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"
21 #define COMPARE_M "check_multi_vect1_comp4.c"
25 #define COMPARE_M "check_multi_vect2_comp4.c"
28 static void md4_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[4])
35 MD4_STEP (MD4_Fo, a, b, c, d, w0[0], MD4C00, MD4S00);
36 MD4_STEP (MD4_Fo, d, a, b, c, w0[1], MD4C00, MD4S01);
37 MD4_STEP (MD4_Fo, c, d, a, b, w0[2], MD4C00, MD4S02);
38 MD4_STEP (MD4_Fo, b, c, d, a, w0[3], MD4C00, MD4S03);
39 MD4_STEP (MD4_Fo, a, b, c, d, w1[0], MD4C00, MD4S00);
40 MD4_STEP (MD4_Fo, d, a, b, c, w1[1], MD4C00, MD4S01);
41 MD4_STEP (MD4_Fo, c, d, a, b, w1[2], MD4C00, MD4S02);
42 MD4_STEP (MD4_Fo, b, c, d, a, w1[3], MD4C00, MD4S03);
43 MD4_STEP (MD4_Fo, a, b, c, d, w2[0], MD4C00, MD4S00);
44 MD4_STEP (MD4_Fo, d, a, b, c, w2[1], MD4C00, MD4S01);
45 MD4_STEP (MD4_Fo, c, d, a, b, w2[2], MD4C00, MD4S02);
46 MD4_STEP (MD4_Fo, b, c, d, a, w2[3], MD4C00, MD4S03);
47 MD4_STEP (MD4_Fo, a, b, c, d, w3[0], MD4C00, MD4S00);
48 MD4_STEP (MD4_Fo, d, a, b, c, w3[1], MD4C00, MD4S01);
49 MD4_STEP (MD4_Fo, c, d, a, b, w3[2], MD4C00, MD4S02);
50 MD4_STEP (MD4_Fo, b, c, d, a, w3[3], MD4C00, MD4S03);
52 MD4_STEP (MD4_Go, a, b, c, d, w0[0], MD4C01, MD4S10);
53 MD4_STEP (MD4_Go, d, a, b, c, w1[0], MD4C01, MD4S11);
54 MD4_STEP (MD4_Go, c, d, a, b, w2[0], MD4C01, MD4S12);
55 MD4_STEP (MD4_Go, b, c, d, a, w3[0], MD4C01, MD4S13);
56 MD4_STEP (MD4_Go, a, b, c, d, w0[1], MD4C01, MD4S10);
57 MD4_STEP (MD4_Go, d, a, b, c, w1[1], MD4C01, MD4S11);
58 MD4_STEP (MD4_Go, c, d, a, b, w2[1], MD4C01, MD4S12);
59 MD4_STEP (MD4_Go, b, c, d, a, w3[1], MD4C01, MD4S13);
60 MD4_STEP (MD4_Go, a, b, c, d, w0[2], MD4C01, MD4S10);
61 MD4_STEP (MD4_Go, d, a, b, c, w1[2], MD4C01, MD4S11);
62 MD4_STEP (MD4_Go, c, d, a, b, w2[2], MD4C01, MD4S12);
63 MD4_STEP (MD4_Go, b, c, d, a, w3[2], MD4C01, MD4S13);
64 MD4_STEP (MD4_Go, a, b, c, d, w0[3], MD4C01, MD4S10);
65 MD4_STEP (MD4_Go, d, a, b, c, w1[3], MD4C01, MD4S11);
66 MD4_STEP (MD4_Go, c, d, a, b, w2[3], MD4C01, MD4S12);
67 MD4_STEP (MD4_Go, b, c, d, a, w3[3], MD4C01, MD4S13);
69 MD4_STEP (MD4_H , a, b, c, d, w0[0], MD4C02, MD4S20);
70 MD4_STEP (MD4_H , d, a, b, c, w2[0], MD4C02, MD4S21);
71 MD4_STEP (MD4_H , c, d, a, b, w1[0], MD4C02, MD4S22);
72 MD4_STEP (MD4_H , b, c, d, a, w3[0], MD4C02, MD4S23);
73 MD4_STEP (MD4_H , a, b, c, d, w0[2], MD4C02, MD4S20);
74 MD4_STEP (MD4_H , d, a, b, c, w2[2], MD4C02, MD4S21);
75 MD4_STEP (MD4_H , c, d, a, b, w1[2], MD4C02, MD4S22);
76 MD4_STEP (MD4_H , b, c, d, a, w3[2], MD4C02, MD4S23);
77 MD4_STEP (MD4_H , a, b, c, d, w0[1], MD4C02, MD4S20);
78 MD4_STEP (MD4_H , d, a, b, c, w2[1], MD4C02, MD4S21);
79 MD4_STEP (MD4_H , c, d, a, b, w1[1], MD4C02, MD4S22);
80 MD4_STEP (MD4_H , b, c, d, a, w3[1], MD4C02, MD4S23);
81 MD4_STEP (MD4_H , a, b, c, d, w0[3], MD4C02, MD4S20);
82 MD4_STEP (MD4_H , d, a, b, c, w2[3], MD4C02, MD4S21);
83 MD4_STEP (MD4_H , c, d, a, b, w1[3], MD4C02, MD4S22);
84 MD4_STEP (MD4_H , b, c, d, a, w3[3], MD4C02, MD4S23);
92 static void sha1_transform (const u32 w0[4], const u32 w1[4], const u32 w2[4], const u32 w3[4], u32 digest[5])
120 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w0_t);
121 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w1_t);
122 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w2_t);
123 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w3_t);
124 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w4_t);
125 SHA1_STEP (SHA1_F0o, A, B, C, D, E, w5_t);
126 SHA1_STEP (SHA1_F0o, E, A, B, C, D, w6_t);
127 SHA1_STEP (SHA1_F0o, D, E, A, B, C, w7_t);
128 SHA1_STEP (SHA1_F0o, C, D, E, A, B, w8_t);
129 SHA1_STEP (SHA1_F0o, B, C, D, E, A, w9_t);
130 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wa_t);
131 SHA1_STEP (SHA1_F0o, E, A, B, C, D, wb_t);
132 SHA1_STEP (SHA1_F0o, D, E, A, B, C, wc_t);
133 SHA1_STEP (SHA1_F0o, C, D, E, A, B, wd_t);
134 SHA1_STEP (SHA1_F0o, B, C, D, E, A, we_t);
135 SHA1_STEP (SHA1_F0o, A, B, C, D, E, wf_t);
136 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, E, A, B, C, D, w0_t);
137 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, D, E, A, B, C, w1_t);
138 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, C, D, E, A, B, w2_t);
139 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, B, C, D, E, A, w3_t);
144 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w4_t);
145 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w5_t);
146 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w6_t);
147 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w7_t);
148 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w8_t);
149 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w9_t);
150 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wa_t);
151 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wb_t);
152 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wc_t);
153 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wd_t);
154 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, we_t);
155 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wf_t);
156 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w0_t);
157 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w1_t);
158 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w2_t);
159 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w3_t);
160 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w4_t);
161 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w5_t);
162 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w6_t);
163 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w7_t);
168 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w8_t);
169 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w9_t);
170 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wa_t);
171 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wb_t);
172 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wc_t);
173 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, wd_t);
174 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, we_t);
175 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, wf_t);
176 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w0_t);
177 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w1_t);
178 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w2_t);
179 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w3_t);
180 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w4_t);
181 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, w5_t);
182 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, w6_t);
183 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, A, B, C, D, E, w7_t);
184 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, E, A, B, C, D, w8_t);
185 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, D, E, A, B, C, w9_t);
186 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, C, D, E, A, B, wa_t);
187 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, B, C, D, E, A, wb_t);
192 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wc_t);
193 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wd_t);
194 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, we_t);
195 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, wf_t);
196 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w0_t);
197 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w1_t);
198 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w2_t);
199 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w3_t);
200 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w4_t);
201 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, w5_t);
202 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, w6_t);
203 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, w7_t);
204 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, w8_t);
205 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, w9_t);
206 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wa_t);
207 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, A, B, C, D, E, wb_t);
208 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, E, A, B, C, D, wc_t);
209 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, D, E, A, B, C, wd_t);
210 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, C, D, E, A, B, we_t);
211 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, B, C, D, E, A, wf_t);
220 static void hmac_sha1_pad (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5])
222 w0[0] = w0[0] ^ 0x36363636;
223 w0[1] = w0[1] ^ 0x36363636;
224 w0[2] = w0[2] ^ 0x36363636;
225 w0[3] = w0[3] ^ 0x36363636;
226 w1[0] = w1[0] ^ 0x36363636;
227 w1[1] = w1[1] ^ 0x36363636;
228 w1[2] = w1[2] ^ 0x36363636;
229 w1[3] = w1[3] ^ 0x36363636;
230 w2[0] = w2[0] ^ 0x36363636;
231 w2[1] = w2[1] ^ 0x36363636;
232 w2[2] = w2[2] ^ 0x36363636;
233 w2[3] = w2[3] ^ 0x36363636;
234 w3[0] = w3[0] ^ 0x36363636;
235 w3[1] = w3[1] ^ 0x36363636;
236 w3[2] = w3[2] ^ 0x36363636;
237 w3[3] = w3[3] ^ 0x36363636;
245 sha1_transform (w0, w1, w2, w3, ipad);
247 w0[0] = w0[0] ^ 0x6a6a6a6a;
248 w0[1] = w0[1] ^ 0x6a6a6a6a;
249 w0[2] = w0[2] ^ 0x6a6a6a6a;
250 w0[3] = w0[3] ^ 0x6a6a6a6a;
251 w1[0] = w1[0] ^ 0x6a6a6a6a;
252 w1[1] = w1[1] ^ 0x6a6a6a6a;
253 w1[2] = w1[2] ^ 0x6a6a6a6a;
254 w1[3] = w1[3] ^ 0x6a6a6a6a;
255 w2[0] = w2[0] ^ 0x6a6a6a6a;
256 w2[1] = w2[1] ^ 0x6a6a6a6a;
257 w2[2] = w2[2] ^ 0x6a6a6a6a;
258 w2[3] = w2[3] ^ 0x6a6a6a6a;
259 w3[0] = w3[0] ^ 0x6a6a6a6a;
260 w3[1] = w3[1] ^ 0x6a6a6a6a;
261 w3[2] = w3[2] ^ 0x6a6a6a6a;
262 w3[3] = w3[3] ^ 0x6a6a6a6a;
270 sha1_transform (w0, w1, w2, w3, opad);
273 static void hmac_sha1_run (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], u32 ipad[5], u32 opad[5], u32 digest[5])
281 sha1_transform (w0, w1, w2, w3, digest);
298 w3[3] = (64 + 20) * 8;
306 sha1_transform (w0, w1, w2, w3, digest);
309 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m02100_init (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global dcc2_tmp_t *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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
315 const u32 gid = get_global_id (0);
317 if (gid >= gid_max) return;
321 w0[0] = pws[gid].i[ 0];
322 w0[1] = pws[gid].i[ 1];
323 w0[2] = pws[gid].i[ 2];
324 w0[3] = pws[gid].i[ 3];
347 const u32 pw_len = pws[gid].pw_len;
353 u32 salt_len = salt_bufs[salt_pos].salt_len;
359 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[0];
360 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[1];
361 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[2];
362 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[3];
363 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[4];
364 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[5];
365 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[6];
366 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[7];
367 salt_buf2[0] = salt_bufs[salt_pos].salt_buf[8];
368 salt_buf2[1] = salt_bufs[salt_pos].salt_buf[9];
376 append_0x80_1 (w0, pw_len);
378 make_unicode (w0, w0, w1);
380 w3[2] = pw_len * 2 * 8;
384 digest_md4[0] = MD4M_A;
385 digest_md4[1] = MD4M_B;
386 digest_md4[2] = MD4M_C;
387 digest_md4[3] = MD4M_D;
389 md4_transform (w0, w1, w2, w3, digest_md4);
391 w0[0] = digest_md4[0];
392 w0[1] = digest_md4[1];
393 w0[2] = digest_md4[2];
394 w0[3] = digest_md4[3];
395 w1[0] = salt_buf0[0];
396 w1[1] = salt_buf0[1];
397 w1[2] = salt_buf0[2];
398 w1[3] = salt_buf0[3];
399 w2[0] = salt_buf1[0];
400 w2[1] = salt_buf1[1];
401 w2[2] = salt_buf1[2];
402 w2[3] = salt_buf1[3];
403 w3[0] = salt_buf2[0];
404 w3[1] = salt_buf2[1];
405 w3[2] = (16 + salt_len) * 8;
408 append_0x80_4 (w0, w1, w2, w3, 16 + salt_len);
410 digest_md4[0] = MD4M_A;
411 digest_md4[1] = MD4M_B;
412 digest_md4[2] = MD4M_C;
413 digest_md4[3] = MD4M_D;
415 md4_transform (w0, w1, w2, w3, digest_md4);
421 w0[0] = swap_workaround (digest_md4[0]);
422 w0[1] = swap_workaround (digest_md4[1]);
423 w0[2] = swap_workaround (digest_md4[2]);
424 w0[3] = swap_workaround (digest_md4[3]);
441 hmac_sha1_pad (w0, w1, w2, w3, ipad, opad);
443 tmps[gid].ipad[0] = ipad[0];
444 tmps[gid].ipad[1] = ipad[1];
445 tmps[gid].ipad[2] = ipad[2];
446 tmps[gid].ipad[3] = ipad[3];
447 tmps[gid].ipad[4] = ipad[4];
449 tmps[gid].opad[0] = opad[0];
450 tmps[gid].opad[1] = opad[1];
451 tmps[gid].opad[2] = opad[2];
452 tmps[gid].opad[3] = opad[3];
453 tmps[gid].opad[4] = opad[4];
459 w0[0] = salt_buf0[0];
460 w0[1] = salt_buf0[1];
461 w0[2] = salt_buf0[2];
462 w0[3] = salt_buf0[3];
463 w1[0] = salt_buf1[0];
464 w1[1] = salt_buf1[1];
465 w1[2] = salt_buf1[2];
466 w1[3] = salt_buf1[3];
467 w2[0] = salt_buf2[0];
468 w2[1] = salt_buf2[1];
474 w3[3] = (64 + salt_len + 4) * 8;
476 append_0x01_4 (w0, w1, w2, w3, salt_len + 3);
477 append_0x80_4 (w0, w1, w2, w3, salt_len + 4);
479 w0[0] = swap_workaround (w0[0]);
480 w0[1] = swap_workaround (w0[1]);
481 w0[2] = swap_workaround (w0[2]);
482 w0[3] = swap_workaround (w0[3]);
483 w1[0] = swap_workaround (w1[0]);
484 w1[1] = swap_workaround (w1[1]);
485 w1[2] = swap_workaround (w1[2]);
486 w1[3] = swap_workaround (w1[3]);
487 w2[0] = swap_workaround (w2[0]);
488 w2[1] = swap_workaround (w2[1]);
489 w2[2] = swap_workaround (w2[2]);
490 w2[3] = swap_workaround (w2[3]);
491 w3[0] = swap_workaround (w3[0]);
492 w3[1] = swap_workaround (w3[1]);
496 hmac_sha1_run (w0, w1, w2, w3, ipad, opad, digest);
498 tmps[gid].dgst[0] = digest[0];
499 tmps[gid].dgst[1] = digest[1];
500 tmps[gid].dgst[2] = digest[2];
501 tmps[gid].dgst[3] = digest[3];
502 tmps[gid].dgst[4] = digest[4];
504 tmps[gid].out[0] = digest[0];
505 tmps[gid].out[1] = digest[1];
506 tmps[gid].out[2] = digest[2];
507 tmps[gid].out[3] = digest[3];
510 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m02100_loop (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global dcc2_tmp_t *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 rules_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;
523 ipad[0] = tmps[gid].ipad[0];
524 ipad[1] = tmps[gid].ipad[1];
525 ipad[2] = tmps[gid].ipad[2];
526 ipad[3] = tmps[gid].ipad[3];
527 ipad[4] = tmps[gid].ipad[4];
529 opad[0] = tmps[gid].opad[0];
530 opad[1] = tmps[gid].opad[1];
531 opad[2] = tmps[gid].opad[2];
532 opad[3] = tmps[gid].opad[3];
533 opad[4] = tmps[gid].opad[4];
542 dgst[0] = tmps[gid].dgst[0];
543 dgst[1] = tmps[gid].dgst[1];
544 dgst[2] = tmps[gid].dgst[2];
545 dgst[3] = tmps[gid].dgst[3];
546 dgst[4] = tmps[gid].dgst[4];
548 out[0] = tmps[gid].out[0];
549 out[1] = tmps[gid].out[1];
550 out[2] = tmps[gid].out[2];
551 out[3] = tmps[gid].out[3];
553 for (u32 i = 0; i < loop_cnt; i++)
575 w3[3] = (64 + 20) * 8;
577 hmac_sha1_run (w0, w1, w2, w3, ipad, opad, dgst);
585 tmps[gid].dgst[0] = dgst[0];
586 tmps[gid].dgst[1] = dgst[1];
587 tmps[gid].dgst[2] = dgst[2];
588 tmps[gid].dgst[3] = dgst[3];
589 tmps[gid].dgst[4] = dgst[4];
591 tmps[gid].out[0] = out[0];
592 tmps[gid].out[1] = out[1];
593 tmps[gid].out[2] = out[2];
594 tmps[gid].out[3] = out[3];
597 __kernel void __attribute__((reqd_work_group_size (64, 1, 1))) m02100_comp (__global pw_t *pws, __global gpu_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global dcc2_tmp_t *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 rules_cnt, const u32 digests_cnt, const u32 digests_offset, const u32 combs_mode, const u32 gid_max)
603 const u32 gid = get_global_id (0);
605 if (gid >= gid_max) return;
607 const u32 lid = get_local_id (0);
609 const u32 r0 = tmps[gid].out[DGST_R0];
610 const u32 r1 = tmps[gid].out[DGST_R1];
611 const u32 r2 = tmps[gid].out[DGST_R2];
612 const u32 r3 = tmps[gid].out[DGST_R3];