2 * Author......: Jens Steube <jens.steube@gmail.com>
8 #include "include/constants.h"
9 #include "include/kernel_vendor.h"
16 #include "include/kernel_functions.c"
17 #include "types_ocl.c"
19 #include "include/rp_gpu.h"
22 #define COMPARE_S "check_single_comp4.c"
23 #define COMPARE_M "check_multi_comp4.c"
25 static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
53 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
54 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
55 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
56 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
57 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
58 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
59 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
60 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
61 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
62 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
63 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
64 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
65 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
66 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
67 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
68 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
69 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
70 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
71 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
72 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
77 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
78 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
79 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
80 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
81 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
82 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
83 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
84 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
85 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
86 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
87 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
88 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
89 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
90 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
91 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
92 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
93 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
94 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
95 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
96 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
101 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
102 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
103 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
104 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
105 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
106 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
107 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
108 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
109 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
110 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
111 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
112 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
113 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
114 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
115 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
116 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
117 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
118 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
119 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
120 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
125 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
126 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
127 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
128 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
129 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
130 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
131 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
132 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
133 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
134 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
135 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
136 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
137 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
138 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
139 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
140 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
141 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
142 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
143 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
144 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
153 __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 *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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
159 const u32 lid = get_local_id (0);
165 const u32 gid = get_global_id (0);
167 if (gid >= gid_max) return;
171 pw_buf0[0] = pws[gid].i[ 0];
172 pw_buf0[1] = pws[gid].i[ 1];
173 pw_buf0[2] = pws[gid].i[ 2];
174 pw_buf0[3] = pws[gid].i[ 3];
178 pw_buf1[0] = pws[gid].i[ 4];
179 pw_buf1[1] = pws[gid].i[ 5];
180 pw_buf1[2] = pws[gid].i[ 6];
181 pw_buf1[3] = pws[gid].i[ 7];
183 const u32 pw_len = pws[gid].pw_len;
189 const u32 salt_iter = salt_bufs[salt_pos].salt_iter;
193 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
194 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
195 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
196 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
200 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
201 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
202 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
203 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
205 const u32 salt_len = salt_bufs[salt_pos].salt_len;
209 domain_buf0[0] = salt_bufs[salt_pos].salt_buf_pc[ 0];
210 domain_buf0[1] = salt_bufs[salt_pos].salt_buf_pc[ 1];
211 domain_buf0[2] = salt_bufs[salt_pos].salt_buf_pc[ 2];
212 domain_buf0[3] = salt_bufs[salt_pos].salt_buf_pc[ 3];
216 domain_buf1[0] = salt_bufs[salt_pos].salt_buf_pc[ 4];
217 domain_buf1[1] = salt_bufs[salt_pos].salt_buf_pc[ 5];
218 domain_buf1[2] = salt_bufs[salt_pos].salt_buf_pc[ 6];
221 const u32 domain_len = salt_bufs[salt_pos].salt_buf_pc[ 7];
227 for (u32 il_pos = 0; il_pos < rules_cnt; il_pos++)
251 const u32 out_len = apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
281 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, 1);
283 w0_t[0] |= pw_len & 0xff;
291 s0[0] = salt_buf0[0];
292 s0[1] = salt_buf0[1];
293 s0[2] = salt_buf0[2];
294 s0[3] = salt_buf0[3];
298 s1[0] = salt_buf1[0];
299 s1[1] = salt_buf1[1];
300 s1[2] = salt_buf1[2];
301 s1[3] = salt_buf1[3];
317 switch_buffer_by_offset (s0, s1, s2, s3, 1 + out_len + domain_len + 1);
321 d0[0] = domain_buf0[0];
322 d0[1] = domain_buf0[1];
323 d0[2] = domain_buf0[2];
324 d0[3] = domain_buf0[3];
328 d1[0] = domain_buf1[0];
329 d1[1] = domain_buf1[1];
330 d1[2] = domain_buf1[2];
347 switch_buffer_by_offset (d0, d1, d2, d3, 1 + out_len);
355 w0_t2[0] = swap32 (w0_t[0] | d0[0] | s0[0]);
356 w0_t2[1] = swap32 (w0_t[1] | d0[1] | s0[1]);
357 w0_t2[2] = swap32 (w0_t[2] | d0[2] | s0[2]);
358 w0_t2[3] = swap32 (w0_t[3] | d0[3] | s0[3]);
362 w1_t2[0] = swap32 (w1_t[0] | d1[0] | s1[0]);
363 w1_t2[1] = swap32 (w1_t[1] | d1[1] | s1[1]);
364 w1_t2[2] = swap32 (w1_t[2] | d1[2] | s1[2]);
365 w1_t2[3] = swap32 (w1_t[3] | d1[3] | s1[3]);
369 w2_t2[0] = swap32 (w2_t[0] | d2[0] | s2[0]);
370 w2_t2[1] = swap32 (w2_t[1] | d2[1] | s2[1]);
371 w2_t2[2] = swap32 (w2_t[2] | d2[2] | s2[2]);
372 w2_t2[3] = swap32 (w2_t[3] | d2[3] | s2[3]);
376 w3_t2[0] = swap32 (w3_t[0] | d3[0] | s3[0]);
377 w3_t2[1] = swap32 (w3_t[1] | d3[1] | s3[1]);
379 w3_t2[3] = (1 + out_len + domain_len + 1 + salt_len) * 8;
389 sha1_transform (w0_t2, w1_t2, w2_t2, w3_t2, digest);
393 for (u32 i = 0; i < salt_iter; i++)
397 w0_t3[0] = digest[0];
398 w0_t3[1] = digest[1];
399 w0_t3[2] = digest[2];
400 w0_t3[3] = digest[3];
404 w1_t3[0] = digest[4];
405 w1_t3[1] = swap32 (salt_buf0[0]);
406 w1_t3[2] = swap32 (salt_buf0[1]);
407 w1_t3[3] = swap32 (salt_buf0[2]);
411 w2_t3[0] = swap32 (salt_buf0[3]);
412 w2_t3[1] = swap32 (salt_buf1[0]);
413 w2_t3[2] = swap32 (salt_buf1[1]);
414 w2_t3[3] = swap32 (salt_buf1[2]);
418 w3_t3[0] = swap32 (salt_buf1[3]);
421 w3_t3[3] = (20 + salt_len) * 8;
429 sha1_transform (w0_t3, w1_t3, w2_t3, w3_t3, digest);
432 const u32 r0 = digest[3];
433 const u32 r1 = digest[4];
434 const u32 r2 = digest[2];
435 const u32 r3 = digest[1];
441 __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 *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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
445 __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 *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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
449 __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 *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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
455 const u32 lid = get_local_id (0);
461 const u32 gid = get_global_id (0);
463 if (gid >= gid_max) return;
467 pw_buf0[0] = pws[gid].i[ 0];
468 pw_buf0[1] = pws[gid].i[ 1];
469 pw_buf0[2] = pws[gid].i[ 2];
470 pw_buf0[3] = pws[gid].i[ 3];
474 pw_buf1[0] = pws[gid].i[ 4];
475 pw_buf1[1] = pws[gid].i[ 5];
476 pw_buf1[2] = pws[gid].i[ 6];
477 pw_buf1[3] = pws[gid].i[ 7];
479 const u32 pw_len = pws[gid].pw_len;
485 const u32 salt_iter = salt_bufs[salt_pos].salt_iter;
489 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
490 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
491 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
492 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
496 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
497 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
498 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
499 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
501 const u32 salt_len = salt_bufs[salt_pos].salt_len;
505 domain_buf0[0] = salt_bufs[salt_pos].salt_buf_pc[ 0];
506 domain_buf0[1] = salt_bufs[salt_pos].salt_buf_pc[ 1];
507 domain_buf0[2] = salt_bufs[salt_pos].salt_buf_pc[ 2];
508 domain_buf0[3] = salt_bufs[salt_pos].salt_buf_pc[ 3];
512 domain_buf1[0] = salt_bufs[salt_pos].salt_buf_pc[ 4];
513 domain_buf1[1] = salt_bufs[salt_pos].salt_buf_pc[ 5];
514 domain_buf1[2] = salt_bufs[salt_pos].salt_buf_pc[ 6];
517 const u32 domain_len = salt_bufs[salt_pos].salt_buf_pc[ 7];
523 const u32 search[4] =
525 digests_buf[digests_offset].digest_buf[DGST_R0],
526 digests_buf[digests_offset].digest_buf[DGST_R1],
527 digests_buf[digests_offset].digest_buf[DGST_R2],
528 digests_buf[digests_offset].digest_buf[DGST_R3]
535 for (u32 il_pos = 0; il_pos < rules_cnt; il_pos++)
559 const u32 out_len = apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
589 switch_buffer_by_offset (w0_t, w1_t, w2_t, w3_t, 1);
591 w0_t[0] |= pw_len & 0xff;
599 s0[0] = salt_buf0[0];
600 s0[1] = salt_buf0[1];
601 s0[2] = salt_buf0[2];
602 s0[3] = salt_buf0[3];
606 s1[0] = salt_buf1[0];
607 s1[1] = salt_buf1[1];
608 s1[2] = salt_buf1[2];
609 s1[3] = salt_buf1[3];
625 switch_buffer_by_offset (s0, s1, s2, s3, 1 + out_len + domain_len + 1);
629 d0[0] = domain_buf0[0];
630 d0[1] = domain_buf0[1];
631 d0[2] = domain_buf0[2];
632 d0[3] = domain_buf0[3];
636 d1[0] = domain_buf1[0];
637 d1[1] = domain_buf1[1];
638 d1[2] = domain_buf1[2];
655 switch_buffer_by_offset (d0, d1, d2, d3, 1 + out_len);
663 w0_t2[0] = swap32 (w0_t[0] | d0[0] | s0[0]);
664 w0_t2[1] = swap32 (w0_t[1] | d0[1] | s0[1]);
665 w0_t2[2] = swap32 (w0_t[2] | d0[2] | s0[2]);
666 w0_t2[3] = swap32 (w0_t[3] | d0[3] | s0[3]);
670 w1_t2[0] = swap32 (w1_t[0] | d1[0] | s1[0]);
671 w1_t2[1] = swap32 (w1_t[1] | d1[1] | s1[1]);
672 w1_t2[2] = swap32 (w1_t[2] | d1[2] | s1[2]);
673 w1_t2[3] = swap32 (w1_t[3] | d1[3] | s1[3]);
677 w2_t2[0] = swap32 (w2_t[0] | d2[0] | s2[0]);
678 w2_t2[1] = swap32 (w2_t[1] | d2[1] | s2[1]);
679 w2_t2[2] = swap32 (w2_t[2] | d2[2] | s2[2]);
680 w2_t2[3] = swap32 (w2_t[3] | d2[3] | s2[3]);
684 w3_t2[0] = swap32 (w3_t[0] | d3[0] | s3[0]);
685 w3_t2[1] = swap32 (w3_t[1] | d3[1] | s3[1]);
687 w3_t2[3] = (1 + out_len + domain_len + 1 + salt_len) * 8;
697 sha1_transform (w0_t2, w1_t2, w2_t2, w3_t2, digest);
701 for (u32 i = 0; i < salt_iter; i++)
705 w0_t3[0] = digest[0];
706 w0_t3[1] = digest[1];
707 w0_t3[2] = digest[2];
708 w0_t3[3] = digest[3];
712 w1_t3[0] = digest[4];
713 w1_t3[1] = swap32 (salt_buf0[0]);
714 w1_t3[2] = swap32 (salt_buf0[1]);
715 w1_t3[3] = swap32 (salt_buf0[2]);
719 w2_t3[0] = swap32 (salt_buf0[3]);
720 w2_t3[1] = swap32 (salt_buf1[0]);
721 w2_t3[2] = swap32 (salt_buf1[1]);
722 w2_t3[3] = swap32 (salt_buf1[2]);
726 w3_t3[0] = swap32 (salt_buf1[3]);
729 w3_t3[3] = (20 + salt_len) * 8;
737 sha1_transform (w0_t3, w1_t3, w2_t3, w3_t3, digest);
740 const u32 r0 = digest[3];
741 const u32 r1 = digest[4];
742 const u32 r2 = digest[2];
743 const u32 r3 = digest[1];
749 __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 *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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
753 __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 *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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)