2 * Author......: Jens Steube <jens.steube@gmail.com>
10 #include "include/constants.h"
11 #include "include/kernel_vendor.h"
18 #include "include/kernel_functions.c"
19 #include "OpenCL/types_ocl.c"
20 #include "OpenCL/common.c"
21 #include "OpenCL/simd.c"
24 #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i)])
26 #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
28 #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
30 #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
33 static void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5])
61 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
62 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
63 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
64 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
65 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
66 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
67 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
68 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
69 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
70 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
71 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
72 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
73 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
74 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
75 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
76 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
77 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
78 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
79 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
80 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
85 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
86 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
87 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
88 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
89 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
90 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
91 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
92 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
93 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
94 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
95 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
96 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
97 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
98 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
99 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
100 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
101 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
102 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
103 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
104 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
109 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
110 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
111 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
112 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
113 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
114 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
115 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
116 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
117 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
118 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
119 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
120 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
121 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
122 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
123 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
124 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
125 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
126 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
127 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
128 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
133 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
134 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
135 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
136 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
137 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
138 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
139 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
140 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
141 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
142 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
143 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
144 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
145 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
146 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
147 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
148 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
149 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
150 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
151 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
152 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
161 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])
167 const u32 gid = get_global_id (0);
168 const u32 lid = get_local_id (0);
176 salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
177 salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
178 salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
179 salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
183 salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
184 salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
185 salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
186 salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
190 salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
191 salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
195 const u32 salt_len = salt_bufs[salt_pos].salt_len;
203 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos += VECT_SIZE)
205 const u32x w0r = w0r_create_bft (bfs_buf, il_pos);
207 const u32x w0lr = w0l | w0r;
235 w3_t[3] = pw_len * 8;
245 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
259 w0_t[0] = salt_buf0[0];
260 w0_t[1] = salt_buf0[1];
261 w0_t[2] = salt_buf0[2];
262 w0_t[3] = salt_buf0[3];
263 w1_t[0] = salt_buf1[0];
264 w1_t[1] = salt_buf1[1];
265 w1_t[2] = salt_buf1[2];
266 w1_t[3] = salt_buf1[3];
267 w2_t[0] = salt_buf2[0];
268 w2_t[1] = salt_buf2[1];
269 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
270 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
271 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
272 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
273 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
274 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
275 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
276 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
277 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
278 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
279 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
280 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
288 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
290 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
291 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
292 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
293 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
294 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
295 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
296 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
297 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
298 w1_t[0] = 0x80000000;
311 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);
373 COMPARE_M_SIMD (digest[3], digest[4], digest[2], digest[1]);
377 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])
383 const u32 gid = get_global_id (0);
384 const u32 lid = get_local_id (0);
390 const u32 search[4] =
392 digests_buf[digests_offset].digest_buf[DGST_R0],
393 digests_buf[digests_offset].digest_buf[DGST_R1],
394 digests_buf[digests_offset].digest_buf[DGST_R2],
395 digests_buf[digests_offset].digest_buf[DGST_R3]
404 salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
405 salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
406 salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
407 salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
411 salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
412 salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
413 salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
414 salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
418 salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
419 salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
423 const u32 salt_len = salt_bufs[salt_pos].salt_len;
431 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos += VECT_SIZE)
433 const u32x w0r = w0r_create_bft (bfs_buf, il_pos);
435 const u32x w0lr = w0l | w0r;
463 w3_t[3] = pw_len * 8;
473 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
487 w0_t[0] = salt_buf0[0];
488 w0_t[1] = salt_buf0[1];
489 w0_t[2] = salt_buf0[2];
490 w0_t[3] = salt_buf0[3];
491 w1_t[0] = salt_buf1[0];
492 w1_t[1] = salt_buf1[1];
493 w1_t[2] = salt_buf1[2];
494 w1_t[3] = salt_buf1[3];
495 w2_t[0] = salt_buf2[0];
496 w2_t[1] = salt_buf2[1];
497 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
498 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
499 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
500 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
501 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
502 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
503 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
504 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
505 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
506 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
507 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
508 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
516 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
518 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
519 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
520 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
521 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
522 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
523 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
524 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
525 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
526 w1_t[0] = 0x80000000;
537 w3_t[3] = (salt_len + 40) * 8;
539 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
547 w0_t[0] = salt_buf0[0];
548 w0_t[1] = salt_buf0[1];
549 w0_t[2] = salt_buf0[2];
550 w0_t[3] = salt_buf0[3];
551 w1_t[0] = salt_buf1[0];
552 w1_t[1] = salt_buf1[1];
553 w1_t[2] = salt_buf1[2];
554 w1_t[3] = salt_buf1[3];
555 w2_t[0] = salt_buf2[0];
556 w2_t[1] = salt_buf2[1];
557 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
558 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
559 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
560 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
561 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
562 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
563 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
564 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
565 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
566 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
567 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
568 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
576 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
578 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
579 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
580 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
581 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
582 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
583 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
584 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
585 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
586 w1_t[0] = 0x80000000;
597 w3_t[3] = (salt_len + 40) * 8;
599 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
601 COMPARE_S_SIMD (digest[3], digest[4], digest[2], digest[1]);
605 __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)
611 const u32 gid = get_global_id (0);
612 const u32 lid = get_local_id (0);
613 const u32 lsz = get_local_size (0);
619 __local u32 l_bin2asc[256];
621 for (u32 i = lid; i < 256; i += lsz)
623 const u32 i0 = (i >> 0) & 15;
624 const u32 i1 = (i >> 4) & 15;
626 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
627 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
630 barrier (CLK_LOCAL_MEM_FENCE);
632 if (gid >= gid_max) return;
640 w0[0] = pws[gid].i[ 0];
641 w0[1] = pws[gid].i[ 1];
642 w0[2] = pws[gid].i[ 2];
643 w0[3] = pws[gid].i[ 3];
666 const u32 pw_len = pws[gid].pw_len;
672 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);
675 __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)
681 const u32 gid = get_global_id (0);
682 const u32 lid = get_local_id (0);
683 const u32 lsz = get_local_size (0);
689 __local u32 l_bin2asc[256];
691 for (u32 i = lid; i < 256; i += lsz)
693 const u32 i0 = (i >> 0) & 15;
694 const u32 i1 = (i >> 4) & 15;
696 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
697 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
700 barrier (CLK_LOCAL_MEM_FENCE);
702 if (gid >= gid_max) return;
710 w0[0] = pws[gid].i[ 0];
711 w0[1] = pws[gid].i[ 1];
712 w0[2] = pws[gid].i[ 2];
713 w0[3] = pws[gid].i[ 3];
717 w1[0] = pws[gid].i[ 4];
718 w1[1] = pws[gid].i[ 5];
719 w1[2] = pws[gid].i[ 6];
720 w1[3] = pws[gid].i[ 7];
736 const u32 pw_len = pws[gid].pw_len;
742 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);
745 __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)
751 const u32 gid = get_global_id (0);
752 const u32 lid = get_local_id (0);
753 const u32 lsz = get_local_size (0);
759 __local u32 l_bin2asc[256];
761 for (u32 i = lid; i < 256; i += lsz)
763 const u32 i0 = (i >> 0) & 15;
764 const u32 i1 = (i >> 4) & 15;
766 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
767 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
770 barrier (CLK_LOCAL_MEM_FENCE);
772 if (gid >= gid_max) return;
780 w0[0] = pws[gid].i[ 0];
781 w0[1] = pws[gid].i[ 1];
782 w0[2] = pws[gid].i[ 2];
783 w0[3] = pws[gid].i[ 3];
787 w1[0] = pws[gid].i[ 4];
788 w1[1] = pws[gid].i[ 5];
789 w1[2] = pws[gid].i[ 6];
790 w1[3] = pws[gid].i[ 7];
794 w2[0] = pws[gid].i[ 8];
795 w2[1] = pws[gid].i[ 9];
796 w2[2] = pws[gid].i[10];
797 w2[3] = pws[gid].i[11];
801 w3[0] = pws[gid].i[12];
802 w3[1] = pws[gid].i[13];
806 const u32 pw_len = pws[gid].pw_len;
812 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);
815 __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)
821 const u32 gid = get_global_id (0);
822 const u32 lid = get_local_id (0);
823 const u32 lsz = get_local_size (0);
829 __local u32 l_bin2asc[256];
831 for (u32 i = lid; i < 256; i += lsz)
833 const u32 i0 = (i >> 0) & 15;
834 const u32 i1 = (i >> 4) & 15;
836 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
837 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
840 barrier (CLK_LOCAL_MEM_FENCE);
842 if (gid >= gid_max) return;
850 w0[0] = pws[gid].i[ 0];
851 w0[1] = pws[gid].i[ 1];
852 w0[2] = pws[gid].i[ 2];
853 w0[3] = pws[gid].i[ 3];
876 const u32 pw_len = pws[gid].pw_len;
882 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);
885 __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)
891 const u32 gid = get_global_id (0);
892 const u32 lid = get_local_id (0);
893 const u32 lsz = get_local_size (0);
899 __local u32 l_bin2asc[256];
901 for (u32 i = lid; i < 256; i += lsz)
903 const u32 i0 = (i >> 0) & 15;
904 const u32 i1 = (i >> 4) & 15;
906 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
907 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
910 barrier (CLK_LOCAL_MEM_FENCE);
912 if (gid >= gid_max) return;
920 w0[0] = pws[gid].i[ 0];
921 w0[1] = pws[gid].i[ 1];
922 w0[2] = pws[gid].i[ 2];
923 w0[3] = pws[gid].i[ 3];
927 w1[0] = pws[gid].i[ 4];
928 w1[1] = pws[gid].i[ 5];
929 w1[2] = pws[gid].i[ 6];
930 w1[3] = pws[gid].i[ 7];
946 const u32 pw_len = pws[gid].pw_len;
952 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);
955 __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)
961 const u32 gid = get_global_id (0);
962 const u32 lid = get_local_id (0);
963 const u32 lsz = get_local_size (0);
969 __local u32 l_bin2asc[256];
971 for (u32 i = lid; i < 256; i += lsz)
973 const u32 i0 = (i >> 0) & 15;
974 const u32 i1 = (i >> 4) & 15;
976 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
977 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
980 barrier (CLK_LOCAL_MEM_FENCE);
982 if (gid >= gid_max) return;
990 w0[0] = pws[gid].i[ 0];
991 w0[1] = pws[gid].i[ 1];
992 w0[2] = pws[gid].i[ 2];
993 w0[3] = pws[gid].i[ 3];
997 w1[0] = pws[gid].i[ 4];
998 w1[1] = pws[gid].i[ 5];
999 w1[2] = pws[gid].i[ 6];
1000 w1[3] = pws[gid].i[ 7];
1004 w2[0] = pws[gid].i[ 8];
1005 w2[1] = pws[gid].i[ 9];
1006 w2[2] = pws[gid].i[10];
1007 w2[3] = pws[gid].i[11];
1011 w3[0] = pws[gid].i[12];
1012 w3[1] = pws[gid].i[13];
1016 const u32 pw_len = pws[gid].pw_len;
1022 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);