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"
19 #include "include/rp_kernel.h"
20 #include "OpenCL/rp.c"
22 #define COMPARE_S "OpenCL/check_single_comp4.c"
23 #define COMPARE_M "OpenCL/check_multi_comp4.c"
25 #define uint_to_hex_lower8_le(i) l_bin2asc[(i)]
27 static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
55 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
56 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
57 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
58 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
59 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
60 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
61 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
62 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
63 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
64 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
65 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
66 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
67 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
68 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
69 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
70 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
71 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
72 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
73 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
74 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
79 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
80 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
81 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
82 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
83 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
84 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
85 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
86 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
87 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
88 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
89 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
90 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
91 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
92 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
93 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
94 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
95 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
96 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
97 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
98 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
103 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
104 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
105 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
106 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
107 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
108 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
109 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
110 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
111 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
112 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
113 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
114 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
115 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
116 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
117 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
118 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
119 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
120 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
121 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
122 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
127 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
128 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
129 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
130 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
131 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
132 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
133 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
134 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
135 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
136 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
137 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
138 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
139 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
140 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
141 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
142 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
143 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
144 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
145 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
146 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
155 __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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
161 const u32 gid = get_global_id (0);
162 const u32 lid = get_local_id (0);
163 const u32 lsz = get_local_size (0);
169 __local u32 l_bin2asc[256];
171 for (u32 i = lid; i < 256; i += lsz)
173 const u32 i0 = (i >> 0) & 15;
174 const u32 i1 = (i >> 4) & 15;
176 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
177 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
180 barrier (CLK_LOCAL_MEM_FENCE);
182 if (gid >= gid_max) return;
190 pw_buf0[0] = pws[gid].i[ 0];
191 pw_buf0[1] = pws[gid].i[ 1];
192 pw_buf0[2] = pws[gid].i[ 2];
193 pw_buf0[3] = pws[gid].i[ 3];
197 pw_buf1[0] = pws[gid].i[ 4];
198 pw_buf1[1] = pws[gid].i[ 5];
199 pw_buf1[2] = pws[gid].i[ 6];
200 pw_buf1[3] = pws[gid].i[ 7];
202 const u32 pw_len = pws[gid].pw_len;
210 salt_buf0[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 0]);
211 salt_buf0[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 1]);
212 salt_buf0[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 2]);
213 salt_buf0[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 3]);
217 salt_buf1[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 4]);
218 salt_buf1[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 5]);
219 salt_buf1[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 6]);
220 salt_buf1[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 7]);
224 salt_buf2[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 8]);
225 salt_buf2[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 9]);
229 const u32 salt_len = salt_bufs[salt_pos].salt_len;
235 for (u32 il_pos = 0; il_pos < rules_cnt; il_pos++)
265 const u32 out_len = apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
267 append_0x80_2x4 (w0, w1, out_len);
271 w0_t[0] = swap32 (w0[0]);
272 w0_t[1] = swap32 (w0[1]);
273 w0_t[2] = swap32 (w0[2]);
274 w0_t[3] = swap32 (w0[3]);
278 w1_t[0] = swap32 (w1[0]);
279 w1_t[1] = swap32 (w1[1]);
280 w1_t[2] = swap32 (w1[2]);
281 w1_t[3] = swap32 (w1[3]);
285 w2_t[0] = swap32 (w2[0]);
286 w2_t[1] = swap32 (w2[1]);
287 w2_t[2] = swap32 (w2[2]);
288 w2_t[3] = swap32 (w2[3]);
292 w3_t[0] = swap32 (w3[0]);
293 w3_t[1] = swap32 (w3[1]);
295 w3_t[3] = pw_len * 8;
305 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
319 w0_t[0] = salt_buf0[0];
320 w0_t[1] = salt_buf0[1];
321 w0_t[2] = salt_buf0[2];
322 w0_t[3] = salt_buf0[3];
323 w1_t[0] = salt_buf1[0];
324 w1_t[1] = salt_buf1[1];
325 w1_t[2] = salt_buf1[2];
326 w1_t[3] = salt_buf1[3];
327 w2_t[0] = salt_buf2[0];
328 w2_t[1] = salt_buf2[1];
329 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
330 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
331 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
332 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
333 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
334 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
335 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
336 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
337 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
338 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
339 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
340 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
348 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
350 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
351 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
352 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
353 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
354 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
355 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
356 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
357 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
358 w1_t[0] = 0x80000000;
371 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
379 w0_t[0] = salt_buf0[0];
380 w0_t[1] = salt_buf0[1];
381 w0_t[2] = salt_buf0[2];
382 w0_t[3] = salt_buf0[3];
383 w1_t[0] = salt_buf1[0];
384 w1_t[1] = salt_buf1[1];
385 w1_t[2] = salt_buf1[2];
386 w1_t[3] = salt_buf1[3];
387 w2_t[0] = salt_buf2[0];
388 w2_t[1] = salt_buf2[1];
389 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
390 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
391 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
392 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
393 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
394 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
395 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
396 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
397 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
398 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
399 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
400 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
408 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
410 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
411 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
412 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
413 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
414 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
415 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
416 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
417 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
418 w1_t[0] = 0x80000000;
431 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
433 const u32 r0 = digest[3];
434 const u32 r1 = digest[4];
435 const u32 r2 = digest[2];
436 const u32 r3 = digest[1];
442 __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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
446 __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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
450 __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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
456 const u32 gid = get_global_id (0);
457 const u32 lid = get_local_id (0);
458 const u32 lsz = get_local_size (0);
464 __local u32 l_bin2asc[256];
466 for (u32 i = lid; i < 256; i += lsz)
468 const u32 i0 = (i >> 0) & 15;
469 const u32 i1 = (i >> 4) & 15;
471 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
472 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
475 barrier (CLK_LOCAL_MEM_FENCE);
477 if (gid >= gid_max) return;
485 pw_buf0[0] = pws[gid].i[ 0];
486 pw_buf0[1] = pws[gid].i[ 1];
487 pw_buf0[2] = pws[gid].i[ 2];
488 pw_buf0[3] = pws[gid].i[ 3];
492 pw_buf1[0] = pws[gid].i[ 4];
493 pw_buf1[1] = pws[gid].i[ 5];
494 pw_buf1[2] = pws[gid].i[ 6];
495 pw_buf1[3] = pws[gid].i[ 7];
497 const u32 pw_len = pws[gid].pw_len;
505 salt_buf0[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 0]);
506 salt_buf0[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 1]);
507 salt_buf0[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 2]);
508 salt_buf0[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 3]);
512 salt_buf1[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 4]);
513 salt_buf1[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 5]);
514 salt_buf1[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 6]);
515 salt_buf1[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 7]);
519 salt_buf2[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 8]);
520 salt_buf2[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 9]);
524 const u32 salt_len = salt_bufs[salt_pos].salt_len;
530 const u32 search[4] =
532 digests_buf[digests_offset].digest_buf[DGST_R0],
533 digests_buf[digests_offset].digest_buf[DGST_R1],
534 digests_buf[digests_offset].digest_buf[DGST_R2],
535 digests_buf[digests_offset].digest_buf[DGST_R3]
542 for (u32 il_pos = 0; il_pos < rules_cnt; il_pos++)
572 const u32 out_len = apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
574 append_0x80_2x4 (w0, w1, out_len);
578 w0_t[0] = swap32 (w0[0]);
579 w0_t[1] = swap32 (w0[1]);
580 w0_t[2] = swap32 (w0[2]);
581 w0_t[3] = swap32 (w0[3]);
585 w1_t[0] = swap32 (w1[0]);
586 w1_t[1] = swap32 (w1[1]);
587 w1_t[2] = swap32 (w1[2]);
588 w1_t[3] = swap32 (w1[3]);
592 w2_t[0] = swap32 (w2[0]);
593 w2_t[1] = swap32 (w2[1]);
594 w2_t[2] = swap32 (w2[2]);
595 w2_t[3] = swap32 (w2[3]);
599 w3_t[0] = swap32 (w3[0]);
600 w3_t[1] = swap32 (w3[1]);
602 w3_t[3] = pw_len * 8;
612 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
626 w0_t[0] = salt_buf0[0];
627 w0_t[1] = salt_buf0[1];
628 w0_t[2] = salt_buf0[2];
629 w0_t[3] = salt_buf0[3];
630 w1_t[0] = salt_buf1[0];
631 w1_t[1] = salt_buf1[1];
632 w1_t[2] = salt_buf1[2];
633 w1_t[3] = salt_buf1[3];
634 w2_t[0] = salt_buf2[0];
635 w2_t[1] = salt_buf2[1];
636 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
637 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
638 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
639 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
640 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
641 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
642 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
643 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
644 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
645 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
646 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
647 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
655 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
657 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
658 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
659 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
660 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
661 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
662 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
663 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
664 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
665 w1_t[0] = 0x80000000;
676 w3_t[3] = (salt_len + 40) * 8;
678 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
686 w0_t[0] = salt_buf0[0];
687 w0_t[1] = salt_buf0[1];
688 w0_t[2] = salt_buf0[2];
689 w0_t[3] = salt_buf0[3];
690 w1_t[0] = salt_buf1[0];
691 w1_t[1] = salt_buf1[1];
692 w1_t[2] = salt_buf1[2];
693 w1_t[3] = salt_buf1[3];
694 w2_t[0] = salt_buf2[0];
695 w2_t[1] = salt_buf2[1];
696 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
697 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
698 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
699 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
700 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
701 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
702 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
703 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
704 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
705 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
706 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
707 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
715 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
717 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
718 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
719 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
720 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
721 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
722 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
723 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
724 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
725 w1_t[0] = 0x80000000;
736 w3_t[3] = (salt_len + 40) * 8;
738 sha1_transform (w0_t, w1_t, w2_t, w3_t, 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 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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
753 __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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)