2 * Author......: Jens Steube <jens.steube@gmail.com>
10 #include "include/constants.h"
11 #include "include/kernel_vendor.h"
18 #include "include/kernel_functions.c"
19 #include "OpenCL/types_ocl.c"
20 #include "OpenCL/common.c"
21 #include "OpenCL/simd.c"
23 #define uint_to_hex_lower8_le(i) l_bin2asc[(i)]
25 static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
53 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
54 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
55 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
56 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
57 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
58 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
59 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
60 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
61 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
62 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
63 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
64 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
65 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
66 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
67 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
68 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
69 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
70 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
71 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
72 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
77 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
78 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
79 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
80 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
81 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
82 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
83 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
84 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
85 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
86 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
87 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
88 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
89 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
90 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
91 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
92 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
93 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
94 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
95 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
96 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
101 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
102 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
103 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
104 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
105 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
106 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
107 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
108 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
109 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
110 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
111 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
112 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
113 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
114 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
115 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
116 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
117 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
118 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
119 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
120 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
125 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
126 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
127 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
128 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
129 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
130 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
131 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
132 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
133 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
134 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
135 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
136 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
137 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
138 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
139 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
140 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
141 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
142 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
143 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
144 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
153 __kernel void m08400_m04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
159 const u32 gid = get_global_id (0);
160 const u32 lid = get_local_id (0);
161 const u32 lsz = get_local_size (0);
167 __local u32 l_bin2asc[256];
169 for (u32 i = lid; i < 256; i += lsz)
171 const u32 i0 = (i >> 0) & 15;
172 const u32 i1 = (i >> 4) & 15;
174 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
175 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
178 barrier (CLK_LOCAL_MEM_FENCE);
180 if (gid >= gid_max) return;
189 pws0[0] = pws[gid].i[0];
190 pws0[1] = pws[gid].i[1];
191 pws0[2] = pws[gid].i[2];
192 pws0[3] = pws[gid].i[3];
193 pws1[0] = pws[gid].i[4];
194 pws1[1] = pws[gid].i[5];
195 pws1[2] = pws[gid].i[6];
196 pws1[3] = pws[gid].i[7];
198 const u32 pw_l_len = pws[gid].pw_len;
206 salt_buf0[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 0]);
207 salt_buf0[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 1]);
208 salt_buf0[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 2]);
209 salt_buf0[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 3]);
213 salt_buf1[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 4]);
214 salt_buf1[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 5]);
215 salt_buf1[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 6]);
216 salt_buf1[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 7]);
220 salt_buf2[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 8]);
221 salt_buf2[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 9]);
225 const u32 salt_len = salt_bufs[salt_pos].salt_len;
231 for (u32 il_pos = 0; il_pos < combs_cnt; il_pos += VECT_SIZE)
233 const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
235 const u32x pw_len = pw_l_len + pw_r_len;
237 u32x wordr0[4] = { 0 };
238 u32x wordr1[4] = { 0 };
239 u32x wordr2[4] = { 0 };
240 u32x wordr3[4] = { 0 };
242 wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
243 wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
244 wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
245 wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
246 wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
247 wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
248 wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
249 wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
251 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
253 append_0x80_2x4 (wordr0, wordr1, pw_r_len);
255 switch_buffer_by_offset_le (wordr0, wordr1, wordr2, wordr3, pw_l_len);
260 w0[0] = wordl0[0] | wordr0[0];
261 w0[1] = wordl0[1] | wordr0[1];
262 w0[2] = wordl0[2] | wordr0[2];
263 w0[3] = wordl0[3] | wordr0[3];
267 w1[0] = wordl1[0] | wordr1[0];
268 w1[1] = wordl1[1] | wordr1[1];
269 w1[2] = wordl1[2] | wordr1[2];
270 w1[3] = wordl1[3] | wordr1[3];
274 w2[0] = wordl2[0] | wordr2[0];
275 w2[1] = wordl2[1] | wordr2[1];
276 w2[2] = wordl2[2] | wordr2[2];
277 w2[3] = wordl2[3] | wordr2[3];
281 w3[0] = wordl3[0] | wordr3[0];
282 w3[1] = wordl3[1] | wordr3[1];
283 w3[2] = wordl3[2] | wordr3[2];
284 w3[3] = wordl3[3] | wordr3[3];
288 w0_t[0] = swap32 (w0[0]);
289 w0_t[1] = swap32 (w0[1]);
290 w0_t[2] = swap32 (w0[2]);
291 w0_t[3] = swap32 (w0[3]);
295 w1_t[0] = swap32 (w1[0]);
296 w1_t[1] = swap32 (w1[1]);
297 w1_t[2] = swap32 (w1[2]);
298 w1_t[3] = swap32 (w1[3]);
302 w2_t[0] = swap32 (w2[0]);
303 w2_t[1] = swap32 (w2[1]);
304 w2_t[2] = swap32 (w2[2]);
305 w2_t[3] = swap32 (w2[3]);
309 w3_t[0] = swap32 (w3[0]);
310 w3_t[1] = swap32 (w3[1]);
312 w3_t[3] = pw_len * 8;
322 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
336 w0_t[0] = salt_buf0[0];
337 w0_t[1] = salt_buf0[1];
338 w0_t[2] = salt_buf0[2];
339 w0_t[3] = salt_buf0[3];
340 w1_t[0] = salt_buf1[0];
341 w1_t[1] = salt_buf1[1];
342 w1_t[2] = salt_buf1[2];
343 w1_t[3] = salt_buf1[3];
344 w2_t[0] = salt_buf2[0];
345 w2_t[1] = salt_buf2[1];
346 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
347 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
348 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
349 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
350 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
351 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
352 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
353 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
354 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
355 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
356 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
357 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
365 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
367 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
368 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
369 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
370 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
371 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
372 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
373 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
374 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
375 w1_t[0] = 0x80000000;
388 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
396 w0_t[0] = salt_buf0[0];
397 w0_t[1] = salt_buf0[1];
398 w0_t[2] = salt_buf0[2];
399 w0_t[3] = salt_buf0[3];
400 w1_t[0] = salt_buf1[0];
401 w1_t[1] = salt_buf1[1];
402 w1_t[2] = salt_buf1[2];
403 w1_t[3] = salt_buf1[3];
404 w2_t[0] = salt_buf2[0];
405 w2_t[1] = salt_buf2[1];
406 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
407 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
408 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
409 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
410 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
411 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
412 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
413 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
414 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
415 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
416 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
417 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
425 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
427 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
428 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
429 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
430 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
431 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
432 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
433 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
434 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
435 w1_t[0] = 0x80000000;
448 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
450 COMPARE_M_SIMD (digest[3], digest[4], digest[2], digest[1]);
454 __kernel void m08400_m08 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
458 __kernel void m08400_m16 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
462 __kernel void m08400_s04 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
468 const u32 gid = get_global_id (0);
469 const u32 lid = get_local_id (0);
470 const u32 lsz = get_local_size (0);
476 __local u32 l_bin2asc[256];
478 for (u32 i = lid; i < 256; i += lsz)
480 const u32 i0 = (i >> 0) & 15;
481 const u32 i1 = (i >> 4) & 15;
483 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
484 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
487 barrier (CLK_LOCAL_MEM_FENCE);
489 if (gid >= gid_max) return;
498 pws0[0] = pws[gid].i[0];
499 pws0[1] = pws[gid].i[1];
500 pws0[2] = pws[gid].i[2];
501 pws0[3] = pws[gid].i[3];
502 pws1[0] = pws[gid].i[4];
503 pws1[1] = pws[gid].i[5];
504 pws1[2] = pws[gid].i[6];
505 pws1[3] = pws[gid].i[7];
507 const u32 pw_l_len = pws[gid].pw_len;
515 salt_buf0[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 0]);
516 salt_buf0[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 1]);
517 salt_buf0[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 2]);
518 salt_buf0[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 3]);
522 salt_buf1[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 4]);
523 salt_buf1[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 5]);
524 salt_buf1[2] = swap32 (salt_bufs[salt_pos].salt_buf[ 6]);
525 salt_buf1[3] = swap32 (salt_bufs[salt_pos].salt_buf[ 7]);
529 salt_buf2[0] = swap32 (salt_bufs[salt_pos].salt_buf[ 8]);
530 salt_buf2[1] = swap32 (salt_bufs[salt_pos].salt_buf[ 9]);
534 const u32 salt_len = salt_bufs[salt_pos].salt_len;
540 const u32 search[4] =
542 digests_buf[digests_offset].digest_buf[DGST_R0],
543 digests_buf[digests_offset].digest_buf[DGST_R1],
544 digests_buf[digests_offset].digest_buf[DGST_R2],
545 digests_buf[digests_offset].digest_buf[DGST_R3]
552 for (u32 il_pos = 0; il_pos < combs_cnt; il_pos += VECT_SIZE)
554 const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
556 const u32x pw_len = pw_l_len + pw_r_len;
558 u32x wordr0[4] = { 0 };
559 u32x wordr1[4] = { 0 };
560 u32x wordr2[4] = { 0 };
561 u32x wordr3[4] = { 0 };
563 wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
564 wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
565 wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
566 wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
567 wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
568 wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
569 wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
570 wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
572 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
574 append_0x80_2x4 (wordr0, wordr1, pw_r_len);
576 switch_buffer_by_offset_le (wordr0, wordr1, wordr2, wordr3, pw_l_len);
581 w0[0] = wordl0[0] | wordr0[0];
582 w0[1] = wordl0[1] | wordr0[1];
583 w0[2] = wordl0[2] | wordr0[2];
584 w0[3] = wordl0[3] | wordr0[3];
588 w1[0] = wordl1[0] | wordr1[0];
589 w1[1] = wordl1[1] | wordr1[1];
590 w1[2] = wordl1[2] | wordr1[2];
591 w1[3] = wordl1[3] | wordr1[3];
595 w2[0] = wordl2[0] | wordr2[0];
596 w2[1] = wordl2[1] | wordr2[1];
597 w2[2] = wordl2[2] | wordr2[2];
598 w2[3] = wordl2[3] | wordr2[3];
602 w3[0] = wordl3[0] | wordr3[0];
603 w3[1] = wordl3[1] | wordr3[1];
604 w3[2] = wordl3[2] | wordr3[2];
605 w3[3] = wordl3[3] | wordr3[3];
609 w0_t[0] = swap32 (w0[0]);
610 w0_t[1] = swap32 (w0[1]);
611 w0_t[2] = swap32 (w0[2]);
612 w0_t[3] = swap32 (w0[3]);
616 w1_t[0] = swap32 (w1[0]);
617 w1_t[1] = swap32 (w1[1]);
618 w1_t[2] = swap32 (w1[2]);
619 w1_t[3] = swap32 (w1[3]);
623 w2_t[0] = swap32 (w2[0]);
624 w2_t[1] = swap32 (w2[1]);
625 w2_t[2] = swap32 (w2[2]);
626 w2_t[3] = swap32 (w2[3]);
630 w3_t[0] = swap32 (w3[0]);
631 w3_t[1] = swap32 (w3[1]);
633 w3_t[3] = pw_len * 8;
643 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
657 w0_t[0] = salt_buf0[0];
658 w0_t[1] = salt_buf0[1];
659 w0_t[2] = salt_buf0[2];
660 w0_t[3] = salt_buf0[3];
661 w1_t[0] = salt_buf1[0];
662 w1_t[1] = salt_buf1[1];
663 w1_t[2] = salt_buf1[2];
664 w1_t[3] = salt_buf1[3];
665 w2_t[0] = salt_buf2[0];
666 w2_t[1] = salt_buf2[1];
667 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
668 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
669 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
670 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
671 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
672 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
673 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
674 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
675 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
676 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
677 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
678 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
686 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
688 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
689 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
690 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
691 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
692 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
693 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
694 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
695 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
696 w1_t[0] = 0x80000000;
707 w3_t[3] = (salt_len + 40) * 8;
709 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
717 w0_t[0] = salt_buf0[0];
718 w0_t[1] = salt_buf0[1];
719 w0_t[2] = salt_buf0[2];
720 w0_t[3] = salt_buf0[3];
721 w1_t[0] = salt_buf1[0];
722 w1_t[1] = salt_buf1[1];
723 w1_t[2] = salt_buf1[2];
724 w1_t[3] = salt_buf1[3];
725 w2_t[0] = salt_buf2[0];
726 w2_t[1] = salt_buf2[1];
727 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
728 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
729 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
730 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
731 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
732 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
733 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
734 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
735 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
736 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
737 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
738 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
746 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
748 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
749 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
750 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
751 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
752 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
753 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
754 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
755 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
756 w1_t[0] = 0x80000000;
767 w3_t[3] = (salt_len + 40) * 8;
769 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
771 COMPARE_S_SIMD (digest[3], digest[4], digest[2], digest[1]);
775 __kernel void m08400_s08 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
779 __kernel void m08400_s16 (__global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __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 combs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)