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_vect4_comp4.c"
35 #define VECT_COMPARE_M "check_multi_vect4_comp4.c"
46 __device__ static void swap (RC4_KEY *rc4_key, const u32 i, const u32 j)
51 rc4_key->S[i] = rc4_key->S[j];
55 __device__ static void rc4_init_16 (RC4_KEY *rc4_key, const u32 data[4])
60 u32 *ptr = (u32 *) rc4_key->S;
63 for (u32 i = 0; i < 64; i++)
70 for (u32 i = 0; i < 16; i++)
78 j += rc4_key->S[idx] + (v >> 0); swap (rc4_key, idx, j & 0xff); idx++;
79 j += rc4_key->S[idx] + (v >> 8); swap (rc4_key, idx, j & 0xff); idx++;
80 j += rc4_key->S[idx] + (v >> 16); swap (rc4_key, idx, j & 0xff); idx++;
81 j += rc4_key->S[idx] + (v >> 24); swap (rc4_key, idx, j & 0xff); idx++;
85 j += rc4_key->S[idx] + (v >> 0); swap (rc4_key, idx, j & 0xff); idx++;
86 j += rc4_key->S[idx] + (v >> 8); swap (rc4_key, idx, j & 0xff); idx++;
87 j += rc4_key->S[idx] + (v >> 16); swap (rc4_key, idx, j & 0xff); idx++;
88 j += rc4_key->S[idx] + (v >> 24); swap (rc4_key, idx, j & 0xff); idx++;
92 j += rc4_key->S[idx] + (v >> 0); swap (rc4_key, idx, j & 0xff); idx++;
93 j += rc4_key->S[idx] + (v >> 8); swap (rc4_key, idx, j & 0xff); idx++;
94 j += rc4_key->S[idx] + (v >> 16); swap (rc4_key, idx, j & 0xff); idx++;
95 j += rc4_key->S[idx] + (v >> 24); swap (rc4_key, idx, j & 0xff); idx++;
99 j += rc4_key->S[idx] + (v >> 0); swap (rc4_key, idx, j & 0xff); idx++;
100 j += rc4_key->S[idx] + (v >> 8); swap (rc4_key, idx, j & 0xff); idx++;
101 j += rc4_key->S[idx] + (v >> 16); swap (rc4_key, idx, j & 0xff); idx++;
102 j += rc4_key->S[idx] + (v >> 24); swap (rc4_key, idx, j & 0xff); idx++;
106 __device__ static u8 rc4_next_16 (RC4_KEY *rc4_key, u8 i, u8 j, const u32 in[4], u32 out[4])
108 for (u32 k = 0; k < 4; k++)
117 swap (rc4_key, i, j);
119 idx = rc4_key->S[i] + rc4_key->S[j];
121 xor4 |= rc4_key->S[idx] << 0;
126 swap (rc4_key, i, j);
128 idx = rc4_key->S[i] + rc4_key->S[j];
130 xor4 |= rc4_key->S[idx] << 8;
135 swap (rc4_key, i, j);
137 idx = rc4_key->S[i] + rc4_key->S[j];
139 xor4 |= rc4_key->S[idx] << 16;
144 swap (rc4_key, i, j);
146 idx = rc4_key->S[i] + rc4_key->S[j];
148 xor4 |= rc4_key->S[idx] << 24;
150 out[k] = in[k] ^ xor4;
156 __device__ static void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5])
184 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
185 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
186 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
187 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
188 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
189 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
190 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
191 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
192 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
193 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
194 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
195 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
196 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
197 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
198 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
199 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
200 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
201 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
202 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
203 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
208 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
209 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
210 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
211 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
212 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
213 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
214 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
215 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
216 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
217 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
218 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
219 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
220 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
221 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
222 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
223 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
224 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
225 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
226 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
227 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
232 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
233 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
234 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
235 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
236 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
237 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
238 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
239 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
240 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
241 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
242 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
243 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
244 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
245 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
246 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
247 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
248 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
249 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
250 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
251 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
256 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
257 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
258 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
259 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
260 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
261 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
262 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
263 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
264 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
265 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
266 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
267 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
268 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
269 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
270 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
271 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
272 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
273 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
274 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
275 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
284 __device__ __constant__ bf_t c_bfs[1024];
286 __device__ static void m09810m (RC4_KEY rc4_keys[64], 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 u32x *bfs_buf, 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 oldoffice34_t *oldoffice34_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)
292 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
293 const u32 lid = threadIdx.x;
295 RC4_KEY *rc4_key = &rc4_keys[lid];
301 const u32 version = oldoffice34_bufs[salt_pos].version;
303 u32 encryptedVerifier[4];
305 encryptedVerifier[0] = oldoffice34_bufs[salt_pos].encryptedVerifier[0];
306 encryptedVerifier[1] = oldoffice34_bufs[salt_pos].encryptedVerifier[1];
307 encryptedVerifier[2] = oldoffice34_bufs[salt_pos].encryptedVerifier[2];
308 encryptedVerifier[3] = oldoffice34_bufs[salt_pos].encryptedVerifier[3];
316 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
318 const u32 w0r = c_bfs[il_pos].i;
325 key[1] = w0[1] & 0xff;
329 rc4_init_16 (rc4_key, key);
333 u8 j = rc4_next_16 (rc4_key, 0, 0, encryptedVerifier, out);
340 w0_t[0] = swap_workaround (out[0]);
341 w0_t[1] = swap_workaround (out[1]);
342 w0_t[2] = swap_workaround (out[2]);
343 w0_t[3] = swap_workaround (out[3]);
344 w1_t[0] = 0x80000000;
365 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
367 digest[0] = swap_workaround (digest[0]);
368 digest[1] = swap_workaround (digest[1]);
369 digest[2] = swap_workaround (digest[2]);
370 digest[3] = swap_workaround (digest[3]);
372 rc4_next_16 (rc4_key, 16, j, digest, out);
374 const u32x r0 = out[0];
375 const u32x r1 = out[1];
376 const u32x r2 = out[2];
377 const u32x r3 = out[3];
379 #include VECT_COMPARE_M
383 __device__ static void m09810s (RC4_KEY rc4_keys[64], 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 u32x *bfs_buf, 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 oldoffice34_t *oldoffice34_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)
389 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
390 const u32 lid = threadIdx.x;
392 RC4_KEY *rc4_key = &rc4_keys[lid];
398 const u32 search[4] =
400 digests_buf[digests_offset].digest_buf[DGST_R0],
401 digests_buf[digests_offset].digest_buf[DGST_R1],
402 digests_buf[digests_offset].digest_buf[DGST_R2],
403 digests_buf[digests_offset].digest_buf[DGST_R3]
410 const u32 version = oldoffice34_bufs[salt_pos].version;
412 u32 encryptedVerifier[4];
414 encryptedVerifier[0] = oldoffice34_bufs[salt_pos].encryptedVerifier[0];
415 encryptedVerifier[1] = oldoffice34_bufs[salt_pos].encryptedVerifier[1];
416 encryptedVerifier[2] = oldoffice34_bufs[salt_pos].encryptedVerifier[2];
417 encryptedVerifier[3] = oldoffice34_bufs[salt_pos].encryptedVerifier[3];
425 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
427 const u32 w0r = c_bfs[il_pos].i;
434 key[1] = w0[1] & 0xff;
438 rc4_init_16 (rc4_key, key);
442 u8 j = rc4_next_16 (rc4_key, 0, 0, encryptedVerifier, out);
449 w0_t[0] = swap_workaround (out[0]);
450 w0_t[1] = swap_workaround (out[1]);
451 w0_t[2] = swap_workaround (out[2]);
452 w0_t[3] = swap_workaround (out[3]);
453 w1_t[0] = 0x80000000;
474 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
476 digest[0] = swap_workaround (digest[0]);
477 digest[1] = swap_workaround (digest[1]);
478 digest[2] = swap_workaround (digest[2]);
479 digest[3] = swap_workaround (digest[3]);
481 rc4_next_16 (rc4_key, 16, j, digest, out);
483 const u32x r0 = out[0];
484 const u32x r1 = out[1];
485 const u32x r2 = out[2];
486 const u32x r3 = out[3];
488 #include VECT_COMPARE_S
492 extern "C" __global__ void __launch_bounds__ (64, 1) m09810_m04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *bfs_buf, 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 oldoffice34_t *oldoffice34_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)
498 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
500 if (gid >= gid_max) return;
504 w0[0] = pws[gid].i[ 0];
505 w0[1] = pws[gid].i[ 1];
506 w0[2] = pws[gid].i[ 2];
507 w0[3] = pws[gid].i[ 3];
530 const u32 pw_len = pws[gid].pw_len;
536 __shared__ RC4_KEY rc4_keys[64];
538 m09810m (rc4_keys, 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, oldoffice34_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);
541 extern "C" __global__ void __launch_bounds__ (64, 1) m09810_m08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *bfs_buf, 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 oldoffice34_t *oldoffice34_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)
547 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
549 if (gid >= gid_max) return;
553 w0[0] = pws[gid].i[ 0];
554 w0[1] = pws[gid].i[ 1];
555 w0[2] = pws[gid].i[ 2];
556 w0[3] = pws[gid].i[ 3];
560 w1[0] = pws[gid].i[ 4];
561 w1[1] = pws[gid].i[ 5];
562 w1[2] = pws[gid].i[ 6];
563 w1[3] = pws[gid].i[ 7];
579 const u32 pw_len = pws[gid].pw_len;
585 __shared__ RC4_KEY rc4_keys[64];
587 m09810m (rc4_keys, 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, oldoffice34_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);
590 extern "C" __global__ void __launch_bounds__ (64, 1) m09810_m16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *bfs_buf, 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 oldoffice34_t *oldoffice34_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)
596 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
598 if (gid >= gid_max) return;
602 w0[0] = pws[gid].i[ 0];
603 w0[1] = pws[gid].i[ 1];
604 w0[2] = pws[gid].i[ 2];
605 w0[3] = pws[gid].i[ 3];
609 w1[0] = pws[gid].i[ 4];
610 w1[1] = pws[gid].i[ 5];
611 w1[2] = pws[gid].i[ 6];
612 w1[3] = pws[gid].i[ 7];
616 w2[0] = pws[gid].i[ 8];
617 w2[1] = pws[gid].i[ 9];
618 w2[2] = pws[gid].i[10];
619 w2[3] = pws[gid].i[11];
623 w3[0] = pws[gid].i[12];
624 w3[1] = pws[gid].i[13];
628 const u32 pw_len = pws[gid].pw_len;
634 __shared__ RC4_KEY rc4_keys[64];
636 m09810m (rc4_keys, 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, oldoffice34_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);
639 extern "C" __global__ void __launch_bounds__ (64, 1) m09810_s04 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *bfs_buf, 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 oldoffice34_t *oldoffice34_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)
645 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
647 if (gid >= gid_max) return;
651 w0[0] = pws[gid].i[ 0];
652 w0[1] = pws[gid].i[ 1];
653 w0[2] = pws[gid].i[ 2];
654 w0[3] = pws[gid].i[ 3];
677 const u32 pw_len = pws[gid].pw_len;
683 __shared__ RC4_KEY rc4_keys[64];
685 m09810s (rc4_keys, 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, oldoffice34_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);
688 extern "C" __global__ void __launch_bounds__ (64, 1) m09810_s08 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *bfs_buf, 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 oldoffice34_t *oldoffice34_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)
694 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
696 if (gid >= gid_max) return;
700 w0[0] = pws[gid].i[ 0];
701 w0[1] = pws[gid].i[ 1];
702 w0[2] = pws[gid].i[ 2];
703 w0[3] = pws[gid].i[ 3];
707 w1[0] = pws[gid].i[ 4];
708 w1[1] = pws[gid].i[ 5];
709 w1[2] = pws[gid].i[ 6];
710 w1[3] = pws[gid].i[ 7];
726 const u32 pw_len = pws[gid].pw_len;
732 __shared__ RC4_KEY rc4_keys[64];
734 m09810s (rc4_keys, 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, oldoffice34_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);
737 extern "C" __global__ void __launch_bounds__ (64, 1) m09810_s16 (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const u32x *bfs_buf, 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 oldoffice34_t *oldoffice34_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)
743 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
745 if (gid >= gid_max) return;
749 w0[0] = pws[gid].i[ 0];
750 w0[1] = pws[gid].i[ 1];
751 w0[2] = pws[gid].i[ 2];
752 w0[3] = pws[gid].i[ 3];
756 w1[0] = pws[gid].i[ 4];
757 w1[1] = pws[gid].i[ 5];
758 w1[2] = pws[gid].i[ 6];
759 w1[3] = pws[gid].i[ 7];
763 w2[0] = pws[gid].i[ 8];
764 w2[1] = pws[gid].i[ 9];
765 w2[2] = pws[gid].i[10];
766 w2[3] = pws[gid].i[11];
770 w3[0] = pws[gid].i[12];
771 w3[1] = pws[gid].i[13];
775 const u32 pw_len = pws[gid].pw_len;
781 __shared__ RC4_KEY rc4_keys[64];
783 m09810s (rc4_keys, 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, oldoffice34_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);