2 * Author......: Jens Steube <jens.steube@gmail.com>
8 #include "include/constants.h"
9 #include "include/kernel_vendor.h"
16 #include "include/kernel_functions.c"
17 #include "OpenCL/types_ocl.c"
18 #include "OpenCL/common.c"
20 #define COMPARE_S "OpenCL/check_single_comp4.c"
21 #define COMPARE_M "OpenCL/check_multi_comp4.c"
23 #define GETSHIFTEDINT(a,n) amd_bytealign ((a)[((n)/4)+1], (a)[((n)/4)+0], (n))
25 #define SETSHIFTEDINT(a,n,v) \
27 const u32 s = ((n) & 3) * 8; \
28 const u64 x = (u64) (v) << s; \
29 (a)[((n)/4)+0] |= x; \
30 (a)[((n)/4)+1] = x >> 32; \
33 __constant u32 theMagicArray[64] =
35 0x1451ac91,0x4354679f,0xe03be724,0xc27b7428,0xeb133386,0x5ccb4f5a,0x37730a08,0x2f1c5d0e,
36 0xe5e68f33,0xddae9bf8,0x8d4bf216,0xdcd4e12c,0x9ddfcbb0,0x176d70d4,0x3f424df9,0x94111b9b,
37 0x9bc15b9f,0x039d0506,0x8a135e9d,0xe86a9a1e,0x17147cd9,0xf62ac758,0x0a6399a1,0xc370fdd7,
38 0x13745ef6,0x040bc903,0x26f79826,0x2593928a,0x230da2b0,0x6d7963ed,0x3cfa3213,0xa39a0235,
39 0x0a8eddb3,0xc351bf24,0x9f55cd7c,0x4c94af37,0x82520829,0x374e3bb2,0x9107179f,0xcdfd3b11,
40 0, 0, 0, 0, 0, 0, 0, 0,
41 0, 0, 0, 0, 0, 0, 0, 0,
42 0, 0, 0, 0, 0, 0, 0, 0
45 static void swap_buffer (u32 final[16])
47 final[ 0] = swap32 (final[ 0]);
48 final[ 1] = swap32 (final[ 1]);
49 final[ 2] = swap32 (final[ 2]);
50 final[ 3] = swap32 (final[ 3]);
51 final[ 4] = swap32 (final[ 4]);
52 final[ 5] = swap32 (final[ 5]);
53 final[ 6] = swap32 (final[ 6]);
54 final[ 7] = swap32 (final[ 7]);
55 final[ 8] = swap32 (final[ 8]);
56 final[ 9] = swap32 (final[ 9]);
57 final[10] = swap32 (final[10]);
58 final[11] = swap32 (final[11]);
59 final[12] = swap32 (final[12]);
60 final[13] = swap32 (final[13]);
61 final[14] = swap32 (final[14]);
62 final[15] = swap32 (final[15]);
65 static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
93 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
94 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
95 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
96 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
97 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
98 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
99 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
100 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
101 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
102 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
103 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
104 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
105 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
106 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
107 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
108 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
109 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
110 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
111 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
112 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
117 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
118 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
119 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
120 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
121 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
122 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
123 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
124 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
125 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
126 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
127 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
128 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
129 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
130 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
131 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
132 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
133 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
134 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
135 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
136 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
141 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
142 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
143 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
144 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
145 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
146 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
147 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
148 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
149 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
150 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
151 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
152 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
153 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
154 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
155 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
156 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
157 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
158 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
159 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
160 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
165 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
166 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
167 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
168 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
169 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
170 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
171 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
172 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
173 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
174 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
175 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
176 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
177 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
178 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
179 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
180 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
181 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
182 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
183 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
184 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
193 static void m07800m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __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)
199 const u32 gid = get_global_id (0);
200 const u32 lid = get_local_id (0);
202 w0[0] = swap32 (w0[0]);
203 w0[1] = swap32 (w0[1]);
204 w0[2] = swap32 (w0[2]);
205 w0[3] = swap32 (w0[3]);
207 w1[0] = swap32 (w1[0]);
208 w1[1] = swap32 (w1[1]);
209 w1[2] = swap32 (w1[2]);
210 w1[3] = swap32 (w1[3]);
218 salt_buf[0] = salt_bufs[salt_pos].salt_buf[0];
219 salt_buf[1] = salt_bufs[salt_pos].salt_buf[1];
220 salt_buf[2] = salt_bufs[salt_pos].salt_buf[2];
221 salt_buf[3] = salt_bufs[salt_pos].salt_buf[3];
222 salt_buf[4] = salt_bufs[salt_pos].salt_buf[4];
223 salt_buf[5] = salt_bufs[salt_pos].salt_buf[5];
224 salt_buf[6] = salt_bufs[salt_pos].salt_buf[6];
225 salt_buf[7] = salt_bufs[salt_pos].salt_buf[7];
227 const u32 salt_len = salt_bufs[salt_pos].salt_len;
257 switch_buffer_by_offset_le (s0, s1, s2, s3, pw_len);
259 const u32 pw_salt_len = pw_len + salt_len;
267 for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
269 const u32 w0r = swap32 (bfs_buf[il_pos].i);
279 final[ 0] = swap32 (w0[0] | s0[0]);
280 final[ 1] = swap32 (w0[1] | s0[1]);
281 final[ 2] = swap32 (w0[2] | s0[2]);
282 final[ 3] = swap32 (w0[3] | s0[3]);
283 final[ 4] = swap32 (w1[0] | s1[0]);
284 final[ 5] = swap32 (w1[1] | s1[1]);
285 final[ 6] = swap32 (w1[2] | s1[2]);
286 final[ 7] = swap32 (w1[3] | s1[3]);
287 final[ 8] = swap32 (w2[0] | s2[0]);
288 final[ 9] = swap32 (w2[1] | s2[1]);
289 final[10] = swap32 (w2[2] | s2[2]);
290 final[11] = swap32 (w2[3] | s2[3]);
291 final[12] = swap32 (w3[0] | s3[0]);
292 final[13] = swap32 (w3[1] | s3[1]);
294 final[15] = pw_salt_len * 8;
304 sha1_transform (&final[0], &final[4], &final[8], &final[12], digest);
306 // prepare magic array range
308 u32 lengthMagicArray = 0x20;
309 u32 offsetMagicArray = 0;
311 lengthMagicArray += ((digest[0] >> 24) & 0xff) % 6;
312 lengthMagicArray += ((digest[0] >> 16) & 0xff) % 6;
313 lengthMagicArray += ((digest[0] >> 8) & 0xff) % 6;
314 lengthMagicArray += ((digest[0] >> 0) & 0xff) % 6;
315 lengthMagicArray += ((digest[1] >> 24) & 0xff) % 6;
316 lengthMagicArray += ((digest[1] >> 16) & 0xff) % 6;
317 lengthMagicArray += ((digest[1] >> 8) & 0xff) % 6;
318 lengthMagicArray += ((digest[1] >> 0) & 0xff) % 6;
319 lengthMagicArray += ((digest[2] >> 24) & 0xff) % 6;
320 lengthMagicArray += ((digest[2] >> 16) & 0xff) % 6;
321 offsetMagicArray += ((digest[2] >> 8) & 0xff) % 8;
322 offsetMagicArray += ((digest[2] >> 0) & 0xff) % 8;
323 offsetMagicArray += ((digest[3] >> 24) & 0xff) % 8;
324 offsetMagicArray += ((digest[3] >> 16) & 0xff) % 8;
325 offsetMagicArray += ((digest[3] >> 8) & 0xff) % 8;
326 offsetMagicArray += ((digest[3] >> 0) & 0xff) % 8;
327 offsetMagicArray += ((digest[4] >> 24) & 0xff) % 8;
328 offsetMagicArray += ((digest[4] >> 16) & 0xff) % 8;
329 offsetMagicArray += ((digest[4] >> 8) & 0xff) % 8;
330 offsetMagicArray += ((digest[4] >> 0) & 0xff) % 8;
341 for (int i = 0; i < 32; i++) final[i] = 0;
352 u32 final_len = pw_len;
358 for (i = 0; i < lengthMagicArray - 4; i += 4)
360 const u32 tmp = GETSHIFTEDINT (theMagicArray, offsetMagicArray + i);
362 SETSHIFTEDINT (final, final_len + i, tmp);
365 const u32 mask = 0xffffffff >> (((i - lengthMagicArray) & 3) * 8);
367 const u32 tmp = GETSHIFTEDINT (theMagicArray, offsetMagicArray + i) & mask;
369 SETSHIFTEDINT (final, final_len + i, tmp);
371 final_len += lengthMagicArray;
375 for (i = 0; i < salt_len + 1; i += 4) // +1 for the 0x80
377 const u32 tmp = salt_buf[i / 4]; // attention, int[] not char[]
379 SETSHIFTEDINT (final, final_len + i, tmp);
382 final_len += salt_len;
389 for (left = final_len, off = 0; left >= 56; left -= 64, off += 16)
391 swap_buffer (&final[off]);
393 sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
396 swap_buffer (&final[off]);
399 final[off + 15] = final_len * 8;
401 sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
403 const u32 r0 = digest[3];
404 const u32 r1 = digest[4];
405 const u32 r2 = digest[2];
406 const u32 r3 = digest[1];
412 static void m07800s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __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)
418 const u32 gid = get_global_id (0);
419 const u32 lid = get_local_id (0);
421 w0[0] = swap32 (w0[0]);
422 w0[1] = swap32 (w0[1]);
423 w0[2] = swap32 (w0[2]);
424 w0[3] = swap32 (w0[3]);
426 w1[0] = swap32 (w1[0]);
427 w1[1] = swap32 (w1[1]);
428 w1[2] = swap32 (w1[2]);
429 w1[3] = swap32 (w1[3]);
437 salt_buf[0] = salt_bufs[salt_pos].salt_buf[0];
438 salt_buf[1] = salt_bufs[salt_pos].salt_buf[1];
439 salt_buf[2] = salt_bufs[salt_pos].salt_buf[2];
440 salt_buf[3] = salt_bufs[salt_pos].salt_buf[3];
441 salt_buf[4] = salt_bufs[salt_pos].salt_buf[4];
442 salt_buf[5] = salt_bufs[salt_pos].salt_buf[5];
443 salt_buf[6] = salt_bufs[salt_pos].salt_buf[6];
444 salt_buf[7] = salt_bufs[salt_pos].salt_buf[7];
446 const u32 salt_len = salt_bufs[salt_pos].salt_len;
476 switch_buffer_by_offset_le (s0, s1, s2, s3, pw_len);
478 const u32 pw_salt_len = pw_len + salt_len;
484 const u32 search[4] =
486 digests_buf[digests_offset].digest_buf[DGST_R0],
487 digests_buf[digests_offset].digest_buf[DGST_R1],
488 digests_buf[digests_offset].digest_buf[DGST_R2],
489 digests_buf[digests_offset].digest_buf[DGST_R3]
498 for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
500 const u32 w0r = swap32 (bfs_buf[il_pos].i);
510 final[ 0] = swap32 (w0[0] | s0[0]);
511 final[ 1] = swap32 (w0[1] | s0[1]);
512 final[ 2] = swap32 (w0[2] | s0[2]);
513 final[ 3] = swap32 (w0[3] | s0[3]);
514 final[ 4] = swap32 (w1[0] | s1[0]);
515 final[ 5] = swap32 (w1[1] | s1[1]);
516 final[ 6] = swap32 (w1[2] | s1[2]);
517 final[ 7] = swap32 (w1[3] | s1[3]);
518 final[ 8] = swap32 (w2[0] | s2[0]);
519 final[ 9] = swap32 (w2[1] | s2[1]);
520 final[10] = swap32 (w2[2] | s2[2]);
521 final[11] = swap32 (w2[3] | s2[3]);
522 final[12] = swap32 (w3[0] | s3[0]);
523 final[13] = swap32 (w3[1] | s3[1]);
525 final[15] = pw_salt_len * 8;
535 sha1_transform (&final[0], &final[4], &final[8], &final[12], digest);
537 // prepare magic array range
539 u32 lengthMagicArray = 0x20;
540 u32 offsetMagicArray = 0;
542 lengthMagicArray += ((digest[0] >> 24) & 0xff) % 6;
543 lengthMagicArray += ((digest[0] >> 16) & 0xff) % 6;
544 lengthMagicArray += ((digest[0] >> 8) & 0xff) % 6;
545 lengthMagicArray += ((digest[0] >> 0) & 0xff) % 6;
546 lengthMagicArray += ((digest[1] >> 24) & 0xff) % 6;
547 lengthMagicArray += ((digest[1] >> 16) & 0xff) % 6;
548 lengthMagicArray += ((digest[1] >> 8) & 0xff) % 6;
549 lengthMagicArray += ((digest[1] >> 0) & 0xff) % 6;
550 lengthMagicArray += ((digest[2] >> 24) & 0xff) % 6;
551 lengthMagicArray += ((digest[2] >> 16) & 0xff) % 6;
552 offsetMagicArray += ((digest[2] >> 8) & 0xff) % 8;
553 offsetMagicArray += ((digest[2] >> 0) & 0xff) % 8;
554 offsetMagicArray += ((digest[3] >> 24) & 0xff) % 8;
555 offsetMagicArray += ((digest[3] >> 16) & 0xff) % 8;
556 offsetMagicArray += ((digest[3] >> 8) & 0xff) % 8;
557 offsetMagicArray += ((digest[3] >> 0) & 0xff) % 8;
558 offsetMagicArray += ((digest[4] >> 24) & 0xff) % 8;
559 offsetMagicArray += ((digest[4] >> 16) & 0xff) % 8;
560 offsetMagicArray += ((digest[4] >> 8) & 0xff) % 8;
561 offsetMagicArray += ((digest[4] >> 0) & 0xff) % 8;
572 for (int i = 0; i < 32; i++) final[i] = 0;
583 u32 final_len = pw_len;
589 for (i = 0; i < lengthMagicArray - 4; i += 4)
591 const u32 tmp = GETSHIFTEDINT (theMagicArray, offsetMagicArray + i);
593 SETSHIFTEDINT (final, final_len + i, tmp);
596 const u32 mask = 0xffffffff >> (((i - lengthMagicArray) & 3) * 8);
598 const u32 tmp = GETSHIFTEDINT (theMagicArray, offsetMagicArray + i) & mask;
600 SETSHIFTEDINT (final, final_len + i, tmp);
602 final_len += lengthMagicArray;
606 for (i = 0; i < salt_len + 1; i += 4) // +1 for the 0x80
608 const u32 tmp = salt_buf[i / 4]; // attention, int[] not char[]
610 SETSHIFTEDINT (final, final_len + i, tmp);
613 final_len += salt_len;
620 for (left = final_len, off = 0; left >= 56; left -= 64, off += 16)
622 swap_buffer (&final[off]);
624 sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
627 swap_buffer (&final[off]);
630 final[off + 15] = final_len * 8;
632 sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
634 const u32 r0 = digest[3];
635 const u32 r1 = digest[4];
636 const u32 r2 = digest[2];
637 const u32 r3 = digest[1];
643 __kernel void m07800_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)
649 const u32 gid = get_global_id (0);
651 if (gid >= gid_max) return;
657 //const u32 lid = get_local_id (0);
661 w0[0] = pws[gid].i[ 0];
662 w0[1] = pws[gid].i[ 1];
663 w0[2] = pws[gid].i[ 2];
664 w0[3] = pws[gid].i[ 3];
687 const u32 pw_len = pws[gid].pw_len;
693 m07800m (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, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
696 __kernel void m07800_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)
702 const u32 gid = get_global_id (0);
704 if (gid >= gid_max) return;
710 //const u32 lid = get_local_id (0);
714 w0[0] = pws[gid].i[ 0];
715 w0[1] = pws[gid].i[ 1];
716 w0[2] = pws[gid].i[ 2];
717 w0[3] = pws[gid].i[ 3];
721 w1[0] = pws[gid].i[ 4];
722 w1[1] = pws[gid].i[ 5];
723 w1[2] = pws[gid].i[ 6];
724 w1[3] = pws[gid].i[ 7];
740 const u32 pw_len = pws[gid].pw_len;
746 m07800m (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, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
749 __kernel void m07800_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)
753 __kernel void m07800_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)
759 const u32 gid = get_global_id (0);
761 if (gid >= gid_max) return;
767 //const u32 lid = get_local_id (0);
771 w0[0] = pws[gid].i[ 0];
772 w0[1] = pws[gid].i[ 1];
773 w0[2] = pws[gid].i[ 2];
774 w0[3] = pws[gid].i[ 3];
797 const u32 pw_len = pws[gid].pw_len;
803 m07800s (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, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
806 __kernel void m07800_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)
812 const u32 gid = get_global_id (0);
814 if (gid >= gid_max) return;
820 //const u32 lid = get_local_id (0);
824 w0[0] = pws[gid].i[ 0];
825 w0[1] = pws[gid].i[ 1];
826 w0[2] = pws[gid].i[ 2];
827 w0[3] = pws[gid].i[ 3];
831 w1[0] = pws[gid].i[ 4];
832 w1[1] = pws[gid].i[ 5];
833 w1[2] = pws[gid].i[ 6];
834 w1[3] = pws[gid].i[ 7];
850 const u32 pw_len = pws[gid].pw_len;
856 m07800s (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, esalt_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, il_cnt, digests_cnt, digests_offset);
859 __kernel void m07800_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)