2 * Author......: Jens Steube <jens.steube@gmail.com>
10 #include "include/constants.h"
11 #include "include/kernel_vendor.h"
18 #include "include/kernel_functions.c"
19 #include "OpenCL/types_ocl.c"
20 #include "OpenCL/common.c"
21 #include "OpenCL/simd.c"
25 __kernel void m00040_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)
31 const u32 lid = get_local_id (0);
37 const u32 gid = get_global_id (0);
39 if (gid >= gid_max) return;
44 pw_buf0[0] = pws[gid].i[0];
45 pw_buf0[1] = pws[gid].i[1];
46 pw_buf0[2] = pws[gid].i[2];
47 pw_buf0[3] = pws[gid].i[3];
48 pw_buf1[0] = pws[gid].i[4];
49 pw_buf1[1] = pws[gid].i[5];
50 pw_buf1[2] = pws[gid].i[6];
51 pw_buf1[3] = pws[gid].i[7];
53 const u32 pw_l_len = pws[gid].pw_len;
64 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
65 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
66 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
67 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
68 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
69 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
70 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
71 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
72 salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
73 salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
74 salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
75 salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
76 salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
77 salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
78 salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
79 salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
81 const u32 salt_len = salt_bufs[salt_pos].salt_len;
87 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
89 const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
91 const u32x pw_len = pw_l_len + pw_r_len;
94 * concat password candidate
97 u32x wordl0[4] = { 0 };
98 u32x wordl1[4] = { 0 };
99 u32x wordl2[4] = { 0 };
100 u32x wordl3[4] = { 0 };
102 wordl0[0] = pw_buf0[0];
103 wordl0[1] = pw_buf0[1];
104 wordl0[2] = pw_buf0[2];
105 wordl0[3] = pw_buf0[3];
106 wordl1[0] = pw_buf1[0];
107 wordl1[1] = pw_buf1[1];
108 wordl1[2] = pw_buf1[2];
109 wordl1[3] = pw_buf1[3];
111 u32x wordr0[4] = { 0 };
112 u32x wordr1[4] = { 0 };
113 u32x wordr2[4] = { 0 };
114 u32x wordr3[4] = { 0 };
116 wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
117 wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
118 wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
119 wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
120 wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
121 wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
122 wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
123 wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
125 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
127 switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
131 switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
139 w0[0] = wordl0[0] | wordr0[0];
140 w0[1] = wordl0[1] | wordr0[1];
141 w0[2] = wordl0[2] | wordr0[2];
142 w0[3] = wordl0[3] | wordr0[3];
143 w1[0] = wordl1[0] | wordr1[0];
144 w1[1] = wordl1[1] | wordr1[1];
145 w1[2] = wordl1[2] | wordr1[2];
146 w1[3] = wordl1[3] | wordr1[3];
147 w2[0] = wordl2[0] | wordr2[0];
148 w2[1] = wordl2[1] | wordr2[1];
149 w2[2] = wordl2[2] | wordr2[2];
150 w2[3] = wordl2[3] | wordr2[3];
151 w3[0] = wordl3[0] | wordr3[0];
152 w3[1] = wordl3[1] | wordr3[1];
153 w3[2] = wordl3[2] | wordr3[2];
154 w3[3] = wordl3[3] | wordr3[3];
156 make_unicode (w1, w2, w3);
157 make_unicode (w0, w0, w1);
159 const u32x pw_len2 = pw_len * 2;
165 switch_buffer_by_offset_le (w0, w1, w2, w3, salt_len);
167 const u32x pw_salt_len = pw_len2 + salt_len;
169 w0[0] |= salt_buf0[0];
170 w0[1] |= salt_buf0[1];
171 w0[2] |= salt_buf0[2];
172 w0[3] |= salt_buf0[3];
173 w1[0] |= salt_buf1[0];
174 w1[1] |= salt_buf1[1];
175 w1[2] |= salt_buf1[2];
176 w1[3] |= salt_buf1[3];
177 w2[0] |= salt_buf2[0];
178 w2[1] |= salt_buf2[1];
179 w2[2] |= salt_buf2[2];
180 w2[3] |= salt_buf2[3];
181 w3[0] |= salt_buf3[0];
182 w3[1] |= salt_buf3[1];
183 w3[2] = pw_salt_len * 8;
195 MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
196 MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
197 MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
198 MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
199 MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
200 MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
201 MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
202 MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
203 MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
204 MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
205 MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
206 MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
207 MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
208 MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
209 MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
210 MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
212 MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
213 MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
214 MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
215 MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
216 MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
217 MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
218 MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
219 MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
220 MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
221 MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
222 MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
223 MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
224 MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
225 MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
226 MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
227 MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
229 MD5_STEP (MD5_H , a, b, c, d, w1[1], MD5C20, MD5S20);
230 MD5_STEP (MD5_H , d, a, b, c, w2[0], MD5C21, MD5S21);
231 MD5_STEP (MD5_H , c, d, a, b, w2[3], MD5C22, MD5S22);
232 MD5_STEP (MD5_H , b, c, d, a, w3[2], MD5C23, MD5S23);
233 MD5_STEP (MD5_H , a, b, c, d, w0[1], MD5C24, MD5S20);
234 MD5_STEP (MD5_H , d, a, b, c, w1[0], MD5C25, MD5S21);
235 MD5_STEP (MD5_H , c, d, a, b, w1[3], MD5C26, MD5S22);
236 MD5_STEP (MD5_H , b, c, d, a, w2[2], MD5C27, MD5S23);
237 MD5_STEP (MD5_H , a, b, c, d, w3[1], MD5C28, MD5S20);
238 MD5_STEP (MD5_H , d, a, b, c, w0[0], MD5C29, MD5S21);
239 MD5_STEP (MD5_H , c, d, a, b, w0[3], MD5C2a, MD5S22);
240 MD5_STEP (MD5_H , b, c, d, a, w1[2], MD5C2b, MD5S23);
241 MD5_STEP (MD5_H , a, b, c, d, w2[1], MD5C2c, MD5S20);
242 MD5_STEP (MD5_H , d, a, b, c, w3[0], MD5C2d, MD5S21);
243 MD5_STEP (MD5_H , c, d, a, b, w3[3], MD5C2e, MD5S22);
244 MD5_STEP (MD5_H , b, c, d, a, w0[2], MD5C2f, MD5S23);
246 MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
247 MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
248 MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
249 MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
250 MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
251 MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
252 MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
253 MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
254 MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
255 MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
256 MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
257 MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
258 MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
259 MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
260 MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
261 MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
263 COMPARE_M_SIMD (a, d, c, b);
267 __kernel void m00040_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)
271 __kernel void m00040_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)
275 __kernel void m00040_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)
281 const u32 lid = get_local_id (0);
287 const u32 gid = get_global_id (0);
289 if (gid >= gid_max) return;
294 pw_buf0[0] = pws[gid].i[0];
295 pw_buf0[1] = pws[gid].i[1];
296 pw_buf0[2] = pws[gid].i[2];
297 pw_buf0[3] = pws[gid].i[3];
298 pw_buf1[0] = pws[gid].i[4];
299 pw_buf1[1] = pws[gid].i[5];
300 pw_buf1[2] = pws[gid].i[6];
301 pw_buf1[3] = pws[gid].i[7];
303 const u32 pw_l_len = pws[gid].pw_len;
314 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
315 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
316 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
317 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
318 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
319 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
320 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
321 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
322 salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
323 salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
324 salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
325 salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
326 salt_buf3[0] = salt_bufs[salt_pos].salt_buf[12];
327 salt_buf3[1] = salt_bufs[salt_pos].salt_buf[13];
328 salt_buf3[2] = salt_bufs[salt_pos].salt_buf[14];
329 salt_buf3[3] = salt_bufs[salt_pos].salt_buf[15];
331 const u32 salt_len = salt_bufs[salt_pos].salt_len;
337 const u32 search[4] =
339 digests_buf[digests_offset].digest_buf[DGST_R0],
340 digests_buf[digests_offset].digest_buf[DGST_R1],
341 digests_buf[digests_offset].digest_buf[DGST_R2],
342 digests_buf[digests_offset].digest_buf[DGST_R3]
349 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
351 const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
353 const u32x pw_len = pw_l_len + pw_r_len;
356 * concat password candidate
359 u32x wordl0[4] = { 0 };
360 u32x wordl1[4] = { 0 };
361 u32x wordl2[4] = { 0 };
362 u32x wordl3[4] = { 0 };
364 wordl0[0] = pw_buf0[0];
365 wordl0[1] = pw_buf0[1];
366 wordl0[2] = pw_buf0[2];
367 wordl0[3] = pw_buf0[3];
368 wordl1[0] = pw_buf1[0];
369 wordl1[1] = pw_buf1[1];
370 wordl1[2] = pw_buf1[2];
371 wordl1[3] = pw_buf1[3];
373 u32x wordr0[4] = { 0 };
374 u32x wordr1[4] = { 0 };
375 u32x wordr2[4] = { 0 };
376 u32x wordr3[4] = { 0 };
378 wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
379 wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
380 wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
381 wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
382 wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
383 wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
384 wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
385 wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
387 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
389 switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
393 switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
401 w0[0] = wordl0[0] | wordr0[0];
402 w0[1] = wordl0[1] | wordr0[1];
403 w0[2] = wordl0[2] | wordr0[2];
404 w0[3] = wordl0[3] | wordr0[3];
405 w1[0] = wordl1[0] | wordr1[0];
406 w1[1] = wordl1[1] | wordr1[1];
407 w1[2] = wordl1[2] | wordr1[2];
408 w1[3] = wordl1[3] | wordr1[3];
409 w2[0] = wordl2[0] | wordr2[0];
410 w2[1] = wordl2[1] | wordr2[1];
411 w2[2] = wordl2[2] | wordr2[2];
412 w2[3] = wordl2[3] | wordr2[3];
413 w3[0] = wordl3[0] | wordr3[0];
414 w3[1] = wordl3[1] | wordr3[1];
415 w3[2] = wordl3[2] | wordr3[2];
416 w3[3] = wordl3[3] | wordr3[3];
418 make_unicode (w1, w2, w3);
419 make_unicode (w0, w0, w1);
421 const u32x pw_len2 = pw_len * 2;
427 switch_buffer_by_offset_le (w0, w1, w2, w3, salt_len);
429 const u32x pw_salt_len = pw_len2 + salt_len;
431 w0[0] |= salt_buf0[0];
432 w0[1] |= salt_buf0[1];
433 w0[2] |= salt_buf0[2];
434 w0[3] |= salt_buf0[3];
435 w1[0] |= salt_buf1[0];
436 w1[1] |= salt_buf1[1];
437 w1[2] |= salt_buf1[2];
438 w1[3] |= salt_buf1[3];
439 w2[0] |= salt_buf2[0];
440 w2[1] |= salt_buf2[1];
441 w2[2] |= salt_buf2[2];
442 w2[3] |= salt_buf2[3];
443 w3[0] |= salt_buf3[0];
444 w3[1] |= salt_buf3[1];
445 w3[2] = pw_salt_len * 8;
457 MD5_STEP (MD5_Fo, a, b, c, d, w0[0], MD5C00, MD5S00);
458 MD5_STEP (MD5_Fo, d, a, b, c, w0[1], MD5C01, MD5S01);
459 MD5_STEP (MD5_Fo, c, d, a, b, w0[2], MD5C02, MD5S02);
460 MD5_STEP (MD5_Fo, b, c, d, a, w0[3], MD5C03, MD5S03);
461 MD5_STEP (MD5_Fo, a, b, c, d, w1[0], MD5C04, MD5S00);
462 MD5_STEP (MD5_Fo, d, a, b, c, w1[1], MD5C05, MD5S01);
463 MD5_STEP (MD5_Fo, c, d, a, b, w1[2], MD5C06, MD5S02);
464 MD5_STEP (MD5_Fo, b, c, d, a, w1[3], MD5C07, MD5S03);
465 MD5_STEP (MD5_Fo, a, b, c, d, w2[0], MD5C08, MD5S00);
466 MD5_STEP (MD5_Fo, d, a, b, c, w2[1], MD5C09, MD5S01);
467 MD5_STEP (MD5_Fo, c, d, a, b, w2[2], MD5C0a, MD5S02);
468 MD5_STEP (MD5_Fo, b, c, d, a, w2[3], MD5C0b, MD5S03);
469 MD5_STEP (MD5_Fo, a, b, c, d, w3[0], MD5C0c, MD5S00);
470 MD5_STEP (MD5_Fo, d, a, b, c, w3[1], MD5C0d, MD5S01);
471 MD5_STEP (MD5_Fo, c, d, a, b, w3[2], MD5C0e, MD5S02);
472 MD5_STEP (MD5_Fo, b, c, d, a, w3[3], MD5C0f, MD5S03);
474 MD5_STEP (MD5_Go, a, b, c, d, w0[1], MD5C10, MD5S10);
475 MD5_STEP (MD5_Go, d, a, b, c, w1[2], MD5C11, MD5S11);
476 MD5_STEP (MD5_Go, c, d, a, b, w2[3], MD5C12, MD5S12);
477 MD5_STEP (MD5_Go, b, c, d, a, w0[0], MD5C13, MD5S13);
478 MD5_STEP (MD5_Go, a, b, c, d, w1[1], MD5C14, MD5S10);
479 MD5_STEP (MD5_Go, d, a, b, c, w2[2], MD5C15, MD5S11);
480 MD5_STEP (MD5_Go, c, d, a, b, w3[3], MD5C16, MD5S12);
481 MD5_STEP (MD5_Go, b, c, d, a, w1[0], MD5C17, MD5S13);
482 MD5_STEP (MD5_Go, a, b, c, d, w2[1], MD5C18, MD5S10);
483 MD5_STEP (MD5_Go, d, a, b, c, w3[2], MD5C19, MD5S11);
484 MD5_STEP (MD5_Go, c, d, a, b, w0[3], MD5C1a, MD5S12);
485 MD5_STEP (MD5_Go, b, c, d, a, w2[0], MD5C1b, MD5S13);
486 MD5_STEP (MD5_Go, a, b, c, d, w3[1], MD5C1c, MD5S10);
487 MD5_STEP (MD5_Go, d, a, b, c, w0[2], MD5C1d, MD5S11);
488 MD5_STEP (MD5_Go, c, d, a, b, w1[3], MD5C1e, MD5S12);
489 MD5_STEP (MD5_Go, b, c, d, a, w3[0], MD5C1f, MD5S13);
491 MD5_STEP (MD5_H , a, b, c, d, w1[1], MD5C20, MD5S20);
492 MD5_STEP (MD5_H , d, a, b, c, w2[0], MD5C21, MD5S21);
493 MD5_STEP (MD5_H , c, d, a, b, w2[3], MD5C22, MD5S22);
494 MD5_STEP (MD5_H , b, c, d, a, w3[2], MD5C23, MD5S23);
495 MD5_STEP (MD5_H , a, b, c, d, w0[1], MD5C24, MD5S20);
496 MD5_STEP (MD5_H , d, a, b, c, w1[0], MD5C25, MD5S21);
497 MD5_STEP (MD5_H , c, d, a, b, w1[3], MD5C26, MD5S22);
498 MD5_STEP (MD5_H , b, c, d, a, w2[2], MD5C27, MD5S23);
499 MD5_STEP (MD5_H , a, b, c, d, w3[1], MD5C28, MD5S20);
500 MD5_STEP (MD5_H , d, a, b, c, w0[0], MD5C29, MD5S21);
501 MD5_STEP (MD5_H , c, d, a, b, w0[3], MD5C2a, MD5S22);
502 MD5_STEP (MD5_H , b, c, d, a, w1[2], MD5C2b, MD5S23);
503 MD5_STEP (MD5_H , a, b, c, d, w2[1], MD5C2c, MD5S20);
504 MD5_STEP (MD5_H , d, a, b, c, w3[0], MD5C2d, MD5S21);
505 MD5_STEP (MD5_H , c, d, a, b, w3[3], MD5C2e, MD5S22);
506 MD5_STEP (MD5_H , b, c, d, a, w0[2], MD5C2f, MD5S23);
508 MD5_STEP (MD5_I , a, b, c, d, w0[0], MD5C30, MD5S30);
509 MD5_STEP (MD5_I , d, a, b, c, w1[3], MD5C31, MD5S31);
510 MD5_STEP (MD5_I , c, d, a, b, w3[2], MD5C32, MD5S32);
511 MD5_STEP (MD5_I , b, c, d, a, w1[1], MD5C33, MD5S33);
512 MD5_STEP (MD5_I , a, b, c, d, w3[0], MD5C34, MD5S30);
513 MD5_STEP (MD5_I , d, a, b, c, w0[3], MD5C35, MD5S31);
514 MD5_STEP (MD5_I , c, d, a, b, w2[2], MD5C36, MD5S32);
515 MD5_STEP (MD5_I , b, c, d, a, w0[1], MD5C37, MD5S33);
516 MD5_STEP (MD5_I , a, b, c, d, w2[0], MD5C38, MD5S30);
517 MD5_STEP (MD5_I , d, a, b, c, w3[3], MD5C39, MD5S31);
518 MD5_STEP (MD5_I , c, d, a, b, w1[2], MD5C3a, MD5S32);
519 MD5_STEP (MD5_I , b, c, d, a, w3[1], MD5C3b, MD5S33);
520 MD5_STEP (MD5_I , a, b, c, d, w1[0], MD5C3c, MD5S30);
522 if (MATCHES_NONE_VS (a, search[0])) continue;
524 MD5_STEP (MD5_I , d, a, b, c, w2[3], MD5C3d, MD5S31);
525 MD5_STEP (MD5_I , c, d, a, b, w0[2], MD5C3e, MD5S32);
526 MD5_STEP (MD5_I , b, c, d, a, w2[1], MD5C3f, MD5S33);
528 COMPARE_S_SIMD (a, d, c, b);
532 __kernel void m00040_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)
536 __kernel void m00040_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)