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 __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 *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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
159 const u32 gid = get_global_id (0);
160 const u32 lid = get_local_id (0);
161 const u32 lsz = get_local_size (0);
167 __local u32 l_bin2asc[256];
169 for (u32 i = lid; i < 256; i += lsz)
171 const u32 i0 = (i >> 0) & 15;
172 const u32 i1 = (i >> 4) & 15;
174 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
175 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
178 barrier (CLK_LOCAL_MEM_FENCE);
180 if (gid >= gid_max) return;
188 wordl0[0] = pws[gid].i[ 0];
189 wordl0[1] = pws[gid].i[ 1];
190 wordl0[2] = pws[gid].i[ 2];
191 wordl0[3] = pws[gid].i[ 3];
195 wordl1[0] = pws[gid].i[ 4];
196 wordl1[1] = pws[gid].i[ 5];
197 wordl1[2] = pws[gid].i[ 6];
198 wordl1[3] = pws[gid].i[ 7];
214 const u32 pw_l_len = pws[gid].pw_len;
216 if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
218 append_0x80_2x4 (wordl0, wordl1, pw_l_len);
220 switch_buffer_by_offset_le (wordl0, wordl1, wordl2, wordl3, combs_buf[0].pw_len);
229 salt_buf0[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 0]);
230 salt_buf0[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 1]);
231 salt_buf0[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 2]);
232 salt_buf0[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 3]);
236 salt_buf1[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 4]);
237 salt_buf1[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 5]);
238 salt_buf1[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 6]);
239 salt_buf1[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 7]);
243 salt_buf2[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 8]);
244 salt_buf2[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 9]);
248 const u32 salt_len = salt_bufs[salt_pos].salt_len;
254 for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
256 const u32 pw_r_len = combs_buf[il_pos].pw_len;
258 const u32 pw_len = pw_l_len + pw_r_len;
262 wordr0[0] = combs_buf[il_pos].i[0];
263 wordr0[1] = combs_buf[il_pos].i[1];
264 wordr0[2] = combs_buf[il_pos].i[2];
265 wordr0[3] = combs_buf[il_pos].i[3];
269 wordr1[0] = combs_buf[il_pos].i[4];
270 wordr1[1] = combs_buf[il_pos].i[5];
271 wordr1[2] = combs_buf[il_pos].i[6];
272 wordr1[3] = combs_buf[il_pos].i[7];
288 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
290 append_0x80_2x4 (wordr0, wordr1, pw_r_len);
292 switch_buffer_by_offset_le (wordr0, wordr1, wordr2, wordr3, pw_l_len);
297 w0[0] = wordl0[0] | wordr0[0];
298 w0[1] = wordl0[1] | wordr0[1];
299 w0[2] = wordl0[2] | wordr0[2];
300 w0[3] = wordl0[3] | wordr0[3];
304 w1[0] = wordl1[0] | wordr1[0];
305 w1[1] = wordl1[1] | wordr1[1];
306 w1[2] = wordl1[2] | wordr1[2];
307 w1[3] = wordl1[3] | wordr1[3];
311 w2[0] = wordl2[0] | wordr2[0];
312 w2[1] = wordl2[1] | wordr2[1];
313 w2[2] = wordl2[2] | wordr2[2];
314 w2[3] = wordl2[3] | wordr2[3];
318 w3[0] = wordl3[0] | wordr3[0];
319 w3[1] = wordl3[1] | wordr3[1];
320 w3[2] = wordl3[2] | wordr3[2];
321 w3[3] = wordl3[3] | wordr3[3];
325 w0_t[0] = swap32 (w0[0]);
326 w0_t[1] = swap32 (w0[1]);
327 w0_t[2] = swap32 (w0[2]);
328 w0_t[3] = swap32 (w0[3]);
332 w1_t[0] = swap32 (w1[0]);
333 w1_t[1] = swap32 (w1[1]);
334 w1_t[2] = swap32 (w1[2]);
335 w1_t[3] = swap32 (w1[3]);
339 w2_t[0] = swap32 (w2[0]);
340 w2_t[1] = swap32 (w2[1]);
341 w2_t[2] = swap32 (w2[2]);
342 w2_t[3] = swap32 (w2[3]);
346 w3_t[0] = swap32 (w3[0]);
347 w3_t[1] = swap32 (w3[1]);
349 w3_t[3] = pw_len * 8;
359 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
373 w0_t[0] = salt_buf0[0];
374 w0_t[1] = salt_buf0[1];
375 w0_t[2] = salt_buf0[2];
376 w0_t[3] = salt_buf0[3];
377 w1_t[0] = salt_buf1[0];
378 w1_t[1] = salt_buf1[1];
379 w1_t[2] = salt_buf1[2];
380 w1_t[3] = salt_buf1[3];
381 w2_t[0] = salt_buf2[0];
382 w2_t[1] = salt_buf2[1];
383 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
384 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
385 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
386 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
387 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
388 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
389 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
390 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
391 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
392 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
393 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
394 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
402 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
404 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
405 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
406 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
407 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
408 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
409 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
410 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
411 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
412 w1_t[0] = 0x80000000;
425 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
433 w0_t[0] = salt_buf0[0];
434 w0_t[1] = salt_buf0[1];
435 w0_t[2] = salt_buf0[2];
436 w0_t[3] = salt_buf0[3];
437 w1_t[0] = salt_buf1[0];
438 w1_t[1] = salt_buf1[1];
439 w1_t[2] = salt_buf1[2];
440 w1_t[3] = salt_buf1[3];
441 w2_t[0] = salt_buf2[0];
442 w2_t[1] = salt_buf2[1];
443 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
444 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
445 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
446 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
447 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
448 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
449 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
450 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
451 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
452 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
453 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
454 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
462 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
464 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
465 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
466 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
467 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
468 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
469 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
470 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
471 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
472 w1_t[0] = 0x80000000;
485 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
487 const u32 r0 = digest[3];
488 const u32 r1 = digest[4];
489 const u32 r2 = digest[2];
490 const u32 r3 = digest[1];
496 __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 *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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
500 __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 *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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
504 __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 *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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
510 const u32 gid = get_global_id (0);
511 const u32 lid = get_local_id (0);
512 const u32 lsz = get_local_size (0);
518 __local u32 l_bin2asc[256];
520 for (u32 i = lid; i < 256; i += lsz)
522 const u32 i0 = (i >> 0) & 15;
523 const u32 i1 = (i >> 4) & 15;
525 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
526 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
529 barrier (CLK_LOCAL_MEM_FENCE);
531 if (gid >= gid_max) return;
539 wordl0[0] = pws[gid].i[ 0];
540 wordl0[1] = pws[gid].i[ 1];
541 wordl0[2] = pws[gid].i[ 2];
542 wordl0[3] = pws[gid].i[ 3];
546 wordl1[0] = pws[gid].i[ 4];
547 wordl1[1] = pws[gid].i[ 5];
548 wordl1[2] = pws[gid].i[ 6];
549 wordl1[3] = pws[gid].i[ 7];
565 const u32 pw_l_len = pws[gid].pw_len;
567 if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
569 append_0x80_2x4 (wordl0, wordl1, pw_l_len);
571 switch_buffer_by_offset_le (wordl0, wordl1, wordl2, wordl3, combs_buf[0].pw_len);
580 salt_buf0[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 0]);
581 salt_buf0[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 1]);
582 salt_buf0[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 2]);
583 salt_buf0[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 3]);
587 salt_buf1[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 4]);
588 salt_buf1[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 5]);
589 salt_buf1[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 6]);
590 salt_buf1[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 7]);
594 salt_buf2[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 8]);
595 salt_buf2[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 9]);
599 const u32 salt_len = salt_bufs[salt_pos].salt_len;
605 const u32 search[4] =
607 digests_buf[digests_offset].digest_buf[DGST_R0],
608 digests_buf[digests_offset].digest_buf[DGST_R1],
609 digests_buf[digests_offset].digest_buf[DGST_R2],
610 digests_buf[digests_offset].digest_buf[DGST_R3]
617 for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
619 const u32 pw_r_len = combs_buf[il_pos].pw_len;
621 const u32 pw_len = pw_l_len + pw_r_len;
625 wordr0[0] = combs_buf[il_pos].i[0];
626 wordr0[1] = combs_buf[il_pos].i[1];
627 wordr0[2] = combs_buf[il_pos].i[2];
628 wordr0[3] = combs_buf[il_pos].i[3];
632 wordr1[0] = combs_buf[il_pos].i[4];
633 wordr1[1] = combs_buf[il_pos].i[5];
634 wordr1[2] = combs_buf[il_pos].i[6];
635 wordr1[3] = combs_buf[il_pos].i[7];
651 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
653 append_0x80_2x4 (wordr0, wordr1, pw_r_len);
655 switch_buffer_by_offset_le (wordr0, wordr1, wordr2, wordr3, pw_l_len);
660 w0[0] = wordl0[0] | wordr0[0];
661 w0[1] = wordl0[1] | wordr0[1];
662 w0[2] = wordl0[2] | wordr0[2];
663 w0[3] = wordl0[3] | wordr0[3];
667 w1[0] = wordl1[0] | wordr1[0];
668 w1[1] = wordl1[1] | wordr1[1];
669 w1[2] = wordl1[2] | wordr1[2];
670 w1[3] = wordl1[3] | wordr1[3];
674 w2[0] = wordl2[0] | wordr2[0];
675 w2[1] = wordl2[1] | wordr2[1];
676 w2[2] = wordl2[2] | wordr2[2];
677 w2[3] = wordl2[3] | wordr2[3];
681 w3[0] = wordl3[0] | wordr3[0];
682 w3[1] = wordl3[1] | wordr3[1];
683 w3[2] = wordl3[2] | wordr3[2];
684 w3[3] = wordl3[3] | wordr3[3];
688 w0_t[0] = swap32 (w0[0]);
689 w0_t[1] = swap32 (w0[1]);
690 w0_t[2] = swap32 (w0[2]);
691 w0_t[3] = swap32 (w0[3]);
695 w1_t[0] = swap32 (w1[0]);
696 w1_t[1] = swap32 (w1[1]);
697 w1_t[2] = swap32 (w1[2]);
698 w1_t[3] = swap32 (w1[3]);
702 w2_t[0] = swap32 (w2[0]);
703 w2_t[1] = swap32 (w2[1]);
704 w2_t[2] = swap32 (w2[2]);
705 w2_t[3] = swap32 (w2[3]);
709 w3_t[0] = swap32 (w3[0]);
710 w3_t[1] = swap32 (w3[1]);
712 w3_t[3] = pw_len * 8;
722 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
736 w0_t[0] = salt_buf0[0];
737 w0_t[1] = salt_buf0[1];
738 w0_t[2] = salt_buf0[2];
739 w0_t[3] = salt_buf0[3];
740 w1_t[0] = salt_buf1[0];
741 w1_t[1] = salt_buf1[1];
742 w1_t[2] = salt_buf1[2];
743 w1_t[3] = salt_buf1[3];
744 w2_t[0] = salt_buf2[0];
745 w2_t[1] = salt_buf2[1];
746 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
747 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
748 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
749 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
750 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
751 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
752 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
753 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
754 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
755 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
756 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
757 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
765 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
767 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
768 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
769 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
770 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
771 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
772 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
773 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
774 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
775 w1_t[0] = 0x80000000;
786 w3_t[3] = (salt_len + 40) * 8;
788 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
796 w0_t[0] = salt_buf0[0];
797 w0_t[1] = salt_buf0[1];
798 w0_t[2] = salt_buf0[2];
799 w0_t[3] = salt_buf0[3];
800 w1_t[0] = salt_buf1[0];
801 w1_t[1] = salt_buf1[1];
802 w1_t[2] = salt_buf1[2];
803 w1_t[3] = salt_buf1[3];
804 w2_t[0] = salt_buf2[0];
805 w2_t[1] = salt_buf2[1];
806 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
807 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
808 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
809 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
810 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
811 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
812 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
813 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
814 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
815 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
816 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
817 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
825 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
827 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
828 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
829 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
830 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
831 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
832 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
833 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
834 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
835 w1_t[0] = 0x80000000;
846 w3_t[3] = (salt_len + 40) * 8;
848 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
850 const u32 r0 = digest[3];
851 const u32 r1 = digest[4];
852 const u32 r2 = digest[2];
853 const u32 r3 = digest[1];
859 __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 *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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
863 __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 *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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)