2 * Author......: Jens Steube <jens.steube@gmail.com>
10 #include "inc_vendor.cl"
11 #include "inc_hash_constants.h"
12 #include "inc_hash_functions.cl"
13 #include "inc_types.cl"
14 #include "inc_common.cl"
15 #include "inc_simd.cl"
18 #define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i)])
20 #define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1])
22 #define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3])
24 #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])
26 #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])
29 __kernel void m04400_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_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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)
35 const u32 gid = get_global_id (0);
36 const u32 lid = get_local_id (0);
37 const u32 lsz = get_local_size (0);
43 __local u32 l_bin2asc[256];
45 for (u32 i = lid; i < 256; i += lsz)
47 const u32 i0 = (i >> 0) & 15;
48 const u32 i1 = (i >> 4) & 15;
50 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
51 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
54 barrier (CLK_LOCAL_MEM_FENCE);
56 if (gid >= gid_max) return;
65 pw_buf0[0] = pws[gid].i[0];
66 pw_buf0[1] = pws[gid].i[1];
67 pw_buf0[2] = pws[gid].i[2];
68 pw_buf0[3] = pws[gid].i[3];
69 pw_buf1[0] = pws[gid].i[4];
70 pw_buf1[1] = pws[gid].i[5];
71 pw_buf1[2] = pws[gid].i[6];
72 pw_buf1[3] = pws[gid].i[7];
74 const u32 pw_l_len = pws[gid].pw_len;
80 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
82 const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
84 const u32x pw_len = pw_l_len + pw_r_len;
87 * concat password candidate
90 u32x wordl0[4] = { 0 };
91 u32x wordl1[4] = { 0 };
92 u32x wordl2[4] = { 0 };
93 u32x wordl3[4] = { 0 };
95 wordl0[0] = pw_buf0[0];
96 wordl0[1] = pw_buf0[1];
97 wordl0[2] = pw_buf0[2];
98 wordl0[3] = pw_buf0[3];
99 wordl1[0] = pw_buf1[0];
100 wordl1[1] = pw_buf1[1];
101 wordl1[2] = pw_buf1[2];
102 wordl1[3] = pw_buf1[3];
104 u32x wordr0[4] = { 0 };
105 u32x wordr1[4] = { 0 };
106 u32x wordr2[4] = { 0 };
107 u32x wordr3[4] = { 0 };
109 wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
110 wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
111 wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
112 wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
113 wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
114 wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
115 wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
116 wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
118 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
120 switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
124 switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
132 w0[0] = wordl0[0] | wordr0[0];
133 w0[1] = wordl0[1] | wordr0[1];
134 w0[2] = wordl0[2] | wordr0[2];
135 w0[3] = wordl0[3] | wordr0[3];
136 w1[0] = wordl1[0] | wordr1[0];
137 w1[1] = wordl1[1] | wordr1[1];
138 w1[2] = wordl1[2] | wordr1[2];
139 w1[3] = wordl1[3] | wordr1[3];
140 w2[0] = wordl2[0] | wordr2[0];
141 w2[1] = wordl2[1] | wordr2[1];
142 w2[2] = wordl2[2] | wordr2[2];
143 w2[3] = wordl2[3] | wordr2[3];
144 w3[0] = wordl3[0] | wordr3[0];
145 w3[1] = wordl3[1] | wordr3[1];
146 w3[2] = wordl3[2] | wordr3[2];
147 w3[3] = wordl3[3] | wordr3[3];
153 u32x w0_t = swap32 (w0[0]);
154 u32x w1_t = swap32 (w0[1]);
155 u32x w2_t = swap32 (w0[2]);
156 u32x w3_t = swap32 (w0[3]);
157 u32x w4_t = swap32 (w1[0]);
158 u32x w5_t = swap32 (w1[1]);
159 u32x w6_t = swap32 (w1[2]);
160 u32x w7_t = swap32 (w1[3]);
161 u32x w8_t = swap32 (w2[0]);
162 u32x w9_t = swap32 (w2[1]);
163 u32x wa_t = swap32 (w2[2]);
164 u32x wb_t = swap32 (w2[3]);
165 u32x wc_t = swap32 (w3[0]);
166 u32x wd_t = swap32 (w3[1]);
168 u32x wf_t = pw_len * 8;
179 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
180 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
181 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
182 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
183 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
184 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
185 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
186 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
187 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
188 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
189 SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
190 SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
191 SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
192 SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
193 SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
194 SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
195 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
196 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
197 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
198 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
203 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
204 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
205 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
206 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
207 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
208 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
209 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
210 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
211 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
212 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
213 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
214 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
215 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
216 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
217 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
218 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
219 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
220 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
221 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
222 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
227 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
228 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
229 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
230 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
231 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
232 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
233 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
234 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
235 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
236 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
237 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
238 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
239 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
240 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
241 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
242 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
243 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
244 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
245 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
246 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
251 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
252 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
253 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
254 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
255 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
256 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
257 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
258 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
259 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
260 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
261 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
262 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
263 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
264 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
265 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
266 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
267 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
268 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
269 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
270 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
282 w0_t = uint_to_hex_lower8 ((a >> 24) & 255) << 0
283 | uint_to_hex_lower8 ((a >> 16) & 255) << 16;
284 w1_t = uint_to_hex_lower8 ((a >> 8) & 255) << 0
285 | uint_to_hex_lower8 ((a >> 0) & 255) << 16;
286 w2_t = uint_to_hex_lower8 ((b >> 24) & 255) << 0
287 | uint_to_hex_lower8 ((b >> 16) & 255) << 16;
288 w3_t = uint_to_hex_lower8 ((b >> 8) & 255) << 0
289 | uint_to_hex_lower8 ((b >> 0) & 255) << 16;
290 w4_t = uint_to_hex_lower8 ((c >> 24) & 255) << 0
291 | uint_to_hex_lower8 ((c >> 16) & 255) << 16;
292 w5_t = uint_to_hex_lower8 ((c >> 8) & 255) << 0
293 | uint_to_hex_lower8 ((c >> 0) & 255) << 16;
294 w6_t = uint_to_hex_lower8 ((d >> 24) & 255) << 0
295 | uint_to_hex_lower8 ((d >> 16) & 255) << 16;
296 w7_t = uint_to_hex_lower8 ((d >> 8) & 255) << 0
297 | uint_to_hex_lower8 ((d >> 0) & 255) << 16;
298 w8_t = uint_to_hex_lower8 ((e >> 24) & 255) << 0
299 | uint_to_hex_lower8 ((e >> 16) & 255) << 16;
300 w9_t = uint_to_hex_lower8 ((e >> 8) & 255) << 0
301 | uint_to_hex_lower8 ((e >> 0) & 255) << 16;
315 MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
316 MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
317 MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
318 MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
319 MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
320 MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
321 MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
322 MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
323 MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
324 MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
325 MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
326 MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
327 MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
328 MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
329 MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
330 MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
332 MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
333 MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
334 MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
335 MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
336 MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
337 MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
338 MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
339 MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
340 MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
341 MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
342 MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
343 MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
344 MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
345 MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
346 MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
347 MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
349 MD5_STEP (MD5_H , a, b, c, d, w5_t, MD5C20, MD5S20);
350 MD5_STEP (MD5_H , d, a, b, c, w8_t, MD5C21, MD5S21);
351 MD5_STEP (MD5_H , c, d, a, b, wb_t, MD5C22, MD5S22);
352 MD5_STEP (MD5_H , b, c, d, a, we_t, MD5C23, MD5S23);
353 MD5_STEP (MD5_H , a, b, c, d, w1_t, MD5C24, MD5S20);
354 MD5_STEP (MD5_H , d, a, b, c, w4_t, MD5C25, MD5S21);
355 MD5_STEP (MD5_H , c, d, a, b, w7_t, MD5C26, MD5S22);
356 MD5_STEP (MD5_H , b, c, d, a, wa_t, MD5C27, MD5S23);
357 MD5_STEP (MD5_H , a, b, c, d, wd_t, MD5C28, MD5S20);
358 MD5_STEP (MD5_H , d, a, b, c, w0_t, MD5C29, MD5S21);
359 MD5_STEP (MD5_H , c, d, a, b, w3_t, MD5C2a, MD5S22);
360 MD5_STEP (MD5_H , b, c, d, a, w6_t, MD5C2b, MD5S23);
361 MD5_STEP (MD5_H , a, b, c, d, w9_t, MD5C2c, MD5S20);
362 MD5_STEP (MD5_H , d, a, b, c, wc_t, MD5C2d, MD5S21);
363 MD5_STEP (MD5_H , c, d, a, b, wf_t, MD5C2e, MD5S22);
364 MD5_STEP (MD5_H , b, c, d, a, w2_t, MD5C2f, MD5S23);
366 MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
367 MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
368 MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
369 MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
370 MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
371 MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
372 MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
373 MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
374 MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
375 MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
376 MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
377 MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
378 MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
379 MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
380 MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
381 MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
383 COMPARE_M_SIMD (a, d, c, b);
387 __kernel void m04400_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_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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 __kernel void m04400_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_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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)
395 __kernel void m04400_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_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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)
401 const u32 gid = get_global_id (0);
402 const u32 lid = get_local_id (0);
403 const u32 lsz = get_local_size (0);
409 __local u32 l_bin2asc[256];
411 for (u32 i = lid; i < 256; i += lsz)
413 const u32 i0 = (i >> 0) & 15;
414 const u32 i1 = (i >> 4) & 15;
416 l_bin2asc[i] = ((i0 < 10) ? '0' + i0 : 'a' - 10 + i0) << 8
417 | ((i1 < 10) ? '0' + i1 : 'a' - 10 + i1) << 0;
420 barrier (CLK_LOCAL_MEM_FENCE);
422 if (gid >= gid_max) return;
431 pw_buf0[0] = pws[gid].i[0];
432 pw_buf0[1] = pws[gid].i[1];
433 pw_buf0[2] = pws[gid].i[2];
434 pw_buf0[3] = pws[gid].i[3];
435 pw_buf1[0] = pws[gid].i[4];
436 pw_buf1[1] = pws[gid].i[5];
437 pw_buf1[2] = pws[gid].i[6];
438 pw_buf1[3] = pws[gid].i[7];
440 const u32 pw_l_len = pws[gid].pw_len;
446 const u32 search[4] =
448 digests_buf[digests_offset].digest_buf[DGST_R0],
449 digests_buf[digests_offset].digest_buf[DGST_R1],
450 digests_buf[digests_offset].digest_buf[DGST_R2],
451 digests_buf[digests_offset].digest_buf[DGST_R3]
458 for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
460 const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos);
462 const u32x pw_len = pw_l_len + pw_r_len;
465 * concat password candidate
468 u32x wordl0[4] = { 0 };
469 u32x wordl1[4] = { 0 };
470 u32x wordl2[4] = { 0 };
471 u32x wordl3[4] = { 0 };
473 wordl0[0] = pw_buf0[0];
474 wordl0[1] = pw_buf0[1];
475 wordl0[2] = pw_buf0[2];
476 wordl0[3] = pw_buf0[3];
477 wordl1[0] = pw_buf1[0];
478 wordl1[1] = pw_buf1[1];
479 wordl1[2] = pw_buf1[2];
480 wordl1[3] = pw_buf1[3];
482 u32x wordr0[4] = { 0 };
483 u32x wordr1[4] = { 0 };
484 u32x wordr2[4] = { 0 };
485 u32x wordr3[4] = { 0 };
487 wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
488 wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
489 wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
490 wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
491 wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
492 wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
493 wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
494 wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
496 if (combs_mode == COMBINATOR_MODE_BASE_LEFT)
498 switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
502 switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
510 w0[0] = wordl0[0] | wordr0[0];
511 w0[1] = wordl0[1] | wordr0[1];
512 w0[2] = wordl0[2] | wordr0[2];
513 w0[3] = wordl0[3] | wordr0[3];
514 w1[0] = wordl1[0] | wordr1[0];
515 w1[1] = wordl1[1] | wordr1[1];
516 w1[2] = wordl1[2] | wordr1[2];
517 w1[3] = wordl1[3] | wordr1[3];
518 w2[0] = wordl2[0] | wordr2[0];
519 w2[1] = wordl2[1] | wordr2[1];
520 w2[2] = wordl2[2] | wordr2[2];
521 w2[3] = wordl2[3] | wordr2[3];
522 w3[0] = wordl3[0] | wordr3[0];
523 w3[1] = wordl3[1] | wordr3[1];
524 w3[2] = wordl3[2] | wordr3[2];
525 w3[3] = wordl3[3] | wordr3[3];
531 u32x w0_t = swap32 (w0[0]);
532 u32x w1_t = swap32 (w0[1]);
533 u32x w2_t = swap32 (w0[2]);
534 u32x w3_t = swap32 (w0[3]);
535 u32x w4_t = swap32 (w1[0]);
536 u32x w5_t = swap32 (w1[1]);
537 u32x w6_t = swap32 (w1[2]);
538 u32x w7_t = swap32 (w1[3]);
539 u32x w8_t = swap32 (w2[0]);
540 u32x w9_t = swap32 (w2[1]);
541 u32x wa_t = swap32 (w2[2]);
542 u32x wb_t = swap32 (w2[3]);
543 u32x wc_t = swap32 (w3[0]);
544 u32x wd_t = swap32 (w3[1]);
546 u32x wf_t = pw_len * 8;
557 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w0_t);
558 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w1_t);
559 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w2_t);
560 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w3_t);
561 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w4_t);
562 SHA1_STEP (SHA1_F0o, a, b, c, d, e, w5_t);
563 SHA1_STEP (SHA1_F0o, e, a, b, c, d, w6_t);
564 SHA1_STEP (SHA1_F0o, d, e, a, b, c, w7_t);
565 SHA1_STEP (SHA1_F0o, c, d, e, a, b, w8_t);
566 SHA1_STEP (SHA1_F0o, b, c, d, e, a, w9_t);
567 SHA1_STEP (SHA1_F0o, a, b, c, d, e, wa_t);
568 SHA1_STEP (SHA1_F0o, e, a, b, c, d, wb_t);
569 SHA1_STEP (SHA1_F0o, d, e, a, b, c, wc_t);
570 SHA1_STEP (SHA1_F0o, c, d, e, a, b, wd_t);
571 SHA1_STEP (SHA1_F0o, b, c, d, e, a, we_t);
572 SHA1_STEP (SHA1_F0o, a, b, c, d, e, wf_t);
573 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F0o, e, a, b, c, d, w0_t);
574 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F0o, d, e, a, b, c, w1_t);
575 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F0o, c, d, e, a, b, w2_t);
576 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F0o, b, c, d, e, a, w3_t);
581 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w4_t);
582 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w5_t);
583 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w6_t);
584 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w7_t);
585 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w8_t);
586 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w9_t);
587 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wa_t);
588 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wb_t);
589 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wc_t);
590 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wd_t);
591 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, we_t);
592 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wf_t);
593 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w0_t);
594 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w1_t);
595 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w2_t);
596 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w3_t);
597 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w4_t);
598 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w5_t);
599 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w6_t);
600 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w7_t);
605 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w8_t);
606 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w9_t);
607 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wa_t);
608 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wb_t);
609 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wc_t);
610 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, wd_t);
611 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, we_t);
612 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, wf_t);
613 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w0_t);
614 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w1_t);
615 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w2_t);
616 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w3_t);
617 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w4_t);
618 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, w5_t);
619 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, w6_t);
620 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F2o, a, b, c, d, e, w7_t);
621 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F2o, e, a, b, c, d, w8_t);
622 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F2o, d, e, a, b, c, w9_t);
623 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F2o, c, d, e, a, b, wa_t);
624 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F2o, b, c, d, e, a, wb_t);
629 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wc_t);
630 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wd_t);
631 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, we_t);
632 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, wf_t);
633 w0_t = rotl32 ((wd_t ^ w8_t ^ w2_t ^ w0_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w0_t);
634 w1_t = rotl32 ((we_t ^ w9_t ^ w3_t ^ w1_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w1_t);
635 w2_t = rotl32 ((wf_t ^ wa_t ^ w4_t ^ w2_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w2_t);
636 w3_t = rotl32 ((w0_t ^ wb_t ^ w5_t ^ w3_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w3_t);
637 w4_t = rotl32 ((w1_t ^ wc_t ^ w6_t ^ w4_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w4_t);
638 w5_t = rotl32 ((w2_t ^ wd_t ^ w7_t ^ w5_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, w5_t);
639 w6_t = rotl32 ((w3_t ^ we_t ^ w8_t ^ w6_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, w6_t);
640 w7_t = rotl32 ((w4_t ^ wf_t ^ w9_t ^ w7_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, w7_t);
641 w8_t = rotl32 ((w5_t ^ w0_t ^ wa_t ^ w8_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, w8_t);
642 w9_t = rotl32 ((w6_t ^ w1_t ^ wb_t ^ w9_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, w9_t);
643 wa_t = rotl32 ((w7_t ^ w2_t ^ wc_t ^ wa_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wa_t);
644 wb_t = rotl32 ((w8_t ^ w3_t ^ wd_t ^ wb_t), 1u); SHA1_STEP (SHA1_F1, a, b, c, d, e, wb_t);
645 wc_t = rotl32 ((w9_t ^ w4_t ^ we_t ^ wc_t), 1u); SHA1_STEP (SHA1_F1, e, a, b, c, d, wc_t);
646 wd_t = rotl32 ((wa_t ^ w5_t ^ wf_t ^ wd_t), 1u); SHA1_STEP (SHA1_F1, d, e, a, b, c, wd_t);
647 we_t = rotl32 ((wb_t ^ w6_t ^ w0_t ^ we_t), 1u); SHA1_STEP (SHA1_F1, c, d, e, a, b, we_t);
648 wf_t = rotl32 ((wc_t ^ w7_t ^ w1_t ^ wf_t), 1u); SHA1_STEP (SHA1_F1, b, c, d, e, a, wf_t);
660 w0_t = uint_to_hex_lower8 ((a >> 24) & 255) << 0
661 | uint_to_hex_lower8 ((a >> 16) & 255) << 16;
662 w1_t = uint_to_hex_lower8 ((a >> 8) & 255) << 0
663 | uint_to_hex_lower8 ((a >> 0) & 255) << 16;
664 w2_t = uint_to_hex_lower8 ((b >> 24) & 255) << 0
665 | uint_to_hex_lower8 ((b >> 16) & 255) << 16;
666 w3_t = uint_to_hex_lower8 ((b >> 8) & 255) << 0
667 | uint_to_hex_lower8 ((b >> 0) & 255) << 16;
668 w4_t = uint_to_hex_lower8 ((c >> 24) & 255) << 0
669 | uint_to_hex_lower8 ((c >> 16) & 255) << 16;
670 w5_t = uint_to_hex_lower8 ((c >> 8) & 255) << 0
671 | uint_to_hex_lower8 ((c >> 0) & 255) << 16;
672 w6_t = uint_to_hex_lower8 ((d >> 24) & 255) << 0
673 | uint_to_hex_lower8 ((d >> 16) & 255) << 16;
674 w7_t = uint_to_hex_lower8 ((d >> 8) & 255) << 0
675 | uint_to_hex_lower8 ((d >> 0) & 255) << 16;
676 w8_t = uint_to_hex_lower8 ((e >> 24) & 255) << 0
677 | uint_to_hex_lower8 ((e >> 16) & 255) << 16;
678 w9_t = uint_to_hex_lower8 ((e >> 8) & 255) << 0
679 | uint_to_hex_lower8 ((e >> 0) & 255) << 16;
693 MD5_STEP (MD5_Fo, a, b, c, d, w0_t, MD5C00, MD5S00);
694 MD5_STEP (MD5_Fo, d, a, b, c, w1_t, MD5C01, MD5S01);
695 MD5_STEP (MD5_Fo, c, d, a, b, w2_t, MD5C02, MD5S02);
696 MD5_STEP (MD5_Fo, b, c, d, a, w3_t, MD5C03, MD5S03);
697 MD5_STEP (MD5_Fo, a, b, c, d, w4_t, MD5C04, MD5S00);
698 MD5_STEP (MD5_Fo, d, a, b, c, w5_t, MD5C05, MD5S01);
699 MD5_STEP (MD5_Fo, c, d, a, b, w6_t, MD5C06, MD5S02);
700 MD5_STEP (MD5_Fo, b, c, d, a, w7_t, MD5C07, MD5S03);
701 MD5_STEP (MD5_Fo, a, b, c, d, w8_t, MD5C08, MD5S00);
702 MD5_STEP (MD5_Fo, d, a, b, c, w9_t, MD5C09, MD5S01);
703 MD5_STEP (MD5_Fo, c, d, a, b, wa_t, MD5C0a, MD5S02);
704 MD5_STEP (MD5_Fo, b, c, d, a, wb_t, MD5C0b, MD5S03);
705 MD5_STEP (MD5_Fo, a, b, c, d, wc_t, MD5C0c, MD5S00);
706 MD5_STEP (MD5_Fo, d, a, b, c, wd_t, MD5C0d, MD5S01);
707 MD5_STEP (MD5_Fo, c, d, a, b, we_t, MD5C0e, MD5S02);
708 MD5_STEP (MD5_Fo, b, c, d, a, wf_t, MD5C0f, MD5S03);
710 MD5_STEP (MD5_Go, a, b, c, d, w1_t, MD5C10, MD5S10);
711 MD5_STEP (MD5_Go, d, a, b, c, w6_t, MD5C11, MD5S11);
712 MD5_STEP (MD5_Go, c, d, a, b, wb_t, MD5C12, MD5S12);
713 MD5_STEP (MD5_Go, b, c, d, a, w0_t, MD5C13, MD5S13);
714 MD5_STEP (MD5_Go, a, b, c, d, w5_t, MD5C14, MD5S10);
715 MD5_STEP (MD5_Go, d, a, b, c, wa_t, MD5C15, MD5S11);
716 MD5_STEP (MD5_Go, c, d, a, b, wf_t, MD5C16, MD5S12);
717 MD5_STEP (MD5_Go, b, c, d, a, w4_t, MD5C17, MD5S13);
718 MD5_STEP (MD5_Go, a, b, c, d, w9_t, MD5C18, MD5S10);
719 MD5_STEP (MD5_Go, d, a, b, c, we_t, MD5C19, MD5S11);
720 MD5_STEP (MD5_Go, c, d, a, b, w3_t, MD5C1a, MD5S12);
721 MD5_STEP (MD5_Go, b, c, d, a, w8_t, MD5C1b, MD5S13);
722 MD5_STEP (MD5_Go, a, b, c, d, wd_t, MD5C1c, MD5S10);
723 MD5_STEP (MD5_Go, d, a, b, c, w2_t, MD5C1d, MD5S11);
724 MD5_STEP (MD5_Go, c, d, a, b, w7_t, MD5C1e, MD5S12);
725 MD5_STEP (MD5_Go, b, c, d, a, wc_t, MD5C1f, MD5S13);
727 MD5_STEP (MD5_H , a, b, c, d, w5_t, MD5C20, MD5S20);
728 MD5_STEP (MD5_H , d, a, b, c, w8_t, MD5C21, MD5S21);
729 MD5_STEP (MD5_H , c, d, a, b, wb_t, MD5C22, MD5S22);
730 MD5_STEP (MD5_H , b, c, d, a, we_t, MD5C23, MD5S23);
731 MD5_STEP (MD5_H , a, b, c, d, w1_t, MD5C24, MD5S20);
732 MD5_STEP (MD5_H , d, a, b, c, w4_t, MD5C25, MD5S21);
733 MD5_STEP (MD5_H , c, d, a, b, w7_t, MD5C26, MD5S22);
734 MD5_STEP (MD5_H , b, c, d, a, wa_t, MD5C27, MD5S23);
735 MD5_STEP (MD5_H , a, b, c, d, wd_t, MD5C28, MD5S20);
736 MD5_STEP (MD5_H , d, a, b, c, w0_t, MD5C29, MD5S21);
737 MD5_STEP (MD5_H , c, d, a, b, w3_t, MD5C2a, MD5S22);
738 MD5_STEP (MD5_H , b, c, d, a, w6_t, MD5C2b, MD5S23);
739 MD5_STEP (MD5_H , a, b, c, d, w9_t, MD5C2c, MD5S20);
740 MD5_STEP (MD5_H , d, a, b, c, wc_t, MD5C2d, MD5S21);
741 MD5_STEP (MD5_H , c, d, a, b, wf_t, MD5C2e, MD5S22);
742 MD5_STEP (MD5_H , b, c, d, a, w2_t, MD5C2f, MD5S23);
744 MD5_STEP (MD5_I , a, b, c, d, w0_t, MD5C30, MD5S30);
745 MD5_STEP (MD5_I , d, a, b, c, w7_t, MD5C31, MD5S31);
746 MD5_STEP (MD5_I , c, d, a, b, we_t, MD5C32, MD5S32);
747 MD5_STEP (MD5_I , b, c, d, a, w5_t, MD5C33, MD5S33);
748 MD5_STEP (MD5_I , a, b, c, d, wc_t, MD5C34, MD5S30);
749 MD5_STEP (MD5_I , d, a, b, c, w3_t, MD5C35, MD5S31);
750 MD5_STEP (MD5_I , c, d, a, b, wa_t, MD5C36, MD5S32);
751 MD5_STEP (MD5_I , b, c, d, a, w1_t, MD5C37, MD5S33);
752 MD5_STEP (MD5_I , a, b, c, d, w8_t, MD5C38, MD5S30);
753 MD5_STEP (MD5_I , d, a, b, c, wf_t, MD5C39, MD5S31);
754 MD5_STEP (MD5_I , c, d, a, b, w6_t, MD5C3a, MD5S32);
755 MD5_STEP (MD5_I , b, c, d, a, wd_t, MD5C3b, MD5S33);
756 MD5_STEP (MD5_I , a, b, c, d, w4_t, MD5C3c, MD5S30);
758 if (MATCHES_NONE_VS (a, search[0])) continue;
760 MD5_STEP (MD5_I , d, a, b, c, wb_t, MD5C3d, MD5S31);
761 MD5_STEP (MD5_I , c, d, a, b, w2_t, MD5C3e, MD5S32);
762 MD5_STEP (MD5_I , b, c, d, a, w9_t, MD5C3f, MD5S33);
764 COMPARE_S_SIMD (a, d, c, b);
768 __kernel void m04400_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_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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)
772 __kernel void m04400_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_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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)