2 * Authors.....: Jens Steube <jens.steube@gmail.com>
3 * magnum <john.magnum@hushmail.com>
12 #include "include/constants.h"
13 #include "include/kernel_vendor.h"
20 #include "include/kernel_functions.c"
21 #include "OpenCL/types_ocl.c"
22 #include "OpenCL/common.c"
23 #include "include/rp_kernel.h"
24 #include "OpenCL/rp.c"
25 #include "OpenCL/simd.c"
28 #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i)])
30 #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
32 #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
34 #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
36 #define uint_to_hex_lower8_le(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
39 static void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5])
67 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
68 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
69 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
70 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
71 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
72 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
73 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
74 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
75 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
76 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
77 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
78 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
79 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
80 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
81 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
82 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
83 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
84 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
85 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
86 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
91 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
92 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
93 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
94 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
95 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
96 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
97 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
98 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
99 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
100 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
101 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
102 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
103 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
104 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
105 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
106 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
107 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
108 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
109 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
110 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
115 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
116 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
117 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
118 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
119 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
120 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
121 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
122 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
123 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
124 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
125 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
126 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
127 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
128 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
129 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
130 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
131 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
132 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
133 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
134 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
139 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
140 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
141 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
142 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
143 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
144 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
145 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
146 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
147 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
148 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
149 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
150 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
151 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
152 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
153 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
154 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
155 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
156 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
157 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
158 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
167 __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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
173 const u32 gid = get_global_id (0);
174 const u32 lid = get_local_id (0);
175 const u32 lsz = get_local_size (0);
181 __local u32 l_bin2asc[256];
183 for (u32 i = lid; i < 256; i += lsz)
185 const u32 i0 = (i >> 0) & 15;
186 const u32 i1 = (i >> 4) & 15;
188 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
189 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
192 barrier (CLK_LOCAL_MEM_FENCE);
194 if (gid >= gid_max) return;
202 pw_buf0[0] = pws[gid].i[ 0];
203 pw_buf0[1] = pws[gid].i[ 1];
204 pw_buf0[2] = pws[gid].i[ 2];
205 pw_buf0[3] = pws[gid].i[ 3];
209 pw_buf1[0] = pws[gid].i[ 4];
210 pw_buf1[1] = pws[gid].i[ 5];
211 pw_buf1[2] = pws[gid].i[ 6];
212 pw_buf1[3] = pws[gid].i[ 7];
214 const u32 pw_len = pws[gid].pw_len;
222 salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
223 salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
224 salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
225 salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
229 salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
230 salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
231 salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
232 salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
236 salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
237 salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
241 const u32 salt_len = salt_bufs[salt_pos].salt_len;
247 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
254 const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
256 append_0x80_2x4_VV (w0, w1, out_len);
260 w0_t[0] = swap32 (w0[0]);
261 w0_t[1] = swap32 (w0[1]);
262 w0_t[2] = swap32 (w0[2]);
263 w0_t[3] = swap32 (w0[3]);
267 w1_t[0] = swap32 (w1[0]);
268 w1_t[1] = swap32 (w1[1]);
269 w1_t[2] = swap32 (w1[2]);
270 w1_t[3] = swap32 (w1[3]);
274 w2_t[0] = swap32 (w2[0]);
275 w2_t[1] = swap32 (w2[1]);
276 w2_t[2] = swap32 (w2[2]);
277 w2_t[3] = swap32 (w2[3]);
281 w3_t[0] = swap32 (w3[0]);
282 w3_t[1] = swap32 (w3[1]);
284 w3_t[3] = out_len * 8;
294 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
308 w0_t[0] = salt_buf0[0];
309 w0_t[1] = salt_buf0[1];
310 w0_t[2] = salt_buf0[2];
311 w0_t[3] = salt_buf0[3];
312 w1_t[0] = salt_buf1[0];
313 w1_t[1] = salt_buf1[1];
314 w1_t[2] = salt_buf1[2];
315 w1_t[3] = salt_buf1[3];
316 w2_t[0] = salt_buf2[0];
317 w2_t[1] = salt_buf2[1];
318 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
319 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
320 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
321 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
322 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
323 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
324 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
325 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
326 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
327 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
328 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
329 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
337 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
339 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
340 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
341 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
342 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
343 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
344 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
345 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
346 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
347 w1_t[0] = 0x80000000;
360 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
368 w0_t[0] = salt_buf0[0];
369 w0_t[1] = salt_buf0[1];
370 w0_t[2] = salt_buf0[2];
371 w0_t[3] = salt_buf0[3];
372 w1_t[0] = salt_buf1[0];
373 w1_t[1] = salt_buf1[1];
374 w1_t[2] = salt_buf1[2];
375 w1_t[3] = salt_buf1[3];
376 w2_t[0] = salt_buf2[0];
377 w2_t[1] = salt_buf2[1];
378 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
379 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
380 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
381 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
382 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
383 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
384 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
385 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
386 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
387 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
388 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
389 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
397 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
399 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
400 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
401 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
402 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
403 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
404 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
405 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
406 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
407 w1_t[0] = 0x80000000;
420 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
422 COMPARE_M_SIMD (digest[3], digest[4], digest[2], digest[1]);
426 __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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
430 __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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
434 __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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
440 const u32 gid = get_global_id (0);
441 const u32 lid = get_local_id (0);
442 const u32 lsz = get_local_size (0);
448 __local u32 l_bin2asc[256];
450 for (u32 i = lid; i < 256; i += lsz)
452 const u32 i0 = (i >> 0) & 15;
453 const u32 i1 = (i >> 4) & 15;
455 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
456 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
459 barrier (CLK_LOCAL_MEM_FENCE);
461 if (gid >= gid_max) return;
469 pw_buf0[0] = pws[gid].i[ 0];
470 pw_buf0[1] = pws[gid].i[ 1];
471 pw_buf0[2] = pws[gid].i[ 2];
472 pw_buf0[3] = pws[gid].i[ 3];
476 pw_buf1[0] = pws[gid].i[ 4];
477 pw_buf1[1] = pws[gid].i[ 5];
478 pw_buf1[2] = pws[gid].i[ 6];
479 pw_buf1[3] = pws[gid].i[ 7];
481 const u32 pw_len = pws[gid].pw_len;
489 salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
490 salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
491 salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
492 salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
496 salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
497 salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
498 salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
499 salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
503 salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
504 salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
508 const u32 salt_len = salt_bufs[salt_pos].salt_len;
514 const u32 search[4] =
516 digests_buf[digests_offset].digest_buf[DGST_R0],
517 digests_buf[digests_offset].digest_buf[DGST_R1],
518 digests_buf[digests_offset].digest_buf[DGST_R2],
519 digests_buf[digests_offset].digest_buf[DGST_R3]
526 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
533 const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
535 append_0x80_2x4_VV (w0, w1, out_len);
539 w0_t[0] = swap32 (w0[0]);
540 w0_t[1] = swap32 (w0[1]);
541 w0_t[2] = swap32 (w0[2]);
542 w0_t[3] = swap32 (w0[3]);
546 w1_t[0] = swap32 (w1[0]);
547 w1_t[1] = swap32 (w1[1]);
548 w1_t[2] = swap32 (w1[2]);
549 w1_t[3] = swap32 (w1[3]);
553 w2_t[0] = swap32 (w2[0]);
554 w2_t[1] = swap32 (w2[1]);
555 w2_t[2] = swap32 (w2[2]);
556 w2_t[3] = swap32 (w2[3]);
560 w3_t[0] = swap32 (w3[0]);
561 w3_t[1] = swap32 (w3[1]);
563 w3_t[3] = out_len * 8;
573 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
587 w0_t[0] = salt_buf0[0];
588 w0_t[1] = salt_buf0[1];
589 w0_t[2] = salt_buf0[2];
590 w0_t[3] = salt_buf0[3];
591 w1_t[0] = salt_buf1[0];
592 w1_t[1] = salt_buf1[1];
593 w1_t[2] = salt_buf1[2];
594 w1_t[3] = salt_buf1[3];
595 w2_t[0] = salt_buf2[0];
596 w2_t[1] = salt_buf2[1];
597 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
598 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
599 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
600 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
601 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
602 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
603 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
604 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
605 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
606 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
607 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
608 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
616 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
618 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
619 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
620 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
621 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
622 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
623 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
624 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
625 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
626 w1_t[0] = 0x80000000;
637 w3_t[3] = (salt_len + 40) * 8;
639 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
647 w0_t[0] = salt_buf0[0];
648 w0_t[1] = salt_buf0[1];
649 w0_t[2] = salt_buf0[2];
650 w0_t[3] = salt_buf0[3];
651 w1_t[0] = salt_buf1[0];
652 w1_t[1] = salt_buf1[1];
653 w1_t[2] = salt_buf1[2];
654 w1_t[3] = salt_buf1[3];
655 w2_t[0] = salt_buf2[0];
656 w2_t[1] = salt_buf2[1];
657 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
658 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
659 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
660 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
661 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
662 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
663 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
664 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
665 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
666 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
667 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
668 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
676 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
678 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
679 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
680 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
681 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
682 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
683 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
684 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
685 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
686 w1_t[0] = 0x80000000;
697 w3_t[3] = (salt_len + 40) * 8;
699 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
701 COMPARE_S_SIMD (digest[3], digest[4], digest[2], digest[1]);
705 __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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
709 __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 il_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)