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"
19 #include "include/rp_kernel.h"
20 #include "OpenCL/rp.c"
22 #define COMPARE_S "OpenCL/check_single_comp4.c"
23 #define COMPARE_M "OpenCL/check_multi_comp4.c"
25 #define GETSHIFTEDINT(a,n) amd_bytealign ((a)[((n)/4)+1], (a)[((n)/4)+0], (n))
27 #define SETSHIFTEDINT(a,n,v) \
29 const u32 s = ((n) & 3) * 8; \
30 const u64 x = (u64) (v) << s; \
31 (a)[((n)/4)+0] |= x; \
32 (a)[((n)/4)+1] = x >> 32; \
35 __constant u32 theMagicArray[64] =
37 0x1451ac91,0x4354679f,0xe03be724,0xc27b7428,0xeb133386,0x5ccb4f5a,0x37730a08,0x2f1c5d0e,
38 0xe5e68f33,0xddae9bf8,0x8d4bf216,0xdcd4e12c,0x9ddfcbb0,0x176d70d4,0x3f424df9,0x94111b9b,
39 0x9bc15b9f,0x039d0506,0x8a135e9d,0xe86a9a1e,0x17147cd9,0xf62ac758,0x0a6399a1,0xc370fdd7,
40 0x13745ef6,0x040bc903,0x26f79826,0x2593928a,0x230da2b0,0x6d7963ed,0x3cfa3213,0xa39a0235,
41 0x0a8eddb3,0xc351bf24,0x9f55cd7c,0x4c94af37,0x82520829,0x374e3bb2,0x9107179f,0xcdfd3b11,
42 0, 0, 0, 0, 0, 0, 0, 0,
43 0, 0, 0, 0, 0, 0, 0, 0,
44 0, 0, 0, 0, 0, 0, 0, 0
47 static void swap_buffer (u32 final[16])
49 final[ 0] = swap32 (final[ 0]);
50 final[ 1] = swap32 (final[ 1]);
51 final[ 2] = swap32 (final[ 2]);
52 final[ 3] = swap32 (final[ 3]);
53 final[ 4] = swap32 (final[ 4]);
54 final[ 5] = swap32 (final[ 5]);
55 final[ 6] = swap32 (final[ 6]);
56 final[ 7] = swap32 (final[ 7]);
57 final[ 8] = swap32 (final[ 8]);
58 final[ 9] = swap32 (final[ 9]);
59 final[10] = swap32 (final[10]);
60 final[11] = swap32 (final[11]);
61 final[12] = swap32 (final[12]);
62 final[13] = swap32 (final[13]);
63 final[14] = swap32 (final[14]);
64 final[15] = swap32 (final[15]);
67 static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
95 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
96 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
97 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
98 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
99 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
100 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
101 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
102 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
103 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
104 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
105 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
106 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
107 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
108 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
109 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
110 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
111 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
112 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
113 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
114 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
119 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
120 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
121 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
122 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
123 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
124 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
125 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
126 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
127 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
128 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
129 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
130 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
131 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
132 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
133 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
134 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
135 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
136 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
137 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
138 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
143 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
144 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
145 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
146 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
147 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
148 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
149 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
150 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
151 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
152 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
153 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
154 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
155 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
156 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
157 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
158 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
159 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
160 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
161 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
162 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
167 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
168 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
169 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
170 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
171 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
172 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
173 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
174 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
175 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
176 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
177 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
178 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
179 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
180 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
181 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
182 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
183 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
184 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
185 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
186 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
195 __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)
201 const u32 lid = get_local_id (0);
207 const u32 gid = get_global_id (0);
209 if (gid >= gid_max) return;
213 pw_buf0[0] = pws[gid].i[ 0];
214 pw_buf0[1] = pws[gid].i[ 1];
215 pw_buf0[2] = pws[gid].i[ 2];
216 pw_buf0[3] = pws[gid].i[ 3];
220 pw_buf1[0] = pws[gid].i[ 4];
221 pw_buf1[1] = pws[gid].i[ 5];
222 pw_buf1[2] = pws[gid].i[ 6];
223 pw_buf1[3] = pws[gid].i[ 7];
225 const u32 pw_len = pws[gid].pw_len;
233 salt_buf[0] = salt_bufs[salt_pos].salt_buf[0];
234 salt_buf[1] = salt_bufs[salt_pos].salt_buf[1];
235 salt_buf[2] = salt_bufs[salt_pos].salt_buf[2];
236 salt_buf[3] = salt_bufs[salt_pos].salt_buf[3];
237 salt_buf[4] = salt_bufs[salt_pos].salt_buf[4];
238 salt_buf[5] = salt_bufs[salt_pos].salt_buf[5];
239 salt_buf[6] = salt_bufs[salt_pos].salt_buf[6];
240 salt_buf[7] = salt_bufs[salt_pos].salt_buf[7];
242 const u32 salt_len = salt_bufs[salt_pos].salt_len;
248 for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
278 const u32 out_len = apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
312 switch_buffer_by_offset_le_VV (s0, s1, s2, s3, out_len);
314 const u32x pw_salt_len = out_len + salt_len;
322 final[ 0] = swap32 (w0[0] | s0[0]);
323 final[ 1] = swap32 (w0[1] | s0[1]);
324 final[ 2] = swap32 (w0[2] | s0[2]);
325 final[ 3] = swap32 (w0[3] | s0[3]);
326 final[ 4] = swap32 (w1[0] | s1[0]);
327 final[ 5] = swap32 (w1[1] | s1[1]);
328 final[ 6] = swap32 (w1[2] | s1[2]);
329 final[ 7] = swap32 (w1[3] | s1[3]);
330 final[ 8] = swap32 (w2[0] | s2[0]);
331 final[ 9] = swap32 (w2[1] | s2[1]);
332 final[10] = swap32 (w2[2] | s2[2]);
333 final[11] = swap32 (w2[3] | s2[3]);
334 final[12] = swap32 (w3[0] | s3[0]);
335 final[13] = swap32 (w3[1] | s3[1]);
337 final[15] = pw_salt_len * 8;
347 sha1_transform (&final[0], &final[4], &final[8], &final[12], digest);
349 // prepare magic array range
351 u32 lengthMagicArray = 0x20;
352 u32 offsetMagicArray = 0;
354 lengthMagicArray += ((digest[0] >> 24) & 0xff) % 6;
355 lengthMagicArray += ((digest[0] >> 16) & 0xff) % 6;
356 lengthMagicArray += ((digest[0] >> 8) & 0xff) % 6;
357 lengthMagicArray += ((digest[0] >> 0) & 0xff) % 6;
358 lengthMagicArray += ((digest[1] >> 24) & 0xff) % 6;
359 lengthMagicArray += ((digest[1] >> 16) & 0xff) % 6;
360 lengthMagicArray += ((digest[1] >> 8) & 0xff) % 6;
361 lengthMagicArray += ((digest[1] >> 0) & 0xff) % 6;
362 lengthMagicArray += ((digest[2] >> 24) & 0xff) % 6;
363 lengthMagicArray += ((digest[2] >> 16) & 0xff) % 6;
364 offsetMagicArray += ((digest[2] >> 8) & 0xff) % 8;
365 offsetMagicArray += ((digest[2] >> 0) & 0xff) % 8;
366 offsetMagicArray += ((digest[3] >> 24) & 0xff) % 8;
367 offsetMagicArray += ((digest[3] >> 16) & 0xff) % 8;
368 offsetMagicArray += ((digest[3] >> 8) & 0xff) % 8;
369 offsetMagicArray += ((digest[3] >> 0) & 0xff) % 8;
370 offsetMagicArray += ((digest[4] >> 24) & 0xff) % 8;
371 offsetMagicArray += ((digest[4] >> 16) & 0xff) % 8;
372 offsetMagicArray += ((digest[4] >> 8) & 0xff) % 8;
373 offsetMagicArray += ((digest[4] >> 0) & 0xff) % 8;
384 for (int i = 0; i < 32; i++) final[i] = 0;
395 u32 final_len = out_len;
401 for (i = 0; i < lengthMagicArray - 4; i += 4)
403 const u32 tmp = GETSHIFTEDINT (theMagicArray, offsetMagicArray + i);
405 SETSHIFTEDINT (final, final_len + i, tmp);
408 const u32 mask = 0xffffffff >> (((i - lengthMagicArray) & 3) * 8);
410 const u32 tmp = GETSHIFTEDINT (theMagicArray, offsetMagicArray + i) & mask;
412 SETSHIFTEDINT (final, final_len + i, tmp);
414 final_len += lengthMagicArray;
418 for (i = 0; i < salt_len + 1; i += 4) // +1 for the 0x80
420 const u32 tmp = salt_buf[i / 4]; // attention, int[] not char[]
422 SETSHIFTEDINT (final, final_len + i, tmp);
425 final_len += salt_len;
432 for (left = final_len, off = 0; left >= 56; left -= 64, off += 16)
434 swap_buffer (&final[off]);
436 sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
439 swap_buffer (&final[off]);
442 final[off + 15] = final_len * 8;
444 sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
446 const u32 r0 = digest[3];
447 const u32 r1 = digest[4];
448 const u32 r2 = digest[2];
449 const u32 r3 = digest[1];
455 __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)
459 __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)
463 __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)
469 const u32 lid = get_local_id (0);
475 const u32 gid = get_global_id (0);
477 if (gid >= gid_max) return;
481 pw_buf0[0] = pws[gid].i[ 0];
482 pw_buf0[1] = pws[gid].i[ 1];
483 pw_buf0[2] = pws[gid].i[ 2];
484 pw_buf0[3] = pws[gid].i[ 3];
488 pw_buf1[0] = pws[gid].i[ 4];
489 pw_buf1[1] = pws[gid].i[ 5];
490 pw_buf1[2] = pws[gid].i[ 6];
491 pw_buf1[3] = pws[gid].i[ 7];
493 const u32 pw_len = pws[gid].pw_len;
501 salt_buf[0] = salt_bufs[salt_pos].salt_buf[0];
502 salt_buf[1] = salt_bufs[salt_pos].salt_buf[1];
503 salt_buf[2] = salt_bufs[salt_pos].salt_buf[2];
504 salt_buf[3] = salt_bufs[salt_pos].salt_buf[3];
505 salt_buf[4] = salt_bufs[salt_pos].salt_buf[4];
506 salt_buf[5] = salt_bufs[salt_pos].salt_buf[5];
507 salt_buf[6] = salt_bufs[salt_pos].salt_buf[6];
508 salt_buf[7] = salt_bufs[salt_pos].salt_buf[7];
510 const u32 salt_len = salt_bufs[salt_pos].salt_len;
516 const u32 search[4] =
518 digests_buf[digests_offset].digest_buf[DGST_R0],
519 digests_buf[digests_offset].digest_buf[DGST_R1],
520 digests_buf[digests_offset].digest_buf[DGST_R2],
521 digests_buf[digests_offset].digest_buf[DGST_R3]
528 for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
558 const u32 out_len = apply_rules (rules_buf[il_pos].cmds, w0, w1, pw_len);
592 switch_buffer_by_offset_le_VV (s0, s1, s2, s3, out_len);
594 const u32x pw_salt_len = out_len + salt_len;
602 final[ 0] = swap32 (w0[0] | s0[0]);
603 final[ 1] = swap32 (w0[1] | s0[1]);
604 final[ 2] = swap32 (w0[2] | s0[2]);
605 final[ 3] = swap32 (w0[3] | s0[3]);
606 final[ 4] = swap32 (w1[0] | s1[0]);
607 final[ 5] = swap32 (w1[1] | s1[1]);
608 final[ 6] = swap32 (w1[2] | s1[2]);
609 final[ 7] = swap32 (w1[3] | s1[3]);
610 final[ 8] = swap32 (w2[0] | s2[0]);
611 final[ 9] = swap32 (w2[1] | s2[1]);
612 final[10] = swap32 (w2[2] | s2[2]);
613 final[11] = swap32 (w2[3] | s2[3]);
614 final[12] = swap32 (w3[0] | s3[0]);
615 final[13] = swap32 (w3[1] | s3[1]);
617 final[15] = pw_salt_len * 8;
627 sha1_transform (&final[0], &final[4], &final[8], &final[12], digest);
629 // prepare magic array range
631 u32 lengthMagicArray = 0x20;
632 u32 offsetMagicArray = 0;
634 lengthMagicArray += ((digest[0] >> 24) & 0xff) % 6;
635 lengthMagicArray += ((digest[0] >> 16) & 0xff) % 6;
636 lengthMagicArray += ((digest[0] >> 8) & 0xff) % 6;
637 lengthMagicArray += ((digest[0] >> 0) & 0xff) % 6;
638 lengthMagicArray += ((digest[1] >> 24) & 0xff) % 6;
639 lengthMagicArray += ((digest[1] >> 16) & 0xff) % 6;
640 lengthMagicArray += ((digest[1] >> 8) & 0xff) % 6;
641 lengthMagicArray += ((digest[1] >> 0) & 0xff) % 6;
642 lengthMagicArray += ((digest[2] >> 24) & 0xff) % 6;
643 lengthMagicArray += ((digest[2] >> 16) & 0xff) % 6;
644 offsetMagicArray += ((digest[2] >> 8) & 0xff) % 8;
645 offsetMagicArray += ((digest[2] >> 0) & 0xff) % 8;
646 offsetMagicArray += ((digest[3] >> 24) & 0xff) % 8;
647 offsetMagicArray += ((digest[3] >> 16) & 0xff) % 8;
648 offsetMagicArray += ((digest[3] >> 8) & 0xff) % 8;
649 offsetMagicArray += ((digest[3] >> 0) & 0xff) % 8;
650 offsetMagicArray += ((digest[4] >> 24) & 0xff) % 8;
651 offsetMagicArray += ((digest[4] >> 16) & 0xff) % 8;
652 offsetMagicArray += ((digest[4] >> 8) & 0xff) % 8;
653 offsetMagicArray += ((digest[4] >> 0) & 0xff) % 8;
664 for (int i = 0; i < 32; i++) final[i] = 0;
675 u32 final_len = out_len;
681 for (i = 0; i < lengthMagicArray - 4; i += 4)
683 const u32 tmp = GETSHIFTEDINT (theMagicArray, offsetMagicArray + i);
685 SETSHIFTEDINT (final, final_len + i, tmp);
688 const u32 mask = 0xffffffff >> (((i - lengthMagicArray) & 3) * 8);
690 const u32 tmp = GETSHIFTEDINT (theMagicArray, offsetMagicArray + i) & mask;
692 SETSHIFTEDINT (final, final_len + i, tmp);
694 final_len += lengthMagicArray;
698 for (i = 0; i < salt_len + 1; i += 4) // +1 for the 0x80
700 const u32 tmp = salt_buf[i / 4]; // attention, int[] not char[]
702 SETSHIFTEDINT (final, final_len + i, tmp);
705 final_len += salt_len;
712 for (left = final_len, off = 0; left >= 56; left -= 64, off += 16)
714 swap_buffer (&final[off]);
716 sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
719 swap_buffer (&final[off]);
722 final[off + 15] = final_len * 8;
724 sha1_transform (&final[off + 0], &final[off + 4], &final[off + 8], &final[off + 12], digest);
726 const u32 r0 = digest[3];
727 const u32 r1 = digest[4];
728 const u32 r2 = digest[2];
729 const u32 r3 = digest[1];
735 __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)
739 __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)