2 * Authors.....: Jens Steube <jens.steube@gmail.com>
3 * Gabriele Gristina <matrix@hashcat.net>
12 #include "include/constants.h"
13 #include "include/kernel_vendor.h"
20 #include "include/kernel_functions.c"
21 #include "OpenCL/types_ocl.c"
22 #include "OpenCL/common.c"
23 #include "OpenCL/simd.c"
26 #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i)])
28 #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
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])
32 #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])
35 static void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5])
63 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
64 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
65 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
66 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
67 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
68 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
69 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
70 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
71 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
72 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
73 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
74 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
75 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
76 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
77 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
78 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
79 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
80 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
81 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
82 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
87 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
88 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
89 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
90 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
91 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
92 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
93 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
94 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
95 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
96 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
97 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
98 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
99 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
100 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
101 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
102 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
103 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
104 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
105 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
106 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
111 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
112 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
113 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
114 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
115 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
116 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
117 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
118 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
119 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
120 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
121 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
122 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
123 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
124 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
125 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
126 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
127 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
128 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
129 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
130 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
135 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
136 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
137 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
138 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
139 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
140 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
141 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
142 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
143 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
144 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
145 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
146 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
147 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
148 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
149 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
150 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
151 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
152 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
153 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
154 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
163 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)
169 const u32 gid = get_global_id (0);
170 const u32 lid = get_local_id (0);
178 salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
179 salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
180 salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
181 salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
185 salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
186 salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
187 salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
188 salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
192 salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
193 salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
197 const u32 salt_len = salt_bufs[salt_pos].salt_len;
205 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos += VECT_SIZE)
207 const u32x w0r = w0r_create_bft (bfs_buf, il_pos);
209 const u32x w0lr = w0l | w0r;
237 w3_t[3] = pw_len * 8;
247 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
261 w0_t[0] = salt_buf0[0];
262 w0_t[1] = salt_buf0[1];
263 w0_t[2] = salt_buf0[2];
264 w0_t[3] = salt_buf0[3];
265 w1_t[0] = salt_buf1[0];
266 w1_t[1] = salt_buf1[1];
267 w1_t[2] = salt_buf1[2];
268 w1_t[3] = salt_buf1[3];
269 w2_t[0] = salt_buf2[0];
270 w2_t[1] = salt_buf2[1];
271 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
272 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
273 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
274 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
275 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
276 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
277 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
278 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
279 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
280 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
281 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
282 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
290 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
292 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
293 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
294 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
295 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
296 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
297 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
298 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
299 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
300 w1_t[0] = 0x80000000;
313 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
321 w0_t[0] = salt_buf0[0];
322 w0_t[1] = salt_buf0[1];
323 w0_t[2] = salt_buf0[2];
324 w0_t[3] = salt_buf0[3];
325 w1_t[0] = salt_buf1[0];
326 w1_t[1] = salt_buf1[1];
327 w1_t[2] = salt_buf1[2];
328 w1_t[3] = salt_buf1[3];
329 w2_t[0] = salt_buf2[0];
330 w2_t[1] = salt_buf2[1];
331 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
332 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
333 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
334 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
335 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
336 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
337 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
338 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
339 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
340 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
341 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
342 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
350 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
352 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
353 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
354 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
355 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
356 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
357 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
358 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
359 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
360 w1_t[0] = 0x80000000;
373 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
375 COMPARE_M_SIMD (digest[3], digest[4], digest[2], digest[1]);
379 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)
385 const u32 gid = get_global_id (0);
386 const u32 lid = get_local_id (0);
392 const u32 search[4] =
394 digests_buf[digests_offset].digest_buf[DGST_R0],
395 digests_buf[digests_offset].digest_buf[DGST_R1],
396 digests_buf[digests_offset].digest_buf[DGST_R2],
397 digests_buf[digests_offset].digest_buf[DGST_R3]
406 salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
407 salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
408 salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
409 salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
413 salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
414 salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
415 salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
416 salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
420 salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
421 salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
425 const u32 salt_len = salt_bufs[salt_pos].salt_len;
433 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos += VECT_SIZE)
435 const u32x w0r = w0r_create_bft (bfs_buf, il_pos);
437 const u32x w0lr = w0l | w0r;
465 w3_t[3] = pw_len * 8;
475 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
489 w0_t[0] = salt_buf0[0];
490 w0_t[1] = salt_buf0[1];
491 w0_t[2] = salt_buf0[2];
492 w0_t[3] = salt_buf0[3];
493 w1_t[0] = salt_buf1[0];
494 w1_t[1] = salt_buf1[1];
495 w1_t[2] = salt_buf1[2];
496 w1_t[3] = salt_buf1[3];
497 w2_t[0] = salt_buf2[0];
498 w2_t[1] = salt_buf2[1];
499 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
500 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
501 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
502 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
503 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
504 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
505 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
506 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
507 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
508 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
509 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
510 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
518 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
520 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
521 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
522 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
523 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
524 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
525 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
526 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
527 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
528 w1_t[0] = 0x80000000;
539 w3_t[3] = (salt_len + 40) * 8;
541 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
549 w0_t[0] = salt_buf0[0];
550 w0_t[1] = salt_buf0[1];
551 w0_t[2] = salt_buf0[2];
552 w0_t[3] = salt_buf0[3];
553 w1_t[0] = salt_buf1[0];
554 w1_t[1] = salt_buf1[1];
555 w1_t[2] = salt_buf1[2];
556 w1_t[3] = salt_buf1[3];
557 w2_t[0] = salt_buf2[0];
558 w2_t[1] = salt_buf2[1];
559 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
560 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
561 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
562 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
563 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
564 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
565 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
566 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
567 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
568 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
569 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
570 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
578 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
580 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
581 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
582 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
583 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
584 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
585 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
586 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
587 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
588 w1_t[0] = 0x80000000;
599 w3_t[3] = (salt_len + 40) * 8;
601 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
603 COMPARE_S_SIMD (digest[3], digest[4], digest[2], 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);