2 * Author......: Jens Steube <jens.steube@gmail.com>
8 #include "include/constants.h"
9 #include "include/kernel_vendor.h"
24 #include "include/kernel_functions.c"
26 #include "common_nv.c"
29 #define VECT_COMPARE_M "check_multi_vect1_comp4.c"
33 #define VECT_COMPARE_M "check_multi_vect2_comp4.c"
36 __device__ static void sha256_transform (const u32x w0[4], const u32x w1[4], const u32x w2[4], const u32x w3[4], u32x digest[8])
64 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C00);
65 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C01);
66 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C02);
67 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C03);
68 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C04);
69 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C05);
70 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C06);
71 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C07);
72 SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C08);
73 SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C09);
74 SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C0a);
75 SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C0b);
76 SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C0c);
77 SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C0d);
78 SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C0e);
79 SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C0f);
80 w0_t = SHA256_S1(we_t) + w9_t + SHA256_S0(w1_t) + w0_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C10);
81 w1_t = SHA256_S1(wf_t) + wa_t + SHA256_S0(w2_t) + w1_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C11);
82 w2_t = SHA256_S1(w0_t) + wb_t + SHA256_S0(w3_t) + w2_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C12);
83 w3_t = SHA256_S1(w1_t) + wc_t + SHA256_S0(w4_t) + w3_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C13);
84 w4_t = SHA256_S1(w2_t) + wd_t + SHA256_S0(w5_t) + w4_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C14);
85 w5_t = SHA256_S1(w3_t) + we_t + SHA256_S0(w6_t) + w5_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C15);
86 w6_t = SHA256_S1(w4_t) + wf_t + SHA256_S0(w7_t) + w6_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C16);
87 w7_t = SHA256_S1(w5_t) + w0_t + SHA256_S0(w8_t) + w7_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C17);
88 w8_t = SHA256_S1(w6_t) + w1_t + SHA256_S0(w9_t) + w8_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C18);
89 w9_t = SHA256_S1(w7_t) + w2_t + SHA256_S0(wa_t) + w9_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C19);
90 wa_t = SHA256_S1(w8_t) + w3_t + SHA256_S0(wb_t) + wa_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C1a);
91 wb_t = SHA256_S1(w9_t) + w4_t + SHA256_S0(wc_t) + wb_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C1b);
92 wc_t = SHA256_S1(wa_t) + w5_t + SHA256_S0(wd_t) + wc_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C1c);
93 wd_t = SHA256_S1(wb_t) + w6_t + SHA256_S0(we_t) + wd_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C1d);
94 we_t = SHA256_S1(wc_t) + w7_t + SHA256_S0(wf_t) + we_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C1e);
95 wf_t = SHA256_S1(wd_t) + w8_t + SHA256_S0(w0_t) + wf_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C1f);
96 w0_t = SHA256_S1(we_t) + w9_t + SHA256_S0(w1_t) + w0_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C20);
97 w1_t = SHA256_S1(wf_t) + wa_t + SHA256_S0(w2_t) + w1_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C21);
98 w2_t = SHA256_S1(w0_t) + wb_t + SHA256_S0(w3_t) + w2_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C22);
99 w3_t = SHA256_S1(w1_t) + wc_t + SHA256_S0(w4_t) + w3_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C23);
100 w4_t = SHA256_S1(w2_t) + wd_t + SHA256_S0(w5_t) + w4_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C24);
101 w5_t = SHA256_S1(w3_t) + we_t + SHA256_S0(w6_t) + w5_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C25);
102 w6_t = SHA256_S1(w4_t) + wf_t + SHA256_S0(w7_t) + w6_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C26);
103 w7_t = SHA256_S1(w5_t) + w0_t + SHA256_S0(w8_t) + w7_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C27);
104 w8_t = SHA256_S1(w6_t) + w1_t + SHA256_S0(w9_t) + w8_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C28);
105 w9_t = SHA256_S1(w7_t) + w2_t + SHA256_S0(wa_t) + w9_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C29);
106 wa_t = SHA256_S1(w8_t) + w3_t + SHA256_S0(wb_t) + wa_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C2a);
107 wb_t = SHA256_S1(w9_t) + w4_t + SHA256_S0(wc_t) + wb_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C2b);
108 wc_t = SHA256_S1(wa_t) + w5_t + SHA256_S0(wd_t) + wc_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C2c);
109 wd_t = SHA256_S1(wb_t) + w6_t + SHA256_S0(we_t) + wd_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C2d);
110 we_t = SHA256_S1(wc_t) + w7_t + SHA256_S0(wf_t) + we_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C2e);
111 wf_t = SHA256_S1(wd_t) + w8_t + SHA256_S0(w0_t) + wf_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C2f);
112 w0_t = SHA256_S1(we_t) + w9_t + SHA256_S0(w1_t) + w0_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w0_t, SHA256C30);
113 w1_t = SHA256_S1(wf_t) + wa_t + SHA256_S0(w2_t) + w1_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w1_t, SHA256C31);
114 w2_t = SHA256_S1(w0_t) + wb_t + SHA256_S0(w3_t) + w2_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, w2_t, SHA256C32);
115 w3_t = SHA256_S1(w1_t) + wc_t + SHA256_S0(w4_t) + w3_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, w3_t, SHA256C33);
116 w4_t = SHA256_S1(w2_t) + wd_t + SHA256_S0(w5_t) + w4_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, w4_t, SHA256C34);
117 w5_t = SHA256_S1(w3_t) + we_t + SHA256_S0(w6_t) + w5_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, w5_t, SHA256C35);
118 w6_t = SHA256_S1(w4_t) + wf_t + SHA256_S0(w7_t) + w6_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, w6_t, SHA256C36);
119 w7_t = SHA256_S1(w5_t) + w0_t + SHA256_S0(w8_t) + w7_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, w7_t, SHA256C37);
120 w8_t = SHA256_S1(w6_t) + w1_t + SHA256_S0(w9_t) + w8_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, a, b, c, d, e, f, g, h, w8_t, SHA256C38);
121 w9_t = SHA256_S1(w7_t) + w2_t + SHA256_S0(wa_t) + w9_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, h, a, b, c, d, e, f, g, w9_t, SHA256C39);
122 wa_t = SHA256_S1(w8_t) + w3_t + SHA256_S0(wb_t) + wa_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, g, h, a, b, c, d, e, f, wa_t, SHA256C3a);
123 wb_t = SHA256_S1(w9_t) + w4_t + SHA256_S0(wc_t) + wb_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, f, g, h, a, b, c, d, e, wb_t, SHA256C3b);
124 wc_t = SHA256_S1(wa_t) + w5_t + SHA256_S0(wd_t) + wc_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, e, f, g, h, a, b, c, d, wc_t, SHA256C3c);
125 wd_t = SHA256_S1(wb_t) + w6_t + SHA256_S0(we_t) + wd_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, d, e, f, g, h, a, b, c, wd_t, SHA256C3d);
126 we_t = SHA256_S1(wc_t) + w7_t + SHA256_S0(wf_t) + we_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, c, d, e, f, g, h, a, b, we_t, SHA256C3e);
127 wf_t = SHA256_S1(wd_t) + w8_t + SHA256_S0(w0_t) + wf_t; SHA256_STEP (SHA256_F0o, SHA256_F1o, b, c, d, e, f, g, h, a, wf_t, SHA256C3f);
139 __device__ static void hmac_sha256_pad (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[8], u32x opad[8])
141 w0[0] = w0[0] ^ 0x36363636;
142 w0[1] = w0[1] ^ 0x36363636;
143 w0[2] = w0[2] ^ 0x36363636;
144 w0[3] = w0[3] ^ 0x36363636;
145 w1[0] = w1[0] ^ 0x36363636;
146 w1[1] = w1[1] ^ 0x36363636;
147 w1[2] = w1[2] ^ 0x36363636;
148 w1[3] = w1[3] ^ 0x36363636;
149 w2[0] = w2[0] ^ 0x36363636;
150 w2[1] = w2[1] ^ 0x36363636;
151 w2[2] = w2[2] ^ 0x36363636;
152 w2[3] = w2[3] ^ 0x36363636;
153 w3[0] = w3[0] ^ 0x36363636;
154 w3[1] = w3[1] ^ 0x36363636;
155 w3[2] = w3[2] ^ 0x36363636;
156 w3[3] = w3[3] ^ 0x36363636;
167 sha256_transform (w0, w1, w2, w3, ipad);
169 w0[0] = w0[0] ^ 0x6a6a6a6a;
170 w0[1] = w0[1] ^ 0x6a6a6a6a;
171 w0[2] = w0[2] ^ 0x6a6a6a6a;
172 w0[3] = w0[3] ^ 0x6a6a6a6a;
173 w1[0] = w1[0] ^ 0x6a6a6a6a;
174 w1[1] = w1[1] ^ 0x6a6a6a6a;
175 w1[2] = w1[2] ^ 0x6a6a6a6a;
176 w1[3] = w1[3] ^ 0x6a6a6a6a;
177 w2[0] = w2[0] ^ 0x6a6a6a6a;
178 w2[1] = w2[1] ^ 0x6a6a6a6a;
179 w2[2] = w2[2] ^ 0x6a6a6a6a;
180 w2[3] = w2[3] ^ 0x6a6a6a6a;
181 w3[0] = w3[0] ^ 0x6a6a6a6a;
182 w3[1] = w3[1] ^ 0x6a6a6a6a;
183 w3[2] = w3[2] ^ 0x6a6a6a6a;
184 w3[3] = w3[3] ^ 0x6a6a6a6a;
195 sha256_transform (w0, w1, w2, w3, opad);
198 __device__ static void hmac_sha256_run (u32x w0[4], u32x w1[4], u32x w2[4], u32x w3[4], u32x ipad[8], u32x opad[8], u32x digest[8])
209 sha256_transform (w0, w1, w2, w3, digest);
226 w3[3] = (64 + 32) * 8;
237 sha256_transform (w0, w1, w2, w3, digest);
240 extern "C" __global__ void __launch_bounds__ (256, 1) m06400_init (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, sha256aix_tmp_t *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
246 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
248 if (gid >= gid_max) return;
252 w0[0] = pws[gid].i[ 0];
253 w0[1] = pws[gid].i[ 1];
254 w0[2] = pws[gid].i[ 2];
255 w0[3] = pws[gid].i[ 3];
259 w1[0] = pws[gid].i[ 4];
260 w1[1] = pws[gid].i[ 5];
261 w1[2] = pws[gid].i[ 6];
262 w1[3] = pws[gid].i[ 7];
266 w2[0] = pws[gid].i[ 8];
267 w2[1] = pws[gid].i[ 9];
268 w2[2] = pws[gid].i[10];
269 w2[3] = pws[gid].i[11];
273 w3[0] = pws[gid].i[12];
274 w3[1] = pws[gid].i[13];
275 w3[2] = pws[gid].i[14];
276 w3[3] = pws[gid].i[15];
282 u32 salt_len = salt_bufs[salt_pos].salt_len;
286 salt_buf0[0] = salt_bufs[salt_pos].salt_buf[ 0];
287 salt_buf0[1] = salt_bufs[salt_pos].salt_buf[ 1];
288 salt_buf0[2] = salt_bufs[salt_pos].salt_buf[ 2];
289 salt_buf0[3] = salt_bufs[salt_pos].salt_buf[ 3];
293 salt_buf1[0] = salt_bufs[salt_pos].salt_buf[ 4];
294 salt_buf1[1] = salt_bufs[salt_pos].salt_buf[ 5];
295 salt_buf1[2] = salt_bufs[salt_pos].salt_buf[ 6];
296 salt_buf1[3] = salt_bufs[salt_pos].salt_buf[ 7];
300 salt_buf2[0] = salt_bufs[salt_pos].salt_buf[ 8];
301 salt_buf2[1] = salt_bufs[salt_pos].salt_buf[ 9];
302 salt_buf2[2] = salt_bufs[salt_pos].salt_buf[10];
303 salt_buf2[3] = salt_bufs[salt_pos].salt_buf[11];
312 append_0x01_4 (salt_buf0, salt_buf1, salt_buf2, salt_buf3, salt_len + 3);
314 append_0x80_4 (salt_buf0, salt_buf1, salt_buf2, salt_buf3, salt_len + 4);
320 w0[0] = swap_workaround (w0[0]);
321 w0[1] = swap_workaround (w0[1]);
322 w0[2] = swap_workaround (w0[2]);
323 w0[3] = swap_workaround (w0[3]);
324 w1[0] = swap_workaround (w1[0]);
325 w1[1] = swap_workaround (w1[1]);
326 w1[2] = swap_workaround (w1[2]);
327 w1[3] = swap_workaround (w1[3]);
328 w2[0] = swap_workaround (w2[0]);
329 w2[1] = swap_workaround (w2[1]);
330 w2[2] = swap_workaround (w2[2]);
331 w2[3] = swap_workaround (w2[3]);
332 w3[0] = swap_workaround (w3[0]);
333 w3[1] = swap_workaround (w3[1]);
334 w3[2] = swap_workaround (w3[2]);
335 w3[3] = swap_workaround (w3[3]);
340 hmac_sha256_pad (w0, w1, w2, w3, ipad, opad);
342 tmps[gid].ipad[0] = ipad[0];
343 tmps[gid].ipad[1] = ipad[1];
344 tmps[gid].ipad[2] = ipad[2];
345 tmps[gid].ipad[3] = ipad[3];
346 tmps[gid].ipad[4] = ipad[4];
347 tmps[gid].ipad[5] = ipad[5];
348 tmps[gid].ipad[6] = ipad[6];
349 tmps[gid].ipad[7] = ipad[7];
351 tmps[gid].opad[0] = opad[0];
352 tmps[gid].opad[1] = opad[1];
353 tmps[gid].opad[2] = opad[2];
354 tmps[gid].opad[3] = opad[3];
355 tmps[gid].opad[4] = opad[4];
356 tmps[gid].opad[5] = opad[5];
357 tmps[gid].opad[6] = opad[6];
358 tmps[gid].opad[7] = opad[7];
360 w0[0] = salt_buf0[0];
361 w0[1] = salt_buf0[1];
362 w0[2] = salt_buf0[2];
363 w0[3] = salt_buf0[3];
364 w1[0] = salt_buf1[0];
365 w1[1] = salt_buf1[1];
366 w1[2] = salt_buf1[2];
367 w1[3] = salt_buf1[3];
368 w2[0] = salt_buf2[0];
369 w2[1] = salt_buf2[1];
370 w2[2] = salt_buf2[2];
371 w2[3] = salt_buf2[3];
372 w3[0] = salt_buf3[0];
373 w3[1] = salt_buf3[1];
374 w3[2] = salt_buf3[2];
377 w0[0] = swap_workaround (w0[0]);
378 w0[1] = swap_workaround (w0[1]);
379 w0[2] = swap_workaround (w0[2]);
380 w0[3] = swap_workaround (w0[3]);
381 w1[0] = swap_workaround (w1[0]);
382 w1[1] = swap_workaround (w1[1]);
383 w1[2] = swap_workaround (w1[2]);
384 w1[3] = swap_workaround (w1[3]);
385 w2[0] = swap_workaround (w2[0]);
386 w2[1] = swap_workaround (w2[1]);
387 w2[2] = swap_workaround (w2[2]);
388 w2[3] = swap_workaround (w2[3]);
389 w3[0] = swap_workaround (w3[0]);
390 w3[1] = swap_workaround (w3[1]);
391 w3[2] = swap_workaround (w3[2]);
392 w3[3] = (64 + salt_len + 4) * 8;
396 hmac_sha256_run (w0, w1, w2, w3, ipad, opad, dgst);
398 tmps[gid].dgst[0] = dgst[0];
399 tmps[gid].dgst[1] = dgst[1];
400 tmps[gid].dgst[2] = dgst[2];
401 tmps[gid].dgst[3] = dgst[3];
402 tmps[gid].dgst[4] = dgst[4];
403 tmps[gid].dgst[5] = dgst[5];
404 tmps[gid].dgst[6] = dgst[6];
405 tmps[gid].dgst[7] = dgst[7];
407 tmps[gid].out[0] = dgst[0];
408 tmps[gid].out[1] = dgst[1];
409 tmps[gid].out[2] = dgst[2];
410 tmps[gid].out[3] = dgst[3];
411 tmps[gid].out[4] = dgst[4];
412 tmps[gid].out[5] = dgst[5];
413 tmps[gid].out[6] = dgst[6];
414 tmps[gid].out[7] = dgst[7];
417 extern "C" __global__ void __launch_bounds__ (256, 1) m06400_loop (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, sha256aix_tmp_t *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
419 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
421 if (gid >= gid_max) return;
426 ipad[0] = tmps[gid].ipad[0];
427 ipad[1] = tmps[gid].ipad[1];
428 ipad[2] = tmps[gid].ipad[2];
429 ipad[3] = tmps[gid].ipad[3];
430 ipad[4] = tmps[gid].ipad[4];
431 ipad[5] = tmps[gid].ipad[5];
432 ipad[6] = tmps[gid].ipad[6];
433 ipad[7] = tmps[gid].ipad[7];
435 opad[0] = tmps[gid].opad[0];
436 opad[1] = tmps[gid].opad[1];
437 opad[2] = tmps[gid].opad[2];
438 opad[3] = tmps[gid].opad[3];
439 opad[4] = tmps[gid].opad[4];
440 opad[5] = tmps[gid].opad[5];
441 opad[6] = tmps[gid].opad[6];
442 opad[7] = tmps[gid].opad[7];
447 dgst[0] = tmps[gid].dgst[0];
448 dgst[1] = tmps[gid].dgst[1];
449 dgst[2] = tmps[gid].dgst[2];
450 dgst[3] = tmps[gid].dgst[3];
451 dgst[4] = tmps[gid].dgst[4];
452 dgst[5] = tmps[gid].dgst[5];
453 dgst[6] = tmps[gid].dgst[6];
454 dgst[7] = tmps[gid].dgst[7];
456 out[0] = tmps[gid].out[0];
457 out[1] = tmps[gid].out[1];
458 out[2] = tmps[gid].out[2];
459 out[3] = tmps[gid].out[3];
460 out[4] = tmps[gid].out[4];
461 out[5] = tmps[gid].out[5];
462 out[6] = tmps[gid].out[6];
463 out[7] = tmps[gid].out[7];
465 for (u32 j = 0; j < loop_cnt; j++)
487 w3[3] = (64 + 32) * 8;
489 hmac_sha256_run (w0, w1, w2, w3, ipad, opad, dgst);
501 tmps[gid].dgst[0] = dgst[0];
502 tmps[gid].dgst[1] = dgst[1];
503 tmps[gid].dgst[2] = dgst[2];
504 tmps[gid].dgst[3] = dgst[3];
505 tmps[gid].dgst[4] = dgst[4];
506 tmps[gid].dgst[5] = dgst[5];
507 tmps[gid].dgst[6] = dgst[6];
508 tmps[gid].dgst[7] = dgst[7];
510 tmps[gid].out[0] = out[0];
511 tmps[gid].out[1] = out[1];
512 tmps[gid].out[2] = out[2];
513 tmps[gid].out[3] = out[3];
514 tmps[gid].out[4] = out[4];
515 tmps[gid].out[5] = out[5];
516 tmps[gid].out[6] = out[6];
517 tmps[gid].out[7] = out[7];
520 extern "C" __global__ void __launch_bounds__ (256, 1) m06400_comp (const pw_t *pws, const gpu_rule_t *rules_buf, const comb_t *combs_buf, const bf_t *bfs_buf, sha256aix_tmp_t *tmps, void *hooks, const u32 *bitmaps_buf_s1_a, const u32 *bitmaps_buf_s1_b, const u32 *bitmaps_buf_s1_c, const u32 *bitmaps_buf_s1_d, const u32 *bitmaps_buf_s2_a, const u32 *bitmaps_buf_s2_b, const u32 *bitmaps_buf_s2_c, const u32 *bitmaps_buf_s2_d, plain_t *plains_buf, const digest_t *digests_buf, u32 *hashes_shown, const salt_t *salt_bufs, const void *esalt_bufs, u32 *d_return_buf, 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)
526 const u32 gid = (blockIdx.x * blockDim.x) + threadIdx.x;
528 if (gid >= gid_max) return;
530 const u32 lid = threadIdx.x;
536 const u32x r0 = tmps[gid].out[DGST_R0];
537 const u32x r1 = tmps[gid].out[DGST_R1];
538 const u32x r2 = tmps[gid].out[DGST_R2];
539 const u32x r3 = tmps[gid].out[DGST_R3];
542 u32x a = tmps[gid].out[0];
543 u32x b = tmps[gid].out[1];
544 u32x c = tmps[gid].out[2];
545 u32x d = tmps[gid].out[3];
546 u32x e = tmps[gid].out[4];
547 u32x f = tmps[gid].out[5];
548 u32x g = tmps[gid].out[6];
549 u32x h = tmps[gid].out[7] & 0xffff03ff;
554 #include VECT_COMPARE_M