forked from monkins1010/ccminer
-
Notifications
You must be signed in to change notification settings - Fork 1
/
balloon.cpp
508 lines (482 loc) · 19.3 KB
/
balloon.cpp
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
#include <stdbool.h>
#include <stdint.h>
#include <stddef.h>
#include <string.h>
#include <openssl/aes.h>
#include <openssl/evp.h>
#include <openssl/sha.h>
#include "balloon.h"
#include <malloc.h>
#include "cuda_helper.h"
#include "miner.h"
//#ifdef __cplusplus
//extern "C" {
//#endif
static uint32_t *d_KNonce[MAX_GPUS];
__constant__ uint32_t pTarget[8];
__constant__ uint2 c_PaddedMessage80[10];
#define TPB 512
#define NONCES_PER_THREAD 32
static void balloon_init(struct balloon_options *opts, int64_t s_cost, int32_t t_cost) {
opts->s_cost = s_cost;
opts->t_cost = t_cost;
}
void balloon_hash(unsigned char *input, unsigned char *output) {
//balloon(input, output);
}
void balloon(int thr_id, uint32_t threads, const uint8_t* input, uint8_t* output, uint32_t *h_nounce) {
struct balloon_options opts;
struct hash_state s;
balloon_init(&opts, (int64_t)128, (int32_t)4);
hash_state_init(&s, &opts, input);
hash_state_fill(&s, input, 80);
hash_state_mix(&s);
uint8_t *b = block_index(&s, 4095);
memcpy((char *)output, (const char *)b, 32);
hash_state_free(&s);
}
__host__
void balloon_128_cuda(int thr_id, uint32_t threads, const uint8_t* input, uint8_t* output, uint32_t *h_nounce) {
CUDA_SAFE_CALL(cudaMemsetAsync(d_KNonce[thr_id], 0xff, 2 * sizeof(uint32_t), gpustream[thr_id]));
const uint32_t threadsperblock = 512;
struct balloon_options opts;
struct hash_state s;
dim3 grid((threads + TPB*NONCES_PER_THREAD - 1) / TPB / NONCES_PER_THREAD);
dim3 block(TPB);
balloon_init(&opts, (int64_t)128, (int32_t)4); //ok
hash_state_init(&s, &opts, input); //ok
hash_state_fill_cuda(&s, input, 80);
hash_state_mix_cuda(&s);
uint8_t *b = block_index(&s, 4095);
memcpy((char *)output, (const char *)b, 32);
hash_state_free(&s);
CUDA_SAFE_CALL(cudaDeviceSynchronize());
CUDA_SAFE_CALL(cudaMemcpy(h_nounce, d_KNonce[thr_id], 2 * sizeof(uint32_t), cudaMemcpyDeviceToHost));
}
static inline void bitstream_init(struct bitstream *b) {
SHA256_Init(&b->c);
#if OPENSSL_VERSION_NUMBER >= 0x10100000L
b->ctx = EVP_CIPHER_CTX_new();
EVP_CIPHER_CTX_init(b->ctx);
#else
//EVP_CIPHER_CTX_init(&b->ctx);
#endif
b->zeros = (uint8_t*)malloc(512);
memset(b->zeros, 0, 512);
}
static inline void bitstream_free(struct bitstream *b) {
uint8_t out[16];
int outl;
#if OPENSSL_VERSION_NUMBER >= 0x10100000L
EVP_EncryptFinal(b->ctx, out, &outl);
EVP_CIPHER_CTX_free(b->ctx);
#else
//EVP_EncryptFinal(&b->ctx, out, &outl);
//EVP_CIPHER_CTX_cleanup(&b->ctx);
#endif
free(b->zeros);
}
static inline void bitstream_seed_add(struct bitstream *b, const void *seed, size_t seedlen) {
SHA256_Update(&b->c, seed, seedlen);
}
static inline void bitstream_seed_finalize(struct bitstream *b) {
uint8_t key_bytes[32];
SHA256_Final(key_bytes, &b->c);
uint8_t iv[16];
memset(iv, 0, 16);
#if OPENSSL_VERSION_NUMBER >= 0x10100000L
EVP_EncryptInit(b->ctx, EVP_aes_128_ctr(), key_bytes, iv);
#else
// EVP_EncryptInit(&b->ctx, EVP_aes_128_ctr(), key_bytes, iv);
#endif
}
void bitstream_fill_buffer(struct bitstream *b, void *out, size_t outlen) {
int encl;
#if OPENSSL_VERSION_NUMBER >= 0x10100000L
EVP_EncryptUpdate(b->ctx, (unsigned char*)out, &encl, b->zeros, 8);
#else
// EVP_EncryptUpdate(&b->ctx, out, &encl, b->zeros, 8);
#endif
}
static void expand(uint64_t *counter, uint8_t *buf) {
const uint8_t *blocks[1] = { buf };
uint8_t *cur = buf + 32;
uint8_t hashmash[40];
int i;
for (i = 1; i < 4096; i++) {
SHA256_CTX ctx;
SHA256_Init(&ctx);
memcpy(&hashmash[0], counter, 8);
memcpy(&hashmash[8], blocks[0], 32);
SHA256_Update(&ctx, hashmash, 40);
SHA256_Final(cur, &ctx);
*counter += 1;
blocks[0] += 32;
cur += 32;
}
}
uint8_t* block_index(const struct hash_state *s, size_t i) {
return s->buffer + (32 * i);
}
void hash_state_init(struct hash_state *s, const struct balloon_options *opts, const uint8_t salt[32]) {
s->counter = 0;
s->buffer = (uint8_t*)malloc(131072);
s->opts = opts;
bitstream_init(&s->bstream);
bitstream_seed_add(&s->bstream, salt, 32);
bitstream_seed_add(&s->bstream, &opts->s_cost, 8);
bitstream_seed_add(&s->bstream, &opts->t_cost, 4);
bitstream_seed_finalize(&s->bstream);
}
void hash_state_free(struct hash_state *s) {
bitstream_free(&s->bstream);
free(s->buffer);
}
void hash_state_fill(struct hash_state *s, const uint8_t *in, size_t inlen) {
uint8_t hashmash[132];
SHA256_CTX c;
SHA256_Init(&c);
memcpy(&hashmash[0], &s->counter, 8);
memcpy(&hashmash[8], in, 32);
memcpy(&hashmash[40], in, 80);
memcpy(&hashmash[120], &s->opts->s_cost, 8);
memcpy(&hashmash[128], &s->opts->t_cost, 4);
SHA256_Update(&c, hashmash, 132);
SHA256_Final(s->buffer, &c);
s->counter++;
expand(&s->counter, s->buffer);
}
void hash_state_fill_cuda(struct hash_state *s, const uint8_t *in, size_t inlen) {
uint8_t hashmash[132];
SHA256_CTX c;
SHA256_Init(&c);
memcpy(&hashmash[0], &s->counter, 8);
memcpy(&hashmash[8], in, 32);
memcpy(&hashmash[40], in, 80);
memcpy(&hashmash[120], &s->opts->s_cost, 8);
memcpy(&hashmash[128], &s->opts->t_cost, 4);
SHA256_Update(&c, hashmash, 132);
SHA256_Final(s->buffer, &c);
s->counter++;
expand(&s->counter, s->buffer);
}
void hash_state_mix(struct hash_state *s) {
SHA256_CTX ctx;
uint8_t buf[8];
uint8_t hashmash[168];
int i;
// round = 0
uint64_t neighbor;
for (i = 0; i < 4096; i++) {
uint8_t *cur_block = s->buffer + (32 * i);
const uint8_t *blocks[5];
const uint8_t *prev_block = i ? cur_block - 32 : block_index(s, 4095);
blocks[0] = prev_block;
blocks[1] = cur_block;
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[2] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[3] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[4] = block_index(s, neighbor % 4096);
SHA256_Init(&ctx);
memcpy(&hashmash[0], &s->counter, 8);
for (int j = 0; j<5; j++)
memcpy(&hashmash[8 + (j * 32)], blocks[j], 32);
SHA256_Update(&ctx, hashmash, 168);
SHA256_Final(cur_block, &ctx);
s->counter += 1;
}
// round = 1
for (i = 0; i < 4096; i++) {
uint8_t *cur_block = s->buffer + (32 * i);
const uint8_t *blocks[5];
const uint8_t *prev_block = i ? cur_block - 32 : block_index(s, 4095);
blocks[0] = prev_block;
blocks[1] = cur_block;
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[2] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[3] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[4] = block_index(s, neighbor % 4096);
SHA256_Init(&ctx);
memcpy(&hashmash[0], &s->counter, 8);
for (int j = 0; j<5; j++)
memcpy(&hashmash[8 + (j * 32)], blocks[j], 32);
SHA256_Update(&ctx, hashmash, 168);
SHA256_Final(cur_block, &ctx);
s->counter += 1;
}
// round = 2
for (i = 0; i < 4096; i++) {
uint8_t *cur_block = s->buffer + (32 * i);
const uint8_t *blocks[5];
const uint8_t *prev_block = i ? cur_block - 32 : block_index(s, 4095);
blocks[0] = prev_block;
blocks[1] = cur_block;
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[2] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[3] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[4] = block_index(s, neighbor % 4096);
SHA256_Init(&ctx);
memcpy(&hashmash[0], &s->counter, 8);
for (int j = 0; j<5; j++)
memcpy(&hashmash[8 + (j * 32)], blocks[j], 32);
SHA256_Update(&ctx, hashmash, 168);
SHA256_Final(cur_block, &ctx);
s->counter += 1;
}
// round = 3
for (i = 0; i < 4096; i++) {
uint8_t *cur_block = s->buffer + (32 * i);
const uint8_t *blocks[5];
const uint8_t *prev_block = i ? cur_block - 32 : block_index(s, 4095);
blocks[0] = prev_block;
blocks[1] = cur_block;
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[2] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[3] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[4] = block_index(s, neighbor % 4096);
SHA256_Init(&ctx);
memcpy(&hashmash[0], &s->counter, 8);
for (int j = 0; j<5; j++)
memcpy(&hashmash[8 + (j * 32)], blocks[j], 32);
SHA256_Update(&ctx, hashmash, 168);
SHA256_Final(cur_block, &ctx);
s->counter += 1;
}
}
void hash_state_mix_cuda(struct hash_state *s) {
SHA256_CTX ctx;
uint8_t buf[8];
uint8_t hashmash[168];
int i;
// round = 0
uint64_t neighbor;
for (i = 0; i < 4096; i++) {
uint8_t *cur_block = s->buffer + (32 * i);
const uint8_t *blocks[5];
const uint8_t *prev_block = i ? cur_block - 32 : block_index(s, 4095);
blocks[0] = prev_block;
blocks[1] = cur_block;
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[2] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[3] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[4] = block_index(s, neighbor % 4096);
SHA256_Init(&ctx);
memcpy(&hashmash[0], &s->counter, 8);
for (int j = 0; j<5; j++)
memcpy(&hashmash[8 + (j * 32)], blocks[j], 32);
SHA256_Update(&ctx, hashmash, 168);
SHA256_Final(cur_block, &ctx);
s->counter += 1;
}
// round = 1
for (i = 0; i < 4096; i++) {
uint8_t *cur_block = s->buffer + (32 * i);
const uint8_t *blocks[5];
const uint8_t *prev_block = i ? cur_block - 32 : block_index(s, 4095);
blocks[0] = prev_block;
blocks[1] = cur_block;
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[2] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[3] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[4] = block_index(s, neighbor % 4096);
SHA256_Init(&ctx);
memcpy(&hashmash[0], &s->counter, 8);
for (int j = 0; j<5; j++)
memcpy(&hashmash[8 + (j * 32)], blocks[j], 32);
SHA256_Update(&ctx, hashmash, 168);
SHA256_Final(cur_block, &ctx);
s->counter += 1;
}
// round = 2
for (i = 0; i < 4096; i++) {
uint8_t *cur_block = s->buffer + (32 * i);
const uint8_t *blocks[5];
const uint8_t *prev_block = i ? cur_block - 32 : block_index(s, 4095);
blocks[0] = prev_block;
blocks[1] = cur_block;
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[2] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[3] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[4] = block_index(s, neighbor % 4096);
SHA256_Init(&ctx);
memcpy(&hashmash[0], &s->counter, 8);
for (int j = 0; j<5; j++)
memcpy(&hashmash[8 + (j * 32)], blocks[j], 32);
SHA256_Update(&ctx, hashmash, 168);
SHA256_Final(cur_block, &ctx);
s->counter += 1;
}
// round = 3
for (i = 0; i < 4096; i++) {
uint8_t *cur_block = s->buffer + (32 * i);
const uint8_t *blocks[5];
const uint8_t *prev_block = i ? cur_block - 32 : block_index(s, 4095);
blocks[0] = prev_block;
blocks[1] = cur_block;
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[2] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[3] = block_index(s, neighbor % 4096);
bitstream_fill_buffer(&s->bstream, buf, 8);
neighbor = 0;
neighbor |= buf[7]; neighbor <<= 8; neighbor |= buf[6]; neighbor <<= 8;
neighbor |= buf[5]; neighbor <<= 8; neighbor |= buf[4]; neighbor <<= 8;
neighbor |= buf[3]; neighbor <<= 8; neighbor |= buf[2]; neighbor <<= 8;
neighbor |= buf[1]; neighbor <<= 8; neighbor |= buf[0];
blocks[4] = block_index(s, neighbor % 4096);
SHA256_Init(&ctx);
memcpy(&hashmash[0], &s->counter, 8);
for (int j = 0; j<5; j++)
memcpy(&hashmash[8 + (j * 32)], blocks[j], 32);
SHA256_Update(&ctx, hashmash, 168);
SHA256_Final(cur_block, &ctx);
s->counter += 1;
}
}
__host__
void balloon256_cpu_init(int thr_id, uint32_t threads)
{
CUDA_SAFE_CALL(cudaMalloc(&d_KNonce[thr_id], 2 * sizeof(uint32_t)));
}
__host__
void balloon_setBlock_80(int thr_id, void *pdata, const void *pTargetIn)
{
unsigned char PaddedMessage[80];
memcpy(PaddedMessage, pdata, 80);
CUDA_SAFE_CALL(cudaMemcpyToSymbolAsync(pTarget, pTargetIn, 8 * sizeof(uint32_t), 0, cudaMemcpyHostToDevice, gpustream[thr_id]));
CUDA_SAFE_CALL(cudaMemcpyToSymbolAsync(c_PaddedMessage80, PaddedMessage, 10 * sizeof(uint64_t), 0, cudaMemcpyHostToDevice, gpustream[thr_id]));
if (opt_debug)
CUDA_SAFE_CALL(cudaDeviceSynchronize());
}
//#ifdef __cplusplus
//}
//#endif