Commit 5133cf5b063e763cde79d0b1e6aa8c59b3e013ce
2011-10-09T12:22:00
Add altivec 4 way support courtesy of Gilles Risch.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655
diff --git a/Makefile.am b/Makefile.am
index 6a24a21..cb7bf85 100644
--- a/Makefile.am
+++ b/Makefile.am
@@ -24,6 +24,7 @@ cgminer_SOURCES = elist.h miner.h compat.h bench_block.h \
sha256_generic.c sha256_4way.c sha256_via.c \
sha256_cryptopp.c sha256_sse2_amd64.c \
sha256_sse4_amd64.c sha256_sse2_i386.c \
+ sha256_altivec_4way.c \
adl.c adl.h adl_functions.h \
phatk110817.cl poclbm110817.cl \
sha2.c sha2.h
diff --git a/configure.ac b/configure.ac
index bf9acbb..333c490 100644
--- a/configure.ac
+++ b/configure.ac
@@ -83,6 +83,11 @@ case $target in
DLOPEN_FLAGS=""
WS2_LIBS="-lws2_32"
;;
+ powerpc-*-darwin*)
+ CFLAGS="$CFLAGS -faltivec"
+ OPENCL_LIBS=""
+ PTHREAD_FLAGS=""
+ ;;
*-*-darwin*)
OPENCL_LIBS="-framework OpenCL"
;;
diff --git a/main.c b/main.c
index 91197d4..2843679 100644
--- a/main.c
+++ b/main.c
@@ -106,6 +106,7 @@ enum sha256_algos {
ALGO_SSE2_32, /* SSE2 for x86_32 */
ALGO_SSE2_64, /* SSE2 for x86_64 */
ALGO_SSE4_64, /* SSE4 for x86_64 */
+ ALGO_ALTIVEC_4WAY, /* parallel Altivec */
};
enum pool_strategy {
@@ -149,6 +150,9 @@ static const char *algo_names[] = {
#ifdef WANT_X8664_SSE4
[ALGO_SSE4_64] = "sse4_64",
#endif
+#ifdef WANT_ALTIVEC_4WAY
+ [ALGO_ALTIVEC_4WAY] = "altivec_4way",
+#endif
};
typedef void (*sha256_func)();
@@ -157,6 +161,9 @@ static const sha256_func sha256_funcs[] = {
#ifdef WANT_SSE2_4WAY
[ALGO_4WAY] = (sha256_func)ScanHash_4WaySSE2,
#endif
+#ifdef WANT_ALTIVEC_4WAY
+ [ALGO_ALTIVEC_4WAY] = (sha256_func) ScanHash_altivec_4way,
+#endif
#ifdef WANT_VIA_PADLOCK
[ALGO_VIA] = (sha256_func)scanhash_via,
#endif
@@ -896,6 +903,10 @@ static enum sha256_algos pick_fastest_algo()
bench_algo(&best_rate, &best_algo, ALGO_SSE4_64);
#endif
+ #if defined(WANT_ALTIVEC_4WAY)
+ bench_algo(&best_rate, &best_algo, ALGO_ALTIVEC_4WAY);
+ #endif
+
size_t n = max_name_len - strlen(algo_names[best_algo]);
memset(name_spaces_pad, ' ', n);
name_spaces_pad[n] = 0;
@@ -1452,6 +1463,9 @@ static struct opt_table opt_config_table[] = {
#ifdef WANT_X8664_SSE4
"\n\tsse4_64\t\tSSE4.1 64 bit implementation for x86_64 machines"
#endif
+#ifdef WANT_ALTIVEC_4WAY
+ "\n\taltivec_4way\tAltivec implementation for PowerPC G4 and G5 machines"
+#endif
),
#ifdef HAVE_ADL
OPT_WITHOUT_ARG("--auto-fan",
@@ -1787,6 +1801,19 @@ static bool work_decode(const json_t *val, struct work *work)
}
memset(work->hash, 0, sizeof(work->hash));
+
+#ifdef __BIG_ENDIAN__
+ int swapcounter = 0;
+ for (swapcounter = 0; swapcounter < 32; swapcounter++)
+ (((uint32_t*) (work->data))[swapcounter]) = swab32(((uint32_t*) (work->data))[swapcounter]);
+ for (swapcounter = 0; swapcounter < 16; swapcounter++)
+ (((uint32_t*) (work->hash1))[swapcounter]) = swab32(((uint32_t*) (work->hash1))[swapcounter]);
+ for (swapcounter = 0; swapcounter < 8; swapcounter++)
+ (((uint32_t*) (work->midstate))[swapcounter]) = swab32(((uint32_t*) (work->midstate))[swapcounter]);
+ for (swapcounter = 0; swapcounter < 8; swapcounter++)
+ (((uint32_t*) (work->target))[swapcounter]) = swab32(((uint32_t*) (work->target))[swapcounter]);
+#endif
+
gettimeofday(&work->tv_staged, NULL);
return true;
@@ -2141,6 +2168,12 @@ static bool submit_upstream_work(const struct work *work)
return rc;
}
+#ifdef __BIG_ENDIAN__
+ int swapcounter = 0;
+ for (swapcounter = 0; swapcounter < 32; swapcounter++)
+ (((uint32_t*) (work->data))[swapcounter]) = swab32(((uint32_t*) (work->data))[swapcounter]);
+#endif
+
/* build hex string */
hexstr = bin2hex(work->data, sizeof(work->data));
if (unlikely(!hexstr)) {
@@ -4081,6 +4114,19 @@ static void *miner_thread(void *userdata)
break;
#endif
+#ifdef WANT_ALTIVEC_4WAY
+ case ALGO_ALTIVEC_4WAY:
+ {
+ unsigned int rc4 = ScanHash_altivec_4way(thr_id, work->midstate, work->data + 64,
+ work->hash1, work->hash,
+ work->target,
+ max_nonce, &hashes_done,
+ work->blk.nonce);
+ rc = (rc4 == -1) ? false : true;
+ }
+ break;
+#endif
+
#ifdef WANT_VIA_PADLOCK
case ALGO_VIA:
rc = scanhash_via(thr_id, work->data, work->target,
diff --git a/miner.h b/miner.h
index c21f189..f187268 100644
--- a/miner.h
+++ b/miner.h
@@ -64,6 +64,10 @@ void *alloca (size_t);
#define WANT_SSE2_4WAY 1
#endif
+#ifdef __ALTIVEC__
+#define WANT_ALTIVEC_4WAY 1
+#endif
+
#if defined(__i386__) && defined(HAS_YASM) && defined(__SSE2__)
#define WANT_X8632_SSE2 1
#endif
@@ -329,6 +333,12 @@ extern unsigned int ScanHash_4WaySSE2(int, const unsigned char *pmidstate,
const unsigned char *ptarget,
uint32_t max_nonce, unsigned long *nHashesDone, uint32_t nonce);
+extern unsigned int ScanHash_altivec_4way(int thr_id, const unsigned char *pmidstate,
+ unsigned char *pdata,
+ unsigned char *phash1, unsigned char *phash,
+ const unsigned char *ptarget,
+ uint32_t max_nonce, unsigned long *nHashesDone, uint32_t nonce);
+
extern unsigned int scanhash_sse2_amd64(int, const unsigned char *pmidstate,
unsigned char *pdata, unsigned char *phash1, unsigned char *phash,
const unsigned char *ptarget,
@@ -342,14 +352,17 @@ extern bool scanhash_c(int, const unsigned char *midstate, unsigned char *data,
unsigned char *hash1, unsigned char *hash,
const unsigned char *target,
uint32_t max_nonce, unsigned long *hashes_done, uint32_t n);
+
extern bool scanhash_cryptopp(int, const unsigned char *midstate,unsigned char *data,
unsigned char *hash1, unsigned char *hash,
const unsigned char *target,
uint32_t max_nonce, unsigned long *hashes_done, uint32_t n);
+
extern bool scanhash_asm32(int, const unsigned char *midstate,unsigned char *data,
unsigned char *hash1, unsigned char *hash,
const unsigned char *target,
uint32_t max_nonce, unsigned long *hashes_done, uint32_t nonce);
+
extern int scanhash_sse2_64(int, const unsigned char *pmidstate, unsigned char *pdata,
unsigned char *phash1, unsigned char *phash,
const unsigned char *ptarget,
diff --git a/sha256_altivec_4way.c b/sha256_altivec_4way.c
new file mode 100644
index 0000000..41dc5a0
--- /dev/null
+++ b/sha256_altivec_4way.c
@@ -0,0 +1,469 @@
+// Copyright (c) 2010 Satoshi Nakamoto
+// Copyright (c) 2011 Gilles Risch
+// Distributed under the MIT/X11 software license, see the accompanying
+// file license.txt or http://www.opensource.org/licenses/mit-license.php.
+
+
+// 4-way 128-bit Altivec SHA-256,
+// based on tcatm's 4-way 128-bit SSE2 SHA-256
+//
+
+
+//#include "config.h"
+#include "miner.h"
+
+#ifdef WANT_ALTIVEC_4WAY
+
+#include <string.h>
+#include <assert.h>
+
+//#include <altivec.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 vector unsigned int Ch(const vector unsigned int b, const vector unsigned int c, const vector unsigned int d) {
+ return vec_sel(d,c,b);
+}
+
+static inline vector unsigned int Maj(const vector unsigned int b, const vector unsigned int c, const vector unsigned int d) {
+ return vec_sel(b,c, vec_xor(b,d));
+}
+
+/* RotateRight(x, n) := RotateLeft(x, 32-n) */
+/* SHA256 Functions */
+#define BIGSIGMA0_256(x) (vec_xor(vec_xor(vec_rl((x), (vector unsigned int)(32-2)),vec_rl((x), (vector unsigned int)(32-13))),vec_rl((x), (vector unsigned int)(32-22))))
+#define BIGSIGMA1_256(x) (vec_xor(vec_xor(vec_rl((x), (vector unsigned int)(32-6)),vec_rl((x), (vector unsigned int)(32-11))),vec_rl((x), (vector unsigned int)(32-25))))
+
+#define SIGMA0_256(x) (vec_xor(vec_xor(vec_rl((x), (vector unsigned int)(32- 7)),vec_rl((x), (vector unsigned int)(32-18))), vec_sr((x), (vector unsigned int)(3 ))))
+#define SIGMA1_256(x) (vec_xor(vec_xor(vec_rl((x), (vector unsigned int)(32-17)),vec_rl((x), (vector unsigned int)(32-19))), vec_sr((x), (vector unsigned int)(10))))
+
+#define add4(x0, x1, x2, x3) vec_add(vec_add(x0, x1),vec_add( x2,x3))
+#define add5(x0, x1, x2, x3, x4) vec_add(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), (vector unsigned int)(sha256_consts[i],sha256_consts[i],sha256_consts[i],sha256_consts[i]), w); \
+ d = vec_add(d, T1); \
+ h = vec_add(T1, vec_add(BIGSIGMA0_256(a), Maj(a, b, c)));
+
+
+static const unsigned int pSHA256InitState[8] =
+{0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a, 0x510e527f, 0x9b05688c, 0x1f83d9ab, 0x5be0cd19};
+
+
+unsigned int ScanHash_altivec_4way(int thr_id, const unsigned char *pmidstate,
+ unsigned char *pdata,
+ unsigned char *phash1, unsigned char *phash,
+ const unsigned char *ptarget,
+ uint32_t max_nonce, unsigned long *nHashesDone,
+ uint32_t nonce)
+{
+ unsigned int *nNonce_p = (unsigned int*)(pdata + 12);
+
+ work_restart[thr_id].restart = 0;
+
+ for (;;)
+ {
+ unsigned int thash[9][NPAR] __attribute__((aligned(128)));
+ int j;
+
+ *nNonce_p = nonce;
+
+ DoubleBlockSHA256(pdata, phash1, pmidstate, thash, pSHA256InitState);
+
+ for (j = 0; j < NPAR; j++)
+ {
+ if (unlikely(thash[7][j] == 0))
+ {
+ int i;
+
+ for (i = 0; i < 32/4; i++)
+ ((unsigned int*)phash)[i] = thash[i][j];
+
+ if (fulltest(phash, ptarget)) {
+ *nHashesDone = nonce;
+ *nNonce_p = nonce + j;
+ return nonce + j;
+ }
+ }
+ }
+
+ if ((nonce >= max_nonce) || work_restart[thr_id].restart)
+ {
+ *nHashesDone = nonce;
+ return -1;
+ }
+
+ nonce += NPAR;
+ }
+}
+
+
+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 */
+ vector unsigned int w0, w1, w2, w3, w4, w5, w6, w7, w8, w9, w10, w11, w12, w13, w14, w15;
+ vector unsigned int T1;
+ vector unsigned int a, b, c, d, e, f, g, h;
+ vector unsigned int nonce, preNonce;
+
+ /* nonce offset for vector */
+ vector unsigned int offset = (vector unsigned int)(0, 1, 2, 3);
+
+ preNonce = vec_add((vector unsigned int)(In[3],In[3],In[3],In[3]), offset);
+
+ for(k = 0; k<NPAR; k+=4)
+ {
+ w0 = (vector unsigned int)(In[0],In[0],In[0],In[0]);
+ w1 = (vector unsigned int)(In[1],In[1],In[1],In[1]);
+ w2 = (vector unsigned int)(In[2],In[2],In[2],In[2]);
+ //w3 = (vector unsigned int)(In[3],In[3],In[3],In[3]); nonce will be later hacked into the hash
+ w4 = (vector unsigned int)(In[4],In[4],In[4],In[4]);
+ w5 = (vector unsigned int)(In[5],In[5],In[5],In[5]);
+ w6 = (vector unsigned int)(In[6],In[6],In[6],In[6]);
+ w7 = (vector unsigned int)(In[7],In[7],In[7],In[7]);
+ w8 = (vector unsigned int)(In[8],In[8],In[8],In[8]);
+ w9 = (vector unsigned int)(In[9],In[9],In[9],In[9]);
+ w10 = (vector unsigned int)(In[10],In[10],In[10],In[10]);
+ w11 = (vector unsigned int)(In[11],In[11],In[11],In[11]);
+ w12 = (vector unsigned int)(In[12],In[12],In[12],In[12]);
+ w13 = (vector unsigned int)(In[13],In[13],In[13],In[13]);
+ w14 = (vector unsigned int)(In[14],In[14],In[14],In[14]);
+ w15 = (vector unsigned int)(In[15],In[15],In[15],In[15]);
+
+ /* hack nonce into lowest byte of w3 */
+ nonce = vec_add(preNonce, (vector unsigned int)(k,k,k,k));
+
+ w3 = nonce;
+ //printf ("W3: %08vlx\n", w3);
+
+ a = (vector unsigned int)(hPre[0],hPre[0],hPre[0],hPre[0]);
+ b = (vector unsigned int)(hPre[1],hPre[1],hPre[1],hPre[1]);
+ c = (vector unsigned int)(hPre[2],hPre[2],hPre[2],hPre[2]);
+ d = (vector unsigned int)(hPre[3],hPre[3],hPre[3],hPre[3]);
+ e = (vector unsigned int)(hPre[4],hPre[4],hPre[4],hPre[4]);
+ f = (vector unsigned int)(hPre[5],hPre[5],hPre[5],hPre[5]);
+ g = (vector unsigned int)(hPre[6],hPre[6],hPre[6],hPre[6]);
+ h = (vector unsigned int)(hPre[7],hPre[7],hPre[7],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 = (vector unsigned int)((hPre)[i],(hPre)[i],(hPre)[i],(hPre)[i]); \
+ dest = vec_add(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);
+
+ /* end of first SHA256 round */
+
+ w8 = (vector unsigned int)(Pad[8],Pad[8],Pad[8],Pad[8]);
+ w9 = (vector unsigned int)(Pad[9],Pad[9],Pad[9],Pad[9]);
+ w10 = (vector unsigned int)(Pad[10],Pad[10],Pad[10],Pad[10]);
+ w11 = (vector unsigned int)(Pad[11],Pad[11],Pad[11],Pad[11]);
+ w12 = (vector unsigned int)(Pad[12],Pad[12],Pad[12],Pad[12]);
+ w13 = (vector unsigned int)(Pad[13],Pad[13],Pad[13],Pad[13]);
+ w14 = (vector unsigned int)(Pad[14],Pad[14],Pad[14],Pad[14]);
+ w15 = (vector unsigned int)(Pad[15],Pad[15],Pad[15],Pad[15]);
+
+ a = (vector unsigned int)(hInit[0],hInit[0],hInit[0],hInit[0]);
+ b = (vector unsigned int)(hInit[1],hInit[1],hInit[1],hInit[1]);
+ c = (vector unsigned int)(hInit[2],hInit[2],hInit[2],hInit[2]);
+ d = (vector unsigned int)(hInit[3],hInit[3],hInit[3],hInit[3]);
+ e = (vector unsigned int)(hInit[4],hInit[4],hInit[4],hInit[4]);
+ f = (vector unsigned int)(hInit[5],hInit[5],hInit[5],hInit[5]);
+ g = (vector unsigned int)(hInit[6],hInit[6],hInit[6],hInit[6]);
+ h = (vector unsigned int)(hInit[7],hInit[7],hInit[7],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);
+
+ /* Skip last 3-rounds; not necessary for H==0 */
+/*#if 0
+ 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);
+#endif*/
+
+ /* store resulsts directly in thash */
+#define store_2(x,i) \
+ w0 = (vector unsigned int)(hInit[i],hInit[i],hInit[i],hInit[i]); \
+ vec_st(vec_add(w0, x), 0 ,&thash[i][k]);
+
+ 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);
+
+ vec_st(nonce, 0 ,&thash[8][k]);
+ /* writing the results into the array is time intensive */
+ /* -> try if it´s faster to compare the results with the target inside this function */
+ }
+
+}
+
+#endif /* WANT_ALTIVEC_4WAY */
+