2 * Author......: Jens Steube <jens.steube@gmail.com>
9 #include "include/constants.h"
10 #include "include/kernel_vendor.h"
29 #include "include/kernel_functions.c"
30 #include "types_amd.c"
31 #include "common_amd.c"
34 #define VECT_COMPARE_S "check_single_vect1_comp4_warp.c"
35 #define VECT_COMPARE_M "check_multi_vect1_comp4_warp.c"
39 #define VECT_COMPARE_S "check_single_vect2_comp4_warp.c"
40 #define VECT_COMPARE_M "check_multi_vect2_comp4_warp.c"
44 #define VECT_COMPARE_S "check_single_vect4_comp4_warp.c"
45 #define VECT_COMPARE_M "check_multi_vect4_comp4_warp.c"
48 static void m00300m (u32 w[16], const u32 pw_len, __global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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)
54 const u32 gid = get_global_id (0);
55 const u32 lid = get_local_id (0);
61 const u32 c_16s = rotl32 ((w[13] ^ w[ 8] ^ w[ 2] ), 1u);
62 const u32 c_17s = rotl32 ((w[14] ^ w[ 9] ^ w[ 3] ^ w[ 1]), 1u);
63 const u32 c_18s = rotl32 ((w[15] ^ w[10] ^ w[ 4] ^ w[ 2]), 1u);
64 const u32 c_19s = rotl32 ((c_16s ^ w[11] ^ w[ 5] ^ w[ 3]), 1u);
65 const u32 c_20s = rotl32 ((c_17s ^ w[12] ^ w[ 6] ^ w[ 4]), 1u);
66 const u32 c_21s = rotl32 ((c_18s ^ w[13] ^ w[ 7] ^ w[ 5]), 1u);
67 const u32 c_22s = rotl32 ((c_19s ^ w[14] ^ w[ 8] ^ w[ 6]), 1u);
68 const u32 c_23s = rotl32 ((c_20s ^ w[15] ^ w[ 9] ^ w[ 7]), 1u);
69 const u32 c_24s = rotl32 ((c_21s ^ c_16s ^ w[10] ^ w[ 8]), 1u);
70 const u32 c_25s = rotl32 ((c_22s ^ c_17s ^ w[11] ^ w[ 9]), 1u);
71 const u32 c_26s = rotl32 ((c_23s ^ c_18s ^ w[12] ^ w[10]), 1u);
72 const u32 c_27s = rotl32 ((c_24s ^ c_19s ^ w[13] ^ w[11]), 1u);
73 const u32 c_28s = rotl32 ((c_25s ^ c_20s ^ w[14] ^ w[12]), 1u);
74 const u32 c_29s = rotl32 ((c_26s ^ c_21s ^ w[15] ^ w[13]), 1u);
75 const u32 c_30s = rotl32 ((c_27s ^ c_22s ^ c_16s ^ w[14]), 1u);
76 const u32 c_31s = rotl32 ((c_28s ^ c_23s ^ c_17s ^ w[15]), 1u);
77 const u32 c_32s = rotl32 ((c_29s ^ c_24s ^ c_18s ^ c_16s), 1u);
78 const u32 c_33s = rotl32 ((c_30s ^ c_25s ^ c_19s ^ c_17s), 1u);
79 const u32 c_34s = rotl32 ((c_31s ^ c_26s ^ c_20s ^ c_18s), 1u);
80 const u32 c_35s = rotl32 ((c_32s ^ c_27s ^ c_21s ^ c_19s), 1u);
81 const u32 c_36s = rotl32 ((c_33s ^ c_28s ^ c_22s ^ c_20s), 1u);
82 const u32 c_37s = rotl32 ((c_34s ^ c_29s ^ c_23s ^ c_21s), 1u);
83 const u32 c_38s = rotl32 ((c_35s ^ c_30s ^ c_24s ^ c_22s), 1u);
84 const u32 c_39s = rotl32 ((c_36s ^ c_31s ^ c_25s ^ c_23s), 1u);
85 const u32 c_40s = rotl32 ((c_37s ^ c_32s ^ c_26s ^ c_24s), 1u);
86 const u32 c_41s = rotl32 ((c_38s ^ c_33s ^ c_27s ^ c_25s), 1u);
87 const u32 c_42s = rotl32 ((c_39s ^ c_34s ^ c_28s ^ c_26s), 1u);
88 const u32 c_43s = rotl32 ((c_40s ^ c_35s ^ c_29s ^ c_27s), 1u);
89 const u32 c_44s = rotl32 ((c_41s ^ c_36s ^ c_30s ^ c_28s), 1u);
90 const u32 c_45s = rotl32 ((c_42s ^ c_37s ^ c_31s ^ c_29s), 1u);
91 const u32 c_46s = rotl32 ((c_43s ^ c_38s ^ c_32s ^ c_30s), 1u);
92 const u32 c_47s = rotl32 ((c_44s ^ c_39s ^ c_33s ^ c_31s), 1u);
93 const u32 c_48s = rotl32 ((c_45s ^ c_40s ^ c_34s ^ c_32s), 1u);
94 const u32 c_49s = rotl32 ((c_46s ^ c_41s ^ c_35s ^ c_33s), 1u);
95 const u32 c_50s = rotl32 ((c_47s ^ c_42s ^ c_36s ^ c_34s), 1u);
96 const u32 c_51s = rotl32 ((c_48s ^ c_43s ^ c_37s ^ c_35s), 1u);
97 const u32 c_52s = rotl32 ((c_49s ^ c_44s ^ c_38s ^ c_36s), 1u);
98 const u32 c_53s = rotl32 ((c_50s ^ c_45s ^ c_39s ^ c_37s), 1u);
99 const u32 c_54s = rotl32 ((c_51s ^ c_46s ^ c_40s ^ c_38s), 1u);
100 const u32 c_55s = rotl32 ((c_52s ^ c_47s ^ c_41s ^ c_39s), 1u);
101 const u32 c_56s = rotl32 ((c_53s ^ c_48s ^ c_42s ^ c_40s), 1u);
102 const u32 c_57s = rotl32 ((c_54s ^ c_49s ^ c_43s ^ c_41s), 1u);
103 const u32 c_58s = rotl32 ((c_55s ^ c_50s ^ c_44s ^ c_42s), 1u);
104 const u32 c_59s = rotl32 ((c_56s ^ c_51s ^ c_45s ^ c_43s), 1u);
105 const u32 c_60s = rotl32 ((c_57s ^ c_52s ^ c_46s ^ c_44s), 1u);
106 const u32 c_61s = rotl32 ((c_58s ^ c_53s ^ c_47s ^ c_45s), 1u);
107 const u32 c_62s = rotl32 ((c_59s ^ c_54s ^ c_48s ^ c_46s), 1u);
108 const u32 c_63s = rotl32 ((c_60s ^ c_55s ^ c_49s ^ c_47s), 1u);
109 const u32 c_64s = rotl32 ((c_61s ^ c_56s ^ c_50s ^ c_48s), 1u);
110 const u32 c_65s = rotl32 ((c_62s ^ c_57s ^ c_51s ^ c_49s), 1u);
111 const u32 c_66s = rotl32 ((c_63s ^ c_58s ^ c_52s ^ c_50s), 1u);
112 const u32 c_67s = rotl32 ((c_64s ^ c_59s ^ c_53s ^ c_51s), 1u);
113 const u32 c_68s = rotl32 ((c_65s ^ c_60s ^ c_54s ^ c_52s), 1u);
114 const u32 c_69s = rotl32 ((c_66s ^ c_61s ^ c_55s ^ c_53s), 1u);
115 const u32 c_70s = rotl32 ((c_67s ^ c_62s ^ c_56s ^ c_54s), 1u);
116 const u32 c_71s = rotl32 ((c_68s ^ c_63s ^ c_57s ^ c_55s), 1u);
117 const u32 c_72s = rotl32 ((c_69s ^ c_64s ^ c_58s ^ c_56s), 1u);
118 const u32 c_73s = rotl32 ((c_70s ^ c_65s ^ c_59s ^ c_57s), 1u);
119 const u32 c_74s = rotl32 ((c_71s ^ c_66s ^ c_60s ^ c_58s), 1u);
120 const u32 c_75s = rotl32 ((c_72s ^ c_67s ^ c_61s ^ c_59s), 1u);
121 const u32 c_76s = rotl32 ((c_73s ^ c_68s ^ c_62s ^ c_60s), 1u);
122 const u32 c_77s = rotl32 ((c_74s ^ c_69s ^ c_63s ^ c_61s), 1u);
123 const u32 c_78s = rotl32 ((c_75s ^ c_70s ^ c_64s ^ c_62s), 1u);
124 const u32 c_79s = rotl32 ((c_76s ^ c_71s ^ c_65s ^ c_63s), 1u);
126 const u32 c_17sK = c_17s + SHA1C00;
127 const u32 c_18sK = c_18s + SHA1C00;
128 const u32 c_20sK = c_20s + SHA1C01;
129 const u32 c_21sK = c_21s + SHA1C01;
130 const u32 c_23sK = c_23s + SHA1C01;
131 const u32 c_26sK = c_26s + SHA1C01;
132 const u32 c_27sK = c_27s + SHA1C01;
133 const u32 c_29sK = c_29s + SHA1C01;
134 const u32 c_33sK = c_33s + SHA1C01;
135 const u32 c_39sK = c_39s + SHA1C01;
136 const u32 c_41sK = c_41s + SHA1C02;
137 const u32 c_45sK = c_45s + SHA1C02;
138 const u32 c_53sK = c_53s + SHA1C02;
139 const u32 c_65sK = c_65s + SHA1C03;
140 const u32 c_69sK = c_69s + SHA1C03;
142 const u32 w1 = w[ 1] + SHA1C00;
143 const u32 w2 = w[ 2] + SHA1C00;
144 const u32 w3 = w[ 3] + SHA1C00;
145 const u32 w4 = w[ 4] + SHA1C00;
146 const u32 w5 = w[ 5] + SHA1C00;
147 const u32 w6 = w[ 6] + SHA1C00;
148 const u32 w7 = w[ 7] + SHA1C00;
149 const u32 w8 = w[ 8] + SHA1C00;
150 const u32 w9 = w[ 9] + SHA1C00;
151 const u32 wa = w[10] + SHA1C00;
152 const u32 wb = w[11] + SHA1C00;
153 const u32 wc = w[12] + SHA1C00;
154 const u32 wd = w[13] + SHA1C00;
155 const u32 we = w[14] + SHA1C00;
156 const u32 wf = w[15] + SHA1C00;
162 const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
166 for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
168 const u32x w0r = words_buf_r[il_pos];
170 const u32x w0 = w0l | w0r;
172 const u32x w0s01 = rotl32 (w0, 1u);
173 const u32x w0s02 = rotl32 (w0, 2u);
174 const u32x w0s03 = rotl32 (w0, 3u);
175 const u32x w0s04 = rotl32 (w0, 4u);
176 const u32x w0s05 = rotl32 (w0, 5u);
177 const u32x w0s06 = rotl32 (w0, 6u);
178 const u32x w0s07 = rotl32 (w0, 7u);
179 const u32x w0s08 = rotl32 (w0, 8u);
180 const u32x w0s09 = rotl32 (w0, 9u);
181 const u32x w0s10 = rotl32 (w0, 10u);
182 const u32x w0s11 = rotl32 (w0, 11u);
183 const u32x w0s12 = rotl32 (w0, 12u);
184 const u32x w0s13 = rotl32 (w0, 13u);
185 const u32x w0s14 = rotl32 (w0, 14u);
186 const u32x w0s15 = rotl32 (w0, 15u);
187 const u32x w0s16 = rotl32 (w0, 16u);
188 const u32x w0s17 = rotl32 (w0, 17u);
189 const u32x w0s18 = rotl32 (w0, 18u);
190 const u32x w0s19 = rotl32 (w0, 19u);
191 const u32x w0s20 = rotl32 (w0, 20u);
192 const u32x w0s21 = rotl32 (w0, 21u);
193 const u32x w0s22 = rotl32 (w0, 22U);
195 const u32x w0s04___w0s06 = w0s04 ^ w0s06;
196 const u32x w0s04___w0s08 = w0s04 ^ w0s08;
197 const u32x w0s08___w0s12 = w0s08 ^ w0s12;
198 const u32x w0s04___w0s06___w0s07 = w0s04___w0s06 ^ w0s07;
209 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0);
210 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, w1);
211 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, w2);
212 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, w3);
213 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, w4);
214 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, w5);
215 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, w6);
216 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, w7);
217 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, w8);
218 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, w9);
219 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, wa);
220 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, wb);
221 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, wc);
222 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, wd);
223 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, we);
224 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, wf);
226 SHA1_STEP (SHA1_F0o, e, a, b, c, d, (c_16s ^ w0s01));
227 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, (c_17sK));
228 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, (c_18sK));
229 SHA1_STEP (SHA1_F0o, b, c, d, e, a, (c_19s ^ w0s02));
234 SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_20sK));
235 SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_21sK));
236 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_22s ^ w0s03));
237 SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_23sK));
238 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_24s ^ w0s02));
239 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_25s ^ w0s04));
240 SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_26sK));
241 SHA1_STEPX(SHA1_F1 , d, e, a, b, c, (c_27sK));
242 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_28s ^ w0s05));
243 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_29sK));
244 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_30s ^ w0s02 ^ w0s04));
245 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_31s ^ w0s06));
246 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_32s ^ w0s02 ^ w0s03));
247 SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_33sK));
248 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_34s ^ w0s07));
249 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_35s ^ w0s04));
250 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_36s ^ w0s04___w0s06));
251 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_37s ^ w0s08));
252 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_38s ^ w0s04));
253 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_39sK));
258 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_40s ^ w0s04 ^ w0s09));
259 SHA1_STEPX(SHA1_F2o, e, a, b, c, d, (c_41sK));
260 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_42s ^ w0s06 ^ w0s08));
261 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_43s ^ w0s10));
262 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_44s ^ w0s03 ^ w0s06 ^ w0s07));
263 SHA1_STEPX(SHA1_F2o, a, b, c, d, e, (c_45sK));
264 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_46s ^ w0s04 ^ w0s11));
265 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_47s ^ w0s04___w0s08));
266 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_48s ^ w0s03 ^ w0s04___w0s08 ^ w0s05 ^ w0s10));
267 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_49s ^ w0s12));
268 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_50s ^ w0s08));
269 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_51s ^ w0s04___w0s06));
270 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_52s ^ w0s04___w0s08 ^ w0s13));
271 SHA1_STEPX(SHA1_F2o, c, d, e, a, b, (c_53sK));
272 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_54s ^ w0s07 ^ w0s10 ^ w0s12));
273 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_55s ^ w0s14));
274 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_56s ^ w0s04___w0s06___w0s07 ^ w0s10 ^ w0s11));
275 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_57s ^ w0s08));
276 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_58s ^ w0s04___w0s08 ^ w0s15));
277 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_59s ^ w0s08___w0s12));
282 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_60s ^ w0s04 ^ w0s08___w0s12 ^ w0s07 ^ w0s14));
283 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_61s ^ w0s16));
284 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_62s ^ w0s04___w0s06 ^ w0s08___w0s12));
285 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_63s ^ w0s08));
286 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_64s ^ w0s04___w0s06___w0s07 ^ w0s08___w0s12 ^ w0s17));
287 SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_65sK));
288 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_66s ^ w0s14 ^ w0s16));
289 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_67s ^ w0s08 ^ w0s18));
290 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_68s ^ w0s11 ^ w0s14 ^ w0s15));
291 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_69sK));
292 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_70s ^ w0s12 ^ w0s19));
293 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_71s ^ w0s12 ^ w0s16));
294 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_72s ^ w0s05 ^ w0s11 ^ w0s12 ^ w0s13 ^ w0s16 ^ w0s18));
295 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_73s ^ w0s20));
296 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_74s ^ w0s08 ^ w0s16));
297 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_75s ^ w0s06 ^ w0s12 ^ w0s14));
298 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_76s ^ w0s07 ^ w0s08___w0s12 ^ w0s16 ^ w0s21));
299 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_77s));
300 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_78s ^ w0s07 ^ w0s08 ^ w0s15 ^ w0s18 ^ w0s20));
301 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_79s ^ w0s08 ^ w0s22));
314 u32x w5_t = 0x80000000;
335 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
336 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
337 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
338 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
339 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
340 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
341 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
342 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
343 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
344 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
345 SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
346 SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
347 SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
348 SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
349 SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
350 SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
351 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
352 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
353 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
354 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
359 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
360 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
361 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
362 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
363 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
364 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
365 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
366 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
367 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
368 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
369 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
370 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
371 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
372 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
373 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
374 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
375 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
376 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
377 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
378 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
383 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
384 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
385 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
386 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
387 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
388 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
389 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
390 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
391 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
392 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
393 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
394 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
395 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
396 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
397 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
398 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
399 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
400 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
401 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
402 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
407 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
408 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
409 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
410 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
411 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
412 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
413 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
414 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
415 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
416 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
417 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
418 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
419 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
420 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
421 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
422 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
423 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
424 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
425 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
426 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
434 #include VECT_COMPARE_M
438 static void m00300s (u32 w[16], const u32 pw_len, __global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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)
444 const u32 gid = get_global_id (0);
445 const u32 lid = get_local_id (0);
451 const u32 c_16s = rotl32 ((w[13] ^ w[ 8] ^ w[ 2] ), 1u);
452 const u32 c_17s = rotl32 ((w[14] ^ w[ 9] ^ w[ 3] ^ w[ 1]), 1u);
453 const u32 c_18s = rotl32 ((w[15] ^ w[10] ^ w[ 4] ^ w[ 2]), 1u);
454 const u32 c_19s = rotl32 ((c_16s ^ w[11] ^ w[ 5] ^ w[ 3]), 1u);
455 const u32 c_20s = rotl32 ((c_17s ^ w[12] ^ w[ 6] ^ w[ 4]), 1u);
456 const u32 c_21s = rotl32 ((c_18s ^ w[13] ^ w[ 7] ^ w[ 5]), 1u);
457 const u32 c_22s = rotl32 ((c_19s ^ w[14] ^ w[ 8] ^ w[ 6]), 1u);
458 const u32 c_23s = rotl32 ((c_20s ^ w[15] ^ w[ 9] ^ w[ 7]), 1u);
459 const u32 c_24s = rotl32 ((c_21s ^ c_16s ^ w[10] ^ w[ 8]), 1u);
460 const u32 c_25s = rotl32 ((c_22s ^ c_17s ^ w[11] ^ w[ 9]), 1u);
461 const u32 c_26s = rotl32 ((c_23s ^ c_18s ^ w[12] ^ w[10]), 1u);
462 const u32 c_27s = rotl32 ((c_24s ^ c_19s ^ w[13] ^ w[11]), 1u);
463 const u32 c_28s = rotl32 ((c_25s ^ c_20s ^ w[14] ^ w[12]), 1u);
464 const u32 c_29s = rotl32 ((c_26s ^ c_21s ^ w[15] ^ w[13]), 1u);
465 const u32 c_30s = rotl32 ((c_27s ^ c_22s ^ c_16s ^ w[14]), 1u);
466 const u32 c_31s = rotl32 ((c_28s ^ c_23s ^ c_17s ^ w[15]), 1u);
467 const u32 c_32s = rotl32 ((c_29s ^ c_24s ^ c_18s ^ c_16s), 1u);
468 const u32 c_33s = rotl32 ((c_30s ^ c_25s ^ c_19s ^ c_17s), 1u);
469 const u32 c_34s = rotl32 ((c_31s ^ c_26s ^ c_20s ^ c_18s), 1u);
470 const u32 c_35s = rotl32 ((c_32s ^ c_27s ^ c_21s ^ c_19s), 1u);
471 const u32 c_36s = rotl32 ((c_33s ^ c_28s ^ c_22s ^ c_20s), 1u);
472 const u32 c_37s = rotl32 ((c_34s ^ c_29s ^ c_23s ^ c_21s), 1u);
473 const u32 c_38s = rotl32 ((c_35s ^ c_30s ^ c_24s ^ c_22s), 1u);
474 const u32 c_39s = rotl32 ((c_36s ^ c_31s ^ c_25s ^ c_23s), 1u);
475 const u32 c_40s = rotl32 ((c_37s ^ c_32s ^ c_26s ^ c_24s), 1u);
476 const u32 c_41s = rotl32 ((c_38s ^ c_33s ^ c_27s ^ c_25s), 1u);
477 const u32 c_42s = rotl32 ((c_39s ^ c_34s ^ c_28s ^ c_26s), 1u);
478 const u32 c_43s = rotl32 ((c_40s ^ c_35s ^ c_29s ^ c_27s), 1u);
479 const u32 c_44s = rotl32 ((c_41s ^ c_36s ^ c_30s ^ c_28s), 1u);
480 const u32 c_45s = rotl32 ((c_42s ^ c_37s ^ c_31s ^ c_29s), 1u);
481 const u32 c_46s = rotl32 ((c_43s ^ c_38s ^ c_32s ^ c_30s), 1u);
482 const u32 c_47s = rotl32 ((c_44s ^ c_39s ^ c_33s ^ c_31s), 1u);
483 const u32 c_48s = rotl32 ((c_45s ^ c_40s ^ c_34s ^ c_32s), 1u);
484 const u32 c_49s = rotl32 ((c_46s ^ c_41s ^ c_35s ^ c_33s), 1u);
485 const u32 c_50s = rotl32 ((c_47s ^ c_42s ^ c_36s ^ c_34s), 1u);
486 const u32 c_51s = rotl32 ((c_48s ^ c_43s ^ c_37s ^ c_35s), 1u);
487 const u32 c_52s = rotl32 ((c_49s ^ c_44s ^ c_38s ^ c_36s), 1u);
488 const u32 c_53s = rotl32 ((c_50s ^ c_45s ^ c_39s ^ c_37s), 1u);
489 const u32 c_54s = rotl32 ((c_51s ^ c_46s ^ c_40s ^ c_38s), 1u);
490 const u32 c_55s = rotl32 ((c_52s ^ c_47s ^ c_41s ^ c_39s), 1u);
491 const u32 c_56s = rotl32 ((c_53s ^ c_48s ^ c_42s ^ c_40s), 1u);
492 const u32 c_57s = rotl32 ((c_54s ^ c_49s ^ c_43s ^ c_41s), 1u);
493 const u32 c_58s = rotl32 ((c_55s ^ c_50s ^ c_44s ^ c_42s), 1u);
494 const u32 c_59s = rotl32 ((c_56s ^ c_51s ^ c_45s ^ c_43s), 1u);
495 const u32 c_60s = rotl32 ((c_57s ^ c_52s ^ c_46s ^ c_44s), 1u);
496 const u32 c_61s = rotl32 ((c_58s ^ c_53s ^ c_47s ^ c_45s), 1u);
497 const u32 c_62s = rotl32 ((c_59s ^ c_54s ^ c_48s ^ c_46s), 1u);
498 const u32 c_63s = rotl32 ((c_60s ^ c_55s ^ c_49s ^ c_47s), 1u);
499 const u32 c_64s = rotl32 ((c_61s ^ c_56s ^ c_50s ^ c_48s), 1u);
500 const u32 c_65s = rotl32 ((c_62s ^ c_57s ^ c_51s ^ c_49s), 1u);
501 const u32 c_66s = rotl32 ((c_63s ^ c_58s ^ c_52s ^ c_50s), 1u);
502 const u32 c_67s = rotl32 ((c_64s ^ c_59s ^ c_53s ^ c_51s), 1u);
503 const u32 c_68s = rotl32 ((c_65s ^ c_60s ^ c_54s ^ c_52s), 1u);
504 const u32 c_69s = rotl32 ((c_66s ^ c_61s ^ c_55s ^ c_53s), 1u);
505 const u32 c_70s = rotl32 ((c_67s ^ c_62s ^ c_56s ^ c_54s), 1u);
506 const u32 c_71s = rotl32 ((c_68s ^ c_63s ^ c_57s ^ c_55s), 1u);
507 const u32 c_72s = rotl32 ((c_69s ^ c_64s ^ c_58s ^ c_56s), 1u);
508 const u32 c_73s = rotl32 ((c_70s ^ c_65s ^ c_59s ^ c_57s), 1u);
509 const u32 c_74s = rotl32 ((c_71s ^ c_66s ^ c_60s ^ c_58s), 1u);
510 const u32 c_75s = rotl32 ((c_72s ^ c_67s ^ c_61s ^ c_59s), 1u);
512 const u32 c_17sK = c_17s + SHA1C00;
513 const u32 c_18sK = c_18s + SHA1C00;
514 const u32 c_20sK = c_20s + SHA1C01;
515 const u32 c_21sK = c_21s + SHA1C01;
516 const u32 c_23sK = c_23s + SHA1C01;
517 const u32 c_26sK = c_26s + SHA1C01;
518 const u32 c_27sK = c_27s + SHA1C01;
519 const u32 c_29sK = c_29s + SHA1C01;
520 const u32 c_33sK = c_33s + SHA1C01;
521 const u32 c_39sK = c_39s + SHA1C01;
522 const u32 c_41sK = c_41s + SHA1C02;
523 const u32 c_45sK = c_45s + SHA1C02;
524 const u32 c_53sK = c_53s + SHA1C02;
525 const u32 c_65sK = c_65s + SHA1C03;
526 const u32 c_69sK = c_69s + SHA1C03;
528 const u32 w1 = w[ 1] + SHA1C00;
529 const u32 w2 = w[ 2] + SHA1C00;
530 const u32 w3 = w[ 3] + SHA1C00;
531 const u32 w4 = w[ 4] + SHA1C00;
532 const u32 w5 = w[ 5] + SHA1C00;
533 const u32 w6 = w[ 6] + SHA1C00;
534 const u32 w7 = w[ 7] + SHA1C00;
535 const u32 w8 = w[ 8] + SHA1C00;
536 const u32 w9 = w[ 9] + SHA1C00;
537 const u32 wa = w[10] + SHA1C00;
538 const u32 wb = w[11] + SHA1C00;
539 const u32 wc = w[12] + SHA1C00;
540 const u32 wd = w[13] + SHA1C00;
541 const u32 we = w[14] + SHA1C00;
542 const u32 wf = w[15] + SHA1C00;
548 const u32 search[4] =
550 digests_buf[digests_offset].digest_buf[DGST_R0],
551 digests_buf[digests_offset].digest_buf[DGST_R1],
552 digests_buf[digests_offset].digest_buf[DGST_R2],
553 digests_buf[digests_offset].digest_buf[DGST_R3]
560 const u32 e_rev = rotl32 (search[1], 2u);
566 const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
570 for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
572 const u32x w0r = words_buf_r[il_pos];
574 const u32x w0 = w0l | w0r;
576 const u32x w0s01 = rotl32 (w0, 1u);
577 const u32x w0s02 = rotl32 (w0, 2u);
578 const u32x w0s03 = rotl32 (w0, 3u);
579 const u32x w0s04 = rotl32 (w0, 4u);
580 const u32x w0s05 = rotl32 (w0, 5u);
581 const u32x w0s06 = rotl32 (w0, 6u);
582 const u32x w0s07 = rotl32 (w0, 7u);
583 const u32x w0s08 = rotl32 (w0, 8u);
584 const u32x w0s09 = rotl32 (w0, 9u);
585 const u32x w0s10 = rotl32 (w0, 10u);
586 const u32x w0s11 = rotl32 (w0, 11u);
587 const u32x w0s12 = rotl32 (w0, 12u);
588 const u32x w0s13 = rotl32 (w0, 13u);
589 const u32x w0s14 = rotl32 (w0, 14u);
590 const u32x w0s15 = rotl32 (w0, 15u);
591 const u32x w0s16 = rotl32 (w0, 16u);
592 const u32x w0s17 = rotl32 (w0, 17u);
593 const u32x w0s18 = rotl32 (w0, 18u);
594 const u32x w0s19 = rotl32 (w0, 19u);
595 const u32x w0s20 = rotl32 (w0, 20u);
597 const u32x w0s04___w0s06 = w0s04 ^ w0s06;
598 const u32x w0s04___w0s08 = w0s04 ^ w0s08;
599 const u32x w0s08___w0s12 = w0s08 ^ w0s12;
600 const u32x w0s04___w0s06___w0s07 = w0s04___w0s06 ^ w0s07;
611 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0);
612 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, w1);
613 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, w2);
614 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, w3);
615 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, w4);
616 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, w5);
617 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, w6);
618 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, w7);
619 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, w8);
620 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, w9);
621 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, wa);
622 SHA1_STEPX(SHA1_F0o, e, a, b, c, d, wb);
623 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, wc);
624 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, wd);
625 SHA1_STEPX(SHA1_F0o, b, c, d, e, a, we);
626 SHA1_STEPX(SHA1_F0o, a, b, c, d, e, wf);
628 SHA1_STEP (SHA1_F0o, e, a, b, c, d, (c_16s ^ w0s01));
629 SHA1_STEPX(SHA1_F0o, d, e, a, b, c, (c_17sK));
630 SHA1_STEPX(SHA1_F0o, c, d, e, a, b, (c_18sK));
631 SHA1_STEP (SHA1_F0o, b, c, d, e, a, (c_19s ^ w0s02));
636 SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_20sK));
637 SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_21sK));
638 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_22s ^ w0s03));
639 SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_23sK));
640 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_24s ^ w0s02));
641 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_25s ^ w0s04));
642 SHA1_STEPX(SHA1_F1 , e, a, b, c, d, (c_26sK));
643 SHA1_STEPX(SHA1_F1 , d, e, a, b, c, (c_27sK));
644 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_28s ^ w0s05));
645 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_29sK));
646 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_30s ^ w0s02 ^ w0s04));
647 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_31s ^ w0s06));
648 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_32s ^ w0s02 ^ w0s03));
649 SHA1_STEPX(SHA1_F1 , c, d, e, a, b, (c_33sK));
650 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_34s ^ w0s07));
651 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_35s ^ w0s04));
652 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_36s ^ w0s04___w0s06));
653 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_37s ^ w0s08));
654 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_38s ^ w0s04));
655 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_39sK));
660 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_40s ^ w0s04 ^ w0s09));
661 SHA1_STEPX(SHA1_F2o, e, a, b, c, d, (c_41sK));
662 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_42s ^ w0s06 ^ w0s08));
663 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_43s ^ w0s10));
664 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_44s ^ w0s03 ^ w0s06 ^ w0s07));
665 SHA1_STEPX(SHA1_F2o, a, b, c, d, e, (c_45sK));
666 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_46s ^ w0s04 ^ w0s11));
667 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_47s ^ w0s04___w0s08));
668 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_48s ^ w0s03 ^ w0s04___w0s08 ^ w0s05 ^ w0s10));
669 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_49s ^ w0s12));
670 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_50s ^ w0s08));
671 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_51s ^ w0s04___w0s06));
672 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_52s ^ w0s04___w0s08 ^ w0s13));
673 SHA1_STEPX(SHA1_F2o, c, d, e, a, b, (c_53sK));
674 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_54s ^ w0s07 ^ w0s10 ^ w0s12));
675 SHA1_STEP (SHA1_F2o, a, b, c, d, e, (c_55s ^ w0s14));
676 SHA1_STEP (SHA1_F2o, e, a, b, c, d, (c_56s ^ w0s04___w0s06___w0s07 ^ w0s10 ^ w0s11));
677 SHA1_STEP (SHA1_F2o, d, e, a, b, c, (c_57s ^ w0s08));
678 SHA1_STEP (SHA1_F2o, c, d, e, a, b, (c_58s ^ w0s04___w0s08 ^ w0s15));
679 SHA1_STEP (SHA1_F2o, b, c, d, e, a, (c_59s ^ w0s08___w0s12));
684 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_60s ^ w0s04 ^ w0s08___w0s12 ^ w0s07 ^ w0s14));
685 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_61s ^ w0s16));
686 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_62s ^ w0s04___w0s06 ^ w0s08___w0s12));
687 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_63s ^ w0s08));
688 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_64s ^ w0s04___w0s06___w0s07 ^ w0s08___w0s12 ^ w0s17));
689 SHA1_STEPX(SHA1_F1 , a, b, c, d, e, (c_65sK));
690 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_66s ^ w0s14 ^ w0s16));
691 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_67s ^ w0s08 ^ w0s18));
692 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_68s ^ w0s11 ^ w0s14 ^ w0s15));
693 SHA1_STEPX(SHA1_F1 , b, c, d, e, a, (c_69sK));
694 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_70s ^ w0s12 ^ w0s19));
695 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_71s ^ w0s12 ^ w0s16));
696 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_72s ^ w0s05 ^ w0s11 ^ w0s12 ^ w0s13 ^ w0s16 ^ w0s18));
697 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_73s ^ w0s20));
698 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_74s ^ w0s08 ^ w0s16));
699 SHA1_STEP (SHA1_F1 , a, b, c, d, e, (c_75s ^ w0s06 ^ w0s12 ^ w0s14));
701 const u32 c_76s = rotl32 ((c_73s ^ c_68s ^ c_62s ^ c_60s), 1u);
702 const u32 c_77s = rotl32 ((c_74s ^ c_69s ^ c_63s ^ c_61s), 1u);
703 const u32 c_78s = rotl32 ((c_75s ^ c_70s ^ c_64s ^ c_62s), 1u);
704 const u32 c_79s = rotl32 ((c_76s ^ c_71s ^ c_65s ^ c_63s), 1u);
706 const u32x w0s21 = rotl32 (w0, 21u);
707 const u32x w0s22 = rotl32 (w0, 22U);
709 SHA1_STEP (SHA1_F1 , e, a, b, c, d, (c_76s ^ w0s07 ^ w0s08___w0s12 ^ w0s16 ^ w0s21));
710 SHA1_STEP (SHA1_F1 , d, e, a, b, c, (c_77s));
711 SHA1_STEP (SHA1_F1 , c, d, e, a, b, (c_78s ^ w0s07 ^ w0s08 ^ w0s15 ^ w0s18 ^ w0s20));
712 SHA1_STEP (SHA1_F1 , b, c, d, e, a, (c_79s ^ w0s08 ^ w0s22));
725 u32x w5_t = 0x80000000;
746 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
747 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
748 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
749 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
750 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
751 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
752 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
753 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
754 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
755 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
756 SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
757 SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
758 SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
759 SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
760 SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
761 SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
762 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
763 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
764 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
765 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
770 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
771 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
772 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
773 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
774 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
775 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
776 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
777 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
778 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
779 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
780 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
781 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
782 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
783 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
784 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
785 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
786 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
787 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
788 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
789 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
794 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
795 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
796 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
797 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
798 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
799 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
800 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
801 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
802 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
803 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
804 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
805 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
806 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
807 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
808 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
809 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
810 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
811 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
812 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
813 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
818 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
819 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
820 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
821 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
822 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
823 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
824 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
825 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
826 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
827 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
828 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
829 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
830 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
831 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
832 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
833 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
835 bool q_cond = allx (e_rev != e);
837 if (q_cond) continue;
839 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
840 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
841 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
842 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
850 #include VECT_COMPARE_S
854 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00300_m04 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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)
860 const u32 gid = get_global_id (0);
862 if (gid >= gid_max) return;
866 w[ 0] = pws[gid].i[ 0];
867 w[ 1] = pws[gid].i[ 1];
868 w[ 2] = pws[gid].i[ 2];
869 w[ 3] = pws[gid].i[ 3];
881 w[15] = pws[gid].i[15];
883 const u32 pw_len = pws[gid].pw_len;
889 m00300m (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);
892 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00300_m08 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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)
898 const u32 gid = get_global_id (0);
900 if (gid >= gid_max) return;
904 w[ 0] = pws[gid].i[ 0];
905 w[ 1] = pws[gid].i[ 1];
906 w[ 2] = pws[gid].i[ 2];
907 w[ 3] = pws[gid].i[ 3];
908 w[ 4] = pws[gid].i[ 4];
909 w[ 5] = pws[gid].i[ 5];
910 w[ 6] = pws[gid].i[ 6];
911 w[ 7] = pws[gid].i[ 7];
919 w[15] = pws[gid].i[15];
921 const u32 pw_len = pws[gid].pw_len;
927 m00300m (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);
930 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00300_m16 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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)
936 const u32 gid = get_global_id (0);
938 if (gid >= gid_max) return;
942 w[ 0] = pws[gid].i[ 0];
943 w[ 1] = pws[gid].i[ 1];
944 w[ 2] = pws[gid].i[ 2];
945 w[ 3] = pws[gid].i[ 3];
946 w[ 4] = pws[gid].i[ 4];
947 w[ 5] = pws[gid].i[ 5];
948 w[ 6] = pws[gid].i[ 6];
949 w[ 7] = pws[gid].i[ 7];
950 w[ 8] = pws[gid].i[ 8];
951 w[ 9] = pws[gid].i[ 9];
952 w[10] = pws[gid].i[10];
953 w[11] = pws[gid].i[11];
954 w[12] = pws[gid].i[12];
955 w[13] = pws[gid].i[13];
956 w[14] = pws[gid].i[14];
957 w[15] = pws[gid].i[15];
959 const u32 pw_len = pws[gid].pw_len;
965 m00300m (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);
968 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00300_s04 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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)
974 const u32 gid = get_global_id (0);
976 if (gid >= gid_max) return;
980 w[ 0] = pws[gid].i[ 0];
981 w[ 1] = pws[gid].i[ 1];
982 w[ 2] = pws[gid].i[ 2];
983 w[ 3] = pws[gid].i[ 3];
995 w[15] = pws[gid].i[15];
997 const u32 pw_len = pws[gid].pw_len;
1003 m00300s (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);
1006 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00300_s08 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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)
1012 const u32 gid = get_global_id (0);
1014 if (gid >= gid_max) return;
1018 w[ 0] = pws[gid].i[ 0];
1019 w[ 1] = pws[gid].i[ 1];
1020 w[ 2] = pws[gid].i[ 2];
1021 w[ 3] = pws[gid].i[ 3];
1022 w[ 4] = pws[gid].i[ 4];
1023 w[ 5] = pws[gid].i[ 5];
1024 w[ 6] = pws[gid].i[ 6];
1025 w[ 7] = pws[gid].i[ 7];
1033 w[15] = pws[gid].i[15];
1035 const u32 pw_len = pws[gid].pw_len;
1041 m00300s (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);
1044 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m00300_s16 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global 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)
1050 const u32 gid = get_global_id (0);
1052 if (gid >= gid_max) return;
1056 w[ 0] = pws[gid].i[ 0];
1057 w[ 1] = pws[gid].i[ 1];
1058 w[ 2] = pws[gid].i[ 2];
1059 w[ 3] = pws[gid].i[ 3];
1060 w[ 4] = pws[gid].i[ 4];
1061 w[ 5] = pws[gid].i[ 5];
1062 w[ 6] = pws[gid].i[ 6];
1063 w[ 7] = pws[gid].i[ 7];
1064 w[ 8] = pws[gid].i[ 8];
1065 w[ 9] = pws[gid].i[ 9];
1066 w[10] = pws[gid].i[10];
1067 w[11] = pws[gid].i[11];
1068 w[12] = pws[gid].i[12];
1069 w[13] = pws[gid].i[13];
1070 w[14] = pws[gid].i[14];
1071 w[15] = pws[gid].i[15];
1073 const u32 pw_len = pws[gid].pw_len;
1079 m00300s (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);