60s ^ c_54s ^ c_52s), 1u);
112 const u32 c_69s = rotl32 ((c_66s ^ c_61s ^ c_55s ^ c_53s), 1u);
113 const u32 c_70s = rotl32 ((c_67s ^ c_62s ^ c_56s ^ c_54s), 1u);
114 const u32 c_71s = rotl32 ((c_68s ^ c_63s ^ c_57s ^ c_55s), 1u);
115 const u32 c_72s = rotl32 ((c_69s ^ c_64s ^ c_58s ^ c_56s), 1u);
116 const u32 c_73s = rotl32 ((c_70s ^ c_65s ^ c_59s ^ c_57s), 1u);
117 const u32 c_74s = rotl32 ((c_71s ^ c_66s ^ c_60s ^ c_58s), 1u);
118 const u32 c_75s = rotl32 ((c_72s ^ c_67s ^ c_61s ^ c_59s), 1u);
119 const u32 c_76s = rotl32 ((c_73s ^ c_68s ^ c_62s ^ c_60s), 1u);
120 const u32 c_77s = rotl32 ((c_74s ^ c_69s ^ c_63s ^ c_61s), 1u);
121 const u32 c_78s = rotl32 ((c_75s ^ c_70s ^ c_64s ^ c_62s), 1u);
122 const u32 c_79s = rotl32 ((c_76s ^ c_71s ^ c_65s ^ c_63s), 1u);
124 const u32 c_17sK = c_17s + SHA1C00;
125 const u32 c_18sK = c_18s + SHA1C00;
126 const u32 c_20sK = c_20s + SHA1C01;
127 const u32 c_21sK = c_21s + SHA1C01;
128 const u32 c_23sK = c_23s + SHA1C01;
129 const u32 c_26sK = c_26s + SHA1C01;
130 const u32 c_27sK = c_27s + SHA1C01;
131 const u32 c_29sK = c_29s + SHA1C01;
132 const u32 c_33sK = c_33s + SHA1C01;
133 const u32 c_39sK = c_39s + SHA1C01;
134 const u32 c_41sK = c_41s + SHA1C02;
135 const u32 c_45sK = c_45s + SHA1C02;
136 const u32 c_53sK = c_53s + SHA1C02;
137 const u32 c_65sK = c_65s + SHA1C03;
138 const u32 c_69sK = c_69s + SHA1C03;
140 const u32 w1 = w[ 1] + SHA1C00;
141 const u32 w2 = w[ 2] + SHA1C00;
142 const u32 w3 = w[ 3] + SHA1C00;
143 const u32 w4 = w[ 4] + SHA1C00;
144 const u32 w5 = w[ 5] + SHA1C00;
145 const u32 w6 = w[ 6] + SHA1C00;
146 const u32 w7 = w[ 7] + SHA1C00;
147 const u32 w8 = w[ 8] + SHA1C00;
148 const u32 w9 = w[ 9] + SHA1C00;
149 const u32 wa = w[10] + SHA1C00;
150 const u32 wb = w[11] + SHA1C00;
151 const u32 wc = w[12] + SHA1C00;
152 const u32 wd = w[13] + SHA1C00;
153 const u32 we = w[14] + SHA1C00;
154 const u32 wf = w[15] + SHA1C00;
160 const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
164 for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
166 const u32x w0r = c_bfs[il_pos];
168 const u32x w0 = w0l | w0r;
170 const u32x w0s01 = rotl32 (w0, 1u);
171 const u32x w0s02 = rotl32 (w0, 2u);
172 const u32x w0s03 = rotl32 (w0, 3u);
173 const u32x w0s04 = rotl32 (w0, 4u);
174 const u32x w0s05 = rotl32 (w0, 5u);
175 const u32x w0s06 = rotl32 (w0, 6u);
176 const u32x w0s07 = rotl32 (w0, 7u);
177 const u32x w0s08 = rotl32 (w0, 8u);
178 const u32x w0s09 = rotl32 (w0, 9u);
179 const u32x w0s10 = rotl32 (w0, 10u);
180 const u32x w0s11 = rotl32 (w0, 11u);
181 const u32x w0s12 = rotl32 (w0, 12u);
182 const u32x w0s13 = rotl32 (w0, 13u);
183 const u32x w0s14 = rotl32 (w0, 14u);
184 const u32x w0s15 = rotl32 (w0, 15u);
185 const u32x w0s16 = rotl32 (w0, 16u);
186 const u32x w0s17 = rotl32 (w0, 17u);
187 const u32x w0s18 = rotl32 (w0, 18u);
188 const u32x w0s19 = rotl32 (w0, 19u);
189 const u32x w0s20 = rotl32 (w0, 20u);
190 const u32x w0s21 = rotl32 (w0, 21u);
191 const u32x w0s22 = rotl32 (w0, 22U);
193 const u32x w0s04___w0s06 = w0s04 ^ w0s06;
194 const u32x w0s04___w0s08 = w0s04 ^ w0s08;
195 const u32x w0s08___w0s12 = w0s08 ^ w0s12;
196 const u32x w0s04___w0s06___w0s07 = w0s04___w0s06 ^ w0s07;
207 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0);
208 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, w1);
209 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, w2);
210 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, w3);
211 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, w4);
212 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, w5);
213 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, w6);
214 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, w7);
215 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, w8);
216 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, w9);
217 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, wa);
218 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, wb);
219 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, wc);
220 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, wd);
221 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, we);
222 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, wf);
224 SHA1_STEP (SHA1_F0o, e, a, b, c, d, (c_16s ^ w0s01));
225 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, (c_17sK));
226 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, (c_18sK));
227 SHA1_STEP (SHA1_F0o, b, c, d, e, a, (c_19s ^ w0s02));
232 SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_20sK));
233 SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_21sK));
234 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_22s ^ w0s03));
235 SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_23sK));
236 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_24s ^ w0s02));
237 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_25s ^ w0s04));
238 SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_26sK));
239 SHA1_STEPX(SHA1_F1 , d, e, a, b, c, (c_27sK));
240 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_28s ^ w0s05));
241 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_29sK));
242 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_30s ^ w0s02 ^ w0s04));
243 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_31s ^ w0s06));
244 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_32s ^ w0s02 ^ w0s03));
245 SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_33sK));
246 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_34s ^ w0s07));
247 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_35s ^ w0s04));
248 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_36s ^ w0s04___w0s06));
249 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_37s ^ w0s08));
250 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_38s ^ w0s04));
251 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_39sK));
256 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_40s ^ w0s04 ^ w0s09));
257 SHA1_STEPX(SHA1_F2o, e, a, b, c, d, (c_41sK));
258 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_42s ^ w0s06 ^ w0s08));
259 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_43s ^ w0s10));
260 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_44s ^ w0s03 ^ w0s06 ^ w0s07));
261 SHA1_STEPX(SHA1_F2o, a, b, c, d, e, (c_45sK));
262 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_46s ^ w0s04 ^ w0s11));
263 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_47s ^ w0s04___w0s08));
264 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_48s ^ w0s03 ^ w0s04___w0s08 ^ w0s05 ^ w0s10));
265 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_49s ^ w0s12));
266 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_50s ^ w0s08));
267 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_51s ^ w0s04___w0s06));
268 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_52s ^ w0s04___w0s08 ^ w0s13));
269 SHA1_STEPX(SHA1_F2o, c, d, e, a, b, (c_53sK));
270 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_54s ^ w0s07 ^ w0s10 ^ w0s12));
271 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_55s ^ w0s14));
272 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_56s ^ w0s04___w0s06___w0s07 ^ w0s10 ^ w0s11));
273 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_57s ^ w0s08));
274 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_58s ^ w0s04___w0s08 ^ w0s15));
275 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_59s ^ w0s08___w0s12));
280 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_60s ^ w0s04 ^ w0s08___w0s12 ^ w0s07 ^ w0s14));
281 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_61s ^ w0s16));
282 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_62s ^ w0s04___w0s06 ^ w0s08___w0s12));
283 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_63s ^ w0s08));
284 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_64s ^ w0s04___w0s06___w0s07 ^ w0s08___w0s12 ^ w0s17));
285 SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_65sK));
286 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_66s ^ w0s14 ^ w0s16));
287 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_67s ^ w0s08 ^ w0s18));
288 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_68s ^ w0s11 ^ w0s14 ^ w0s15));
289 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_69sK));
290 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_70s ^ w0s12 ^ w0s19));
291 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_71s ^ w0s12 ^ w0s16));
292 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_72s ^ w0s05 ^ w0s11 ^ w0s12 ^ w0s13 ^ w0s16 ^ w0s18));
293 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_73s ^ w0s20));
294 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_74s ^ w0s08 ^ w0s16));
295 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_75s ^ w0s06 ^ w0s12 ^ w0s14));
296 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_76s ^ w0s07 ^ w0s08___w0s12 ^ w0s16 ^ w0s21));
297 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_77s));
298 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_78s ^ w0s07 ^ w0s08 ^ w0s15 ^ w0s18 ^ w0s20));
299 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_79s ^ w0s08 ^ w0s22));
307 #include VECT_COMPARE_M
311 __device__ static void m00100s (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)
317 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
318 const u32 lid = threadIdx.x;
324 const u32 c_16s = rotl32 ((w[13] ^ w[ 8] ^ w[ 2] ), 1u);
325 const u32 c_17s = rotl32 ((w[14] ^ w[ 9] ^ w[ 3] ^ w[ 1]), 1u);
326 const u32 c_18s = rotl32 ((w[15] ^ w[10] ^ w[ 4] ^ w[ 2]), 1u);
327 const u32 c_19s = rotl32 ((c_16s ^ w[11] ^ w[ 5] ^ w[ 3]), 1u);
328 const u32 c_20s = rotl32 ((c_17s ^ w[12] ^ w[ 6] ^ w[ 4]), 1u);
329 const u32 c_21s = rotl32 ((c_18s ^ w[13] ^ w[ 7] ^ w[ 5]), 1u);
330 const u32 c_22s = rotl32 ((c_19s ^ w[14] ^ w[ 8] ^ w[ 6]), 1u);
331 const u32 c_23s = rotl32 ((c_20s ^ w[15] ^ w[ 9] ^ w[ 7]), 1u);
332 const u32 c_24s = rotl32 ((c_21s ^ c_16s ^ w[10] ^ w[ 8]), 1u);
333 const u32 c_25s = rotl32 ((c_22s ^ c_17s ^ w[11] ^ w[ 9]), 1u);
334 const u32 c_26s = rotl32 ((c_23s ^ c_18s ^ w[12] ^ w[10]), 1u);
335 const u32 c_27s = rotl32 ((c_24s ^ c_19s ^ w[13] ^ w[11]), 1u);
336 const u32 c_28s = rotl32 ((c_25s ^ c_20s ^ w[14] ^ w[12]), 1u);
337 const u32 c_29s = rotl32 ((c_26s ^ c_21s ^ w[15] ^ w[13]), 1u);
338 const u32 c_30s = rotl32 ((c_27s ^ c_22s ^ c_16s ^ w[14]), 1u);
339 const u32 c_31s = rotl32 ((c_28s ^ c_23s ^ c_17s ^ w[15]), 1u);
340 const u32 c_32s = rotl32 ((c_29s ^ c_24s ^ c_18s ^ c_16s), 1u);
341 const u32 c_33s = rotl32 ((c_30s ^ c_25s ^ c_19s ^ c_17s), 1u);
342 const u32 c_34s = rotl32 ((c_31s ^ c_26s ^ c_20s ^ c_18s), 1u);
343 const u32 c_35s = rotl32 ((c_32s ^ c_27s ^ c_21s ^ c_19s), 1u);
344 const u32 c_36s = rotl32 ((c_33s ^ c_28s ^ c_22s ^ c_20s), 1u);
345 const u32 c_37s = rotl32 ((c_34s ^ c_29s ^ c_23s ^ c_21s), 1u);
346 const u32 c_38s = rotl32 ((c_35s ^ c_30s ^ c_24s ^ c_22s), 1u);
347 const u32 c_39s = rotl32 ((c_36s ^ c_31s ^ c_25s ^ c_23s), 1u);
348 const u32 c_40s = rotl32 ((c_37s ^ c_32s ^ c_26s ^ c_24s), 1u);
349 const u32 c_41s = rotl32 ((c_38s ^ c_33s ^ c_27s ^ c_25s), 1u);
350 const u32 c_42s = rotl32 ((c_39s ^ c_34s ^ c_28s ^ c_26s), 1u);
351 const u32 c_43s = rotl32 ((c_40s ^ c_35s ^ c_29s ^ c_27s), 1u);
352 const u32 c_44s = rotl32 ((c_41s ^ c_36s ^ c_30s ^ c_28s), 1u);
353 const u32 c_45s = rotl32 ((c_42s ^ c_37s ^ c_31s ^ c_29s), 1u);
354 const u32 c_46s = rotl32 ((c_43s ^ c_38s ^ c_32s ^ c_30s), 1u);
355 const u32 c_47s = rotl32 ((c_44s ^ c_39s ^ c_33s ^ c_31s), 1u);
356 const u32 c_48s = rotl32 ((c_45s ^ c_40s ^ c_34s ^ c_32s), 1u);
357 const u32 c_49s = rotl32 ((c_46s ^ c_41s ^ c_35s ^ c_33s), 1u);
358 const u32 c_50s = rotl32 ((c_47s ^ c_42s ^ c_36s ^ c_34s), 1u);
359 const u32 c_51s = rotl32 ((c_48s ^ c_43s ^ c_37s ^ c_35s), 1u);
360 const u32 c_52s = rotl32 ((c_49s ^ c_44s ^ c_38s ^ c_36s), 1u);
361 const u32 c_53s = rotl32 ((c_50s ^ c_45s ^ c_39s ^ c_37s), 1u);
362 const u32 c_54s = rotl32 ((c_51s ^ c_46s ^ c_40s ^ c_38s), 1u);
363 const u32 c_55s = rotl32 ((c_52s ^ c_47s ^ c_41s ^ c_39s), 1u);
364 const u32 c_56s = rotl32 ((c_53s ^ c_48s ^ c_42s ^ c_40s), 1u);
365 const u32 c_57s = rotl32 ((c_54s ^ c_49s ^ c_43s ^ c_41s), 1u);
366 const u32 c_58s = rotl32 ((c_55s ^ c_50s ^ c_44s ^ c_42s), 1u);
367 const u32 c_59s = rotl32 ((c_56s ^ c_51s ^ c_45s ^ c_43s), 1u);
368 const u32 c_60s = rotl32 ((c_57s ^ c_52s ^ c_46s ^ c_44s), 1u);
369 const u32 c_61s = rotl32 ((c_58s ^ c_53s ^ c_47s ^ c_45s), 1u);
370 const u32 c_62s = rotl32 ((c_59s ^ c_54s ^ c_48s ^ c_46s), 1u);
371 const u32 c_63s = rotl32 ((c_60s ^ c_55s ^ c_49s ^ c_47s), 1u);
372 const u32 c_64s = rotl32 ((c_61s ^ c_56s ^ c_50s ^ c_48s), 1u);
373 const u32 c_65s = rotl32 ((c_62s ^ c_57s ^ c_51s ^ c_49s), 1u);
374 const u32 c_66s = rotl32 ((c_63s ^ c_58s ^ c_52s ^ c_50s), 1u);
375 const u32 c_67s = rotl32 ((c_64s ^ c_59s ^ c_53s ^ c_51s), 1u);
376 const u32 c_68s = rotl32 ((c_65s ^ c_60s ^ c_54s ^ c_52s), 1u);
377 const u32 c_69s = rotl32 ((c_66s ^ c_61s ^ c_55s ^ c_53s), 1u);
378 const u32 c_70s = rotl32 ((c_67s ^ c_62s ^ c_56s ^ c_54s), 1u);
379 const u32 c_71s = rotl32 ((c_68s ^ c_63s ^ c_57s ^ c_55s), 1u);
380 const u32 c_72s = rotl32 ((c_69s ^ c_64s ^ c_58s ^ c_56s), 1u);
381 const u32 c_73s = rotl32 ((c_70s ^ c_65s ^ c_59s ^ c_57s), 1u);
382 const u32 c_74s = rotl32 ((c_71s ^ c_66s ^ c_60s ^ c_58s), 1u);
383 const u32 c_75s = rotl32 ((c_72s ^ c_67s ^ c_61s ^ c_59s), 1u);
385 const u32 c_17sK = c_17s + SHA1C00;
386 const u32 c_18sK = c_18s + SHA1C00;
387 const u32 c_20sK = c_20s + SHA1C01;
388 const u32 c_21sK = c_21s + SHA1C01;
389 const u32 c_23sK = c_23s + SHA1C01;
390 const u32 c_26sK = c_26s + SHA1C01;
391 const u32 c_27sK = c_27s + SHA1C01;
392 const u32 c_29sK = c_29s + SHA1C01;
393 const u32 c_33sK = c_33s + SHA1C01;
394 const u32 c_39sK = c_39s + SHA1C01;
395 const u32 c_41sK = c_41s + SHA1C02;
396 const u32 c_45sK = c_45s + SHA1C02;
397 const u32 c_53sK = c_53s + SHA1C02;
398 const u32 c_65sK = c_65s + SHA1C03;
399 const u32 c_69sK = c_69s + SHA1C03;
401 const u32 w1 = w[ 1] + SHA1C00;
402 const u32 w2 = w[ 2] + SHA1C00;
403 const u32 w3 = w[ 3] + SHA1C00;
404 const u32 w4 = w[ 4] + SHA1C00;
405 const u32 w5 = w[ 5] + SHA1C00;
406 const u32 w6 = w[ 6] + SHA1C00;
407 const u32 w7 = w[ 7] + SHA1C00;
408 const u32 w8 = w[ 8] + SHA1C00;
409 const u32 w9 = w[ 9] + SHA1C00;
410 const u32 wa = w[10] + SHA1C00;
411 const u32 wb = w[11] + SHA1C00;
412 const u32 wc = w[12] + SHA1C00;
413 const u32 wd = w[13] + SHA1C00;
414 const u32 we = w[14] + SHA1C00;
415 const u32 wf = w[15] + SHA1C00;
421 const u32 search[4] =
423 digests_buf[digests_offset].digest_buf[DGST_R0],
424 digests_buf[digests_offset].digest_buf[DGST_R1],
425 digests_buf[digests_offset].digest_buf[DGST_R2],
426 digests_buf[digests_offset].digest_buf[DGST_R3],
433 const u32 e_rev = rotl32 (search[1], 2u) - SHA1C03;
439 const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
443 for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
445 const u32x w0r = c_bfs[il_pos];
447 const u32x w0 = w0l | w0r;
449 const u32x w0s01 = rotl32 (w0, 1u);
450 const u32x w0s02 = rotl32 (w0, 2u);
451 const u32x w0s03 = rotl32 (w0, 3u);
452 const u32x w0s04 = rotl32 (w0, 4u);
453 const u32x w0s05 = rotl32 (w0, 5u);
454 const u32x w0s06 = rotl32 (w0, 6u);
455 const u32x w0s07 = rotl32 (w0, 7u);
456 const u32x w0s08 = rotl32 (w0, 8u);
457 const u32x w0s09 = rotl32 (w0, 9u);
458 const u32x w0s10 = rotl32 (w0, 10u);
459 const u32x w0s11 = rotl32 (w0, 11u);
460 const u32x w0s12 = rotl32 (w0, 12u);
461 const u32x w0s13 = rotl32 (w0, 13u);
462 const u32x w0s14 = rotl32 (w0, 14u);
463 const u32x w0s15 = rotl32 (w0, 15u);
464 const u32x w0s16 = rotl32 (w0, 16u);
465 const u32x w0s17 = rotl32 (w0, 17u);
466 const u32x w0s18 = rotl32 (w0, 18u);
467 const u32x w0s19 = rotl32 (w0, 19u);
468 const u32x w0s20 = rotl32 (w0, 20u);
470 const u32x w0s04___w0s06 = w0s04 ^ w0s06;
471 const u32x w0s04___w0s08 = w0s04 ^ w0s08;
472 const u32x w0s08___w0s12 = w0s08 ^ w0s12;
473 const u32x w0s04___w0s06___w0s07 = w0s04___w0s06 ^ w0s07;
484 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0);
485 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, w1);
486 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, w2);
487 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, w3);
488 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, w4);
489 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, w5);
490 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, w6);
491 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, w7);
492 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, w8);
493 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, w9);
494 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, wa);
495 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, wb);
496 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, wc);
497 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, wd);
498 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, we);
499 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, wf);
501 SHA1_STEP (SHA1_F0o, e, a, b, c, d, (c_16s ^ w0s01));
502 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, (c_17sK));
503 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, (c_18sK));
504 SHA1_STEP (SHA1_F0o, b, c, d, e, a, (c_19s ^ w0s02));
509 SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_20sK));
510 SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_21sK));
511 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_22s ^ w0s03));
512 SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_23sK));
513 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_24s ^ w0s02));
514 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_25s ^ w0s04));
515 SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_26sK));
516 SHA1_STEPX(SHA1_F1 , d, e, a, b, c, (c_27sK));
517 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_28s ^ w0s05));
518 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_29sK));
519 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_30s ^ w0s02 ^ w0s04));
520 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_31s ^ w0s06));
521 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_32s ^ w0s02 ^ w0s03));
522 SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_33sK));
523 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_34s ^ w0s07));
524 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_35s ^ w0s04));
525 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_36s ^ w0s04___w0s06));
526 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_37s ^ w0s08));
527 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_38s ^ w0s04));
528 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_39sK));
533 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_40s ^ w0s04 ^ w0s09));
534 SHA1_STEPX(SHA1_F2o, e, a, b, c, d, (c_41sK));
535 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_42s ^ w0s06 ^ w0s08));
536 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_43s ^ w0s10));
537 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_44s ^ w0s03 ^ w0s06 ^ w0s07));
538 SHA1_STEPX(SHA1_F2o, a, b, c, d, e, (c_45sK));
539 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_46s ^ w0s04 ^ w0s11));
540 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_47s ^ w0s04___w0s08));
541 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_48s ^ w0s03 ^ w0s04___w0s08 ^ w0s05 ^ w0s10));
542 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_49s ^ w0s12));
543 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_50s ^ w0s08));
544 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_51s ^ w0s04___w0s06));
545 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_52s ^ w0s04___w0s08 ^ w0s13));
546 SHA1_STEPX(SHA1_F2o, c, d, e, a, b, (c_53sK));
547 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_54s ^ w0s07 ^ w0s10 ^ w0s12));
548 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_55s ^ w0s14));
549 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_56s ^ w0s04___w0s06___w0s07 ^ w0s10 ^ w0s11));
550 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_57s ^ w0s08));
551 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_58s ^ w0s04___w0s08 ^ w0s15));
552 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_59s ^ w0s08___w0s12));
557 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_60s ^ w0s04 ^ w0s08___w0s12 ^ w0s07 ^ w0s14));
558 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_61s ^ w0s16));
559 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_62s ^ w0s04___w0s06 ^ w0s08___w0s12));
560 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_63s ^ w0s08));
561 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_64s ^ w0s04___w0s06___w0s07 ^ w0s08___w0s12 ^ w0s17));
562 SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_65sK));
563 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_66s ^ w0s14 ^ w0s16));
564 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_67s ^ w0s08 ^ w0s18));
565 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_68s ^ w0s11 ^ w0s14 ^ w0s15));
566 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_69sK));
567 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_70s ^ w0s12 ^ w0s19));
568 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_71s ^ w0s12 ^ w0s16));
569 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_72s ^ w0s05 ^ w0s11 ^ w0s12 ^ w0s13 ^ w0s16 ^ w0s18));
570 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_73s ^ w0s20));
571 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_74s ^ w0s08 ^ w0s16));
573 SHA1_STEP_PE (SHA1_F1, a, b, c, d, e, (c_75s ^ w0s06 ^ w0s12 ^ w0s14));
575 bool q_cond = (e_rev != e);
577 if (q_cond) continue;
579 SHA1_STEP_PB (SHA1_F1, a, b, c, d, e, 0);
581 const u32 c_76s = rotl32 ((c_73s ^ c_68s ^ c_62s ^ c_60s), 1u);
582 const u32 c_77s = rotl32 ((c_74s ^ c_69s ^ c_63s ^ c_61s), 1u);
583 const u32 c_78s = rotl32 ((c_75s ^ c_70s ^ c_64s ^ c_62s), 1u);
584 const u32 c_79s = rotl32 ((c_76s ^ c_71s ^ c_65s ^ c_63s), 1u);
586 const u32x w0s21 = rotl32 (w0, 21u);
587 const u32x w0s22 = rotl32 (w0, 22U);
589 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_76s ^ w0s07 ^ w0s08___w0s12 ^ w0s16 ^ w0s21));
590 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_77s));
591 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_78s ^ w0s07 ^ w0s08 ^ w0s15 ^ w0s18 ^ w0s20));
592 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_79s ^ w0s08 ^ w0s22));
600 #include VECT_COMPARE_S
604 extern "C" __global__ void __launch_bounds__ (256, 1) m00100_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)
610 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
612 if (gid >= gid_max) return;
616 w[ 0] = pws[gid].i[ 0];
617 w[ 1] = pws[gid].i[ 1];
618 w[ 2] = pws[gid].i[ 2];
619 w[ 3] = pws[gid].i[ 3];
631 w[15] = pws[gid].i[15];
633 const u32 pw_len = pws[gid].pw_len;
639 m00100m (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);
642 extern "C" __global__ void __launch_bounds__ (256, 1) m00100_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)
648 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
650 if (gid >= gid_max) return;
654 w[ 0] = pws[gid].i[ 0];
655 w[ 1] = pws[gid].i[ 1];
656 w[ 2] = pws[gid].i[ 2];
657 w[ 3] = pws[gid].i[ 3];
658 w[ 4] = pws[gid].i[ 4];
659 w[ 5] = pws[gid].i[ 5];
660 w[ 6] = pws[gid].i[ 6];
661 w[ 7] = pws[gid].i[ 7];
669 w[15] = pws[gid].i[15];
671 const u32 pw_len = pws[gid].pw_len;
677 m00100m (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);
680 extern "C" __global__ void __launch_bounds__ (256, 1) m00100_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)
686 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
688 if (gid >= gid_max) return;
692 w[ 0] = pws[gid].i[ 0];
693 w[ 1] = pws[gid].i[ 1];
694 w[ 2] = pws[gid].i[ 2];
695 w[ 3] = pws[gid].i[ 3];
696 w[ 4] = pws[gid].i[ 4];
697 w[ 5] = pws[gid].i[ 5];
698 w[ 6] = pws[gid].i[ 6];
699 w[ 7] = pws[gid].i[ 7];
700 w[ 8] = pws[gid].i[ 8];
701 w[ 9] = pws[gid].i[ 9];
702 w[10] = pws[gid].i[10];
703 w[11] = pws[gid].i[11];
704 w[12] = pws[gid].i[12];
705 w[13] = pws[gid].i[13];
706 w[14] = pws[gid].i[14];
707 w[15] = pws[gid].i[15];
709 const u32 pw_len = pws[gid].pw_len;
715 m00100m (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);
718 extern "C" __global__ void __launch_bounds__ (256, 1) m00100_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)
724 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
726 if (gid >= gid_max) return;
730 w[ 0] = pws[gid].i[ 0];
731 w[ 1] = pws[gid].i[ 1];
732 w[ 2] = pws[gid].i[ 2];
733 w[ 3] = pws[gid].i[ 3];
745 w[15] = pws[gid].i[15];
747 const u32 pw_len = pws[gid].pw_len;
753 m00100s (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);
756 extern "C" __global__ void __launch_bounds__ (256, 1) m00100_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)
762 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
764 if (gid >= gid_max) return;
768 w[ 0] = pws[gid].i[ 0];
769 w[ 1] = pws[gid].i[ 1];
770 w[ 2] = pws[gid].i[ 2];
771 w[ 3] = pws[gid].i[ 3];
772 w[ 4] = pws[gid].i[ 4];
773 w[ 5] = pws[gid].i[ 5];
774 w[ 6] = pws[gid].i[ 6];
775 w[ 7] = pws[gid].i[ 7];
783 w[15] = pws[gid].i[15];
785 const u32 pw_len = pws[gid].pw_len;
791 m00100s (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);
794 extern "C" __global__ void __launch_bounds__ (256, 1) m00100_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)
800 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
802 if (gid >= gid_max) return;
806 w[ 0] = pws[gid].i[ 0];
807 w[ 1] = pws[gid].i[ 1];
808 w[ 2] = pws[gid].i[ 2];
809 w[ 3] = pws[gid].i[ 3];
810 w[ 4] = pws[gid].i[ 4];
811 w[ 5] = pws[gid].i[ 5];
812 w[ 6] = pws[gid].i[ 6];
813 w[ 7] = pws[gid].i[ 7];
814 w[ 8] = pws[gid].i[ 8];
815 w[ 9] = pws[gid].i[ 9];
816 w[10] = pws[gid].i[10];
817 w[11] = pws[gid].i[11];
818 w[12] = pws[gid].i[12];
819 w[13] = pws[gid].i[13];
820 w[14] = pws[gid].i[14];
821 w[15] = pws[gid].i[15];
823 const u32 pw_len = pws[gid].pw_len;
829 m00100s (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);