2 * Author......: Jens Steube <jens.steube@gmail.com>
8 #include "include/constants.h"
9 #include "include/kernel_vendor.h"
24 #include "include/kernel_functions.c"
26 #include "common_nv.c"
29 #define VECT_COMPARE_S "check_single_vect1_comp4.c"
30 #define VECT_COMPARE_M "check_multi_vect1_comp4.c"
34 #define VECT_COMPARE_S "check_single_vect2_comp4.c"
35 #define VECT_COMPARE_M "check_multi_vect2_comp4.c"
39 #define VECT_COMPARE_S "check_single_vect4_comp4.c"
40 #define VECT_COMPARE_M "check_multi_vect4_comp4.c"
43 __device__ __constant__ u32 k_sha256[64] =
45 SHA256C00, SHA256C01, SHA256C02, SHA256C03,
46 SHA256C04, SHA256C05, SHA256C06, SHA256C07,
47 SHA256C08, SHA256C09, SHA256C0a, SHA256C0b,
48 SHA256C0c, SHA256C0d, SHA256C0e, SHA256C0f,
49 SHA256C10, SHA256C11, SHA256C12, SHA256C13,
50 SHA256C14, SHA256C15, SHA256C16, SHA256C17,
51 SHA256C18, SHA256C19, SHA256C1a, SHA256C1b,
52 SHA256C1c, SHA256C1d, SHA256C1e, SHA256C1f,
53 SHA256C20, SHA256C21, SHA256C22, SHA256C23,
54 SHA256C24, SHA256C25, SHA256C26, SHA256C27,
55 SHA256C28, SHA256C29, SHA256C2a, SHA256C2b,
56 SHA256C2c, SHA256C2d, SHA256C2e, SHA256C2f,
57 SHA256C30, SHA256C31, SHA256C32, SHA256C33,
58 SHA256C34, SHA256C35, SHA256C36, SHA256C37,
59 SHA256C38, SHA256C39, SHA256C3a, SHA256C3b,
60 SHA256C3c, SHA256C3d, SHA256C3e, SHA256C3f,
63 __device__ __constant__ bf_t c_bfs[1024];
65 __device__ static void sha256_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[8])
93 #define ROUND_EXPAND() \
95 w0_t = SHA256_EXPAND (we_t, w9_t, w1_t, w0_t); \
96 w1_t = SHA256_EXPAND (wf_t, wa_t, w2_t, w1_t); \
97 w2_t = SHA256_EXPAND (w0_t, wb_t, w3_t, w2_t); \
98 w3_t = SHA256_EXPAND (w1_t, wc_t, w4_t, w3_t); \
99 w4_t = SHA256_EXPAND (w2_t, wd_t, w5_t, w4_t); \
100 w5_t = SHA256_EXPAND (w3_t, we_t, w6_t, w5_t); \
101 w6_t = SHA256_EXPAND (w4_t, wf_t, w7_t, w6_t); \
102 w7_t = SHA256_EXPAND (w5_t, w0_t, w8_t, w7_t); \
103 w8_t = SHA256_EXPAND (w6_t, w1_t, w9_t, w8_t); \
104 w9_t = SHA256_EXPAND (w7_t, w2_t, wa_t, w9_t); \
105 wa_t = SHA256_EXPAND (w8_t, w3_t, wb_t, wa_t); \
106 wb_t = SHA256_EXPAND (w9_t, w4_t, wc_t, wb_t); \
107 wc_t = SHA256_EXPAND (wa_t, w5_t, wd_t, wc_t); \
108 wd_t = SHA256_EXPAND (wb_t, w6_t, we_t, wd_t); \
109 we_t = SHA256_EXPAND (wc_t, w7_t, wf_t, we_t); \
110 wf_t = SHA256_EXPAND (wd_t, w8_t, w0_t, wf_t); \
113 #define ROUND_STEP(i) \
115 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha256[i + 0]); \
116 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha256[i + 1]); \
117 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha256[i + 2]); \
118 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha256[i + 3]); \
119 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha256[i + 4]); \
120 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha256[i + 5]); \
121 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha256[i + 6]); \
122 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha256[i + 7]); \
123 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha256[i + 8]); \
124 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha256[i + 9]); \
125 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha256[i + 10]); \
126 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha256[i + 11]); \
127 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha256[i + 12]); \
128 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha256[i + 13]); \
129 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, k_sha256[i + 14]); \
130 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha256[i + 15]); \
135 for (int i = 16; i < 64; i += 16)
137 ROUND_EXPAND (); ROUND_STEP (i);
150 __device__ static void hmac_sha256_pad (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[8], u32x opad[8])
152 w0[0] = w0[0] ^ 0x36363636;
153 w0[1] = w0[1] ^ 0x36363636;
154 w0[2] = w0[2] ^ 0x36363636;
155 w0[3] = w0[3] ^ 0x36363636;
156 w1[0] = w1[0] ^ 0x36363636;
157 w1[1] = w1[1] ^ 0x36363636;
158 w1[2] = w1[2] ^ 0x36363636;
159 w1[3] = w1[3] ^ 0x36363636;
160 w2[0] = w2[0] ^ 0x36363636;
161 w2[1] = w2[1] ^ 0x36363636;
162 w2[2] = w2[2] ^ 0x36363636;
163 w2[3] = w2[3] ^ 0x36363636;
164 w3[0] = w3[0] ^ 0x36363636;
165 w3[1] = w3[1] ^ 0x36363636;
166 w3[2] = w3[2] ^ 0x36363636;
167 w3[3] = w3[3] ^ 0x36363636;
178 sha256_transform (w0, w1, w2, w3, ipad);
180 w0[0] = w0[0] ^ 0x6a6a6a6a;
181 w0[1] = w0[1] ^ 0x6a6a6a6a;
182 w0[2] = w0[2] ^ 0x6a6a6a6a;
183 w0[3] = w0[3] ^ 0x6a6a6a6a;
184 w1[0] = w1[0] ^ 0x6a6a6a6a;
185 w1[1] = w1[1] ^ 0x6a6a6a6a;
186 w1[2] = w1[2] ^ 0x6a6a6a6a;
187 w1[3] = w1[3] ^ 0x6a6a6a6a;
188 w2[0] = w2[0] ^ 0x6a6a6a6a;
189 w2[1] = w2[1] ^ 0x6a6a6a6a;
190 w2[2] = w2[2] ^ 0x6a6a6a6a;
191 w2[3] = w2[3] ^ 0x6a6a6a6a;
192 w3[0] = w3[0] ^ 0x6a6a6a6a;
193 w3[1] = w3[1] ^ 0x6a6a6a6a;
194 w3[2] = w3[2] ^ 0x6a6a6a6a;
195 w3[3] = w3[3] ^ 0x6a6a6a6a;
206 sha256_transform (w0, w1, w2, w3, opad);
209 __device__ 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])
220 sha256_transform (w0, w1, w2, w3, digest);
237 w3[3] = (64 + 32) * 8;
248 sha256_transform (w0, w1, w2, w3, digest);
251 __device__ static void m01460m (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], const u32 pw_len, const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
257 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
258 const u32 lid = threadIdx.x;
266 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
267 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
268 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
269 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
273 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
274 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
275 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
276 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
284 w0_t[0] = swap_workaround (salt_buf0[0]);
285 w0_t[1] = swap_workaround (salt_buf0[1]);
286 w0_t[2] = swap_workaround (salt_buf0[2]);
287 w0_t[3] = swap_workaround (salt_buf0[3]);
291 w1_t[0] = swap_workaround (salt_buf1[0]);
292 w1_t[1] = swap_workaround (salt_buf1[1]);
293 w1_t[2] = swap_workaround (salt_buf1[2]);
294 w1_t[3] = swap_workaround (salt_buf1[3]);
313 hmac_sha256_pad (w0_t, w1_t, w2_t, w3_t, ipad, opad);
321 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
323 const u32 w0r = c_bfs[il_pos].i;
342 w3_t[3] = (64 + pw_len) * 8;
346 hmac_sha256_run (w0_t, w1_t, w2_t, w3_t, ipad, opad, digest);
348 const u32x r0 = digest[3];
349 const u32x r1 = digest[7];
350 const u32x r2 = digest[2];
351 const u32x r3 = digest[6];
353 #include VECT_COMPARE_M
357 __device__ static void m01460s (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], const u32 pw_len, const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
363 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
364 const u32 lid = threadIdx.x;
372 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
373 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
374 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
375 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
379 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
380 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
381 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
382 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
390 w0_t[0] = swap_workaround (salt_buf0[0]);
391 w0_t[1] = swap_workaround (salt_buf0[1]);
392 w0_t[2] = swap_workaround (salt_buf0[2]);
393 w0_t[3] = swap_workaround (salt_buf0[3]);
397 w1_t[0] = swap_workaround (salt_buf1[0]);
398 w1_t[1] = swap_workaround (salt_buf1[1]);
399 w1_t[2] = swap_workaround (salt_buf1[2]);
400 w1_t[3] = swap_workaround (salt_buf1[3]);
419 hmac_sha256_pad (w0_t, w1_t, w2_t, w3_t, ipad, opad);
425 const u32 search[4] =
427 digests_buf[digests_offset].digest_buf[DGST_R0],
428 digests_buf[digests_offset].digest_buf[DGST_R1],
429 digests_buf[digests_offset].digest_buf[DGST_R2],
430 digests_buf[digests_offset].digest_buf[DGST_R3]
439 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
441 const u32 w0r = c_bfs[il_pos].i;
460 w3_t[3] = (64 + pw_len) * 8;
464 hmac_sha256_run (w0_t, w1_t, w2_t, w3_t, ipad, opad, digest);
466 const u32x r0 = digest[3];
467 const u32x r1 = digest[7];
468 const u32x r2 = digest[2];
469 const u32x r3 = digest[6];
471 #include VECT_COMPARE_S
475 extern "C" __global__ void __launch_bounds__ (256, 1) m01460_m04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
481 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
483 if (gid >= gid_max) return;
487 w0[0] = pws[gid].i[ 0];
488 w0[1] = pws[gid].i[ 1];
489 w0[2] = pws[gid].i[ 2];
490 w0[3] = pws[gid].i[ 3];
513 const u32 pw_len = pws[gid].pw_len;
519 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);
522 extern "C" __global__ void __launch_bounds__ (256, 1) m01460_m08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
528 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
530 if (gid >= gid_max) return;
534 w0[0] = pws[gid].i[ 0];
535 w0[1] = pws[gid].i[ 1];
536 w0[2] = pws[gid].i[ 2];
537 w0[3] = pws[gid].i[ 3];
541 w1[0] = pws[gid].i[ 4];
542 w1[1] = pws[gid].i[ 5];
543 w1[2] = pws[gid].i[ 6];
544 w1[3] = pws[gid].i[ 7];
560 const u32 pw_len = pws[gid].pw_len;
566 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);
569 extern "C" __global__ void __launch_bounds__ (256, 1) m01460_m16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
575 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
577 if (gid >= gid_max) return;
581 w0[0] = pws[gid].i[ 0];
582 w0[1] = pws[gid].i[ 1];
583 w0[2] = pws[gid].i[ 2];
584 w0[3] = pws[gid].i[ 3];
588 w1[0] = pws[gid].i[ 4];
589 w1[1] = pws[gid].i[ 5];
590 w1[2] = pws[gid].i[ 6];
591 w1[3] = pws[gid].i[ 7];
595 w2[0] = pws[gid].i[ 8];
596 w2[1] = pws[gid].i[ 9];
597 w2[2] = pws[gid].i[10];
598 w2[3] = pws[gid].i[11];
602 w3[0] = pws[gid].i[12];
603 w3[1] = pws[gid].i[13];
607 const u32 pw_len = pws[gid].pw_len;
613 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);
616 extern "C" __global__ void __launch_bounds__ (256, 1) m01460_s04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
622 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
624 if (gid >= gid_max) return;
628 w0[0] = pws[gid].i[ 0];
629 w0[1] = pws[gid].i[ 1];
630 w0[2] = pws[gid].i[ 2];
631 w0[3] = pws[gid].i[ 3];
654 const u32 pw_len = pws[gid].pw_len;
660 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);
663 extern "C" __global__ void __launch_bounds__ (256, 1) m01460_s08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
669 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
671 if (gid >= gid_max) return;
675 w0[0] = pws[gid].i[ 0];
676 w0[1] = pws[gid].i[ 1];
677 w0[2] = pws[gid].i[ 2];
678 w0[3] = pws[gid].i[ 3];
682 w1[0] = pws[gid].i[ 4];
683 w1[1] = pws[gid].i[ 5];
684 w1[2] = pws[gid].i[ 6];
685 w1[3] = pws[gid].i[ 7];
701 const u32 pw_len = pws[gid].pw_len;
707 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);
710 extern "C" __global__ void __launch_bounds__ (256, 1) m01460_s16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, const void *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
716 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
718 if (gid >= gid_max) return;
722 w0[0] = pws[gid].i[ 0];
723 w0[1] = pws[gid].i[ 1];
724 w0[2] = pws[gid].i[ 2];
725 w0[3] = pws[gid].i[ 3];
729 w1[0] = pws[gid].i[ 4];
730 w1[1] = pws[gid].i[ 5];
731 w1[2] = pws[gid].i[ 6];
732 w1[3] = pws[gid].i[ 7];
736 w2[0] = pws[gid].i[ 8];
737 w2[1] = pws[gid].i[ 9];
738 w2[2] = pws[gid].i[10];
739 w2[3] = pws[gid].i[11];
743 w3[0] = pws[gid].i[12];
744 w3[1] = pws[gid].i[13];
748 const u32 pw_len = pws[gid].pw_len;
754 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);