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 "types_ocl.c"
20 #define COMPARE_S "check_single_comp4.c"
21 #define COMPARE_M "check_multi_comp4.c"
24 #define uint_to_hex_lower8_le(i) l_bin2asc[(i)]
28 #define uint_to_hex_lower8_le(i) u32 (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
32 #define uint_to_hex_lower8_le(i) u32 (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
35 static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
63 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
64 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
65 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
66 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
67 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
68 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
69 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
70 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
71 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
72 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
73 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
74 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
75 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
76 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
77 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
78 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
79 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
80 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
81 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
82 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
87 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
88 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
89 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
90 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
91 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
92 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
93 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
94 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
95 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
96 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
97 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
98 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
99 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
100 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
101 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
102 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
103 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
104 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
105 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
106 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
111 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
112 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
113 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
114 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
115 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
116 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
117 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
118 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
119 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
120 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
121 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
122 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
123 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
124 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
125 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
126 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
127 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
128 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
129 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
130 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
135 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
136 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
137 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
138 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
139 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
140 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
141 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
142 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
143 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
144 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
145 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
146 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
147 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
148 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
149 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
150 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
151 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
152 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
153 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
154 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
163 static void m08400m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global gpu_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, __local u32 l_bin2asc[256])
169 const u32 gid = get_global_id (0);
170 const u32 lid = get_local_id (0);
178 salt_buf0[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 0]);
179 salt_buf0[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 1]);
180 salt_buf0[2] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 2]);
181 salt_buf0[3] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 3]);
185 salt_buf1[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 4]);
186 salt_buf1[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 5]);
187 salt_buf1[2] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 6]);
188 salt_buf1[3] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 7]);
192 salt_buf2[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 8]);
193 salt_buf2[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 9]);
197 const u32 salt_len = salt_bufs[salt_pos].salt_len;
205 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
207 const u32 w0r = bfs_buf[il_pos].i;
237 w3_t[3] = pw_len * 8;
247 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
261 w0_t[0] = salt_buf0[0];
262 w0_t[1] = salt_buf0[1];
263 w0_t[2] = salt_buf0[2];
264 w0_t[3] = salt_buf0[3];
265 w1_t[0] = salt_buf1[0];
266 w1_t[1] = salt_buf1[1];
267 w1_t[2] = salt_buf1[2];
268 w1_t[3] = salt_buf1[3];
269 w2_t[0] = salt_buf2[0];
270 w2_t[1] = salt_buf2[1];
271 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
272 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
273 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
274 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
275 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
276 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
277 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
278 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
279 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
280 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
281 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
282 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
290 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
292 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
293 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
294 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
295 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
296 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
297 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
298 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
299 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
300 w1_t[0] = 0x80000000;
313 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
321 w0_t[0] = salt_buf0[0];
322 w0_t[1] = salt_buf0[1];
323 w0_t[2] = salt_buf0[2];
324 w0_t[3] = salt_buf0[3];
325 w1_t[0] = salt_buf1[0];
326 w1_t[1] = salt_buf1[1];
327 w1_t[2] = salt_buf1[2];
328 w1_t[3] = salt_buf1[3];
329 w2_t[0] = salt_buf2[0];
330 w2_t[1] = salt_buf2[1];
331 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
332 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
333 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
334 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
335 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
336 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
337 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
338 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
339 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
340 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
341 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
342 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
350 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
352 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
353 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
354 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
355 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
356 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
357 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
358 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
359 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
360 w1_t[0] = 0x80000000;
373 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
375 const u32 r0 = digest[3];
376 const u32 r1 = digest[4];
377 const u32 r2 = digest[2];
378 const u32 r3 = digest[1];
384 static void m08400s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global gpu_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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, __local u32 l_bin2asc[256])
390 const u32 gid = get_global_id (0);
391 const u32 lid = get_local_id (0);
397 const u32 search[4] =
399 digests_buf[digests_offset].digest_buf[DGST_R0],
400 digests_buf[digests_offset].digest_buf[DGST_R1],
401 digests_buf[digests_offset].digest_buf[DGST_R2],
402 digests_buf[digests_offset].digest_buf[DGST_R3]
411 salt_buf0[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 0]);
412 salt_buf0[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 1]);
413 salt_buf0[2] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 2]);
414 salt_buf0[3] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 3]);
418 salt_buf1[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 4]);
419 salt_buf1[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 5]);
420 salt_buf1[2] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 6]);
421 salt_buf1[3] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 7]);
425 salt_buf2[0] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 8]);
426 salt_buf2[1] = swap_workaround (salt_bufs[salt_pos].salt_buf[ 9]);
430 const u32 salt_len = salt_bufs[salt_pos].salt_len;
438 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
440 const u32 w0r = bfs_buf[il_pos].i;
470 w3_t[3] = pw_len * 8;
480 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
494 w0_t[0] = salt_buf0[0];
495 w0_t[1] = salt_buf0[1];
496 w0_t[2] = salt_buf0[2];
497 w0_t[3] = salt_buf0[3];
498 w1_t[0] = salt_buf1[0];
499 w1_t[1] = salt_buf1[1];
500 w1_t[2] = salt_buf1[2];
501 w1_t[3] = salt_buf1[3];
502 w2_t[0] = salt_buf2[0];
503 w2_t[1] = salt_buf2[1];
504 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
505 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
506 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
507 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
508 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
509 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
510 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
511 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
512 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
513 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
514 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
515 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
523 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
525 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
526 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
527 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
528 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
529 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
530 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
531 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
532 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
533 w1_t[0] = 0x80000000;
544 w3_t[3] = (salt_len + 40) * 8;
546 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
554 w0_t[0] = salt_buf0[0];
555 w0_t[1] = salt_buf0[1];
556 w0_t[2] = salt_buf0[2];
557 w0_t[3] = salt_buf0[3];
558 w1_t[0] = salt_buf1[0];
559 w1_t[1] = salt_buf1[1];
560 w1_t[2] = salt_buf1[2];
561 w1_t[3] = salt_buf1[3];
562 w2_t[0] = salt_buf2[0];
563 w2_t[1] = salt_buf2[1];
564 w2_t[2] = uint_to_hex_lower8_le ((a >> 16) & 255) << 0
565 | uint_to_hex_lower8_le ((a >> 24) & 255) << 16;
566 w2_t[3] = uint_to_hex_lower8_le ((a >> 0) & 255) << 0
567 | uint_to_hex_lower8_le ((a >> 8) & 255) << 16;
568 w3_t[0] = uint_to_hex_lower8_le ((b >> 16) & 255) << 0
569 | uint_to_hex_lower8_le ((b >> 24) & 255) << 16;
570 w3_t[1] = uint_to_hex_lower8_le ((b >> 0) & 255) << 0
571 | uint_to_hex_lower8_le ((b >> 8) & 255) << 16;
572 w3_t[2] = uint_to_hex_lower8_le ((c >> 16) & 255) << 0
573 | uint_to_hex_lower8_le ((c >> 24) & 255) << 16;
574 w3_t[3] = uint_to_hex_lower8_le ((c >> 0) & 255) << 0
575 | uint_to_hex_lower8_le ((c >> 8) & 255) << 16;
583 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
585 w0_t[0] = uint_to_hex_lower8_le ((d >> 16) & 255) << 0
586 | uint_to_hex_lower8_le ((d >> 24) & 255) << 16;
587 w0_t[1] = uint_to_hex_lower8_le ((d >> 0) & 255) << 0
588 | uint_to_hex_lower8_le ((d >> 8) & 255) << 16;
589 w0_t[2] = uint_to_hex_lower8_le ((e >> 16) & 255) << 0
590 | uint_to_hex_lower8_le ((e >> 24) & 255) << 16;
591 w0_t[3] = uint_to_hex_lower8_le ((e >> 0) & 255) << 0
592 | uint_to_hex_lower8_le ((e >> 8) & 255) << 16;
593 w1_t[0] = 0x80000000;
604 w3_t[3] = (salt_len + 40) * 8;
606 sha1_transform (w0_t, w1_t, w2_t, w3_t, digest);
608 const u32 r0 = digest[3];
609 const u32 r1 = digest[4];
610 const u32 r2 = digest[2];
611 const u32 r3 = digest[1];
617 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08400_m04 (__global pw_t *pws, __global gpu_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 *ss, __global void *ess, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
623 const u32 gid = get_global_id (0);
624 const u32 lid = get_local_id (0);
628 w0[0] = pws[gid].i[ 0];
629 w0[1] = pws[gid].i[ 1];
630 w0[2] = pws[gid].i[ 2];
631 w0[3] = pws[gid].i[ 3];
654 const u32 pw_len = pws[gid].pw_len;
660 __local u32 l_bin2asc[256];
662 const u32 lid4 = lid * 4;
664 const u32 lid40 = lid4 + 0;
665 const u32 lid41 = lid4 + 1;
666 const u32 lid42 = lid4 + 2;
667 const u32 lid43 = lid4 + 3;
669 const u32 v400 = (lid40 >> 0) & 15;
670 const u32 v401 = (lid40 >> 4) & 15;
671 const u32 v410 = (lid41 >> 0) & 15;
672 const u32 v411 = (lid41 >> 4) & 15;
673 const u32 v420 = (lid42 >> 0) & 15;
674 const u32 v421 = (lid42 >> 4) & 15;
675 const u32 v430 = (lid43 >> 0) & 15;
676 const u32 v431 = (lid43 >> 4) & 15;
678 l_bin2asc[lid40] = ((v400 < 10) ? '0' + v400 : 'a' - 10 + v400) << 0
679 | ((v401 < 10) ? '0' + v401 : 'a' - 10 + v401) << 8;
680 l_bin2asc[lid41] = ((v410 < 10) ? '0' + v410 : 'a' - 10 + v410) << 0
681 | ((v411 < 10) ? '0' + v411 : 'a' - 10 + v411) << 8;
682 l_bin2asc[lid42] = ((v420 < 10) ? '0' + v420 : 'a' - 10 + v420) << 0
683 | ((v421 < 10) ? '0' + v421 : 'a' - 10 + v421) << 8;
684 l_bin2asc[lid43] = ((v430 < 10) ? '0' + v430 : 'a' - 10 + v430) << 0
685 | ((v431 < 10) ? '0' + v431 : 'a' - 10 + v431) << 8;
687 barrier (CLK_LOCAL_MEM_FENCE);
689 if (gid >= gid_max) return;
695 m08400m (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, ss, ess, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset, l_bin2asc);
698 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08400_m08 (__global pw_t *pws, __global gpu_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 *ss, __global void *ess, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
704 const u32 gid = get_global_id (0);
705 const u32 lid = get_local_id (0);
709 w0[0] = pws[gid].i[ 0];
710 w0[1] = pws[gid].i[ 1];
711 w0[2] = pws[gid].i[ 2];
712 w0[3] = pws[gid].i[ 3];
716 w1[0] = pws[gid].i[ 4];
717 w1[1] = pws[gid].i[ 5];
718 w1[2] = pws[gid].i[ 6];
719 w1[3] = pws[gid].i[ 7];
735 const u32 pw_len = pws[gid].pw_len;
741 __local u32 l_bin2asc[256];
743 const u32 lid4 = lid * 4;
745 const u32 lid40 = lid4 + 0;
746 const u32 lid41 = lid4 + 1;
747 const u32 lid42 = lid4 + 2;
748 const u32 lid43 = lid4 + 3;
750 const u32 v400 = (lid40 >> 0) & 15;
751 const u32 v401 = (lid40 >> 4) & 15;
752 const u32 v410 = (lid41 >> 0) & 15;
753 const u32 v411 = (lid41 >> 4) & 15;
754 const u32 v420 = (lid42 >> 0) & 15;
755 const u32 v421 = (lid42 >> 4) & 15;
756 const u32 v430 = (lid43 >> 0) & 15;
757 const u32 v431 = (lid43 >> 4) & 15;
759 l_bin2asc[lid40] = ((v400 < 10) ? '0' + v400 : 'a' - 10 + v400) << 0
760 | ((v401 < 10) ? '0' + v401 : 'a' - 10 + v401) << 8;
761 l_bin2asc[lid41] = ((v410 < 10) ? '0' + v410 : 'a' - 10 + v410) << 0
762 | ((v411 < 10) ? '0' + v411 : 'a' - 10 + v411) << 8;
763 l_bin2asc[lid42] = ((v420 < 10) ? '0' + v420 : 'a' - 10 + v420) << 0
764 | ((v421 < 10) ? '0' + v421 : 'a' - 10 + v421) << 8;
765 l_bin2asc[lid43] = ((v430 < 10) ? '0' + v430 : 'a' - 10 + v430) << 0
766 | ((v431 < 10) ? '0' + v431 : 'a' - 10 + v431) << 8;
768 barrier (CLK_LOCAL_MEM_FENCE);
770 if (gid >= gid_max) return;
776 m08400m (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, ss, ess, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset, l_bin2asc);
779 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08400_m16 (__global pw_t *pws, __global gpu_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 *ss, __global void *ess, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
785 const u32 gid = get_global_id (0);
786 const u32 lid = get_local_id (0);
790 w0[0] = pws[gid].i[ 0];
791 w0[1] = pws[gid].i[ 1];
792 w0[2] = pws[gid].i[ 2];
793 w0[3] = pws[gid].i[ 3];
797 w1[0] = pws[gid].i[ 4];
798 w1[1] = pws[gid].i[ 5];
799 w1[2] = pws[gid].i[ 6];
800 w1[3] = pws[gid].i[ 7];
804 w2[0] = pws[gid].i[ 8];
805 w2[1] = pws[gid].i[ 9];
806 w2[2] = pws[gid].i[10];
807 w2[3] = pws[gid].i[11];
811 w3[0] = pws[gid].i[12];
812 w3[1] = pws[gid].i[13];
816 const u32 pw_len = pws[gid].pw_len;
822 __local u32 l_bin2asc[256];
824 const u32 lid4 = lid * 4;
826 const u32 lid40 = lid4 + 0;
827 const u32 lid41 = lid4 + 1;
828 const u32 lid42 = lid4 + 2;
829 const u32 lid43 = lid4 + 3;
831 const u32 v400 = (lid40 >> 0) & 15;
832 const u32 v401 = (lid40 >> 4) & 15;
833 const u32 v410 = (lid41 >> 0) & 15;
834 const u32 v411 = (lid41 >> 4) & 15;
835 const u32 v420 = (lid42 >> 0) & 15;
836 const u32 v421 = (lid42 >> 4) & 15;
837 const u32 v430 = (lid43 >> 0) & 15;
838 const u32 v431 = (lid43 >> 4) & 15;
840 l_bin2asc[lid40] = ((v400 < 10) ? '0' + v400 : 'a' - 10 + v400) << 0
841 | ((v401 < 10) ? '0' + v401 : 'a' - 10 + v401) << 8;
842 l_bin2asc[lid41] = ((v410 < 10) ? '0' + v410 : 'a' - 10 + v410) << 0
843 | ((v411 < 10) ? '0' + v411 : 'a' - 10 + v411) << 8;
844 l_bin2asc[lid42] = ((v420 < 10) ? '0' + v420 : 'a' - 10 + v420) << 0
845 | ((v421 < 10) ? '0' + v421 : 'a' - 10 + v421) << 8;
846 l_bin2asc[lid43] = ((v430 < 10) ? '0' + v430 : 'a' - 10 + v430) << 0
847 | ((v431 < 10) ? '0' + v431 : 'a' - 10 + v431) << 8;
849 barrier (CLK_LOCAL_MEM_FENCE);
851 if (gid >= gid_max) return;
857 m08400m (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, ss, ess, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset, l_bin2asc);
860 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08400_s04 (__global pw_t *pws, __global gpu_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 *ss, __global void *ess, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
866 const u32 gid = get_global_id (0);
867 const u32 lid = get_local_id (0);
871 w0[0] = pws[gid].i[ 0];
872 w0[1] = pws[gid].i[ 1];
873 w0[2] = pws[gid].i[ 2];
874 w0[3] = pws[gid].i[ 3];
897 const u32 pw_len = pws[gid].pw_len;
903 __local u32 l_bin2asc[256];
905 const u32 lid4 = lid * 4;
907 const u32 lid40 = lid4 + 0;
908 const u32 lid41 = lid4 + 1;
909 const u32 lid42 = lid4 + 2;
910 const u32 lid43 = lid4 + 3;
912 const u32 v400 = (lid40 >> 0) & 15;
913 const u32 v401 = (lid40 >> 4) & 15;
914 const u32 v410 = (lid41 >> 0) & 15;
915 const u32 v411 = (lid41 >> 4) & 15;
916 const u32 v420 = (lid42 >> 0) & 15;
917 const u32 v421 = (lid42 >> 4) & 15;
918 const u32 v430 = (lid43 >> 0) & 15;
919 const u32 v431 = (lid43 >> 4) & 15;
921 l_bin2asc[lid40] = ((v400 < 10) ? '0' + v400 : 'a' - 10 + v400) << 0
922 | ((v401 < 10) ? '0' + v401 : 'a' - 10 + v401) << 8;
923 l_bin2asc[lid41] = ((v410 < 10) ? '0' + v410 : 'a' - 10 + v410) << 0
924 | ((v411 < 10) ? '0' + v411 : 'a' - 10 + v411) << 8;
925 l_bin2asc[lid42] = ((v420 < 10) ? '0' + v420 : 'a' - 10 + v420) << 0
926 | ((v421 < 10) ? '0' + v421 : 'a' - 10 + v421) << 8;
927 l_bin2asc[lid43] = ((v430 < 10) ? '0' + v430 : 'a' - 10 + v430) << 0
928 | ((v431 < 10) ? '0' + v431 : 'a' - 10 + v431) << 8;
930 barrier (CLK_LOCAL_MEM_FENCE);
932 if (gid >= gid_max) return;
938 m08400s (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, ss, ess, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset, l_bin2asc);
941 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08400_s08 (__global pw_t *pws, __global gpu_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 *ss, __global void *ess, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
947 const u32 gid = get_global_id (0);
948 const u32 lid = get_local_id (0);
952 w0[0] = pws[gid].i[ 0];
953 w0[1] = pws[gid].i[ 1];
954 w0[2] = pws[gid].i[ 2];
955 w0[3] = pws[gid].i[ 3];
959 w1[0] = pws[gid].i[ 4];
960 w1[1] = pws[gid].i[ 5];
961 w1[2] = pws[gid].i[ 6];
962 w1[3] = pws[gid].i[ 7];
978 const u32 pw_len = pws[gid].pw_len;
984 __local u32 l_bin2asc[256];
986 const u32 lid4 = lid * 4;
988 const u32 lid40 = lid4 + 0;
989 const u32 lid41 = lid4 + 1;
990 const u32 lid42 = lid4 + 2;
991 const u32 lid43 = lid4 + 3;
993 const u32 v400 = (lid40 >> 0) & 15;
994 const u32 v401 = (lid40 >> 4) & 15;
995 const u32 v410 = (lid41 >> 0) & 15;
996 const u32 v411 = (lid41 >> 4) & 15;
997 const u32 v420 = (lid42 >> 0) & 15;
998 const u32 v421 = (lid42 >> 4) & 15;
999 const u32 v430 = (lid43 >> 0) & 15;
1000 const u32 v431 = (lid43 >> 4) & 15;
1002 l_bin2asc[lid40] = ((v400 < 10) ? '0' + v400 : 'a' - 10 + v400) << 0
1003 | ((v401 < 10) ? '0' + v401 : 'a' - 10 + v401) << 8;
1004 l_bin2asc[lid41] = ((v410 < 10) ? '0' + v410 : 'a' - 10 + v410) << 0
1005 | ((v411 < 10) ? '0' + v411 : 'a' - 10 + v411) << 8;
1006 l_bin2asc[lid42] = ((v420 < 10) ? '0' + v420 : 'a' - 10 + v420) << 0
1007 | ((v421 < 10) ? '0' + v421 : 'a' - 10 + v421) << 8;
1008 l_bin2asc[lid43] = ((v430 < 10) ? '0' + v430 : 'a' - 10 + v430) << 0
1009 | ((v431 < 10) ? '0' + v431 : 'a' - 10 + v431) << 8;
1011 barrier (CLK_LOCAL_MEM_FENCE);
1013 if (gid >= gid_max) return;
1019 m08400s (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, ss, ess, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset, l_bin2asc);
1022 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m08400_s16 (__global pw_t *pws, __global gpu_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 *ss, __global void *ess, __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 bfs_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
1028 const u32 gid = get_global_id (0);
1029 const u32 lid = get_local_id (0);
1033 w0[0] = pws[gid].i[ 0];
1034 w0[1] = pws[gid].i[ 1];
1035 w0[2] = pws[gid].i[ 2];
1036 w0[3] = pws[gid].i[ 3];
1040 w1[0] = pws[gid].i[ 4];
1041 w1[1] = pws[gid].i[ 5];
1042 w1[2] = pws[gid].i[ 6];
1043 w1[3] = pws[gid].i[ 7];
1047 w2[0] = pws[gid].i[ 8];
1048 w2[1] = pws[gid].i[ 9];
1049 w2[2] = pws[gid].i[10];
1050 w2[3] = pws[gid].i[11];
1054 w3[0] = pws[gid].i[12];
1055 w3[1] = pws[gid].i[13];
1059 const u32 pw_len = pws[gid].pw_len;
1065 __local u32 l_bin2asc[256];
1067 const u32 lid4 = lid * 4;
1069 const u32 lid40 = lid4 + 0;
1070 const u32 lid41 = lid4 + 1;
1071 const u32 lid42 = lid4 + 2;
1072 const u32 lid43 = lid4 + 3;
1074 const u32 v400 = (lid40 >> 0) & 15;
1075 const u32 v401 = (lid40 >> 4) & 15;
1076 const u32 v410 = (lid41 >> 0) & 15;
1077 const u32 v411 = (lid41 >> 4) & 15;
1078 const u32 v420 = (lid42 >> 0) & 15;
1079 const u32 v421 = (lid42 >> 4) & 15;
1080 const u32 v430 = (lid43 >> 0) & 15;
1081 const u32 v431 = (lid43 >> 4) & 15;
1083 l_bin2asc[lid40] = ((v400 < 10) ? '0' + v400 : 'a' - 10 + v400) << 0
1084 | ((v401 < 10) ? '0' + v401 : 'a' - 10 + v401) << 8;
1085 l_bin2asc[lid41] = ((v410 < 10) ? '0' + v410 : 'a' - 10 + v410) << 0
1086 | ((v411 < 10) ? '0' + v411 : 'a' - 10 + v411) << 8;
1087 l_bin2asc[lid42] = ((v420 < 10) ? '0' + v420 : 'a' - 10 + v420) << 0
1088 | ((v421 < 10) ? '0' + v421 : 'a' - 10 + v421) << 8;
1089 l_bin2asc[lid43] = ((v430 < 10) ? '0' + v430 : 'a' - 10 + v430) << 0
1090 | ((v431 < 10) ? '0' + v431 : 'a' - 10 + v431) << 8;
1092 barrier (CLK_LOCAL_MEM_FENCE);
1094 if (gid >= gid_max) return;
1100 m08400s (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, ss, ess, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset, l_bin2asc);