2 * Authors.....: Jens Steube <jens.steube@gmail.com>
3 * magnum <john.magnum@hushmail.com>
12 #include "include/constants.h"
13 #include "include/kernel_vendor.h"
20 #include "include/kernel_functions.c"
21 #include "OpenCL/types_ocl.c"
22 #include "OpenCL/common.c"
23 #include "include/rp_kernel.h"
24 #include "OpenCL/rp.c"
25 #include "OpenCL/simd.c"
28 #define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i)])
30 #define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
32 #define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
34 #define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7])
36 #define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
39 __kernel void m11100_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)
45 const u32 gid = get_global_id (0);
46 const u32 lid = get_local_id (0);
47 const u32 lsz = get_local_size (0);
53 __local u32 l_bin2asc[256];
55 for (u32 i = lid; i < 256; i += lsz)
57 const u32 i0 = (i >> 0) & 15;
58 const u32 i1 = (i >> 4) & 15;
60 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
61 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
64 barrier (CLK_LOCAL_MEM_FENCE);
66 if (gid >= gid_max) return;
74 pw_buf0[0] = pws[gid].i[ 0];
75 pw_buf0[1] = pws[gid].i[ 1];
76 pw_buf0[2] = pws[gid].i[ 2];
77 pw_buf0[3] = pws[gid].i[ 3];
81 pw_buf1[0] = pws[gid].i[ 4];
82 pw_buf1[1] = pws[gid].i[ 5];
83 pw_buf1[2] = pws[gid].i[ 6];
84 pw_buf1[3] = pws[gid].i[ 7];
86 const u32 pw_len = pws[gid].pw_len;
94 challenge = salt_bufs[salt_pos].salt_buf[0];
102 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 1]; // not a bug
103 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 2];
104 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 3];
105 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 4];
109 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 5];
110 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 6];
111 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 7];
112 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 8];
114 const u32 salt_len = salt_bufs[salt_pos].salt_len - 4;
120 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
127 const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
131 w0_t[0] = salt_buf0[0];
132 w0_t[1] = salt_buf0[1];
133 w0_t[2] = salt_buf0[2];
134 w0_t[3] = salt_buf0[3];
138 w1_t[0] = salt_buf1[0];
139 w1_t[1] = salt_buf1[1];
140 w1_t[2] = salt_buf1[2];
141 w1_t[3] = salt_buf1[3];
161 switch_buffer_by_offset_le_VV (w0_t, w1_t, w2_t, w3_t, out_len);
163 const u32x pw_salt_len = out_len + salt_len;
182 w3_t[2] = pw_salt_len * 8;
194 MD5_STEP (MD5_Fo, a, b, c, d, w0_t[0], MD5C00, MD5S00);
195 MD5_STEP (MD5_Fo, d, a, b, c, w0_t[1], MD5C01, MD5S01);
196 MD5_STEP (MD5_Fo, c, d, a, b, w0_t[2], MD5C02, MD5S02);
197 MD5_STEP (MD5_Fo, b, c, d, a, w0_t[3], MD5C03, MD5S03);
198 MD5_STEP (MD5_Fo, a, b, c, d, w1_t[0], MD5C04, MD5S00);
199 MD5_STEP (MD5_Fo, d, a, b, c, w1_t[1], MD5C05, MD5S01);
200 MD5_STEP (MD5_Fo, c, d, a, b, w1_t[2], MD5C06, MD5S02);
201 MD5_STEP (MD5_Fo, b, c, d, a, w1_t[3], MD5C07, MD5S03);
202 MD5_STEP (MD5_Fo, a, b, c, d, w2_t[0], MD5C08, MD5S00);
203 MD5_STEP (MD5_Fo, d, a, b, c, w2_t[1], MD5C09, MD5S01);
204 MD5_STEP (MD5_Fo, c, d, a, b, w2_t[2], MD5C0a, MD5S02);
205 MD5_STEP (MD5_Fo, b, c, d, a, w2_t[3], MD5C0b, MD5S03);
206 MD5_STEP (MD5_Fo, a, b, c, d, w3_t[0], MD5C0c, MD5S00);
207 MD5_STEP (MD5_Fo, d, a, b, c, w3_t[1], MD5C0d, MD5S01);
208 MD5_STEP (MD5_Fo, c, d, a, b, w3_t[2], MD5C0e, MD5S02);
209 MD5_STEP (MD5_Fo, b, c, d, a, w3_t[3], MD5C0f, MD5S03);
211 MD5_STEP (MD5_Go, a, b, c, d, w0_t[1], MD5C10, MD5S10);
212 MD5_STEP (MD5_Go, d, a, b, c, w1_t[2], MD5C11, MD5S11);
213 MD5_STEP (MD5_Go, c, d, a, b, w2_t[3], MD5C12, MD5S12);
214 MD5_STEP (MD5_Go, b, c, d, a, w0_t[0], MD5C13, MD5S13);
215 MD5_STEP (MD5_Go, a, b, c, d, w1_t[1], MD5C14, MD5S10);
216 MD5_STEP (MD5_Go, d, a, b, c, w2_t[2], MD5C15, MD5S11);
217 MD5_STEP (MD5_Go, c, d, a, b, w3_t[3], MD5C16, MD5S12);
218 MD5_STEP (MD5_Go, b, c, d, a, w1_t[0], MD5C17, MD5S13);
219 MD5_STEP (MD5_Go, a, b, c, d, w2_t[1], MD5C18, MD5S10);
220 MD5_STEP (MD5_Go, d, a, b, c, w3_t[2], MD5C19, MD5S11);
221 MD5_STEP (MD5_Go, c, d, a, b, w0_t[3], MD5C1a, MD5S12);
222 MD5_STEP (MD5_Go, b, c, d, a, w2_t[0], MD5C1b, MD5S13);
223 MD5_STEP (MD5_Go, a, b, c, d, w3_t[1], MD5C1c, MD5S10);
224 MD5_STEP (MD5_Go, d, a, b, c, w0_t[2], MD5C1d, MD5S11);
225 MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
226 MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
228 MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
229 MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
230 MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
231 MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
232 MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
233 MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
234 MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
235 MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
236 MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
237 MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
238 MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
239 MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
240 MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
241 MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
242 MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
243 MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
245 MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
246 MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
247 MD5_STEP (MD5_I , c, d, a, b, w3_t[2], MD5C32, MD5S32);
248 MD5_STEP (MD5_I , b, c, d, a, w1_t[1], MD5C33, MD5S33);
249 MD5_STEP (MD5_I , a, b, c, d, w3_t[0], MD5C34, MD5S30);
250 MD5_STEP (MD5_I , d, a, b, c, w0_t[3], MD5C35, MD5S31);
251 MD5_STEP (MD5_I , c, d, a, b, w2_t[2], MD5C36, MD5S32);
252 MD5_STEP (MD5_I , b, c, d, a, w0_t[1], MD5C37, MD5S33);
253 MD5_STEP (MD5_I , a, b, c, d, w2_t[0], MD5C38, MD5S30);
254 MD5_STEP (MD5_I , d, a, b, c, w3_t[3], MD5C39, MD5S31);
255 MD5_STEP (MD5_I , c, d, a, b, w1_t[2], MD5C3a, MD5S32);
256 MD5_STEP (MD5_I , b, c, d, a, w3_t[1], MD5C3b, MD5S33);
257 MD5_STEP (MD5_I , a, b, c, d, w1_t[0], MD5C3c, MD5S30);
258 MD5_STEP (MD5_I , d, a, b, c, w2_t[3], MD5C3d, MD5S31);
259 MD5_STEP (MD5_I , c, d, a, b, w0_t[2], MD5C3e, MD5S32);
260 MD5_STEP (MD5_I , b, c, d, a, w2_t[1], MD5C3f, MD5S33);
267 w0_t[0] = uint_to_hex_lower8 ((a >> 0) & 255) << 0
268 | uint_to_hex_lower8 ((a >> 8) & 255) << 16;
269 w0_t[1] = uint_to_hex_lower8 ((a >> 16) & 255) << 0
270 | uint_to_hex_lower8 ((a >> 24) & 255) << 16;
271 w0_t[2] = uint_to_hex_lower8 ((b >> 0) & 255) << 0
272 | uint_to_hex_lower8 ((b >> 8) & 255) << 16;
273 w0_t[3] = uint_to_hex_lower8 ((b >> 16) & 255) << 0
274 | uint_to_hex_lower8 ((b >> 24) & 255) << 16;
275 w1_t[0] = uint_to_hex_lower8 ((c >> 0) & 255) << 0
276 | uint_to_hex_lower8 ((c >> 8) & 255) << 16;
277 w1_t[1] = uint_to_hex_lower8 ((c >> 16) & 255) << 0
278 | uint_to_hex_lower8 ((c >> 24) & 255) << 16;
279 w1_t[2] = uint_to_hex_lower8 ((d >> 0) & 255) << 0
280 | uint_to_hex_lower8 ((d >> 8) & 255) << 16;
281 w1_t[3] = uint_to_hex_lower8 ((d >> 16) & 255) << 0
282 | uint_to_hex_lower8 ((d >> 24) & 255) << 16;
284 // add the 4 byte challenge here
287 w2_t[1] = 0x00000080;
293 w3_t[2] = (32 + 4) * 8;
297 * md5 ($hash.$challenge)
305 MD5_STEP (MD5_Fo, a, b, c, d, w0_t[0], MD5C00, MD5S00);
306 MD5_STEP (MD5_Fo, d, a, b, c, w0_t[1], MD5C01, MD5S01);
307 MD5_STEP (MD5_Fo, c, d, a, b, w0_t[2], MD5C02, MD5S02);
308 MD5_STEP (MD5_Fo, b, c, d, a, w0_t[3], MD5C03, MD5S03);
309 MD5_STEP (MD5_Fo, a, b, c, d, w1_t[0], MD5C04, MD5S00);
310 MD5_STEP (MD5_Fo, d, a, b, c, w1_t[1], MD5C05, MD5S01);
311 MD5_STEP (MD5_Fo, c, d, a, b, w1_t[2], MD5C06, MD5S02);
312 MD5_STEP (MD5_Fo, b, c, d, a, w1_t[3], MD5C07, MD5S03);
313 MD5_STEP (MD5_Fo, a, b, c, d, w2_t[0], MD5C08, MD5S00);
314 MD5_STEP (MD5_Fo, d, a, b, c, w2_t[1], MD5C09, MD5S01);
315 MD5_STEP (MD5_Fo, c, d, a, b, w2_t[2], MD5C0a, MD5S02);
316 MD5_STEP (MD5_Fo, b, c, d, a, w2_t[3], MD5C0b, MD5S03);
317 MD5_STEP (MD5_Fo, a, b, c, d, w3_t[0], MD5C0c, MD5S00);
318 MD5_STEP (MD5_Fo, d, a, b, c, w3_t[1], MD5C0d, MD5S01);
319 MD5_STEP (MD5_Fo, c, d, a, b, w3_t[2], MD5C0e, MD5S02);
320 MD5_STEP (MD5_Fo, b, c, d, a, w3_t[3], MD5C0f, MD5S03);
322 MD5_STEP (MD5_Go, a, b, c, d, w0_t[1], MD5C10, MD5S10);
323 MD5_STEP (MD5_Go, d, a, b, c, w1_t[2], MD5C11, MD5S11);
324 MD5_STEP (MD5_Go, c, d, a, b, w2_t[3], MD5C12, MD5S12);
325 MD5_STEP (MD5_Go, b, c, d, a, w0_t[0], MD5C13, MD5S13);
326 MD5_STEP (MD5_Go, a, b, c, d, w1_t[1], MD5C14, MD5S10);
327 MD5_STEP (MD5_Go, d, a, b, c, w2_t[2], MD5C15, MD5S11);
328 MD5_STEP (MD5_Go, c, d, a, b, w3_t[3], MD5C16, MD5S12);
329 MD5_STEP (MD5_Go, b, c, d, a, w1_t[0], MD5C17, MD5S13);
330 MD5_STEP (MD5_Go, a, b, c, d, w2_t[1], MD5C18, MD5S10);
331 MD5_STEP (MD5_Go, d, a, b, c, w3_t[2], MD5C19, MD5S11);
332 MD5_STEP (MD5_Go, c, d, a, b, w0_t[3], MD5C1a, MD5S12);
333 MD5_STEP (MD5_Go, b, c, d, a, w2_t[0], MD5C1b, MD5S13);
334 MD5_STEP (MD5_Go, a, b, c, d, w3_t[1], MD5C1c, MD5S10);
335 MD5_STEP (MD5_Go, d, a, b, c, w0_t[2], MD5C1d, MD5S11);
336 MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
337 MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
339 MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
340 MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
341 MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
342 MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
343 MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
344 MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
345 MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
346 MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
347 MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
348 MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
349 MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
350 MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
351 MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
352 MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
353 MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
354 MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
356 MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
357 MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
358 MD5_STEP (MD5_I , c, d, a, b, w3_t[2], MD5C32, MD5S32);
359 MD5_STEP (MD5_I , b, c, d, a, w1_t[1], MD5C33, MD5S33);
360 MD5_STEP (MD5_I , a, b, c, d, w3_t[0], MD5C34, MD5S30);
361 MD5_STEP (MD5_I , d, a, b, c, w0_t[3], MD5C35, MD5S31);
362 MD5_STEP (MD5_I , c, d, a, b, w2_t[2], MD5C36, MD5S32);
363 MD5_STEP (MD5_I , b, c, d, a, w0_t[1], MD5C37, MD5S33);
364 MD5_STEP (MD5_I , a, b, c, d, w2_t[0], MD5C38, MD5S30);
365 MD5_STEP (MD5_I , d, a, b, c, w3_t[3], MD5C39, MD5S31);
366 MD5_STEP (MD5_I , c, d, a, b, w1_t[2], MD5C3a, MD5S32);
367 MD5_STEP (MD5_I , b, c, d, a, w3_t[1], MD5C3b, MD5S33);
368 MD5_STEP (MD5_I , a, b, c, d, w1_t[0], MD5C3c, MD5S30);
369 MD5_STEP (MD5_I , d, a, b, c, w2_t[3], MD5C3d, MD5S31);
370 MD5_STEP (MD5_I , c, d, a, b, w0_t[2], MD5C3e, MD5S32);
371 MD5_STEP (MD5_I , b, c, d, a, w2_t[1], MD5C3f, MD5S33);
373 COMPARE_M_SIMD (a, d, c, b);
377 __kernel void m11100_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)
381 __kernel void m11100_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)
385 __kernel void m11100_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)
391 const u32 gid = get_global_id (0);
392 const u32 lid = get_local_id (0);
393 const u32 lsz = get_local_size (0);
399 __local u32 l_bin2asc[256];
401 for (u32 i = lid; i < 256; i += lsz)
403 const u32 i0 = (i >> 0) & 15;
404 const u32 i1 = (i >> 4) & 15;
406 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
407 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
410 barrier (CLK_LOCAL_MEM_FENCE);
412 if (gid >= gid_max) return;
420 pw_buf0[0] = pws[gid].i[ 0];
421 pw_buf0[1] = pws[gid].i[ 1];
422 pw_buf0[2] = pws[gid].i[ 2];
423 pw_buf0[3] = pws[gid].i[ 3];
427 pw_buf1[0] = pws[gid].i[ 4];
428 pw_buf1[1] = pws[gid].i[ 5];
429 pw_buf1[2] = pws[gid].i[ 6];
430 pw_buf1[3] = pws[gid].i[ 7];
432 const u32 pw_len = pws[gid].pw_len;
440 challenge = salt_bufs[salt_pos].salt_buf[0];
448 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 1]; // not a bug
449 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 2];
450 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 3];
451 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 4];
455 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 5];
456 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 6];
457 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 7];
458 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 8];
460 const u32 salt_len = salt_bufs[salt_pos].salt_len - 4;
466 const u32 search[4] =
468 digests_buf[digests_offset].digest_buf[DGST_R0],
469 digests_buf[digests_offset].digest_buf[DGST_R1],
470 digests_buf[digests_offset].digest_buf[DGST_R2],
471 digests_buf[digests_offset].digest_buf[DGST_R3]
478 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
485 const u32x out_len = apply_rules_vect (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
489 w0_t[0] = salt_buf0[0];
490 w0_t[1] = salt_buf0[1];
491 w0_t[2] = salt_buf0[2];
492 w0_t[3] = salt_buf0[3];
496 w1_t[0] = salt_buf1[0];
497 w1_t[1] = salt_buf1[1];
498 w1_t[2] = salt_buf1[2];
499 w1_t[3] = salt_buf1[3];
519 switch_buffer_by_offset_le_VV (w0_t, w1_t, w2_t, w3_t, out_len);
521 const u32x pw_salt_len = out_len + salt_len;
540 w3_t[2] = pw_salt_len * 8;
552 MD5_STEP (MD5_Fo, a, b, c, d, w0_t[0], MD5C00, MD5S00);
553 MD5_STEP (MD5_Fo, d, a, b, c, w0_t[1], MD5C01, MD5S01);
554 MD5_STEP (MD5_Fo, c, d, a, b, w0_t[2], MD5C02, MD5S02);
555 MD5_STEP (MD5_Fo, b, c, d, a, w0_t[3], MD5C03, MD5S03);
556 MD5_STEP (MD5_Fo, a, b, c, d, w1_t[0], MD5C04, MD5S00);
557 MD5_STEP (MD5_Fo, d, a, b, c, w1_t[1], MD5C05, MD5S01);
558 MD5_STEP (MD5_Fo, c, d, a, b, w1_t[2], MD5C06, MD5S02);
559 MD5_STEP (MD5_Fo, b, c, d, a, w1_t[3], MD5C07, MD5S03);
560 MD5_STEP (MD5_Fo, a, b, c, d, w2_t[0], MD5C08, MD5S00);
561 MD5_STEP (MD5_Fo, d, a, b, c, w2_t[1], MD5C09, MD5S01);
562 MD5_STEP (MD5_Fo, c, d, a, b, w2_t[2], MD5C0a, MD5S02);
563 MD5_STEP (MD5_Fo, b, c, d, a, w2_t[3], MD5C0b, MD5S03);
564 MD5_STEP (MD5_Fo, a, b, c, d, w3_t[0], MD5C0c, MD5S00);
565 MD5_STEP (MD5_Fo, d, a, b, c, w3_t[1], MD5C0d, MD5S01);
566 MD5_STEP (MD5_Fo, c, d, a, b, w3_t[2], MD5C0e, MD5S02);
567 MD5_STEP (MD5_Fo, b, c, d, a, w3_t[3], MD5C0f, MD5S03);
569 MD5_STEP (MD5_Go, a, b, c, d, w0_t[1], MD5C10, MD5S10);
570 MD5_STEP (MD5_Go, d, a, b, c, w1_t[2], MD5C11, MD5S11);
571 MD5_STEP (MD5_Go, c, d, a, b, w2_t[3], MD5C12, MD5S12);
572 MD5_STEP (MD5_Go, b, c, d, a, w0_t[0], MD5C13, MD5S13);
573 MD5_STEP (MD5_Go, a, b, c, d, w1_t[1], MD5C14, MD5S10);
574 MD5_STEP (MD5_Go, d, a, b, c, w2_t[2], MD5C15, MD5S11);
575 MD5_STEP (MD5_Go, c, d, a, b, w3_t[3], MD5C16, MD5S12);
576 MD5_STEP (MD5_Go, b, c, d, a, w1_t[0], MD5C17, MD5S13);
577 MD5_STEP (MD5_Go, a, b, c, d, w2_t[1], MD5C18, MD5S10);
578 MD5_STEP (MD5_Go, d, a, b, c, w3_t[2], MD5C19, MD5S11);
579 MD5_STEP (MD5_Go, c, d, a, b, w0_t[3], MD5C1a, MD5S12);
580 MD5_STEP (MD5_Go, b, c, d, a, w2_t[0], MD5C1b, MD5S13);
581 MD5_STEP (MD5_Go, a, b, c, d, w3_t[1], MD5C1c, MD5S10);
582 MD5_STEP (MD5_Go, d, a, b, c, w0_t[2], MD5C1d, MD5S11);
583 MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
584 MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
586 MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
587 MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
588 MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
589 MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
590 MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
591 MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
592 MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
593 MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
594 MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
595 MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
596 MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
597 MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
598 MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
599 MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
600 MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
601 MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
603 MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
604 MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
605 MD5_STEP (MD5_I , c, d, a, b, w3_t[2], MD5C32, MD5S32);
606 MD5_STEP (MD5_I , b, c, d, a, w1_t[1], MD5C33, MD5S33);
607 MD5_STEP (MD5_I , a, b, c, d, w3_t[0], MD5C34, MD5S30);
608 MD5_STEP (MD5_I , d, a, b, c, w0_t[3], MD5C35, MD5S31);
609 MD5_STEP (MD5_I , c, d, a, b, w2_t[2], MD5C36, MD5S32);
610 MD5_STEP (MD5_I , b, c, d, a, w0_t[1], MD5C37, MD5S33);
611 MD5_STEP (MD5_I , a, b, c, d, w2_t[0], MD5C38, MD5S30);
612 MD5_STEP (MD5_I , d, a, b, c, w3_t[3], MD5C39, MD5S31);
613 MD5_STEP (MD5_I , c, d, a, b, w1_t[2], MD5C3a, MD5S32);
614 MD5_STEP (MD5_I , b, c, d, a, w3_t[1], MD5C3b, MD5S33);
615 MD5_STEP (MD5_I , a, b, c, d, w1_t[0], MD5C3c, MD5S30);
616 MD5_STEP (MD5_I , d, a, b, c, w2_t[3], MD5C3d, MD5S31);
617 MD5_STEP (MD5_I , c, d, a, b, w0_t[2], MD5C3e, MD5S32);
618 MD5_STEP (MD5_I , b, c, d, a, w2_t[1], MD5C3f, MD5S33);
625 w0_t[0] = uint_to_hex_lower8 ((a >> 0) & 255) << 0
626 | uint_to_hex_lower8 ((a >> 8) & 255) << 16;
627 w0_t[1] = uint_to_hex_lower8 ((a >> 16) & 255) << 0
628 | uint_to_hex_lower8 ((a >> 24) & 255) << 16;
629 w0_t[2] = uint_to_hex_lower8 ((b >> 0) & 255) << 0
630 | uint_to_hex_lower8 ((b >> 8) & 255) << 16;
631 w0_t[3] = uint_to_hex_lower8 ((b >> 16) & 255) << 0
632 | uint_to_hex_lower8 ((b >> 24) & 255) << 16;
633 w1_t[0] = uint_to_hex_lower8 ((c >> 0) & 255) << 0
634 | uint_to_hex_lower8 ((c >> 8) & 255) << 16;
635 w1_t[1] = uint_to_hex_lower8 ((c >> 16) & 255) << 0
636 | uint_to_hex_lower8 ((c >> 24) & 255) << 16;
637 w1_t[2] = uint_to_hex_lower8 ((d >> 0) & 255) << 0
638 | uint_to_hex_lower8 ((d >> 8) & 255) << 16;
639 w1_t[3] = uint_to_hex_lower8 ((d >> 16) & 255) << 0
640 | uint_to_hex_lower8 ((d >> 24) & 255) << 16;
642 // add the 4 byte challenge here
645 w2_t[1] = 0x00000080;
651 w3_t[2] = (32 + 4) * 8;
655 * md5 ($hash.$challenge)
663 MD5_STEP (MD5_Fo, a, b, c, d, w0_t[0], MD5C00, MD5S00);
664 MD5_STEP (MD5_Fo, d, a, b, c, w0_t[1], MD5C01, MD5S01);
665 MD5_STEP (MD5_Fo, c, d, a, b, w0_t[2], MD5C02, MD5S02);
666 MD5_STEP (MD5_Fo, b, c, d, a, w0_t[3], MD5C03, MD5S03);
667 MD5_STEP (MD5_Fo, a, b, c, d, w1_t[0], MD5C04, MD5S00);
668 MD5_STEP (MD5_Fo, d, a, b, c, w1_t[1], MD5C05, MD5S01);
669 MD5_STEP (MD5_Fo, c, d, a, b, w1_t[2], MD5C06, MD5S02);
670 MD5_STEP (MD5_Fo, b, c, d, a, w1_t[3], MD5C07, MD5S03);
671 MD5_STEP (MD5_Fo, a, b, c, d, w2_t[0], MD5C08, MD5S00);
672 MD5_STEP (MD5_Fo, d, a, b, c, w2_t[1], MD5C09, MD5S01);
673 MD5_STEP (MD5_Fo, c, d, a, b, w2_t[2], MD5C0a, MD5S02);
674 MD5_STEP (MD5_Fo, b, c, d, a, w2_t[3], MD5C0b, MD5S03);
675 MD5_STEP (MD5_Fo, a, b, c, d, w3_t[0], MD5C0c, MD5S00);
676 MD5_STEP (MD5_Fo, d, a, b, c, w3_t[1], MD5C0d, MD5S01);
677 MD5_STEP (MD5_Fo, c, d, a, b, w3_t[2], MD5C0e, MD5S02);
678 MD5_STEP (MD5_Fo, b, c, d, a, w3_t[3], MD5C0f, MD5S03);
680 MD5_STEP (MD5_Go, a, b, c, d, w0_t[1], MD5C10, MD5S10);
681 MD5_STEP (MD5_Go, d, a, b, c, w1_t[2], MD5C11, MD5S11);
682 MD5_STEP (MD5_Go, c, d, a, b, w2_t[3], MD5C12, MD5S12);
683 MD5_STEP (MD5_Go, b, c, d, a, w0_t[0], MD5C13, MD5S13);
684 MD5_STEP (MD5_Go, a, b, c, d, w1_t[1], MD5C14, MD5S10);
685 MD5_STEP (MD5_Go, d, a, b, c, w2_t[2], MD5C15, MD5S11);
686 MD5_STEP (MD5_Go, c, d, a, b, w3_t[3], MD5C16, MD5S12);
687 MD5_STEP (MD5_Go, b, c, d, a, w1_t[0], MD5C17, MD5S13);
688 MD5_STEP (MD5_Go, a, b, c, d, w2_t[1], MD5C18, MD5S10);
689 MD5_STEP (MD5_Go, d, a, b, c, w3_t[2], MD5C19, MD5S11);
690 MD5_STEP (MD5_Go, c, d, a, b, w0_t[3], MD5C1a, MD5S12);
691 MD5_STEP (MD5_Go, b, c, d, a, w2_t[0], MD5C1b, MD5S13);
692 MD5_STEP (MD5_Go, a, b, c, d, w3_t[1], MD5C1c, MD5S10);
693 MD5_STEP (MD5_Go, d, a, b, c, w0_t[2], MD5C1d, MD5S11);
694 MD5_STEP (MD5_Go, c, d, a, b, w1_t[3], MD5C1e, MD5S12);
695 MD5_STEP (MD5_Go, b, c, d, a, w3_t[0], MD5C1f, MD5S13);
697 MD5_STEP (MD5_H , a, b, c, d, w1_t[1], MD5C20, MD5S20);
698 MD5_STEP (MD5_H , d, a, b, c, w2_t[0], MD5C21, MD5S21);
699 MD5_STEP (MD5_H , c, d, a, b, w2_t[3], MD5C22, MD5S22);
700 MD5_STEP (MD5_H , b, c, d, a, w3_t[2], MD5C23, MD5S23);
701 MD5_STEP (MD5_H , a, b, c, d, w0_t[1], MD5C24, MD5S20);
702 MD5_STEP (MD5_H , d, a, b, c, w1_t[0], MD5C25, MD5S21);
703 MD5_STEP (MD5_H , c, d, a, b, w1_t[3], MD5C26, MD5S22);
704 MD5_STEP (MD5_H , b, c, d, a, w2_t[2], MD5C27, MD5S23);
705 MD5_STEP (MD5_H , a, b, c, d, w3_t[1], MD5C28, MD5S20);
706 MD5_STEP (MD5_H , d, a, b, c, w0_t[0], MD5C29, MD5S21);
707 MD5_STEP (MD5_H , c, d, a, b, w0_t[3], MD5C2a, MD5S22);
708 MD5_STEP (MD5_H , b, c, d, a, w1_t[2], MD5C2b, MD5S23);
709 MD5_STEP (MD5_H , a, b, c, d, w2_t[1], MD5C2c, MD5S20);
710 MD5_STEP (MD5_H , d, a, b, c, w3_t[0], MD5C2d, MD5S21);
711 MD5_STEP (MD5_H , c, d, a, b, w3_t[3], MD5C2e, MD5S22);
712 MD5_STEP (MD5_H , b, c, d, a, w0_t[2], MD5C2f, MD5S23);
714 MD5_STEP (MD5_I , a, b, c, d, w0_t[0], MD5C30, MD5S30);
715 MD5_STEP (MD5_I , d, a, b, c, w1_t[3], MD5C31, MD5S31);
716 MD5_STEP (MD5_I , c, d, a, b, w3_t[2], MD5C32, MD5S32);
717 MD5_STEP (MD5_I , b, c, d, a, w1_t[1], MD5C33, MD5S33);
718 MD5_STEP (MD5_I , a, b, c, d, w3_t[0], MD5C34, MD5S30);
719 MD5_STEP (MD5_I , d, a, b, c, w0_t[3], MD5C35, MD5S31);
720 MD5_STEP (MD5_I , c, d, a, b, w2_t[2], MD5C36, MD5S32);
721 MD5_STEP (MD5_I , b, c, d, a, w0_t[1], MD5C37, MD5S33);
722 MD5_STEP (MD5_I , a, b, c, d, w2_t[0], MD5C38, MD5S30);
723 MD5_STEP (MD5_I , d, a, b, c, w3_t[3], MD5C39, MD5S31);
724 MD5_STEP (MD5_I , c, d, a, b, w1_t[2], MD5C3a, MD5S32);
725 MD5_STEP (MD5_I , b, c, d, a, w3_t[1], MD5C3b, MD5S33);
726 MD5_STEP (MD5_I , a, b, c, d, w1_t[0], MD5C3c, MD5S30);
727 MD5_STEP (MD5_I , d, a, b, c, w2_t[3], MD5C3d, MD5S31);
728 MD5_STEP (MD5_I , c, d, a, b, w0_t[2], MD5C3e, MD5S32);
729 MD5_STEP (MD5_I , b, c, d, a, w2_t[1], MD5C3f, MD5S33);
731 COMPARE_S_SIMD (a, d, c, b);
735 __kernel void m11100_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)
739 __kernel void m11100_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)