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;
203 pw_buf0[0] = pws[gid].i[0];
204 pw_buf0[1] = pws[gid].i[1];
205 pw_buf0[2] = pws[gid].i[2];
206 pw_buf0[3] = pws[gid].i[3];
207 pw_buf1[0] = pws[gid].i[4];
208 pw_buf1[1] = pws[gid].i[5];
209 pw_buf1[2] = pws[gid].i[6];
210 pw_buf1[3] = pws[gid].i[7];
212 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]);
226 salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
227 salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
228 salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
229 salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
230 salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
231 salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
235 const u32 salt_len = salt_bufs[salt_pos].salt_len;
241 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
248 const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
250 append_0x80_2x4_VV (w0, w1, out_len);
256 w0[0] = swap32 (w0[0]);
257 w0[1] = swap32 (w0[1]);
258 w0[2] = swap32 (w0[2]);
259 w0[3] = swap32 (w0[3]);
260 w1[0] = swap32 (w1[0]);
261 w1[1] = swap32 (w1[1]);
262 w1[2] = swap32 (w1[2]);
263 w1[3] = swap32 (w1[3]);
264 w2[0] = swap32 (w2[0]);
265 w2[1] = swap32 (w2[1]);
266 w2[2] = swap32 (w2[2]);
267 w2[3] = swap32 (w2[3]);
268 w3[0] = swap32 (w3[0]);
269 w3[1] = swap32 (w3[1]);
281 sha1_transform (w0, w1, w2, w3, digest);
295 w0[0] = salt_buf0[0];
296 w0[1] = salt_buf0[1];
297 w0[2] = salt_buf0[2];
298 w0[3] = salt_buf0[3];
299 w1[0] = salt_buf1[0];
300 w1[1] = salt_buf1[1];
301 w1[2] = salt_buf1[2];
302 w1[3] = salt_buf1[3];
303 w2[0] = salt_buf2[0];
304 w2[1] = salt_buf2[1];
305 w2[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
306 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
307 w2[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
308 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
309 w3[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
310 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
311 w3[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
312 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
313 w3[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
314 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
315 w3[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
316 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
324 sha1_transform (w0, w1, w2, w3, digest);
326 w0[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
327 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
328 w0[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
329 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
330 w0[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
331 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
332 w0[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
333 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
347 sha1_transform (w0, w1, w2, w3, digest);
355 w0[0] = salt_buf0[0];
356 w0[1] = salt_buf0[1];
357 w0[2] = salt_buf0[2];
358 w0[3] = salt_buf0[3];
359 w1[0] = salt_buf1[0];
360 w1[1] = salt_buf1[1];
361 w1[2] = salt_buf1[2];
362 w1[3] = salt_buf1[3];
363 w2[0] = salt_buf2[0];
364 w2[1] = salt_buf2[1];
365 w2[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
366 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
367 w2[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
368 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
369 w3[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
370 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
371 w3[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
372 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
373 w3[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
374 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
375 w3[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
376 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
384 sha1_transform (w0, w1, w2, w3, digest);
386 w0[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
387 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
388 w0[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
389 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
390 w0[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
391 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
392 w0[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
393 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
407 sha1_transform (w0, w1, w2, w3, digest);
409 COMPARE_M_SIMD (digest[3], digest[4], digest[2], digest[1]);
413 __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)
417 __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)
421 __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)
427 const u32 gid = get_global_id (0);
428 const u32 lid = get_local_id (0);
429 const u32 lsz = get_local_size (0);
435 __local u32 l_bin2asc[256];
437 for (u32 i = lid; i < 256; i += lsz)
439 const u32 i0 = (i >> 0) & 15;
440 const u32 i1 = (i >> 4) & 15;
442 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 0
443 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 8;
446 barrier (CLK_LOCAL_MEM_FENCE);
448 if (gid >= gid_max) return;
457 pw_buf0[0] = pws[gid].i[0];
458 pw_buf0[1] = pws[gid].i[1];
459 pw_buf0[2] = pws[gid].i[2];
460 pw_buf0[3] = pws[gid].i[3];
461 pw_buf1[0] = pws[gid].i[4];
462 pw_buf1[1] = pws[gid].i[5];
463 pw_buf1[2] = pws[gid].i[6];
464 pw_buf1[3] = pws[gid].i[7];
466 const u32 pw_len = pws[gid].pw_len;
476 salt_buf0[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 0]);
477 salt_buf0[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 1]);
478 salt_buf0[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 2]);
479 salt_buf0[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 3]);
480 salt_buf1[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 4]);
481 salt_buf1[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 5]);
482 salt_buf1[2] = swap32_S (salt_bufs[salt_pos].salt_buf[ 6]);
483 salt_buf1[3] = swap32_S (salt_bufs[salt_pos].salt_buf[ 7]);
484 salt_buf2[0] = swap32_S (salt_bufs[salt_pos].salt_buf[ 8]);
485 salt_buf2[1] = swap32_S (salt_bufs[salt_pos].salt_buf[ 9]);
489 const u32 salt_len = salt_bufs[salt_pos].salt_len;
495 const u32 search[4] =
497 digests_buf[digests_offset].digest_buf[DGST_R0],
498 digests_buf[digests_offset].digest_buf[DGST_R1],
499 digests_buf[digests_offset].digest_buf[DGST_R2],
500 digests_buf[digests_offset].digest_buf[DGST_R3]
507 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
514 const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
516 append_0x80_2x4_VV (w0, w1, out_len);
522 w0[0] = swap32 (w0[0]);
523 w0[1] = swap32 (w0[1]);
524 w0[2] = swap32 (w0[2]);
525 w0[3] = swap32 (w0[3]);
526 w1[0] = swap32 (w1[0]);
527 w1[1] = swap32 (w1[1]);
528 w1[2] = swap32 (w1[2]);
529 w1[3] = swap32 (w1[3]);
530 w2[0] = swap32 (w2[0]);
531 w2[1] = swap32 (w2[1]);
532 w2[2] = swap32 (w2[2]);
533 w2[3] = swap32 (w2[3]);
534 w3[0] = swap32 (w3[0]);
535 w3[1] = swap32 (w3[1]);
547 sha1_transform (w0, w1, w2, w3, digest);
561 w0[0] = salt_buf0[0];
562 w0[1] = salt_buf0[1];
563 w0[2] = salt_buf0[2];
564 w0[3] = salt_buf0[3];
565 w1[0] = salt_buf1[0];
566 w1[1] = salt_buf1[1];
567 w1[2] = salt_buf1[2];
568 w1[3] = salt_buf1[3];
569 w2[0] = salt_buf2[0];
570 w2[1] = salt_buf2[1];
571 w2[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
572 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
573 w2[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
574 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
575 w3[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
576 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
577 w3[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
578 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
579 w3[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
580 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
581 w3[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
582 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
590 sha1_transform (w0, w1, w2, w3, digest);
592 w0[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
593 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
594 w0[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
595 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
596 w0[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
597 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
598 w0[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
599 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
613 sha1_transform (w0, w1, w2, w3, digest);
621 w0[0] = salt_buf0[0];
622 w0[1] = salt_buf0[1];
623 w0[2] = salt_buf0[2];
624 w0[3] = salt_buf0[3];
625 w1[0] = salt_buf1[0];
626 w1[1] = salt_buf1[1];
627 w1[2] = salt_buf1[2];
628 w1[3] = salt_buf1[3];
629 w2[0] = salt_buf2[0];
630 w2[1] = salt_buf2[1];
631 w2[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
632 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
633 w2[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
634 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
635 w3[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
636 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
637 w3[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
638 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
639 w3[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
640 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
641 w3[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
642 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
650 sha1_transform (w0, w1, w2, w3, digest);
652 w0[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
653 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
654 w0[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
655 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
656 w0[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
657 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
658 w0[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
659 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
673 sha1_transform (w0, w1, w2, w3, digest);
675 COMPARE_S_SIMD (digest[3], digest[4], digest[2], digest[1]);
679 __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)
683 __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)