Commit c639149977837c26c0f9c50352ffebd95d519456
2010-11-26T19:04:48
Add tcatm's 4way SSE2 sha256 implementation.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606
diff --git a/Makefile.am b/Makefile.am
index a7b09fa..2c149d0 100644
--- a/Makefile.am
+++ b/Makefile.am
@@ -13,7 +13,7 @@ bin_PROGRAMS = minerd
EXTRA_DIST = sha256_generic.c
-minerd_SOURCES = util.c cpu-miner.c miner.h compat.h
+minerd_SOURCES = cpu-miner.c sha256_4way.c util.c miner.h compat.h
minerd_LDFLAGS = $(PTHREAD_FLAGS)
minerd_LDADD = @LIBCURL@ @JANSSON_LIBS@ @PTHREAD_LIBS@
diff --git a/README b/README
index 40dafb1..01455c1 100644
--- a/README
+++ b/README
@@ -15,7 +15,7 @@ Basic *nix build instructions:
Basic WIN32 build instructions (on Fedora 13; requires mingw32):
./autogen.sh
- mingw32-configure
+ MINGW32_CFLAGS="-O2 -Wall -msse2 -g" mingw32-configure
make
./mknsis.sh
diff --git a/cpu-miner.c b/cpu-miner.c
index 45e4e55..052c3fe 100644
--- a/cpu-miner.c
+++ b/cpu-miner.c
@@ -36,10 +36,16 @@ enum {
STAT_CTR_INTERVAL = 10000000,
};
+enum sha256_algos {
+ ALGO_C,
+ ALGO_4WAY
+};
+
static bool opt_debug;
bool opt_protocol = false;
static bool program_running = true;
static const bool opt_time = true;
+static enum sha256_algos opt_algo = ALGO_C;
static int opt_n_threads = 1;
static pthread_mutex_t stats_mutex = PTHREAD_MUTEX_INITIALIZER;
static uint64_t hash_ctr;
@@ -56,6 +62,14 @@ static struct option_help options_help[] = {
{ "help",
"(-h) Display this help text" },
+ { "algo",
+ "(-a) Specify sha256 implementation:\n"
+ "\tc\t\tLinux kernel sha256, implemented in C"
+#ifdef __SSE__
+ "\n\t4way\t\ttcatm's 4-way SSE2 implementation"
+#endif
+ },
+
{ "debug",
"(-D) Enable debug output" },
@@ -76,6 +90,7 @@ static struct option_help options_help[] = {
static struct option options[] = {
{ "help", 0, NULL, 'h' },
+ { "algo", 1, NULL, 'a' },
{ "debug", 0, NULL, 'D' },
{ "protocol-dump", 0, NULL, 'P' },
{ "threads", 1, NULL, 't' },
@@ -276,8 +291,19 @@ static void *miner_thread(void *dummy)
json_decref(val);
/* scan nonces for a proof-of-work hash */
- rc = scanhash(work.midstate, work.data + 64,
- work.hash1, work.hash);
+ if (opt_algo == ALGO_C)
+ rc = scanhash(work.midstate, work.data + 64,
+ work.hash1, work.hash);
+#ifdef __SSE__
+ else {
+ unsigned int hashesdone = 0;
+ unsigned int rc4 =
+ ScanHash_4WaySSE2(work.midstate, work.data + 64,
+ work.hash1, work.hash,
+ &hashesdone);
+ rc = (rc4 == -1) ? false : true;
+ }
+#endif
/* if nonce found, submit work */
if (rc)
@@ -307,6 +333,16 @@ static void parse_arg (int key, char *arg)
int v;
switch(key) {
+ case 'a':
+ if (!strcmp(arg, "c"))
+ opt_algo = ALGO_C;
+#ifdef __SSE__
+ else if (!strcmp(arg, "4way"))
+ opt_algo = ALGO_4WAY;
+#endif
+ else
+ show_usage();
+ break;
case 'D':
opt_debug = true;
break;
@@ -343,7 +379,7 @@ static void parse_cmdline(int argc, char *argv[])
int key;
while (1) {
- key = getopt_long(argc, argv, "DPt:h?", options, NULL);
+ key = getopt_long(argc, argv, "a:DPt:h?", options, NULL);
if (key < 0)
break;
diff --git a/miner.h b/miner.h
index dc84c1c..b4cc939 100644
--- a/miner.h
+++ b/miner.h
@@ -14,4 +14,8 @@ extern json_t *json_rpc_call(const char *url, const char *userpass,
extern char *bin2hex(unsigned char *p, size_t len);
extern bool hex2bin(unsigned char *p, const char *hexstr, size_t len);
+extern unsigned int ScanHash_4WaySSE2(unsigned char *pmidstate,
+ unsigned char *pdata, unsigned char *phash1, unsigned char *phash,
+ unsigned int *nHashesDone);
+
#endif /* __MINER_H__ */
diff --git a/sha256_4way.c b/sha256_4way.c
new file mode 100644
index 0000000..56132ff
--- /dev/null
+++ b/sha256_4way.c
@@ -0,0 +1,469 @@
+// Copyright (c) 2010 Satoshi Nakamoto
+// Distributed under the MIT/X11 software license, see the accompanying
+// file license.txt or http://www.opensource.org/licenses/mit-license.php.
+
+// tcatm's 4-way 128-bit SSE2 SHA-256
+
+#ifdef __SSE__
+
+#include <string.h>
+#include <assert.h>
+
+#include <xmmintrin.h>
+#include <stdint.h>
+#include <stdio.h>
+
+#define NPAR 32
+
+static void DoubleBlockSHA256(const void* pin, void* pout, const void* pinit, unsigned int hash[8][NPAR], const void* init2);
+
+static const unsigned int sha256_consts[] = {
+ 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, /* 0 */
+ 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
+ 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3, /* 8 */
+ 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174,
+ 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc, /* 16 */
+ 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
+ 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, /* 24 */
+ 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967,
+ 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13, /* 32 */
+ 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85,
+ 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3, /* 40 */
+ 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
+ 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, /* 48 */
+ 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3,
+ 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208, /* 56 */
+ 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+};
+
+
+static inline __m128i Ch(const __m128i b, const __m128i c, const __m128i d) {
+ return (b & c) ^ (~b & d);
+}
+
+static inline __m128i Maj(const __m128i b, const __m128i c, const __m128i d) {
+ return (b & c) ^ (b & d) ^ (c & d);
+}
+
+static inline __m128i ROTR(__m128i x, const int n) {
+ return _mm_srli_epi32(x, n) | _mm_slli_epi32(x, 32 - n);
+}
+
+static inline __m128i SHR(__m128i x, const int n) {
+ return _mm_srli_epi32(x, n);
+}
+
+/* SHA256 Functions */
+#define BIGSIGMA0_256(x) (ROTR((x), 2) ^ ROTR((x), 13) ^ ROTR((x), 22))
+#define BIGSIGMA1_256(x) (ROTR((x), 6) ^ ROTR((x), 11) ^ ROTR((x), 25))
+#define SIGMA0_256(x) (ROTR((x), 7) ^ ROTR((x), 18) ^ SHR((x), 3))
+#define SIGMA1_256(x) (ROTR((x), 17) ^ ROTR((x), 19) ^ SHR((x), 10))
+
+static inline unsigned int store32(const __m128i x, int i) {
+ union { unsigned int ret[4]; __m128i x; } box;
+ box.x = x;
+ return box.ret[i];
+}
+
+static inline void store_epi32(const __m128i x, unsigned int *x0, unsigned int *x1, unsigned int *x2, unsigned int *x3) {
+ union { unsigned int ret[4]; __m128i x; } box;
+ box.x = x;
+ *x0 = box.ret[3]; *x1 = box.ret[2]; *x2 = box.ret[1]; *x3 = box.ret[0];
+}
+
+#define add4(x0, x1, x2, x3) _mm_add_epi32(_mm_add_epi32(_mm_add_epi32(x0, x1), x2), x3)
+#define add5(x0, x1, x2, x3, x4) _mm_add_epi32(add4(x0, x1, x2, x3), x4)
+
+#define SHA256ROUND(a, b, c, d, e, f, g, h, i, w) \
+ T1 = add5(h, BIGSIGMA1_256(e), Ch(e, f, g), _mm_set1_epi32(sha256_consts[i]), w); \
+d = _mm_add_epi32(d, T1); \
+h = _mm_add_epi32(T1, _mm_add_epi32(BIGSIGMA0_256(a), Maj(a, b, c)));
+
+static inline void dumpreg(__m128i x, char *msg) {
+ union { unsigned int ret[4]; __m128i x; } box;
+ box.x = x ;
+ printf("%s %08x %08x %08x %08x\n", msg, box.ret[0], box.ret[1], box.ret[2], box.ret[3]);
+}
+
+#if 1
+#define dumpstate(i) printf("%s: %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", \
+ __func__, store32(w0, i), store32(a, i), store32(b, i), store32(c, i), store32(d, i), store32(e, i), store32(f, i), store32(g, i), store32(h, i));
+#else
+#define dumpstate()
+#endif
+
+static const unsigned int pSHA256InitState[8] =
+{0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a, 0x510e527f, 0x9b05688c, 0x1f83d9ab, 0x5be0cd19};
+
+
+unsigned int ScanHash_4WaySSE2(unsigned char *pmidstate, unsigned char *pdata,
+ unsigned char *phash1, unsigned char *phash, unsigned int *nHashesDone)
+{
+ unsigned int *nNonce_p = (unsigned int*)(pdata + 12);
+ unsigned int nonce = 0;
+
+ for (;;)
+ {
+ unsigned int thash[9][NPAR] __attribute__((aligned(128)));
+ int j;
+
+ nonce += NPAR;
+ *nNonce_p = nonce;
+
+ DoubleBlockSHA256(pdata, phash1, pmidstate, thash, pSHA256InitState);
+
+ for (j = 0; j < NPAR; j++)
+ {
+ if (thash[7][j] == 0)
+ {
+ int i;
+
+ for (i = 0; i < 32/4; i++)
+ ((unsigned int*)phash)[i] = thash[i][j];
+ return nonce + j;
+ }
+ }
+
+ if ((nonce & 0xffff) == 0)
+ {
+ *nHashesDone = 0xffff+1;
+ return -1;
+ }
+ }
+}
+
+
+static void DoubleBlockSHA256(const void* pin, void* pad, const void *pre, unsigned int thash[9][NPAR], const void *init)
+{
+ unsigned int* In = (unsigned int*)pin;
+ unsigned int* Pad = (unsigned int*)pad;
+ unsigned int* hPre = (unsigned int*)pre;
+ unsigned int* hInit = (unsigned int*)init;
+ unsigned int /* i, j, */ k;
+
+ /* vectors used in calculation */
+ __m128i w0, w1, w2, w3, w4, w5, w6, w7;
+ __m128i w8, w9, w10, w11, w12, w13, w14, w15;
+ __m128i T1;
+ __m128i a, b, c, d, e, f, g, h;
+ __m128i nonce;
+
+ /* nonce offset for vector */
+ __m128i offset = _mm_set_epi32(0x00000003, 0x00000002, 0x00000001, 0x00000000);
+
+
+ for(k = 0; k<NPAR; k+=4) {
+ w0 = _mm_set1_epi32(In[0]);
+ w1 = _mm_set1_epi32(In[1]);
+ w2 = _mm_set1_epi32(In[2]);
+ //w3 = _mm_set1_epi32(In[3]); nonce will be later hacked into the hash
+ w4 = _mm_set1_epi32(In[4]);
+ w5 = _mm_set1_epi32(In[5]);
+ w6 = _mm_set1_epi32(In[6]);
+ w7 = _mm_set1_epi32(In[7]);
+ w8 = _mm_set1_epi32(In[8]);
+ w9 = _mm_set1_epi32(In[9]);
+ w10 = _mm_set1_epi32(In[10]);
+ w11 = _mm_set1_epi32(In[11]);
+ w12 = _mm_set1_epi32(In[12]);
+ w13 = _mm_set1_epi32(In[13]);
+ w14 = _mm_set1_epi32(In[14]);
+ w15 = _mm_set1_epi32(In[15]);
+
+ /* hack nonce into lowest byte of w3 */
+ nonce = _mm_set1_epi32(In[3]);
+ nonce = _mm_add_epi32(nonce, offset);
+ nonce = _mm_add_epi32(nonce, _mm_set1_epi32(k));
+ w3 = nonce;
+
+ a = _mm_set1_epi32(hPre[0]);
+ b = _mm_set1_epi32(hPre[1]);
+ c = _mm_set1_epi32(hPre[2]);
+ d = _mm_set1_epi32(hPre[3]);
+ e = _mm_set1_epi32(hPre[4]);
+ f = _mm_set1_epi32(hPre[5]);
+ g = _mm_set1_epi32(hPre[6]);
+ h = _mm_set1_epi32(hPre[7]);
+
+ SHA256ROUND(a, b, c, d, e, f, g, h, 0, w0);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 1, w1);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 2, w2);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 3, w3);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 4, w4);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 5, w5);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 6, w6);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 7, w7);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 8, w8);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 9, w9);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 10, w10);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 11, w11);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 12, w12);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 13, w13);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 14, w14);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 15, w15);
+
+ w0 = add4(SIGMA1_256(w14), w9, SIGMA0_256(w1), w0);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 16, w0);
+ w1 = add4(SIGMA1_256(w15), w10, SIGMA0_256(w2), w1);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 17, w1);
+ w2 = add4(SIGMA1_256(w0), w11, SIGMA0_256(w3), w2);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 18, w2);
+ w3 = add4(SIGMA1_256(w1), w12, SIGMA0_256(w4), w3);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 19, w3);
+ w4 = add4(SIGMA1_256(w2), w13, SIGMA0_256(w5), w4);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 20, w4);
+ w5 = add4(SIGMA1_256(w3), w14, SIGMA0_256(w6), w5);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 21, w5);
+ w6 = add4(SIGMA1_256(w4), w15, SIGMA0_256(w7), w6);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 22, w6);
+ w7 = add4(SIGMA1_256(w5), w0, SIGMA0_256(w8), w7);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 23, w7);
+ w8 = add4(SIGMA1_256(w6), w1, SIGMA0_256(w9), w8);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 24, w8);
+ w9 = add4(SIGMA1_256(w7), w2, SIGMA0_256(w10), w9);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 25, w9);
+ w10 = add4(SIGMA1_256(w8), w3, SIGMA0_256(w11), w10);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 26, w10);
+ w11 = add4(SIGMA1_256(w9), w4, SIGMA0_256(w12), w11);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 27, w11);
+ w12 = add4(SIGMA1_256(w10), w5, SIGMA0_256(w13), w12);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 28, w12);
+ w13 = add4(SIGMA1_256(w11), w6, SIGMA0_256(w14), w13);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 29, w13);
+ w14 = add4(SIGMA1_256(w12), w7, SIGMA0_256(w15), w14);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 30, w14);
+ w15 = add4(SIGMA1_256(w13), w8, SIGMA0_256(w0), w15);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 31, w15);
+
+ w0 = add4(SIGMA1_256(w14), w9, SIGMA0_256(w1), w0);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 32, w0);
+ w1 = add4(SIGMA1_256(w15), w10, SIGMA0_256(w2), w1);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 33, w1);
+ w2 = add4(SIGMA1_256(w0), w11, SIGMA0_256(w3), w2);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 34, w2);
+ w3 = add4(SIGMA1_256(w1), w12, SIGMA0_256(w4), w3);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 35, w3);
+ w4 = add4(SIGMA1_256(w2), w13, SIGMA0_256(w5), w4);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 36, w4);
+ w5 = add4(SIGMA1_256(w3), w14, SIGMA0_256(w6), w5);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 37, w5);
+ w6 = add4(SIGMA1_256(w4), w15, SIGMA0_256(w7), w6);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 38, w6);
+ w7 = add4(SIGMA1_256(w5), w0, SIGMA0_256(w8), w7);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 39, w7);
+ w8 = add4(SIGMA1_256(w6), w1, SIGMA0_256(w9), w8);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 40, w8);
+ w9 = add4(SIGMA1_256(w7), w2, SIGMA0_256(w10), w9);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 41, w9);
+ w10 = add4(SIGMA1_256(w8), w3, SIGMA0_256(w11), w10);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 42, w10);
+ w11 = add4(SIGMA1_256(w9), w4, SIGMA0_256(w12), w11);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 43, w11);
+ w12 = add4(SIGMA1_256(w10), w5, SIGMA0_256(w13), w12);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 44, w12);
+ w13 = add4(SIGMA1_256(w11), w6, SIGMA0_256(w14), w13);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 45, w13);
+ w14 = add4(SIGMA1_256(w12), w7, SIGMA0_256(w15), w14);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 46, w14);
+ w15 = add4(SIGMA1_256(w13), w8, SIGMA0_256(w0), w15);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 47, w15);
+
+ w0 = add4(SIGMA1_256(w14), w9, SIGMA0_256(w1), w0);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 48, w0);
+ w1 = add4(SIGMA1_256(w15), w10, SIGMA0_256(w2), w1);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 49, w1);
+ w2 = add4(SIGMA1_256(w0), w11, SIGMA0_256(w3), w2);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 50, w2);
+ w3 = add4(SIGMA1_256(w1), w12, SIGMA0_256(w4), w3);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 51, w3);
+ w4 = add4(SIGMA1_256(w2), w13, SIGMA0_256(w5), w4);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 52, w4);
+ w5 = add4(SIGMA1_256(w3), w14, SIGMA0_256(w6), w5);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 53, w5);
+ w6 = add4(SIGMA1_256(w4), w15, SIGMA0_256(w7), w6);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 54, w6);
+ w7 = add4(SIGMA1_256(w5), w0, SIGMA0_256(w8), w7);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 55, w7);
+ w8 = add4(SIGMA1_256(w6), w1, SIGMA0_256(w9), w8);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 56, w8);
+ w9 = add4(SIGMA1_256(w7), w2, SIGMA0_256(w10), w9);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 57, w9);
+ w10 = add4(SIGMA1_256(w8), w3, SIGMA0_256(w11), w10);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 58, w10);
+ w11 = add4(SIGMA1_256(w9), w4, SIGMA0_256(w12), w11);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 59, w11);
+ w12 = add4(SIGMA1_256(w10), w5, SIGMA0_256(w13), w12);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 60, w12);
+ w13 = add4(SIGMA1_256(w11), w6, SIGMA0_256(w14), w13);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 61, w13);
+ w14 = add4(SIGMA1_256(w12), w7, SIGMA0_256(w15), w14);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 62, w14);
+ w15 = add4(SIGMA1_256(w13), w8, SIGMA0_256(w0), w15);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 63, w15);
+
+#define store_load(x, i, dest) \
+ T1 = _mm_set1_epi32((hPre)[i]); \
+ dest = _mm_add_epi32(T1, x);
+
+ store_load(a, 0, w0);
+ store_load(b, 1, w1);
+ store_load(c, 2, w2);
+ store_load(d, 3, w3);
+ store_load(e, 4, w4);
+ store_load(f, 5, w5);
+ store_load(g, 6, w6);
+ store_load(h, 7, w7);
+
+ w8 = _mm_set1_epi32(Pad[8]);
+ w9 = _mm_set1_epi32(Pad[9]);
+ w10 = _mm_set1_epi32(Pad[10]);
+ w11 = _mm_set1_epi32(Pad[11]);
+ w12 = _mm_set1_epi32(Pad[12]);
+ w13 = _mm_set1_epi32(Pad[13]);
+ w14 = _mm_set1_epi32(Pad[14]);
+ w15 = _mm_set1_epi32(Pad[15]);
+
+ a = _mm_set1_epi32(hInit[0]);
+ b = _mm_set1_epi32(hInit[1]);
+ c = _mm_set1_epi32(hInit[2]);
+ d = _mm_set1_epi32(hInit[3]);
+ e = _mm_set1_epi32(hInit[4]);
+ f = _mm_set1_epi32(hInit[5]);
+ g = _mm_set1_epi32(hInit[6]);
+ h = _mm_set1_epi32(hInit[7]);
+
+ SHA256ROUND(a, b, c, d, e, f, g, h, 0, w0);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 1, w1);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 2, w2);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 3, w3);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 4, w4);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 5, w5);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 6, w6);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 7, w7);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 8, w8);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 9, w9);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 10, w10);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 11, w11);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 12, w12);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 13, w13);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 14, w14);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 15, w15);
+
+ w0 = add4(SIGMA1_256(w14), w9, SIGMA0_256(w1), w0);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 16, w0);
+ w1 = add4(SIGMA1_256(w15), w10, SIGMA0_256(w2), w1);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 17, w1);
+ w2 = add4(SIGMA1_256(w0), w11, SIGMA0_256(w3), w2);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 18, w2);
+ w3 = add4(SIGMA1_256(w1), w12, SIGMA0_256(w4), w3);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 19, w3);
+ w4 = add4(SIGMA1_256(w2), w13, SIGMA0_256(w5), w4);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 20, w4);
+ w5 = add4(SIGMA1_256(w3), w14, SIGMA0_256(w6), w5);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 21, w5);
+ w6 = add4(SIGMA1_256(w4), w15, SIGMA0_256(w7), w6);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 22, w6);
+ w7 = add4(SIGMA1_256(w5), w0, SIGMA0_256(w8), w7);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 23, w7);
+ w8 = add4(SIGMA1_256(w6), w1, SIGMA0_256(w9), w8);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 24, w8);
+ w9 = add4(SIGMA1_256(w7), w2, SIGMA0_256(w10), w9);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 25, w9);
+ w10 = add4(SIGMA1_256(w8), w3, SIGMA0_256(w11), w10);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 26, w10);
+ w11 = add4(SIGMA1_256(w9), w4, SIGMA0_256(w12), w11);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 27, w11);
+ w12 = add4(SIGMA1_256(w10), w5, SIGMA0_256(w13), w12);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 28, w12);
+ w13 = add4(SIGMA1_256(w11), w6, SIGMA0_256(w14), w13);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 29, w13);
+ w14 = add4(SIGMA1_256(w12), w7, SIGMA0_256(w15), w14);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 30, w14);
+ w15 = add4(SIGMA1_256(w13), w8, SIGMA0_256(w0), w15);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 31, w15);
+
+ w0 = add4(SIGMA1_256(w14), w9, SIGMA0_256(w1), w0);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 32, w0);
+ w1 = add4(SIGMA1_256(w15), w10, SIGMA0_256(w2), w1);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 33, w1);
+ w2 = add4(SIGMA1_256(w0), w11, SIGMA0_256(w3), w2);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 34, w2);
+ w3 = add4(SIGMA1_256(w1), w12, SIGMA0_256(w4), w3);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 35, w3);
+ w4 = add4(SIGMA1_256(w2), w13, SIGMA0_256(w5), w4);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 36, w4);
+ w5 = add4(SIGMA1_256(w3), w14, SIGMA0_256(w6), w5);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 37, w5);
+ w6 = add4(SIGMA1_256(w4), w15, SIGMA0_256(w7), w6);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 38, w6);
+ w7 = add4(SIGMA1_256(w5), w0, SIGMA0_256(w8), w7);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 39, w7);
+ w8 = add4(SIGMA1_256(w6), w1, SIGMA0_256(w9), w8);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 40, w8);
+ w9 = add4(SIGMA1_256(w7), w2, SIGMA0_256(w10), w9);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 41, w9);
+ w10 = add4(SIGMA1_256(w8), w3, SIGMA0_256(w11), w10);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 42, w10);
+ w11 = add4(SIGMA1_256(w9), w4, SIGMA0_256(w12), w11);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 43, w11);
+ w12 = add4(SIGMA1_256(w10), w5, SIGMA0_256(w13), w12);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 44, w12);
+ w13 = add4(SIGMA1_256(w11), w6, SIGMA0_256(w14), w13);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 45, w13);
+ w14 = add4(SIGMA1_256(w12), w7, SIGMA0_256(w15), w14);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 46, w14);
+ w15 = add4(SIGMA1_256(w13), w8, SIGMA0_256(w0), w15);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 47, w15);
+
+ w0 = add4(SIGMA1_256(w14), w9, SIGMA0_256(w1), w0);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 48, w0);
+ w1 = add4(SIGMA1_256(w15), w10, SIGMA0_256(w2), w1);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 49, w1);
+ w2 = add4(SIGMA1_256(w0), w11, SIGMA0_256(w3), w2);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 50, w2);
+ w3 = add4(SIGMA1_256(w1), w12, SIGMA0_256(w4), w3);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 51, w3);
+ w4 = add4(SIGMA1_256(w2), w13, SIGMA0_256(w5), w4);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 52, w4);
+ w5 = add4(SIGMA1_256(w3), w14, SIGMA0_256(w6), w5);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 53, w5);
+ w6 = add4(SIGMA1_256(w4), w15, SIGMA0_256(w7), w6);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 54, w6);
+ w7 = add4(SIGMA1_256(w5), w0, SIGMA0_256(w8), w7);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 55, w7);
+ w8 = add4(SIGMA1_256(w6), w1, SIGMA0_256(w9), w8);
+ SHA256ROUND(a, b, c, d, e, f, g, h, 56, w8);
+ w9 = add4(SIGMA1_256(w7), w2, SIGMA0_256(w10), w9);
+ SHA256ROUND(h, a, b, c, d, e, f, g, 57, w9);
+ w10 = add4(SIGMA1_256(w8), w3, SIGMA0_256(w11), w10);
+ SHA256ROUND(g, h, a, b, c, d, e, f, 58, w10);
+ w11 = add4(SIGMA1_256(w9), w4, SIGMA0_256(w12), w11);
+ SHA256ROUND(f, g, h, a, b, c, d, e, 59, w11);
+ w12 = add4(SIGMA1_256(w10), w5, SIGMA0_256(w13), w12);
+ SHA256ROUND(e, f, g, h, a, b, c, d, 60, w12);
+ w13 = add4(SIGMA1_256(w11), w6, SIGMA0_256(w14), w13);
+ SHA256ROUND(d, e, f, g, h, a, b, c, 61, w13);
+ w14 = add4(SIGMA1_256(w12), w7, SIGMA0_256(w15), w14);
+ SHA256ROUND(c, d, e, f, g, h, a, b, 62, w14);
+ w15 = add4(SIGMA1_256(w13), w8, SIGMA0_256(w0), w15);
+ SHA256ROUND(b, c, d, e, f, g, h, a, 63, w15);
+
+ /* store resulsts directly in thash */
+#define store_2(x,i) \
+ w0 = _mm_set1_epi32(hInit[i]); \
+ *(__m128i *)&(thash)[i][0+k] = _mm_add_epi32(w0, x);
+
+ store_2(a, 0);
+ store_2(b, 1);
+ store_2(c, 2);
+ store_2(d, 3);
+ store_2(e, 4);
+ store_2(f, 5);
+ store_2(g, 6);
+ store_2(h, 7);
+ *(__m128i *)&(thash)[8][0+k] = nonce;
+ }
+
+}
+
+#endif /* __SSE__ */