2 * Author......: Jens Steube <jens.steube@gmail.com>
9 #include "include/constants.h"
10 #include "include/kernel_vendor.h"
25 #include "include/kernel_functions.c"
27 #include "common_nv.c"
30 #define VECT_COMPARE_S "check_single_vect1_comp4_warp.c"
31 #define VECT_COMPARE_M "check_multi_vect1_comp4_warp.c"
35 #define VECT_COMPARE_S "check_single_vect2_comp4_warp.c"
36 #define VECT_COMPARE_M "check_multi_vect2_comp4_warp.c"
40 #define VECT_COMPARE_S "check_single_vect4_comp4_warp.c"
41 #define VECT_COMPARE_M "check_multi_vect4_comp4_warp.c"
44 __device__ __constant__ u32x c_bfs[1024];
46 __device__ __constant__ u64 k_sha512[80] =
48 SHA512C00, SHA512C01, SHA512C02, SHA512C03,
49 SHA512C04, SHA512C05, SHA512C06, SHA512C07,
50 SHA512C08, SHA512C09, SHA512C0a, SHA512C0b,
51 SHA512C0c, SHA512C0d, SHA512C0e, SHA512C0f,
52 SHA512C10, SHA512C11, SHA512C12, SHA512C13,
53 SHA512C14, SHA512C15, SHA512C16, SHA512C17,
54 SHA512C18, SHA512C19, SHA512C1a, SHA512C1b,
55 SHA512C1c, SHA512C1d, SHA512C1e, SHA512C1f,
56 SHA512C20, SHA512C21, SHA512C22, SHA512C23,
57 SHA512C24, SHA512C25, SHA512C26, SHA512C27,
58 SHA512C28, SHA512C29, SHA512C2a, SHA512C2b,
59 SHA512C2c, SHA512C2d, SHA512C2e, SHA512C2f,
60 SHA512C30, SHA512C31, SHA512C32, SHA512C33,
61 SHA512C34, SHA512C35, SHA512C36, SHA512C37,
62 SHA512C38, SHA512C39, SHA512C3a, SHA512C3b,
63 SHA512C3c, SHA512C3d, SHA512C3e, SHA512C3f,
64 SHA512C40, SHA512C41, SHA512C42, SHA512C43,
65 SHA512C44, SHA512C45, SHA512C46, SHA512C47,
66 SHA512C48, SHA512C49, SHA512C4a, SHA512C4b,
67 SHA512C4c, SHA512C4d, SHA512C4e, SHA512C4f,
70 __device__ static void sha512_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u64x digest[8])
72 u64x w0_t = hl32_to_64 (w0[0], w0[1]);
73 u64x w1_t = hl32_to_64 (w0[2], w0[3]);
74 u64x w2_t = hl32_to_64 (w1[0], w1[1]);
75 u64x w3_t = hl32_to_64 (w1[2], w1[3]);
76 u64x w4_t = hl32_to_64 (w2[0], w2[1]);
77 u64x w5_t = hl32_to_64 (w2[2], w2[3]);
78 u64x w6_t = hl32_to_64 (w3[0], w3[1]);
87 u64x wf_t = hl32_to_64 (w3[2], w3[3]);
98 #define ROUND_EXPAND() \
100 w0_t = SHA512_EXPAND (we_t, w9_t, w1_t, w0_t); \
101 w1_t = SHA512_EXPAND (wf_t, wa_t, w2_t, w1_t); \
102 w2_t = SHA512_EXPAND (w0_t, wb_t, w3_t, w2_t); \
103 w3_t = SHA512_EXPAND (w1_t, wc_t, w4_t, w3_t); \
104 w4_t = SHA512_EXPAND (w2_t, wd_t, w5_t, w4_t); \
105 w5_t = SHA512_EXPAND (w3_t, we_t, w6_t, w5_t); \
106 w6_t = SHA512_EXPAND (w4_t, wf_t, w7_t, w6_t); \
107 w7_t = SHA512_EXPAND (w5_t, w0_t, w8_t, w7_t); \
108 w8_t = SHA512_EXPAND (w6_t, w1_t, w9_t, w8_t); \
109 w9_t = SHA512_EXPAND (w7_t, w2_t, wa_t, w9_t); \
110 wa_t = SHA512_EXPAND (w8_t, w3_t, wb_t, wa_t); \
111 wb_t = SHA512_EXPAND (w9_t, w4_t, wc_t, wb_t); \
112 wc_t = SHA512_EXPAND (wa_t, w5_t, wd_t, wc_t); \
113 wd_t = SHA512_EXPAND (wb_t, w6_t, we_t, wd_t); \
114 we_t = SHA512_EXPAND (wc_t, w7_t, wf_t, we_t); \
115 wf_t = SHA512_EXPAND (wd_t, w8_t, w0_t, wf_t); \
118 #define ROUND_STEP(i) \
120 SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w0_t, k_sha512[i + 0]); \
121 SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w1_t, k_sha512[i + 1]); \
122 SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, w2_t, k_sha512[i + 2]); \
123 SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, w3_t, k_sha512[i + 3]); \
124 SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, w4_t, k_sha512[i + 4]); \
125 SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, w5_t, k_sha512[i + 5]); \
126 SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, w6_t, k_sha512[i + 6]); \
127 SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, w7_t, k_sha512[i + 7]); \
128 SHA512_STEP (SHA512_F0o, SHA512_F1o, a, b, c, d, e, f, g, h, w8_t, k_sha512[i + 8]); \
129 SHA512_STEP (SHA512_F0o, SHA512_F1o, h, a, b, c, d, e, f, g, w9_t, k_sha512[i + 9]); \
130 SHA512_STEP (SHA512_F0o, SHA512_F1o, g, h, a, b, c, d, e, f, wa_t, k_sha512[i + 10]); \
131 SHA512_STEP (SHA512_F0o, SHA512_F1o, f, g, h, a, b, c, d, e, wb_t, k_sha512[i + 11]); \
132 SHA512_STEP (SHA512_F0o, SHA512_F1o, e, f, g, h, a, b, c, d, wc_t, k_sha512[i + 12]); \
133 SHA512_STEP (SHA512_F0o, SHA512_F1o, d, e, f, g, h, a, b, c, wd_t, k_sha512[i + 13]); \
134 SHA512_STEP (SHA512_F0o, SHA512_F1o, c, d, e, f, g, h, a, b, we_t, k_sha512[i + 14]); \
135 SHA512_STEP (SHA512_F0o, SHA512_F1o, b, c, d, e, f, g, h, a, wf_t, k_sha512[i + 15]); \
140 for (int i = 16; i < 80; i += 16)
142 ROUND_EXPAND (); ROUND_STEP (i);
166 __device__ static void m01710m (u32 w[16], const u32 pw_len, const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
172 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
173 const u32 lid = threadIdx.x;
181 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
182 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
183 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
184 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
188 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
189 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
190 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
191 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
195 salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
207 switch_buffer_by_offset (salt_buf0, salt_buf1, salt_buf2, salt_buf3, pw_len);
209 w[ 0] |= swap_workaround (salt_buf0[0]);
210 w[ 1] |= swap_workaround (salt_buf0[1]);
211 w[ 2] |= swap_workaround (salt_buf0[2]);
212 w[ 3] |= swap_workaround (salt_buf0[3]);
213 w[ 4] |= swap_workaround (salt_buf1[0]);
214 w[ 5] |= swap_workaround (salt_buf1[1]);
215 w[ 6] |= swap_workaround (salt_buf1[2]);
216 w[ 7] |= swap_workaround (salt_buf1[3]);
217 w[ 8] |= swap_workaround (salt_buf2[0]);
218 w[ 9] |= swap_workaround (salt_buf2[1]);
219 w[10] |= swap_workaround (salt_buf2[2]);
220 w[11] |= swap_workaround (salt_buf2[3]);
221 w[12] |= swap_workaround (salt_buf3[0]);
222 w[13] |= swap_workaround (salt_buf3[1]);
223 w[14] |= swap_workaround (salt_buf3[2]);
224 w[15] |= swap_workaround (salt_buf3[3]);
226 const u32 salt_len = salt_bufs[salt_pos].salt_len;
228 const u32 pw_salt_len = pw_len + salt_len;
230 w[15] = pw_salt_len * 8;
236 const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
240 for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
242 const u32x w0r = c_bfs[il_pos];
244 const u32x w0 = w0l | w0r;
270 digest[0] = SHA512M_A;
271 digest[1] = SHA512M_B;
272 digest[2] = SHA512M_C;
273 digest[3] = SHA512M_D;
274 digest[4] = SHA512M_E;
275 digest[5] = SHA512M_F;
276 digest[6] = SHA512M_G;
277 digest[7] = SHA512M_H;
279 sha512_transform (w0_t, w1_t, w2_t, w3_t, digest);
282 const u32x r0 = l32_from_64 (digest[7]);
283 const u32x r1 = h32_from_64 (digest[7]);
284 const u32x r2 = l32_from_64 (digest[3]);
285 const u32x r3 = h32_from_64 (digest[3]);
287 #include VECT_COMPARE_M
291 __device__ static void m01710s (u32 w[16], const u32 pw_len, const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
297 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
298 const u32 lid = threadIdx.x;
304 const u32 search[4] =
306 digests_buf[digests_offset].digest_buf[DGST_R0],
307 digests_buf[digests_offset].digest_buf[DGST_R1],
308 digests_buf[digests_offset].digest_buf[DGST_R2],
309 digests_buf[digests_offset].digest_buf[DGST_R3]
316 const u32 bf_loops = ceil ((float) bfs_cnt / VECT_DIV);
320 for (u32 il_pos = 0; il_pos < bf_loops; il_pos++)
322 const u32x w0r = c_bfs[il_pos];
324 const u32x w0 = w0l | w0r;
350 digest[0] = SHA512M_A;
351 digest[1] = SHA512M_B;
352 digest[2] = SHA512M_C;
353 digest[3] = SHA512M_D;
354 digest[4] = SHA512M_E;
355 digest[5] = SHA512M_F;
356 digest[6] = SHA512M_G;
357 digest[7] = SHA512M_H;
359 sha512_transform (w0_t, w1_t, w2_t, w3_t, digest);
362 const u32x r0 = l32_from_64 (digest[7]);
363 const u32x r1 = h32_from_64 (digest[7]);
364 const u32x r2 = l32_from_64 (digest[3]);
365 const u32x r3 = h32_from_64 (digest[3]);
367 #include VECT_COMPARE_S
371 extern "C" __global__ void __launch_bounds__ (256, 1) m01710_m04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
377 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
379 if (gid >= gid_max) return;
383 w[ 0] = pws[gid].i[ 0];
384 w[ 1] = pws[gid].i[ 1];
385 w[ 2] = pws[gid].i[ 2];
386 w[ 3] = pws[gid].i[ 3];
398 w[15] = pws[gid].i[15];
400 const u32 pw_len = pws[gid].pw_len;
406 m01710m (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);
409 extern "C" __global__ void __launch_bounds__ (256, 1) m01710_m08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
415 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
417 if (gid >= gid_max) return;
421 w[ 0] = pws[gid].i[ 0];
422 w[ 1] = pws[gid].i[ 1];
423 w[ 2] = pws[gid].i[ 2];
424 w[ 3] = pws[gid].i[ 3];
425 w[ 4] = pws[gid].i[ 4];
426 w[ 5] = pws[gid].i[ 5];
427 w[ 6] = pws[gid].i[ 6];
428 w[ 7] = pws[gid].i[ 7];
436 w[15] = pws[gid].i[15];
438 const u32 pw_len = pws[gid].pw_len;
444 m01710m (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);
447 extern "C" __global__ void __launch_bounds__ (256, 1) m01710_m16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
453 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
455 if (gid >= gid_max) return;
459 w[ 0] = pws[gid].i[ 0];
460 w[ 1] = pws[gid].i[ 1];
461 w[ 2] = pws[gid].i[ 2];
462 w[ 3] = pws[gid].i[ 3];
463 w[ 4] = pws[gid].i[ 4];
464 w[ 5] = pws[gid].i[ 5];
465 w[ 6] = pws[gid].i[ 6];
466 w[ 7] = pws[gid].i[ 7];
467 w[ 8] = pws[gid].i[ 8];
468 w[ 9] = pws[gid].i[ 9];
469 w[10] = pws[gid].i[10];
470 w[11] = pws[gid].i[11];
471 w[12] = pws[gid].i[12];
472 w[13] = pws[gid].i[13];
473 w[14] = pws[gid].i[14];
474 w[15] = pws[gid].i[15];
476 const u32 pw_len = pws[gid].pw_len;
482 m01710m (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);
485 extern "C" __global__ void __launch_bounds__ (256, 1) m01710_s04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
491 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
493 if (gid >= gid_max) return;
497 w[ 0] = pws[gid].i[ 0];
498 w[ 1] = pws[gid].i[ 1];
499 w[ 2] = pws[gid].i[ 2];
500 w[ 3] = pws[gid].i[ 3];
512 w[15] = pws[gid].i[15];
514 const u32 pw_len = pws[gid].pw_len;
520 m01710s (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);
523 extern "C" __global__ void __launch_bounds__ (256, 1) m01710_s08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
529 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
531 if (gid >= gid_max) return;
535 w[ 0] = pws[gid].i[ 0];
536 w[ 1] = pws[gid].i[ 1];
537 w[ 2] = pws[gid].i[ 2];
538 w[ 3] = pws[gid].i[ 3];
539 w[ 4] = pws[gid].i[ 4];
540 w[ 5] = pws[gid].i[ 5];
541 w[ 6] = pws[gid].i[ 6];
542 w[ 7] = pws[gid].i[ 7];
550 w[15] = pws[gid].i[15];
552 const u32 pw_len = pws[gid].pw_len;
558 m01710s (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);
561 extern "C" __global__ void __launch_bounds__ (256, 1) m01710_s16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *words_buf_r, 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)
567 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
569 if (gid >= gid_max) return;
573 w[ 0] = pws[gid].i[ 0];
574 w[ 1] = pws[gid].i[ 1];
575 w[ 2] = pws[gid].i[ 2];
576 w[ 3] = pws[gid].i[ 3];
577 w[ 4] = pws[gid].i[ 4];
578 w[ 5] = pws[gid].i[ 5];
579 w[ 6] = pws[gid].i[ 6];
580 w[ 7] = pws[gid].i[ 7];
581 w[ 8] = pws[gid].i[ 8];
582 w[ 9] = pws[gid].i[ 9];
583 w[10] = pws[gid].i[10];
584 w[11] = pws[gid].i[11];
585 w[12] = pws[gid].i[12];
586 w[13] = pws[gid].i[13];
587 w[14] = pws[gid].i[14];
588 w[15] = pws[gid].i[15];
590 const u32 pw_len = pws[gid].pw_len;
596 m01710s (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);