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 uint_to_hex_lower8_le(i) l_bin2asc[(i)]
43 #define uint_to_hex_lower8_le(i) u32x (l_bin2asc[(i).x], l_bin2asc[(i).y])
46 __device__ __constant__ char c_bin2asc[16] = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'a', 'b', 'c', 'd', 'e', 'f' };
48 __device__ __shared__ short l_bin2asc[256];
50 __device__ __constant__ comb_t c_combs[1024];
52 __device__ static void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5])
80 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
81 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
82 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
83 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
84 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
85 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
86 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
87 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
88 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
89 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
90 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
91 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
92 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
93 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
94 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
95 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
96 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
97 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
98 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
99 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
104 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
105 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
106 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
107 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
108 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
109 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
110 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
111 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
112 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
113 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
114 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
115 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
116 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
117 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
118 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
119 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
120 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
121 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
122 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
123 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
128 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
129 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
130 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
131 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
132 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
133 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
134 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
135 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
136 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
137 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
138 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
139 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
140 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
141 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
142 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
143 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
144 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
145 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
146 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
147 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
152 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
153 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
154 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
155 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
156 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
157 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
158 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
159 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
160 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
161 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
162 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
163 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
164 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
165 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
166 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
167 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
168 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
169 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
170 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
171 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
180 extern "C" __global__ void __launch_bounds__ (256, 1) m08400_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
186 const u32 lid = threadIdx.x;
192 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
196 wordl0[0] = pws[gid].i[ 0];
197 wordl0[1] = pws[gid].i[ 1];
198 wordl0[2] = pws[gid].i[ 2];
199 wordl0[3] = pws[gid].i[ 3];
203 wordl1[0] = pws[gid].i[ 4];
204 wordl1[1] = pws[gid].i[ 5];
205 wordl1[2] = pws[gid].i[ 6];
206 wordl1[3] = pws[gid].i[ 7];
222 const u32 pw_l_len = pws[gid].pw_len;
224 if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
226 append_0x80_2 (wordl0, wordl1, pw_l_len);
228 switch_buffer_by_offset (wordl0, wordl1, wordl2, wordl3, c_combs[0].pw_len);
235 l_bin2asc[lid] = c_bin2asc[(lid >> 0) & 15] << 0
236 | c_bin2asc[(lid >> 4) & 15] << 8;
240 if (gid >= gid_max) return;
248 salt_buf0[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 0]);
249 salt_buf0[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 1]);
250 salt_buf0[2] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 2]);
251 salt_buf0[3] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 3]);
255 salt_buf1[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 4]);
256 salt_buf1[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 5]);
257 salt_buf1[2] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 6]);
258 salt_buf1[3] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 7]);
262 salt_buf2[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 8]);
263 salt_buf2[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 9]);
267 const u32 salt_len = salt_bufs[salt_pos].salt_len;
273 for (u32 il_pos = 0; il_pos < combs_cnt; il_pos++)
275 const u32 pw_r_len = c_combs[il_pos].pw_len;
277 const u32 pw_len = pw_l_len + pw_r_len;
281 wordr0[0] = c_combs[il_pos].i[0];
282 wordr0[1] = c_combs[il_pos].i[1];
283 wordr0[2] = c_combs[il_pos].i[2];
284 wordr0[3] = c_combs[il_pos].i[3];
288 wordr1[0] = c_combs[il_pos].i[4];
289 wordr1[1] = c_combs[il_pos].i[5];
290 wordr1[2] = c_combs[il_pos].i[6];
291 wordr1[3] = c_combs[il_pos].i[7];
307 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
309 append_0x80_2 (wordr0, wordr1, pw_r_len);
311 switch_buffer_by_offset (wordr0, wordr1, wordr2, wordr3, pw_l_len);
316 w0[0] = wordl0[0] | wordr0[0];
317 w0[1] = wordl0[1] | wordr0[1];
318 w0[2] = wordl0[2] | wordr0[2];
319 w0[3] = wordl0[3] | wordr0[3];
323 w1[0] = wordl1[0] | wordr1[0];
324 w1[1] = wordl1[1] | wordr1[1];
325 w1[2] = wordl1[2] | wordr1[2];
326 w1[3] = wordl1[3] | wordr1[3];
330 w2[0] = wordl2[0] | wordr2[0];
331 w2[1] = wordl2[1] | wordr2[1];
332 w2[2] = wordl2[2] | wordr2[2];
333 w2[3] = wordl2[3] | wordr2[3];
337 w3[0] = wordl3[0] | wordr3[0];
338 w3[1] = wordl3[1] | wordr3[1];
344 w0_t[0] = swap_workaround (w0[0]);
345 w0_t[1] = swap_workaround (w0[1]);
346 w0_t[2] = swap_workaround (w0[2]);
347 w0_t[3] = swap_workaround (w0[3]);
351 w1_t[0] = swap_workaround (w1[0]);
352 w1_t[1] = swap_workaround (w1[1]);
353 w1_t[2] = swap_workaround (w1[2]);
354 w1_t[3] = swap_workaround (w1[3]);
358 w2_t[0] = swap_workaround (w2[0]);
359 w2_t[1] = swap_workaround (w2[1]);
360 w2_t[2] = swap_workaround (w2[2]);
361 w2_t[3] = swap_workaround (w2[3]);
365 w3_t[0] = swap_workaround (w3[0]);
366 w3_t[1] = swap_workaround (w3[1]);
368 w3_t[3] = pw_len * 8;
378 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
392 w0_t[0] = salt_buf0[0];
393 w0_t[1] = salt_buf0[1];
394 w0_t[2] = salt_buf0[2];
395 w0_t[3] = salt_buf0[3];
396 w1_t[0] = salt_buf1[0];
397 w1_t[1] = salt_buf1[1];
398 w1_t[2] = salt_buf1[2];
399 w1_t[3] = salt_buf1[3];
400 w2_t[0] = salt_buf2[0];
401 w2_t[1] = salt_buf2[1];
402 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
403 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
404 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
405 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
406 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
407 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
408 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
409 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
410 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
411 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
412 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
413 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
421 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
423 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
424 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
425 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
426 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
427 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
428 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
429 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
430 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
431 w1_t[0] = 0x80000000;
444 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
452 w0_t[0] = salt_buf0[0];
453 w0_t[1] = salt_buf0[1];
454 w0_t[2] = salt_buf0[2];
455 w0_t[3] = salt_buf0[3];
456 w1_t[0] = salt_buf1[0];
457 w1_t[1] = salt_buf1[1];
458 w1_t[2] = salt_buf1[2];
459 w1_t[3] = salt_buf1[3];
460 w2_t[0] = salt_buf2[0];
461 w2_t[1] = salt_buf2[1];
462 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
463 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
464 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
465 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
466 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
467 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
468 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
469 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
470 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
471 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
472 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
473 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
481 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
483 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
484 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
485 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
486 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
487 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
488 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
489 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
490 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
491 w1_t[0] = 0x80000000;
504 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
506 const u32x r0 = digest[3];
507 const u32x r1 = digest[4];
508 const u32x r2 = digest[2];
509 const u32x r3 = digest[1];
511 #include VECT_COMPARE_M
515 extern "C" __global__ void __launch_bounds__ (256, 1) m08400_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
519 extern "C" __global__ void __launch_bounds__ (256, 1) m08400_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
523 extern "C" __global__ void __launch_bounds__ (256, 1) m08400_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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
529 const u32 lid = threadIdx.x;
535 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
539 wordl0[0] = pws[gid].i[ 0];
540 wordl0[1] = pws[gid].i[ 1];
541 wordl0[2] = pws[gid].i[ 2];
542 wordl0[3] = pws[gid].i[ 3];
546 wordl1[0] = pws[gid].i[ 4];
547 wordl1[1] = pws[gid].i[ 5];
548 wordl1[2] = pws[gid].i[ 6];
549 wordl1[3] = pws[gid].i[ 7];
565 const u32 pw_l_len = pws[gid].pw_len;
567 if (combs_mode == COMBINATOR_MODE_BASE_RIGHT)
569 append_0x80_2 (wordl0, wordl1, pw_l_len);
571 switch_buffer_by_offset (wordl0, wordl1, wordl2, wordl3, c_combs[0].pw_len);
578 l_bin2asc[lid] = c_bin2asc[(lid >> 0) & 15] << 0
579 | c_bin2asc[(lid >> 4) & 15] << 8;
583 if (gid >= gid_max) return;
591 salt_buf0[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 0]);
592 salt_buf0[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 1]);
593 salt_buf0[2] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 2]);
594 salt_buf0[3] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 3]);
598 salt_buf1[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 4]);
599 salt_buf1[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 5]);
600 salt_buf1[2] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 6]);
601 salt_buf1[3] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 7]);
605 salt_buf2[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 8]);
606 salt_buf2[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 9]);
610 const u32 salt_len = salt_bufs[salt_pos].salt_len;
616 const u32 search[4] =
618 digests_buf[digests_offset].digest_buf[DGST_R0],
619 digests_buf[digests_offset].digest_buf[DGST_R1],
620 digests_buf[digests_offset].digest_buf[DGST_R2],
621 digests_buf[digests_offset].digest_buf[DGST_R3]
628 for (u32 il_pos = 0; il_pos < combs_cnt; il_pos++)
630 const u32 pw_r_len = c_combs[il_pos].pw_len;
632 const u32 pw_len = pw_l_len + pw_r_len;
636 wordr0[0] = c_combs[il_pos].i[0];
637 wordr0[1] = c_combs[il_pos].i[1];
638 wordr0[2] = c_combs[il_pos].i[2];
639 wordr0[3] = c_combs[il_pos].i[3];
643 wordr1[0] = c_combs[il_pos].i[4];
644 wordr1[1] = c_combs[il_pos].i[5];
645 wordr1[2] = c_combs[il_pos].i[6];
646 wordr1[3] = c_combs[il_pos].i[7];
662 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
664 append_0x80_2 (wordr0, wordr1, pw_r_len);
666 switch_buffer_by_offset (wordr0, wordr1, wordr2, wordr3, pw_l_len);
671 w0[0] = wordl0[0] | wordr0[0];
672 w0[1] = wordl0[1] | wordr0[1];
673 w0[2] = wordl0[2] | wordr0[2];
674 w0[3] = wordl0[3] | wordr0[3];
678 w1[0] = wordl1[0] | wordr1[0];
679 w1[1] = wordl1[1] | wordr1[1];
680 w1[2] = wordl1[2] | wordr1[2];
681 w1[3] = wordl1[3] | wordr1[3];
685 w2[0] = wordl2[0] | wordr2[0];
686 w2[1] = wordl2[1] | wordr2[1];
687 w2[2] = wordl2[2] | wordr2[2];
688 w2[3] = wordl2[3] | wordr2[3];
692 w3[0] = wordl3[0] | wordr3[0];
693 w3[1] = wordl3[1] | wordr3[1];
699 w0_t[0] = swap_workaround (w0[0]);
700 w0_t[1] = swap_workaround (w0[1]);
701 w0_t[2] = swap_workaround (w0[2]);
702 w0_t[3] = swap_workaround (w0[3]);
706 w1_t[0] = swap_workaround (w1[0]);
707 w1_t[1] = swap_workaround (w1[1]);
708 w1_t[2] = swap_workaround (w1[2]);
709 w1_t[3] = swap_workaround (w1[3]);
713 w2_t[0] = swap_workaround (w2[0]);
714 w2_t[1] = swap_workaround (w2[1]);
715 w2_t[2] = swap_workaround (w2[2]);
716 w2_t[3] = swap_workaround (w2[3]);
720 w3_t[0] = swap_workaround (w3[0]);
721 w3_t[1] = swap_workaround (w3[1]);
723 w3_t[3] = pw_len * 8;
733 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
747 w0_t[0] = salt_buf0[0];
748 w0_t[1] = salt_buf0[1];
749 w0_t[2] = salt_buf0[2];
750 w0_t[3] = salt_buf0[3];
751 w1_t[0] = salt_buf1[0];
752 w1_t[1] = salt_buf1[1];
753 w1_t[2] = salt_buf1[2];
754 w1_t[3] = salt_buf1[3];
755 w2_t[0] = salt_buf2[0];
756 w2_t[1] = salt_buf2[1];
757 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
758 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
759 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
760 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
761 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
762 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
763 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
764 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
765 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
766 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
767 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
768 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
776 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
778 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
779 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
780 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
781 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
782 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
783 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
784 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
785 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
786 w1_t[0] = 0x80000000;
797 w3_t[3] = (salt_len + 40) * 8;
799 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
807 w0_t[0] = salt_buf0[0];
808 w0_t[1] = salt_buf0[1];
809 w0_t[2] = salt_buf0[2];
810 w0_t[3] = salt_buf0[3];
811 w1_t[0] = salt_buf1[0];
812 w1_t[1] = salt_buf1[1];
813 w1_t[2] = salt_buf1[2];
814 w1_t[3] = salt_buf1[3];
815 w2_t[0] = salt_buf2[0];
816 w2_t[1] = salt_buf2[1];
817 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
818 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
819 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
820 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
821 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
822 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
823 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
824 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
825 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
826 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
827 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
828 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
836 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
838 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
839 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
840 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
841 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
842 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
843 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
844 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
845 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
846 w1_t[0] = 0x80000000;
857 w3_t[3] = (salt_len + 40) * 8;
859 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
861 const u32x r0 = digest[3];
862 const u32x r1 = digest[4];
863 const u32x r2 = digest[2];
864 const u32x r3 = digest[1];
866 #include VECT_COMPARE_S
870 extern "C" __global__ void __launch_bounds__ (256, 1) m08400_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
874 extern "C" __global__ void __launch_bounds__ (256, 1) m08400_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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)