2 * Author......: Jens Steube <jens.steube@gmail.com>
8 #include "include/constants.h"
9 #include "include/kernel_vendor.h"
28 #include "include/kernel_functions.c"
29 #include "types_amd.c"
30 #include "common_amd.c"
33 #define VECT_COMPARE_S "check_single_vect1_comp4.c"
34 #define VECT_COMPARE_M "check_multi_vect1_comp4.c"
38 #define VECT_COMPARE_S "check_single_vect2_comp4.c"
39 #define VECT_COMPARE_M "check_multi_vect2_comp4.c"
43 #define VECT_COMPARE_S "check_single_vect4_comp4.c"
44 #define VECT_COMPARE_M "check_multi_vect4_comp4.c"
47 static void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5])
75 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
76 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
77 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
78 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
79 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
80 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
81 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
82 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
83 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
84 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
85 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
86 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
87 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
88 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
89 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
90 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
91 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
92 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
93 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
94 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
99 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
100 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
101 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
102 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
103 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
104 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
105 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
106 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
107 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
108 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
109 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
110 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
111 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
112 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
113 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
114 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
115 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
116 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
117 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
118 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
123 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
124 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
125 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
126 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
127 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
128 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
129 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
130 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
131 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
132 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
133 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
134 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
135 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
136 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
137 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
138 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
139 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
140 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
141 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
142 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
147 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
148 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
149 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
150 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
151 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
152 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
153 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
154 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
155 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
156 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
157 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
158 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
159 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
160 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
161 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
162 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
163 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
164 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
165 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
166 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
175 static void m08300m (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], const u32 pw_len, __global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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)
181 const u32 gid = get_global_id (0);
182 const u32 lid = get_local_id (0);
188 const u32 salt_iter = salt_bufs[salt_pos].salt_iter;
192 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
193 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
194 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
195 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
199 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
200 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
201 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
202 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
204 const u32 salt_len = salt_bufs[salt_pos].salt_len;
208 domain_buf0[0] = salt_bufs[salt_pos].salt_buf_pc[ 0];
209 domain_buf0[1] = salt_bufs[salt_pos].salt_buf_pc[ 1];
210 domain_buf0[2] = salt_bufs[salt_pos].salt_buf_pc[ 2];
211 domain_buf0[3] = salt_bufs[salt_pos].salt_buf_pc[ 3];
215 domain_buf1[0] = salt_bufs[salt_pos].salt_buf_pc[ 4];
216 domain_buf1[1] = salt_bufs[salt_pos].salt_buf_pc[ 5];
217 domain_buf1[2] = salt_bufs[salt_pos].salt_buf_pc[ 6];
220 const u32 domain_len = salt_bufs[salt_pos].salt_buf_pc[ 7];
228 s0[0] = salt_buf0[0];
229 s0[1] = salt_buf0[1];
230 s0[2] = salt_buf0[2];
231 s0[3] = salt_buf0[3];
235 s1[0] = salt_buf1[0];
236 s1[1] = salt_buf1[1];
237 s1[2] = salt_buf1[2];
238 s1[3] = salt_buf1[3];
254 switch_buffer_by_offset (s0, s1, s2, s3, 1 + pw_len + domain_len + 1);
258 d0[0] = domain_buf0[0];
259 d0[1] = domain_buf0[1];
260 d0[2] = domain_buf0[2];
261 d0[3] = domain_buf0[3];
265 d1[0] = domain_buf1[0];
266 d1[1] = domain_buf1[1];
267 d1[2] = domain_buf1[2];
284 switch_buffer_by_offset (d0, d1, d2, d3, 1 + pw_len);
292 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
294 const u32 w0r = bfs_buf[il_pos].i;
326 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, 1);
328 w0_t[0] |= pw_len & 0xff;
336 w0_t2[0] = swap_workaround (w0_t[0] | d0[0] | s0[0]);
337 w0_t2[1] = swap_workaround (w0_t[1] | d0[1] | s0[1]);
338 w0_t2[2] = swap_workaround (w0_t[2] | d0[2] | s0[2]);
339 w0_t2[3] = swap_workaround (w0_t[3] | d0[3] | s0[3]);
343 w1_t2[0] = swap_workaround (w1_t[0] | d1[0] | s1[0]);
344 w1_t2[1] = swap_workaround (w1_t[1] | d1[1] | s1[1]);
345 w1_t2[2] = swap_workaround (w1_t[2] | d1[2] | s1[2]);
346 w1_t2[3] = swap_workaround (w1_t[3] | d1[3] | s1[3]);
350 w2_t2[0] = swap_workaround (w2_t[0] | d2[0] | s2[0]);
351 w2_t2[1] = swap_workaround (w2_t[1] | d2[1] | s2[1]);
352 w2_t2[2] = swap_workaround (w2_t[2] | d2[2] | s2[2]);
353 w2_t2[3] = swap_workaround (w2_t[3] | d2[3] | s2[3]);
357 w3_t2[0] = swap_workaround (w3_t[0] | d3[0] | s3[0]);
358 w3_t2[1] = swap_workaround (w3_t[1] | d3[1] | s3[1]);
360 w3_t2[3] = (1 + pw_len + domain_len + 1 + salt_len) * 8;
370 sha1_transform (w0_t2, w1_t2, w2_t2, w3_t2, digest);
374 for (u32 i = 0; i < salt_iter; i++)
378 w0_t3[0] = digest[0];
379 w0_t3[1] = digest[1];
380 w0_t3[2] = digest[2];
381 w0_t3[3] = digest[3];
385 w1_t3[0] = digest[4];
386 w1_t3[1] = swap_workaround (salt_buf0[0]);
387 w1_t3[2] = swap_workaround (salt_buf0[1]);
388 w1_t3[3] = swap_workaround (salt_buf0[2]);
392 w2_t3[0] = swap_workaround (salt_buf0[3]);
393 w2_t3[1] = swap_workaround (salt_buf1[0]);
394 w2_t3[2] = swap_workaround (salt_buf1[1]);
395 w2_t3[3] = swap_workaround (salt_buf1[2]);
399 w3_t3[0] = swap_workaround (salt_buf1[3]);
402 w3_t3[3] = (20 + salt_len) * 8;
410 sha1_transform (w0_t3, w1_t3, w2_t3, w3_t3, digest);
413 const u32x r0 = digest[3];
414 const u32x r1 = digest[4];
415 const u32x r2 = digest[2];
416 const u32x r3 = digest[1];
418 #include VECT_COMPARE_M
422 static void m08300s (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], const u32 pw_len, __global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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)
428 const u32 gid = get_global_id (0);
429 const u32 lid = get_local_id (0);
435 const u32 search[4] =
437 digests_buf[digests_offset].digest_buf[DGST_R0],
438 digests_buf[digests_offset].digest_buf[DGST_R1],
439 digests_buf[digests_offset].digest_buf[DGST_R2],
440 digests_buf[digests_offset].digest_buf[DGST_R3]
447 const u32 salt_iter = salt_bufs[salt_pos].salt_iter;
451 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
452 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
453 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
454 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
458 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
459 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
460 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
461 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
463 const u32 salt_len = salt_bufs[salt_pos].salt_len;
467 domain_buf0[0] = salt_bufs[salt_pos].salt_buf_pc[ 0];
468 domain_buf0[1] = salt_bufs[salt_pos].salt_buf_pc[ 1];
469 domain_buf0[2] = salt_bufs[salt_pos].salt_buf_pc[ 2];
470 domain_buf0[3] = salt_bufs[salt_pos].salt_buf_pc[ 3];
474 domain_buf1[0] = salt_bufs[salt_pos].salt_buf_pc[ 4];
475 domain_buf1[1] = salt_bufs[salt_pos].salt_buf_pc[ 5];
476 domain_buf1[2] = salt_bufs[salt_pos].salt_buf_pc[ 6];
479 const u32 domain_len = salt_bufs[salt_pos].salt_buf_pc[ 7];
487 s0[0] = salt_buf0[0];
488 s0[1] = salt_buf0[1];
489 s0[2] = salt_buf0[2];
490 s0[3] = salt_buf0[3];
494 s1[0] = salt_buf1[0];
495 s1[1] = salt_buf1[1];
496 s1[2] = salt_buf1[2];
497 s1[3] = salt_buf1[3];
513 switch_buffer_by_offset (s0, s1, s2, s3, 1 + pw_len + domain_len + 1);
517 d0[0] = domain_buf0[0];
518 d0[1] = domain_buf0[1];
519 d0[2] = domain_buf0[2];
520 d0[3] = domain_buf0[3];
524 d1[0] = domain_buf1[0];
525 d1[1] = domain_buf1[1];
526 d1[2] = domain_buf1[2];
543 switch_buffer_by_offset (d0, d1, d2, d3, 1 + pw_len);
551 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
553 const u32 w0r = bfs_buf[il_pos].i;
585 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, 1);
587 w0_t[0] |= pw_len & 0xff;
595 w0_t2[0] = swap_workaround (w0_t[0] | d0[0] | s0[0]);
596 w0_t2[1] = swap_workaround (w0_t[1] | d0[1] | s0[1]);
597 w0_t2[2] = swap_workaround (w0_t[2] | d0[2] | s0[2]);
598 w0_t2[3] = swap_workaround (w0_t[3] | d0[3] | s0[3]);
602 w1_t2[0] = swap_workaround (w1_t[0] | d1[0] | s1[0]);
603 w1_t2[1] = swap_workaround (w1_t[1] | d1[1] | s1[1]);
604 w1_t2[2] = swap_workaround (w1_t[2] | d1[2] | s1[2]);
605 w1_t2[3] = swap_workaround (w1_t[3] | d1[3] | s1[3]);
609 w2_t2[0] = swap_workaround (w2_t[0] | d2[0] | s2[0]);
610 w2_t2[1] = swap_workaround (w2_t[1] | d2[1] | s2[1]);
611 w2_t2[2] = swap_workaround (w2_t[2] | d2[2] | s2[2]);
612 w2_t2[3] = swap_workaround (w2_t[3] | d2[3] | s2[3]);
616 w3_t2[0] = swap_workaround (w3_t[0] | d3[0] | s3[0]);
617 w3_t2[1] = swap_workaround (w3_t[1] | d3[1] | s3[1]);
619 w3_t2[3] = (1 + pw_len + domain_len + 1 + salt_len) * 8;
629 sha1_transform (w0_t2, w1_t2, w2_t2, w3_t2, digest);
633 for (u32 i = 0; i < salt_iter; i++)
637 w0_t3[0] = digest[0];
638 w0_t3[1] = digest[1];
639 w0_t3[2] = digest[2];
640 w0_t3[3] = digest[3];
644 w1_t3[0] = digest[4];
645 w1_t3[1] = swap_workaround (salt_buf0[0]);
646 w1_t3[2] = swap_workaround (salt_buf0[1]);
647 w1_t3[3] = swap_workaround (salt_buf0[2]);
651 w2_t3[0] = swap_workaround (salt_buf0[3]);
652 w2_t3[1] = swap_workaround (salt_buf1[0]);
653 w2_t3[2] = swap_workaround (salt_buf1[1]);
654 w2_t3[3] = swap_workaround (salt_buf1[2]);
658 w3_t3[0] = swap_workaround (salt_buf1[3]);
661 w3_t3[3] = (20 + salt_len) * 8;
669 sha1_transform (w0_t3, w1_t3, w2_t3, w3_t3, digest);
672 const u32x r0 = digest[3];
673 const u32x r1 = digest[4];
674 const u32x r2 = digest[2];
675 const u32x r3 = digest[1];
677 #include VECT_COMPARE_S
681 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08300_m04 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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 *ss, __global void *ess, __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)
687 const u32 gid = get_global_id (0);
689 if (gid >= gid_max) return;
693 w0[0] = pws[gid].i[ 0];
694 w0[1] = pws[gid].i[ 1];
695 w0[2] = pws[gid].i[ 2];
696 w0[3] = pws[gid].i[ 3];
719 const u32 pw_len = pws[gid].pw_len;
725 m08300m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, ss, ess, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
728 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08300_m08 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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 *ss, __global void *ess, __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)
734 const u32 gid = get_global_id (0);
736 if (gid >= gid_max) return;
740 w0[0] = pws[gid].i[ 0];
741 w0[1] = pws[gid].i[ 1];
742 w0[2] = pws[gid].i[ 2];
743 w0[3] = pws[gid].i[ 3];
747 w1[0] = pws[gid].i[ 4];
748 w1[1] = pws[gid].i[ 5];
749 w1[2] = pws[gid].i[ 6];
750 w1[3] = pws[gid].i[ 7];
766 const u32 pw_len = pws[gid].pw_len;
772 m08300m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, ss, ess, 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 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08300_m16 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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 *ss, __global void *ess, __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)
781 const u32 gid = get_global_id (0);
783 if (gid >= gid_max) return;
787 w0[0] = pws[gid].i[ 0];
788 w0[1] = pws[gid].i[ 1];
789 w0[2] = pws[gid].i[ 2];
790 w0[3] = pws[gid].i[ 3];
794 w1[0] = pws[gid].i[ 4];
795 w1[1] = pws[gid].i[ 5];
796 w1[2] = pws[gid].i[ 6];
797 w1[3] = pws[gid].i[ 7];
801 w2[0] = pws[gid].i[ 8];
802 w2[1] = pws[gid].i[ 9];
803 w2[2] = pws[gid].i[10];
804 w2[3] = pws[gid].i[11];
808 w3[0] = pws[gid].i[12];
809 w3[1] = pws[gid].i[13];
813 const u32 pw_len = pws[gid].pw_len;
819 m08300m (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, ss, ess, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
822 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08300_s04 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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 *ss, __global void *ess, __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)
828 const u32 gid = get_global_id (0);
830 if (gid >= gid_max) return;
834 w0[0] = pws[gid].i[ 0];
835 w0[1] = pws[gid].i[ 1];
836 w0[2] = pws[gid].i[ 2];
837 w0[3] = pws[gid].i[ 3];
860 const u32 pw_len = pws[gid].pw_len;
866 m08300s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, ss, ess, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
869 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08300_s08 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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 *ss, __global void *ess, __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)
875 const u32 gid = get_global_id (0);
877 if (gid >= gid_max) return;
881 w0[0] = pws[gid].i[ 0];
882 w0[1] = pws[gid].i[ 1];
883 w0[2] = pws[gid].i[ 2];
884 w0[3] = pws[gid].i[ 3];
888 w1[0] = pws[gid].i[ 4];
889 w1[1] = pws[gid].i[ 5];
890 w1[2] = pws[gid].i[ 6];
891 w1[3] = pws[gid].i[ 7];
907 const u32 pw_len = pws[gid].pw_len;
913 m08300s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, ss, ess, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
916 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08300_s16 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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 *ss, __global void *ess, __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)
922 const u32 gid = get_global_id (0);
924 if (gid >= gid_max) return;
928 w0[0] = pws[gid].i[ 0];
929 w0[1] = pws[gid].i[ 1];
930 w0[2] = pws[gid].i[ 2];
931 w0[3] = pws[gid].i[ 3];
935 w1[0] = pws[gid].i[ 4];
936 w1[1] = pws[gid].i[ 5];
937 w1[2] = pws[gid].i[ 6];
938 w1[3] = pws[gid].i[ 7];
942 w2[0] = pws[gid].i[ 8];
943 w2[1] = pws[gid].i[ 9];
944 w2[2] = pws[gid].i[10];
945 w2[3] = pws[gid].i[11];
949 w3[0] = pws[gid].i[12];
950 w3[1] = pws[gid].i[13];
954 const u32 pw_len = pws[gid].pw_len;
960 m08300s (w0, w1, w2, w3, pw_len, pws, rules_buf, combs_buf, bfs_buf, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, ss, ess, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);