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 "OpenCL/types_ocl.c"
18 #include "OpenCL/common.c"
20 #define COMPARE_S "OpenCL/check_single_comp4.c"
21 #define COMPARE_M "OpenCL/check_multi_comp4.c"
23 #define uint_to_hex_lower8_le(i) l_bin2asc[(i)]
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 static void m08400m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global kernel_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, __local u32 l_bin2asc[256])
159 const u32 gid = get_global_id (0);
160 const u32 lid = get_local_id (0);
168 salt_buf0[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 0]);
169 salt_buf0[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 1]);
170 salt_buf0[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 2]);
171 salt_buf0[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 3]);
175 salt_buf1[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 4]);
176 salt_buf1[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 5]);
177 salt_buf1[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 6]);
178 salt_buf1[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 7]);
182 salt_buf2[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 8]);
183 salt_buf2[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 9]);
187 const u32 salt_len = salt_bufs[salt_pos].salt_len;
195 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
197 const u32 w0r = bfs_buf[il_pos].i;
227 w3_t[3] = pw_len * 8;
237 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
251 w0_t[0] = salt_buf0[0];
252 w0_t[1] = salt_buf0[1];
253 w0_t[2] = salt_buf0[2];
254 w0_t[3] = salt_buf0[3];
255 w1_t[0] = salt_buf1[0];
256 w1_t[1] = salt_buf1[1];
257 w1_t[2] = salt_buf1[2];
258 w1_t[3] = salt_buf1[3];
259 w2_t[0] = salt_buf2[0];
260 w2_t[1] = salt_buf2[1];
261 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
262 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
263 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
264 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
265 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
266 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
267 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
268 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
269 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
270 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
271 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
272 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
280 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
282 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
283 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
284 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
285 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
286 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
287 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
288 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
289 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
290 w1_t[0] = 0x80000000;
303 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
311 w0_t[0] = salt_buf0[0];
312 w0_t[1] = salt_buf0[1];
313 w0_t[2] = salt_buf0[2];
314 w0_t[3] = salt_buf0[3];
315 w1_t[0] = salt_buf1[0];
316 w1_t[1] = salt_buf1[1];
317 w1_t[2] = salt_buf1[2];
318 w1_t[3] = salt_buf1[3];
319 w2_t[0] = salt_buf2[0];
320 w2_t[1] = salt_buf2[1];
321 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
322 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
323 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
324 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
325 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
326 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
327 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
328 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
329 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
330 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
331 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
332 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
340 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
342 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
343 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
344 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
345 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
346 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
347 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
348 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
349 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
350 w1_t[0] = 0x80000000;
363 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
365 const u32 r0 = digest[3];
366 const u32 r1 = digest[4];
367 const u32 r2 = digest[2];
368 const u32 r3 = digest[1];
374 static void m08400s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global kernel_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, __local u32 l_bin2asc[256])
380 const u32 gid = get_global_id (0);
381 const u32 lid = get_local_id (0);
387 const u32 search[4] =
389 digests_buf[digests_offset].digest_buf[DGST_R0],
390 digests_buf[digests_offset].digest_buf[DGST_R1],
391 digests_buf[digests_offset].digest_buf[DGST_R2],
392 digests_buf[digests_offset].digest_buf[DGST_R3]
401 salt_buf0[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 0]);
402 salt_buf0[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 1]);
403 salt_buf0[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 2]);
404 salt_buf0[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 3]);
408 salt_buf1[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 4]);
409 salt_buf1[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 5]);
410 salt_buf1[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 6]);
411 salt_buf1[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 7]);
415 salt_buf2[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 8]);
416 salt_buf2[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 9]);
420 const u32 salt_len = salt_bufs[salt_pos].salt_len;
428 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
430 const u32 w0r = bfs_buf[il_pos].i;
460 w3_t[3] = pw_len * 8;
470 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
484 w0_t[0] = salt_buf0[0];
485 w0_t[1] = salt_buf0[1];
486 w0_t[2] = salt_buf0[2];
487 w0_t[3] = salt_buf0[3];
488 w1_t[0] = salt_buf1[0];
489 w1_t[1] = salt_buf1[1];
490 w1_t[2] = salt_buf1[2];
491 w1_t[3] = salt_buf1[3];
492 w2_t[0] = salt_buf2[0];
493 w2_t[1] = salt_buf2[1];
494 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
495 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
496 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
497 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
498 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
499 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
500 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
501 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
502 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
503 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
504 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
505 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
513 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
515 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
516 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
517 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
518 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
519 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
520 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
521 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
522 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
523 w1_t[0] = 0x80000000;
534 w3_t[3] = (salt_len + 40) * 8;
536 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
544 w0_t[0] = salt_buf0[0];
545 w0_t[1] = salt_buf0[1];
546 w0_t[2] = salt_buf0[2];
547 w0_t[3] = salt_buf0[3];
548 w1_t[0] = salt_buf1[0];
549 w1_t[1] = salt_buf1[1];
550 w1_t[2] = salt_buf1[2];
551 w1_t[3] = salt_buf1[3];
552 w2_t[0] = salt_buf2[0];
553 w2_t[1] = salt_buf2[1];
554 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
555 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
556 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
557 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
558 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
559 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
560 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
561 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
562 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
563 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
564 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
565 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
573 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
575 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
576 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
577 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
578 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
579 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
580 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
581 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
582 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
583 w1_t[0] = 0x80000000;
594 w3_t[3] = (salt_len + 40) * 8;
596 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
598 const u32 r0 = digest[3];
599 const u32 r1 = digest[4];
600 const u32 r2 = digest[2];
601 const u32 r3 = digest[1];
607 __kernel void m08400_m04 (__global pw_t *pws, __global kernel_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)
613 const u32 gid = get_global_id (0);
614 const u32 lid = get_local_id (0);
615 const u32 lsz = get_local_size (0);
621 __local u32 l_bin2asc[256];
623 for (u32 i = lid; i < 256; i += lsz)
625 const u32 i0 = (i >> 0) & 15;
626 const u32 i1 = (i >> 4) & 15;
628 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
629 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
632 barrier (CLK_LOCAL_MEM_FENCE);
634 if (gid >= gid_max) return;
642 w0[0] = pws[gid].i[ 0];
643 w0[1] = pws[gid].i[ 1];
644 w0[2] = pws[gid].i[ 2];
645 w0[3] = pws[gid].i[ 3];
668 const u32 pw_len = pws[gid].pw_len;
674 m08400m (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, l_bin2asc);
677 __kernel void m08400_m08 (__global pw_t *pws, __global kernel_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)
683 const u32 gid = get_global_id (0);
684 const u32 lid = get_local_id (0);
685 const u32 lsz = get_local_size (0);
691 __local u32 l_bin2asc[256];
693 for (u32 i = lid; i < 256; i += lsz)
695 const u32 i0 = (i >> 0) & 15;
696 const u32 i1 = (i >> 4) & 15;
698 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
699 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
702 barrier (CLK_LOCAL_MEM_FENCE);
704 if (gid >= gid_max) return;
712 w0[0] = pws[gid].i[ 0];
713 w0[1] = pws[gid].i[ 1];
714 w0[2] = pws[gid].i[ 2];
715 w0[3] = pws[gid].i[ 3];
719 w1[0] = pws[gid].i[ 4];
720 w1[1] = pws[gid].i[ 5];
721 w1[2] = pws[gid].i[ 6];
722 w1[3] = pws[gid].i[ 7];
738 const u32 pw_len = pws[gid].pw_len;
744 m08400m (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, l_bin2asc);
747 __kernel void m08400_m16 (__global pw_t *pws, __global kernel_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)
753 const u32 gid = get_global_id (0);
754 const u32 lid = get_local_id (0);
755 const u32 lsz = get_local_size (0);
761 __local u32 l_bin2asc[256];
763 for (u32 i = lid; i < 256; i += lsz)
765 const u32 i0 = (i >> 0) & 15;
766 const u32 i1 = (i >> 4) & 15;
768 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
769 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
772 barrier (CLK_LOCAL_MEM_FENCE);
774 if (gid >= gid_max) return;
782 w0[0] = pws[gid].i[ 0];
783 w0[1] = pws[gid].i[ 1];
784 w0[2] = pws[gid].i[ 2];
785 w0[3] = pws[gid].i[ 3];
789 w1[0] = pws[gid].i[ 4];
790 w1[1] = pws[gid].i[ 5];
791 w1[2] = pws[gid].i[ 6];
792 w1[3] = pws[gid].i[ 7];
796 w2[0] = pws[gid].i[ 8];
797 w2[1] = pws[gid].i[ 9];
798 w2[2] = pws[gid].i[10];
799 w2[3] = pws[gid].i[11];
803 w3[0] = pws[gid].i[12];
804 w3[1] = pws[gid].i[13];
808 const u32 pw_len = pws[gid].pw_len;
814 m08400m (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, l_bin2asc);
817 __kernel void m08400_s04 (__global pw_t *pws, __global kernel_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)
823 const u32 gid = get_global_id (0);
824 const u32 lid = get_local_id (0);
825 const u32 lsz = get_local_size (0);
831 __local u32 l_bin2asc[256];
833 for (u32 i = lid; i < 256; i += lsz)
835 const u32 i0 = (i >> 0) & 15;
836 const u32 i1 = (i >> 4) & 15;
838 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
839 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
842 barrier (CLK_LOCAL_MEM_FENCE);
844 if (gid >= gid_max) return;
852 w0[0] = pws[gid].i[ 0];
853 w0[1] = pws[gid].i[ 1];
854 w0[2] = pws[gid].i[ 2];
855 w0[3] = pws[gid].i[ 3];
878 const u32 pw_len = pws[gid].pw_len;
884 m08400s (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, l_bin2asc);
887 __kernel void m08400_s08 (__global pw_t *pws, __global kernel_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)
893 const u32 gid = get_global_id (0);
894 const u32 lid = get_local_id (0);
895 const u32 lsz = get_local_size (0);
901 __local u32 l_bin2asc[256];
903 for (u32 i = lid; i < 256; i += lsz)
905 const u32 i0 = (i >> 0) & 15;
906 const u32 i1 = (i >> 4) & 15;
908 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
909 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
912 barrier (CLK_LOCAL_MEM_FENCE);
914 if (gid >= gid_max) return;
922 w0[0] = pws[gid].i[ 0];
923 w0[1] = pws[gid].i[ 1];
924 w0[2] = pws[gid].i[ 2];
925 w0[3] = pws[gid].i[ 3];
929 w1[0] = pws[gid].i[ 4];
930 w1[1] = pws[gid].i[ 5];
931 w1[2] = pws[gid].i[ 6];
932 w1[3] = pws[gid].i[ 7];
948 const u32 pw_len = pws[gid].pw_len;
954 m08400s (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, l_bin2asc);
957 __kernel void m08400_s16 (__global pw_t *pws, __global kernel_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)
963 const u32 gid = get_global_id (0);
964 const u32 lid = get_local_id (0);
965 const u32 lsz = get_local_size (0);
971 __local u32 l_bin2asc[256];
973 for (u32 i = lid; i < 256; i += lsz)
975 const u32 i0 = (i >> 0) & 15;
976 const u32 i1 = (i >> 4) & 15;
978 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
979 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
982 barrier (CLK_LOCAL_MEM_FENCE);
984 if (gid >= gid_max) return;
992 w0[0] = pws[gid].i[ 0];
993 w0[1] = pws[gid].i[ 1];
994 w0[2] = pws[gid].i[ 2];
995 w0[3] = pws[gid].i[ 3];
999 w1[0] = pws[gid].i[ 4];
1000 w1[1] = pws[gid].i[ 5];
1001 w1[2] = pws[gid].i[ 6];
1002 w1[3] = pws[gid].i[ 7];
1006 w2[0] = pws[gid].i[ 8];
1007 w2[1] = pws[gid].i[ 9];
1008 w2[2] = pws[gid].i[10];
1009 w2[3] = pws[gid].i[11];
1013 w3[0] = pws[gid].i[12];
1014 w3[1] = pws[gid].i[13];
1018 const u32 pw_len = pws[gid].pw_len;
1024 m08400s (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, l_bin2asc);