2 * Author......: Jens Steube <jens.steube@gmail.com>
9 #include "include/constants.h"
10 #include "include/kernel_vendor.h"
29 #include "include/kernel_functions.c"
30 #include "types_amd.c"
31 #include "common_amd.c"
34 #define VECT_COMPARE_S "check_single_vect1_comp4_warp.c"
35 #define VECT_COMPARE_M "check_multi_vect1_comp4_warp.c"
39 #define VECT_COMPARE_S "check_single_vect2_comp4_warp.c"
40 #define VECT_COMPARE_M "check_multi_vect2_comp4_warp.c"
44 #define VECT_COMPARE_S "check_single_vect4_comp4_warp.c"
45 #define VECT_COMPARE_M "check_multi_vect4_comp4_warp.c"
48 __constant u32 k_sha256[64] =
50 SHA256C00, SHA256C01, SHA256C02, SHA256C03,
51 SHA256C04, SHA256C05, SHA256C06, SHA256C07,
52 SHA256C08, SHA256C09, SHA256C0a, SHA256C0b,
53 SHA256C0c, SHA256C0d, SHA256C0e, SHA256C0f,
54 SHA256C10, SHA256C11, SHA256C12, SHA256C13,
55 SHA256C14, SHA256C15, SHA256C16, SHA256C17,
56 SHA256C18, SHA256C19, SHA256C1a, SHA256C1b,
57 SHA256C1c, SHA256C1d, SHA256C1e, SHA256C1f,
58 SHA256C20, SHA256C21, SHA256C22, SHA256C23,
59 SHA256C24, SHA256C25, SHA256C26, SHA256C27,
60 SHA256C28, SHA256C29, SHA256C2a, SHA256C2b,
61 SHA256C2c, SHA256C2d, SHA256C2e, SHA256C2f,
62 SHA256C30, SHA256C31, SHA256C32, SHA256C33,
63 SHA256C34, SHA256C35, SHA256C36, SHA256C37,
64 SHA256C38, SHA256C39, SHA256C3a, SHA256C3b,
65 SHA256C3c, SHA256C3d, SHA256C3e, SHA256C3f,
68 static void sha256_transform (u32x digest[8], const u32x w[16])
96 #define ROUND_EXPAND() \
98 w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); \
99 w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); \
100 w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); \
101 w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); \
102 w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); \
103 w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); \
104 w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); \
105 w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); \
106 w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); \
107 w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); \
108 wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); \
109 wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); \
110 wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); \
111 wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); \
112 we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); \
113 wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); \
116 #define ROUND_STEP(i) \
118 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha256[i + 0]); \
119 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha256[i + 1]); \
120 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha256[i + 2]); \
121 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha256[i + 3]); \
122 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha256[i + 4]); \
123 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha256[i + 5]); \
124 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha256[i + 6]); \
125 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha256[i + 7]); \
126 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha256[i + 8]); \
127 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha256[i + 9]); \
128 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha256[i + 10]); \
129 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha256[i + 11]); \
130 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha256[i + 12]); \
131 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha256[i + 13]); \
132 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, k_sha256[i + 14]); \
133 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha256[i + 15]); \
139 for (int i = 16; i < 64; i += 16)
141 ROUND_EXPAND (); ROUND_STEP (i);
154 static void m08000m (u32 w[16], const u32 pw_len, __global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __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)
160 const u32 gid = get_global_id (0);
161 const u32 lid = get_local_id (0);
167 const u32 salt_buf0 = swap_workaround (salt_bufs[salt_pos].salt_buf[ 0]);
168 const u32 salt_buf1 = swap_workaround (salt_bufs[salt_pos].salt_buf[ 1]);
169 const u32 salt_buf2 = swap_workaround (salt_bufs[salt_pos].salt_buf[ 2]); // 0x80
175 const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
179 for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
181 const u32x w0r = words_buf_r[il_pos];
183 const u32x w0 = w0l | w0r;
188 w_t[ 1] = w[ 1] >> 8;
189 w_t[ 2] = w[ 2] >> 8;
190 w_t[ 3] = w[ 3] >> 8;
191 w_t[ 4] = w[ 4] >> 8;
192 w_t[ 5] = w[ 5] >> 8;
193 w_t[ 6] = w[ 6] >> 8;
194 w_t[ 7] = w[ 7] >> 8;
195 w_t[ 8] = w[ 8] >> 8;
196 w_t[ 9] = w[ 9] >> 8;
197 w_t[10] = w[10] >> 8;
198 w_t[11] = w[11] >> 8;
199 w_t[12] = w[12] >> 8;
200 w_t[13] = w[13] >> 8;
201 w_t[14] = w[14] >> 8;
202 w_t[15] = w[15] >> 8;
206 digest[0] = SHA256M_A;
207 digest[1] = SHA256M_B;
208 digest[2] = SHA256M_C;
209 digest[3] = SHA256M_D;
210 digest[4] = SHA256M_E;
211 digest[5] = SHA256M_F;
212 digest[6] = SHA256M_G;
213 digest[7] = SHA256M_H;
215 sha256_transform (digest, w_t); // 0 - 64
234 sha256_transform (digest, w_t); // 64 - 128
235 sha256_transform (digest, w_t); // 128 - 192
236 sha256_transform (digest, w_t); // 192 - 256
237 sha256_transform (digest, w_t); // 256 - 320
238 sha256_transform (digest, w_t); // 320 - 384
239 sha256_transform (digest, w_t); // 384 - 448
241 w_t[15] = 0 | salt_buf0 >> 16;
243 sha256_transform (digest, w_t); // 448 - 512
245 w_t[ 0] = salt_buf0 << 16 | salt_buf1 >> 16;
246 w_t[ 1] = salt_buf1 << 16 | salt_buf2 >> 16;
247 w_t[ 2] = salt_buf2 << 16 | 0;
248 w_t[15] = (510 + 8) * 8;
250 sha256_transform (digest, w_t); // 512 - 576
252 const u32x r0 = digest[3];
253 const u32x r1 = digest[7];
254 const u32x r2 = digest[2];
255 const u32x r3 = digest[6];
257 #include VECT_COMPARE_M
261 static void m08000s (u32 w[16], const u32 pw_len, __global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __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)
267 const u32 gid = get_global_id (0);
268 const u32 lid = get_local_id (0);
274 const u32 search[4] =
276 digests_buf[digests_offset].digest_buf[DGST_R0],
277 digests_buf[digests_offset].digest_buf[DGST_R1],
278 digests_buf[digests_offset].digest_buf[DGST_R2],
279 digests_buf[digests_offset].digest_buf[DGST_R3]
286 const u32 salt_buf0 = swap_workaround (salt_bufs[salt_pos].salt_buf[ 0]);
287 const u32 salt_buf1 = swap_workaround (salt_bufs[salt_pos].salt_buf[ 1]);
288 const u32 salt_buf2 = swap_workaround (salt_bufs[salt_pos].salt_buf[ 2]); // 0x80
294 const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
298 for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
300 const u32x w0r = words_buf_r[il_pos];
302 const u32x w0 = w0l | w0r;
307 w_t[ 1] = w[ 1] >> 8;
308 w_t[ 2] = w[ 2] >> 8;
309 w_t[ 3] = w[ 3] >> 8;
310 w_t[ 4] = w[ 4] >> 8;
311 w_t[ 5] = w[ 5] >> 8;
312 w_t[ 6] = w[ 6] >> 8;
313 w_t[ 7] = w[ 7] >> 8;
314 w_t[ 8] = w[ 8] >> 8;
315 w_t[ 9] = w[ 9] >> 8;
316 w_t[10] = w[10] >> 8;
317 w_t[11] = w[11] >> 8;
318 w_t[12] = w[12] >> 8;
319 w_t[13] = w[13] >> 8;
320 w_t[14] = w[14] >> 8;
321 w_t[15] = w[15] >> 8;
325 digest[0] = SHA256M_A;
326 digest[1] = SHA256M_B;
327 digest[2] = SHA256M_C;
328 digest[3] = SHA256M_D;
329 digest[4] = SHA256M_E;
330 digest[5] = SHA256M_F;
331 digest[6] = SHA256M_G;
332 digest[7] = SHA256M_H;
334 sha256_transform (digest, w_t); // 0 - 64
353 sha256_transform (digest, w_t); // 64 - 128
354 sha256_transform (digest, w_t); // 128 - 192
355 sha256_transform (digest, w_t); // 192 - 256
356 sha256_transform (digest, w_t); // 256 - 320
357 sha256_transform (digest, w_t); // 320 - 384
358 sha256_transform (digest, w_t); // 384 - 448
360 w_t[15] = 0 | salt_buf0 >> 16;
362 sha256_transform (digest, w_t); // 448 - 512
364 w_t[ 0] = salt_buf0 << 16 | salt_buf1 >> 16;
365 w_t[ 1] = salt_buf1 << 16 | salt_buf2 >> 16;
366 w_t[ 2] = salt_buf2 << 16 | 0;
367 w_t[15] = (510 + 8) * 8;
369 sha256_transform (digest, w_t); // 512 - 576
371 const u32x r0 = digest[3];
372 const u32x r1 = digest[7];
373 const u32x r2 = digest[2];
374 const u32x r3 = digest[6];
376 #include VECT_COMPARE_S
380 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08000_m04 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __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)
386 const u32 gid = get_global_id (0);
388 if (gid >= gid_max) return;
392 w[ 0] = pws[gid].i[ 0];
393 w[ 1] = pws[gid].i[ 1];
394 w[ 2] = pws[gid].i[ 2];
395 w[ 3] = pws[gid].i[ 3];
409 const u32 pw_len = pws[gid].pw_len;
415 m08000m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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);
418 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08000_m08 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __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)
424 const u32 gid = get_global_id (0);
426 if (gid >= gid_max) return;
430 w[ 0] = pws[gid].i[ 0];
431 w[ 1] = pws[gid].i[ 1];
432 w[ 2] = pws[gid].i[ 2];
433 w[ 3] = pws[gid].i[ 3];
434 w[ 4] = pws[gid].i[ 4];
435 w[ 5] = pws[gid].i[ 5];
436 w[ 6] = pws[gid].i[ 6];
437 w[ 7] = pws[gid].i[ 7];
447 const u32 pw_len = pws[gid].pw_len;
453 m08000m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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);
456 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08000_m16 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __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)
462 const u32 gid = get_global_id (0);
464 if (gid >= gid_max) return;
468 w[ 0] = pws[gid].i[ 0];
469 w[ 1] = pws[gid].i[ 1];
470 w[ 2] = pws[gid].i[ 2];
471 w[ 3] = pws[gid].i[ 3];
472 w[ 4] = pws[gid].i[ 4];
473 w[ 5] = pws[gid].i[ 5];
474 w[ 6] = pws[gid].i[ 6];
475 w[ 7] = pws[gid].i[ 7];
476 w[ 8] = pws[gid].i[ 8];
477 w[ 9] = pws[gid].i[ 9];
478 w[10] = pws[gid].i[10];
479 w[11] = pws[gid].i[11];
480 w[12] = pws[gid].i[12];
481 w[13] = pws[gid].i[13];
482 w[14] = pws[gid].i[14];
483 w[15] = pws[gid].i[15];
485 const u32 pw_len = pws[gid].pw_len;
491 m08000m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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);
494 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08000_s04 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __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)
500 const u32 gid = get_global_id (0);
502 if (gid >= gid_max) return;
506 w[ 0] = pws[gid].i[ 0];
507 w[ 1] = pws[gid].i[ 1];
508 w[ 2] = pws[gid].i[ 2];
509 w[ 3] = pws[gid].i[ 3];
523 const u32 pw_len = pws[gid].pw_len;
529 m08000s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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);
532 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08000_s08 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __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)
538 const u32 gid = get_global_id (0);
540 if (gid >= gid_max) return;
544 w[ 0] = pws[gid].i[ 0];
545 w[ 1] = pws[gid].i[ 1];
546 w[ 2] = pws[gid].i[ 2];
547 w[ 3] = pws[gid].i[ 3];
548 w[ 4] = pws[gid].i[ 4];
549 w[ 5] = pws[gid].i[ 5];
550 w[ 6] = pws[gid].i[ 6];
551 w[ 7] = pws[gid].i[ 7];
561 const u32 pw_len = pws[gid].pw_len;
567 m08000s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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);
570 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08000_s16 (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global u32x * words_buf_r, __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)
576 const u32 gid = get_global_id (0);
578 if (gid >= gid_max) return;
582 w[ 0] = pws[gid].i[ 0];
583 w[ 1] = pws[gid].i[ 1];
584 w[ 2] = pws[gid].i[ 2];
585 w[ 3] = pws[gid].i[ 3];
586 w[ 4] = pws[gid].i[ 4];
587 w[ 5] = pws[gid].i[ 5];
588 w[ 6] = pws[gid].i[ 6];
589 w[ 7] = pws[gid].i[ 7];
590 w[ 8] = pws[gid].i[ 8];
591 w[ 9] = pws[gid].i[ 9];
592 w[10] = pws[gid].i[10];
593 w[11] = pws[gid].i[11];
594 w[12] = pws[gid].i[12];
595 w[13] = pws[gid].i[13];
596 w[14] = pws[gid].i[14];
597 w[15] = pws[gid].i[15];
599 const u32 pw_len = pws[gid].pw_len;
605 m08000s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, 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);