2 * Author......: Jens Steube <jens.steube@gmail.com>
8 #include "include/constants.h"
9 #include "include/kernel_vendor.h"
28 #include "include/kernel_functions.c"
29 #include "types_amd.c"
30 #include "common_amd.c"
33 #define VECT_COMPARE_S "check_single_vect1_comp4.c"
34 #define VECT_COMPARE_M "check_multi_vect1_comp4.c"
38 #define VECT_COMPARE_S "check_single_vect2_comp4.c"
39 #define VECT_COMPARE_M "check_multi_vect2_comp4.c"
43 #define VECT_COMPARE_S "check_single_vect4_comp4.c"
44 #define VECT_COMPARE_M "check_multi_vect4_comp4.c"
47 __constant u32 k_sha256[64] =
49 SHA256C00, SHA256C01, SHA256C02, SHA256C03,
50 SHA256C04, SHA256C05, SHA256C06, SHA256C07,
51 SHA256C08, SHA256C09, SHA256C0a, SHA256C0b,
52 SHA256C0c, SHA256C0d, SHA256C0e, SHA256C0f,
53 SHA256C10, SHA256C11, SHA256C12, SHA256C13,
54 SHA256C14, SHA256C15, SHA256C16, SHA256C17,
55 SHA256C18, SHA256C19, SHA256C1a, SHA256C1b,
56 SHA256C1c, SHA256C1d, SHA256C1e, SHA256C1f,
57 SHA256C20, SHA256C21, SHA256C22, SHA256C23,
58 SHA256C24, SHA256C25, SHA256C26, SHA256C27,
59 SHA256C28, SHA256C29, SHA256C2a, SHA256C2b,
60 SHA256C2c, SHA256C2d, SHA256C2e, SHA256C2f,
61 SHA256C30, SHA256C31, SHA256C32, SHA256C33,
62 SHA256C34, SHA256C35, SHA256C36, SHA256C37,
63 SHA256C38, SHA256C39, SHA256C3a, SHA256C3b,
64 SHA256C3c, SHA256C3d, SHA256C3e, SHA256C3f,
67 static void sha256_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[8])
95 #define ROUND_EXPAND() \
97 w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); \
98 w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); \
99 w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); \
100 w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); \
101 w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); \
102 w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); \
103 w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); \
104 w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); \
105 w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); \
106 w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); \
107 wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); \
108 wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); \
109 wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); \
110 wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); \
111 we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); \
112 wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); \
115 #define ROUND_STEP(i) \
117 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha256[i + 0]); \
118 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha256[i + 1]); \
119 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha256[i + 2]); \
120 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha256[i + 3]); \
121 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha256[i + 4]); \
122 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha256[i + 5]); \
123 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha256[i + 6]); \
124 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha256[i + 7]); \
125 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha256[i + 8]); \
126 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha256[i + 9]); \
127 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha256[i + 10]); \
128 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha256[i + 11]); \
129 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha256[i + 12]); \
130 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha256[i + 13]); \
131 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, k_sha256[i + 14]); \
132 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha256[i + 15]); \
138 for (int i = 16; i < 64; i += 16)
140 ROUND_EXPAND (); ROUND_STEP (i);
153 static void hmac_sha256_pad (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[8], u32x opad[8])
155 w0[0] = w0[0] ^ 0x36363636;
156 w0[1] = w0[1] ^ 0x36363636;
157 w0[2] = w0[2] ^ 0x36363636;
158 w0[3] = w0[3] ^ 0x36363636;
159 w1[0] = w1[0] ^ 0x36363636;
160 w1[1] = w1[1] ^ 0x36363636;
161 w1[2] = w1[2] ^ 0x36363636;
162 w1[3] = w1[3] ^ 0x36363636;
163 w2[0] = w2[0] ^ 0x36363636;
164 w2[1] = w2[1] ^ 0x36363636;
165 w2[2] = w2[2] ^ 0x36363636;
166 w2[3] = w2[3] ^ 0x36363636;
167 w3[0] = w3[0] ^ 0x36363636;
168 w3[1] = w3[1] ^ 0x36363636;
169 w3[2] = w3[2] ^ 0x36363636;
170 w3[3] = w3[3] ^ 0x36363636;
181 sha256_transform (w0, w1, w2, w3, ipad);
183 w0[0] = w0[0] ^ 0x6a6a6a6a;
184 w0[1] = w0[1] ^ 0x6a6a6a6a;
185 w0[2] = w0[2] ^ 0x6a6a6a6a;
186 w0[3] = w0[3] ^ 0x6a6a6a6a;
187 w1[0] = w1[0] ^ 0x6a6a6a6a;
188 w1[1] = w1[1] ^ 0x6a6a6a6a;
189 w1[2] = w1[2] ^ 0x6a6a6a6a;
190 w1[3] = w1[3] ^ 0x6a6a6a6a;
191 w2[0] = w2[0] ^ 0x6a6a6a6a;
192 w2[1] = w2[1] ^ 0x6a6a6a6a;
193 w2[2] = w2[2] ^ 0x6a6a6a6a;
194 w2[3] = w2[3] ^ 0x6a6a6a6a;
195 w3[0] = w3[0] ^ 0x6a6a6a6a;
196 w3[1] = w3[1] ^ 0x6a6a6a6a;
197 w3[2] = w3[2] ^ 0x6a6a6a6a;
198 w3[3] = w3[3] ^ 0x6a6a6a6a;
209 sha256_transform (w0, w1, w2, w3, opad);
212 static void hmac_sha256_run (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[8], u32x opad[8], u32x digest[8])
223 sha256_transform (w0, w1, w2, w3, digest);
240 w3[3] = (64 + 32) * 8;
251 sha256_transform (w0, w1, w2, w3, digest);
254 static void m01460m (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], const u32 pw_len, __global pw_t *pws, __global gpu_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 *esal_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)
260 const u32 gid = get_global_id (0);
261 const u32 lid = get_local_id (0);
269 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
270 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
271 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
272 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
276 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
277 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
278 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
279 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
287 w0_t[0] = swap_workaround (salt_buf0[0]);
288 w0_t[1] = swap_workaround (salt_buf0[1]);
289 w0_t[2] = swap_workaround (salt_buf0[2]);
290 w0_t[3] = swap_workaround (salt_buf0[3]);
294 w1_t[0] = swap_workaround (salt_buf1[0]);
295 w1_t[1] = swap_workaround (salt_buf1[1]);
296 w1_t[2] = swap_workaround (salt_buf1[2]);
297 w1_t[3] = swap_workaround (salt_buf1[3]);
316 hmac_sha256_pad (w0_t, w1_t, w2_t, w3_t, ipad, opad);
324 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
326 const u32 w0r = bfs_buf[il_pos].i;
345 w3_t[3] = (64 + pw_len) * 8;
349 hmac_sha256_run (w0_t, w1_t, w2_t, w3_t, ipad, opad, digest);
351 const u32x r0 = digest[3];
352 const u32x r1 = digest[7];
353 const u32x r2 = digest[2];
354 const u32x r3 = digest[6];
356 #include VECT_COMPARE_M
360 static void m01460s (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], const u32 pw_len, __global pw_t *pws, __global gpu_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)
366 const u32 gid = get_global_id (0);
367 const u32 lid = get_local_id (0);
375 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
376 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
377 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
378 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
382 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
383 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
384 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
385 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
393 w0_t[0] = swap_workaround (salt_buf0[0]);
394 w0_t[1] = swap_workaround (salt_buf0[1]);
395 w0_t[2] = swap_workaround (salt_buf0[2]);
396 w0_t[3] = swap_workaround (salt_buf0[3]);
400 w1_t[0] = swap_workaround (salt_buf1[0]);
401 w1_t[1] = swap_workaround (salt_buf1[1]);
402 w1_t[2] = swap_workaround (salt_buf1[2]);
403 w1_t[3] = swap_workaround (salt_buf1[3]);
422 hmac_sha256_pad (w0_t, w1_t, w2_t, w3_t, ipad, opad);
428 const u32 search[4] =
430 digests_buf[digests_offset].digest_buf[DGST_R0],
431 digests_buf[digests_offset].digest_buf[DGST_R1],
432 digests_buf[digests_offset].digest_buf[DGST_R2],
433 digests_buf[digests_offset].digest_buf[DGST_R3]
442 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
444 const u32 w0r = bfs_buf[il_pos].i;
463 w3_t[3] = (64 + pw_len) * 8;
467 hmac_sha256_run (w0_t, w1_t, w2_t, w3_t, ipad, opad, digest);
469 const u32x r0 = digest[3];
470 const u32x r1 = digest[7];
471 const u32x r2 = digest[2];
472 const u32x r3 = digest[6];
474 #include VECT_COMPARE_S
478 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01460_m04 (__global pw_t *pws, __global gpu_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, const u32 combs_mode, const u32 gid_max)
484 const u32 gid = get_global_id (0);
486 if (gid >= gid_max) return;
490 w0[0] = pws[gid].i[ 0];
491 w0[1] = pws[gid].i[ 1];
492 w0[2] = pws[gid].i[ 2];
493 w0[3] = pws[gid].i[ 3];
516 const u32 pw_len = pws[gid].pw_len;
522 m01460m (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, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
525 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01460_m08 (__global pw_t *pws, __global gpu_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, const u32 combs_mode, const u32 gid_max)
531 const u32 gid = get_global_id (0);
533 if (gid >= gid_max) return;
537 w0[0] = pws[gid].i[ 0];
538 w0[1] = pws[gid].i[ 1];
539 w0[2] = pws[gid].i[ 2];
540 w0[3] = pws[gid].i[ 3];
544 w1[0] = pws[gid].i[ 4];
545 w1[1] = pws[gid].i[ 5];
546 w1[2] = pws[gid].i[ 6];
547 w1[3] = pws[gid].i[ 7];
563 const u32 pw_len = pws[gid].pw_len;
569 m01460m (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, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
572 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01460_m16 (__global pw_t *pws, __global gpu_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, const u32 combs_mode, const u32 gid_max)
578 const u32 gid = get_global_id (0);
580 if (gid >= gid_max) return;
584 w0[0] = pws[gid].i[ 0];
585 w0[1] = pws[gid].i[ 1];
586 w0[2] = pws[gid].i[ 2];
587 w0[3] = pws[gid].i[ 3];
591 w1[0] = pws[gid].i[ 4];
592 w1[1] = pws[gid].i[ 5];
593 w1[2] = pws[gid].i[ 6];
594 w1[3] = pws[gid].i[ 7];
598 w2[0] = pws[gid].i[ 8];
599 w2[1] = pws[gid].i[ 9];
600 w2[2] = pws[gid].i[10];
601 w2[3] = pws[gid].i[11];
605 w3[0] = pws[gid].i[12];
606 w3[1] = pws[gid].i[13];
610 const u32 pw_len = pws[gid].pw_len;
616 m01460m (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, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
619 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01460_s04 (__global pw_t *pws, __global gpu_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, const u32 combs_mode, const u32 gid_max)
625 const u32 gid = get_global_id (0);
627 if (gid >= gid_max) return;
631 w0[0] = pws[gid].i[ 0];
632 w0[1] = pws[gid].i[ 1];
633 w0[2] = pws[gid].i[ 2];
634 w0[3] = pws[gid].i[ 3];
657 const u32 pw_len = pws[gid].pw_len;
663 m01460s (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, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
666 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01460_s08 (__global pw_t *pws, __global gpu_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, const u32 combs_mode, const u32 gid_max)
672 const u32 gid = get_global_id (0);
674 if (gid >= gid_max) return;
678 w0[0] = pws[gid].i[ 0];
679 w0[1] = pws[gid].i[ 1];
680 w0[2] = pws[gid].i[ 2];
681 w0[3] = pws[gid].i[ 3];
685 w1[0] = pws[gid].i[ 4];
686 w1[1] = pws[gid].i[ 5];
687 w1[2] = pws[gid].i[ 6];
688 w1[3] = pws[gid].i[ 7];
704 const u32 pw_len = pws[gid].pw_len;
710 m01460s (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, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
713 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m01460_s16 (__global pw_t *pws, __global gpu_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, const u32 combs_mode, const u32 gid_max)
719 const u32 gid = get_global_id (0);
721 if (gid >= gid_max) return;
725 w0[0] = pws[gid].i[ 0];
726 w0[1] = pws[gid].i[ 1];
727 w0[2] = pws[gid].i[ 2];
728 w0[3] = pws[gid].i[ 3];
732 w1[0] = pws[gid].i[ 4];
733 w1[1] = pws[gid].i[ 5];
734 w1[2] = pws[gid].i[ 6];
735 w1[3] = pws[gid].i[ 7];
739 w2[0] = pws[gid].i[ 8];
740 w2[1] = pws[gid].i[ 9];
741 w2[2] = pws[gid].i[10];
742 w2[3] = pws[gid].i[11];
746 w3[0] = pws[gid].i[12];
747 w3[1] = pws[gid].i[13];
751 const u32 pw_len = pws[gid].pw_len;
757 m01460s (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, salt_bufs, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);