2 * Author......: Jens Steube <jens.steube@gmail.com>
8 #include "include/constants.h"
9 #include "include/kernel_vendor.h"
28 #include "include/kernel_functions.c"
29 #include "types_amd.c"
30 #include "common_amd.c"
33 #define VECT_COMPARE_S "check_single_vect1_comp4.c"
34 #define VECT_COMPARE_M "check_multi_vect1_comp4.c"
38 #define VECT_COMPARE_S "check_single_vect2_comp4.c"
39 #define VECT_COMPARE_M "check_multi_vect2_comp4.c"
43 #define VECT_COMPARE_S "check_single_vect4_comp4.c"
44 #define VECT_COMPARE_M "check_multi_vect4_comp4.c"
47 static void sha1_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[5])
75 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
76 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
77 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
78 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
79 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
80 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
81 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
82 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
83 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
84 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
85 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
86 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
87 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
88 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
89 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
90 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
91 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
92 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
93 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
94 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
99 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
100 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
101 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
102 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
103 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
104 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
105 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
106 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
107 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
108 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
109 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
110 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
111 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
112 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
113 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
114 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
115 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
116 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
117 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
118 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
123 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
124 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
125 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
126 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
127 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
128 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
129 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
130 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
131 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
132 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
133 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
134 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
135 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
136 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
137 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
138 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
139 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
140 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
141 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
142 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
147 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
148 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
149 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
150 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
151 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
152 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
153 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
154 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
155 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
156 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
157 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
158 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
159 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
160 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
161 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
162 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
163 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
164 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
165 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
166 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
175 static void hmac_sha1_pad (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[5], u32x opad[5])
177 w0[0] = w0[0] ^ 0x36363636;
178 w0[1] = w0[1] ^ 0x36363636;
179 w0[2] = w0[2] ^ 0x36363636;
180 w0[3] = w0[3] ^ 0x36363636;
181 w1[0] = w1[0] ^ 0x36363636;
182 w1[1] = w1[1] ^ 0x36363636;
183 w1[2] = w1[2] ^ 0x36363636;
184 w1[3] = w1[3] ^ 0x36363636;
185 w2[0] = w2[0] ^ 0x36363636;
186 w2[1] = w2[1] ^ 0x36363636;
187 w2[2] = w2[2] ^ 0x36363636;
188 w2[3] = w2[3] ^ 0x36363636;
189 w3[0] = w3[0] ^ 0x36363636;
190 w3[1] = w3[1] ^ 0x36363636;
191 w3[2] = w3[2] ^ 0x36363636;
192 w3[3] = w3[3] ^ 0x36363636;
200 sha1_transform (w0, w1, w2, w3, ipad);
202 w0[0] = w0[0] ^ 0x6a6a6a6a;
203 w0[1] = w0[1] ^ 0x6a6a6a6a;
204 w0[2] = w0[2] ^ 0x6a6a6a6a;
205 w0[3] = w0[3] ^ 0x6a6a6a6a;
206 w1[0] = w1[0] ^ 0x6a6a6a6a;
207 w1[1] = w1[1] ^ 0x6a6a6a6a;
208 w1[2] = w1[2] ^ 0x6a6a6a6a;
209 w1[3] = w1[3] ^ 0x6a6a6a6a;
210 w2[0] = w2[0] ^ 0x6a6a6a6a;
211 w2[1] = w2[1] ^ 0x6a6a6a6a;
212 w2[2] = w2[2] ^ 0x6a6a6a6a;
213 w2[3] = w2[3] ^ 0x6a6a6a6a;
214 w3[0] = w3[0] ^ 0x6a6a6a6a;
215 w3[1] = w3[1] ^ 0x6a6a6a6a;
216 w3[2] = w3[2] ^ 0x6a6a6a6a;
217 w3[3] = w3[3] ^ 0x6a6a6a6a;
225 sha1_transform (w0, w1, w2, w3, opad);
228 static void hmac_sha1_run (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[5], u32x opad[5], u32x digest[5])
236 sha1_transform (w0, w1, w2, w3, digest);
253 w3[3] = (64 + 20) * 8;
261 sha1_transform (w0, w1, w2, w3, digest);
264 static void m07300m (u32x w0[4], u32x w1[4], u32x w2[4], u32x 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 rakp_t *rakp_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)
270 const u32 gid = get_global_id (0);
271 const u32 lid = get_local_id (0);
273 const u32 esalt_len = rakp_bufs[salt_pos].salt_len;
281 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
283 const u32 w0r = bfs_buf[il_pos].i;
322 hmac_sha1_pad (w0_t, w1_t, w2_t, w3_t, ipad, opad);
324 int esalt_size = esalt_len;
329 for (esalt_left = esalt_size, esalt_off = 0; esalt_left >= 56; esalt_left -= 64, esalt_off += 16)
331 w0_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 0];
332 w0_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 1];
333 w0_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 2];
334 w0_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 3];
335 w1_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 4];
336 w1_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 5];
337 w1_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 6];
338 w1_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 7];
339 w2_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 8];
340 w2_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 9];
341 w2_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 10];
342 w2_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 11];
343 w3_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 12];
344 w3_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 13];
345 w3_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 14];
346 w3_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 15];
348 sha1_transform (w0_t, w1_t, w2_t, w3_t, ipad);
351 w0_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 0];
352 w0_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 1];
353 w0_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 2];
354 w0_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 3];
355 w1_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 4];
356 w1_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 5];
357 w1_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 6];
358 w1_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 7];
359 w2_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 8];
360 w2_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 9];
361 w2_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 10];
362 w2_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 11];
363 w3_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 12];
364 w3_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 13];
366 w3_t[3] = (64 + esalt_size) * 8;
370 hmac_sha1_run (w0_t, w1_t, w2_t, w3_t, ipad, opad, digest);
372 const u32x r0 = digest[3];
373 const u32x r1 = digest[4];
374 const u32x r2 = digest[2];
375 const u32x r3 = digest[1];
377 #include VECT_COMPARE_M
381 static void m07300s (u32x w0[4], u32x w1[4], u32x w2[4], u32x 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 rakp_t *rakp_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)
387 const u32 gid = get_global_id (0);
388 const u32 lid = get_local_id (0);
390 const u32 esalt_len = rakp_bufs[salt_pos].salt_len;
396 const u32 search[4] =
398 digests_buf[digests_offset].digest_buf[DGST_R0],
399 digests_buf[digests_offset].digest_buf[DGST_R1],
400 digests_buf[digests_offset].digest_buf[DGST_R2],
401 digests_buf[digests_offset].digest_buf[DGST_R3]
410 for (u32 il_pos = 0; il_pos < bfs_cnt; il_pos++)
412 const u32 w0r = bfs_buf[il_pos].i;
451 hmac_sha1_pad (w0_t, w1_t, w2_t, w3_t, ipad, opad);
453 int esalt_size = esalt_len;
458 for (esalt_left = esalt_size, esalt_off = 0; esalt_left >= 56; esalt_left -= 64, esalt_off += 16)
460 w0_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 0];
461 w0_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 1];
462 w0_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 2];
463 w0_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 3];
464 w1_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 4];
465 w1_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 5];
466 w1_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 6];
467 w1_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 7];
468 w2_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 8];
469 w2_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 9];
470 w2_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 10];
471 w2_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 11];
472 w3_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 12];
473 w3_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 13];
474 w3_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 14];
475 w3_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 15];
477 sha1_transform (w0_t, w1_t, w2_t, w3_t, ipad);
480 w0_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 0];
481 w0_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 1];
482 w0_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 2];
483 w0_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 3];
484 w1_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 4];
485 w1_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 5];
486 w1_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 6];
487 w1_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 7];
488 w2_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 8];
489 w2_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 9];
490 w2_t[2] = rakp_bufs[salt_pos].salt_buf[esalt_off + 10];
491 w2_t[3] = rakp_bufs[salt_pos].salt_buf[esalt_off + 11];
492 w3_t[0] = rakp_bufs[salt_pos].salt_buf[esalt_off + 12];
493 w3_t[1] = rakp_bufs[salt_pos].salt_buf[esalt_off + 13];
495 w3_t[3] = (64 + esalt_size) * 8;
499 hmac_sha1_run (w0_t, w1_t, w2_t, w3_t, ipad, opad, digest);
501 const u32x r0 = digest[3];
502 const u32x r1 = digest[4];
503 const u32x r2 = digest[2];
504 const u32x r3 = digest[1];
506 #include VECT_COMPARE_S
510 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07300_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 *salts, __global rakp_t *rakp_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, const u32 combs_mode, const u32 gid_max)
516 const u32 gid = get_global_id (0);
518 if (gid >= gid_max) return;
522 w0[0] = pws[gid].i[ 0];
523 w0[1] = pws[gid].i[ 1];
524 w0[2] = pws[gid].i[ 2];
525 w0[3] = pws[gid].i[ 3];
548 const u32 pw_len = pws[gid].pw_len;
554 m07300m (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, salts, rakp_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
557 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07300_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 *salts, __global rakp_t *rakp_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, const u32 combs_mode, const u32 gid_max)
563 const u32 gid = get_global_id (0);
565 if (gid >= gid_max) return;
569 w0[0] = pws[gid].i[ 0];
570 w0[1] = pws[gid].i[ 1];
571 w0[2] = pws[gid].i[ 2];
572 w0[3] = pws[gid].i[ 3];
576 w1[0] = pws[gid].i[ 4];
577 w1[1] = pws[gid].i[ 5];
578 w1[2] = pws[gid].i[ 6];
579 w1[3] = pws[gid].i[ 7];
595 const u32 pw_len = pws[gid].pw_len;
601 m07300m (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, salts, rakp_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
604 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07300_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 *salts, __global rakp_t *rakp_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, const u32 combs_mode, const u32 gid_max)
610 const u32 gid = get_global_id (0);
612 if (gid >= gid_max) return;
616 w0[0] = pws[gid].i[ 0];
617 w0[1] = pws[gid].i[ 1];
618 w0[2] = pws[gid].i[ 2];
619 w0[3] = pws[gid].i[ 3];
623 w1[0] = pws[gid].i[ 4];
624 w1[1] = pws[gid].i[ 5];
625 w1[2] = pws[gid].i[ 6];
626 w1[3] = pws[gid].i[ 7];
630 w2[0] = pws[gid].i[ 8];
631 w2[1] = pws[gid].i[ 9];
632 w2[2] = pws[gid].i[10];
633 w2[3] = pws[gid].i[11];
637 w3[0] = pws[gid].i[12];
638 w3[1] = pws[gid].i[13];
642 const u32 pw_len = pws[gid].pw_len;
648 m07300m (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, salts, rakp_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
651 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07300_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 *salts, __global rakp_t *rakp_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, const u32 combs_mode, const u32 gid_max)
657 const u32 gid = get_global_id (0);
659 if (gid >= gid_max) return;
663 w0[0] = pws[gid].i[ 0];
664 w0[1] = pws[gid].i[ 1];
665 w0[2] = pws[gid].i[ 2];
666 w0[3] = pws[gid].i[ 3];
689 const u32 pw_len = pws[gid].pw_len;
695 m07300s (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, salts, rakp_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
698 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07300_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 *salts, __global rakp_t *rakp_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, const u32 combs_mode, const u32 gid_max)
704 const u32 gid = get_global_id (0);
706 if (gid >= gid_max) return;
710 w0[0] = pws[gid].i[ 0];
711 w0[1] = pws[gid].i[ 1];
712 w0[2] = pws[gid].i[ 2];
713 w0[3] = pws[gid].i[ 3];
717 w1[0] = pws[gid].i[ 4];
718 w1[1] = pws[gid].i[ 5];
719 w1[2] = pws[gid].i[ 6];
720 w1[3] = pws[gid].i[ 7];
736 const u32 pw_len = pws[gid].pw_len;
742 m07300s (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, salts, rakp_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);
745 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m07300_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 *salts, __global rakp_t *rakp_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, const u32 combs_mode, const u32 gid_max)
751 const u32 gid = get_global_id (0);
753 if (gid >= gid_max) return;
757 w0[0] = pws[gid].i[ 0];
758 w0[1] = pws[gid].i[ 1];
759 w0[2] = pws[gid].i[ 2];
760 w0[3] = pws[gid].i[ 3];
764 w1[0] = pws[gid].i[ 4];
765 w1[1] = pws[gid].i[ 5];
766 w1[2] = pws[gid].i[ 6];
767 w1[3] = pws[gid].i[ 7];
771 w2[0] = pws[gid].i[ 8];
772 w2[1] = pws[gid].i[ 9];
773 w2[2] = pws[gid].i[10];
774 w2[3] = pws[gid].i[11];
778 w3[0] = pws[gid].i[12];
779 w3[1] = pws[gid].i[13];
783 const u32 pw_len = pws[gid].pw_len;
789 m07300s (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, salts, rakp_bufs, d_return_buf, d_scryptV_buf, bitmap_mask, bitmap_shift1, bitmap_shift2, salt_pos, loop_pos, loop_cnt, bfs_cnt, digests_cnt, digests_offset);