Commit 48f07d921933dadfaa3558f59b22010d818106b5
2011-08-24T23:07:46
Update to latest sse2 code from cpuminer-ng.
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
diff --git a/sha256_sse2_amd64.c b/sha256_sse2_amd64.c
index 3b34b30..561aa3a 100644
--- a/sha256_sse2_amd64.c
+++ b/sha256_sse2_amd64.c
@@ -22,9 +22,9 @@
#include <stdint.h>
#include <stdio.h>
-extern void CalcSha256_x64(__m128i *res, __m128i *data, uint32_t init[8]);
+extern void sha256_sse2_64_new (__m128i *res, __m128i *res1, __m128i *data, const uint32_t init[8]);
-static uint32_t g_sha256_k[] = {
+static uint32_t g_sha256_k[]__attribute__((aligned(0x100))) = {
0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, /* 0 */
0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3, /* 8 */
@@ -44,10 +44,11 @@ static uint32_t g_sha256_k[] = {
};
-static uint32_t g_sha256_hinit[8] =
+const uint32_t sha256_init[8]__attribute__((aligned(0x100))) =
{0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a, 0x510e527f, 0x9b05688c, 0x1f83d9ab, 0x5be0cd19};
__m128i g_4sha256_k[64];
+__m128i sha256_consts_m128i[64]__attribute__((aligned(0x1000)));
int scanhash_sse2_64(int thr_id, const unsigned char *pmidstate,
unsigned char *pdata,
@@ -58,7 +59,9 @@ int scanhash_sse2_64(int thr_id, const unsigned char *pmidstate,
{
uint32_t *nNonce_p = (uint32_t *)(pdata + 12);
uint32_t m_midstate[8], m_w[16], m_w1[16];
- __m128i m_4w[64], m_4hash[64], m_4hash1[64];
+ __m128i m_4w[64] __attribute__ ((aligned (0x100)));
+ __m128i m_4hash[64] __attribute__ ((aligned (0x100)));
+ __m128i m_4hash1[64] __attribute__ ((aligned (0x100)));
__m128i offset;
int i;
@@ -84,7 +87,7 @@ int scanhash_sse2_64(int thr_id, const unsigned char *pmidstate,
m_4hash1[i] = _mm_set1_epi32(m_w1[i]);
for (i = 0; i < 64; i++)
- g_4sha256_k[i] = _mm_set1_epi32(g_sha256_k[i]);
+ sha256_consts_m128i[i] = _mm_set1_epi32(g_sha256_k[i]);
offset = _mm_set_epi32(0x3, 0x2, 0x1, 0x0);
@@ -94,9 +97,7 @@ int scanhash_sse2_64(int thr_id, const unsigned char *pmidstate,
m_4w[3] = _mm_add_epi32(offset, _mm_set1_epi32(nonce));
- /* Some optimization can be done here W.R.T. precalculating some hash */
- CalcSha256_x64(m_4hash1, m_4w, m_midstate);
- CalcSha256_x64(m_4hash, m_4hash1, g_sha256_hinit);
+ sha256_sse2_64_new (m_4hash, m_4hash1, m_4w, m_midstate);
for (j = 0; j < 4; j++) {
mi.m = m_4hash[7];
diff --git a/x86_64/sha256_xmm_amd64.asm b/x86_64/sha256_xmm_amd64.asm
index b5d5001..15ee855 100644
--- a/x86_64/sha256_xmm_amd64.asm
+++ b/x86_64/sha256_xmm_amd64.asm
@@ -1,256 +1,322 @@
-;; SHA-256 for X86-64 for Linux, based off of:
-
-; (c) Ufasoft 2011 http://ufasoft.com mailto:support@ufasoft.com
-; Version 2011
-; This software is Public Domain
-
-; Significant re-write/optimisation and reordering by,
-; Neil Kettle <mu-b@digit-labs.org>
-; ~18% performance improvement
-
-; SHA-256 CPU SSE cruncher for Bitcoin Miner
+;/*
+; * Copyright (C) 2011 - Neil Kettle <neil@digit-labs.org>
+; *
+; * This file is part of cpuminer-ng.
+; *
+; * cpuminer-ng is free software: you can redistribute it and/or modify
+; * it under the terms of the GNU General Public License as published by
+; * the Free Software Foundation, either version 3 of the License, or
+; * (at your option) any later version.
+; *
+; * cpuminer-ng is distributed in the hope that it will be useful,
+; * but WITHOUT ANY WARRANTY; without even the implied warranty of
+; * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+; * GNU General Public License for more details.
+; *
+; * You should have received a copy of the GNU General Public License
+; * along with cpuminer-ng. If not, see <http://www.gnu.org/licenses/>.
+; */
+
+; %rbp, %rbx, and %r12-%r15 - callee save
ALIGN 32
BITS 64
-%define hash rdi
-%define data rsi
-%define init rdx
+%define hash rdi
+%define hash1 rsi
+%define data rdx
+%define init rcx
; 0 = (1024 - 256) (mod (LAB_CALC_UNROLL*LAB_CALC_PARA*16))
-%define LAB_CALC_PARA 2
-%define LAB_CALC_UNROLL 8
-
-%define LAB_LOOP_UNROLL 8
-
-extern g_4sha256_k
-
-global CalcSha256_x64
-; CalcSha256 hash(rdi), data(rsi), init(rdx)
-CalcSha256_x64:
-
- push rbx
-
-LAB_NEXT_NONCE:
-
- mov rcx, 64*4 ; 256 - rcx is # of SHA-2 rounds
- mov rax, 16*4 ; 64 - rax is where we expand to
-
-LAB_SHA:
- push rcx
- lea rcx, qword [data+rcx*4] ; + 1024
- lea r11, qword [data+rax*4] ; + 256
-
-LAB_CALC:
-%macro lab_calc_blk 1
- movdqa xmm0, [r11-(15-%1)*16] ; xmm0 = W[I-15]
- movdqa xmm4, [r11-(15-(%1+1))*16] ; xmm4 = W[I-15+1]
- movdqa xmm2, xmm0 ; xmm2 = W[I-15]
- movdqa xmm6, xmm4 ; xmm6 = W[I-15+1]
- psrld xmm0, 3 ; xmm0 = W[I-15] >> 3
- psrld xmm4, 3 ; xmm4 = W[I-15+1] >> 3
- movdqa xmm1, xmm0 ; xmm1 = W[I-15] >> 3
- movdqa xmm5, xmm4 ; xmm5 = W[I-15+1] >> 3
- pslld xmm2, 14 ; xmm2 = W[I-15] << 14
- pslld xmm6, 14 ; xmm6 = W[I-15+1] << 14
- psrld xmm1, 4 ; xmm1 = W[I-15] >> 7
- psrld xmm5, 4 ; xmm5 = W[I-15+1] >> 7
- pxor xmm0, xmm1 ; xmm0 = (W[I-15] >> 3) ^ (W[I-15] >> 7)
- pxor xmm4, xmm5 ; xmm4 = (W[I-15+1] >> 3) ^ (W[I-15+1] >> 7)
- psrld xmm1, 11 ; xmm1 = W[I-15] >> 18
- psrld xmm5, 11 ; xmm5 = W[I-15+1] >> 18
- pxor xmm0, xmm2 ; xmm0 = (W[I-15] >> 3) ^ (W[I-15] >> 7) ^ (W[I-15] << 14)
- pxor xmm4, xmm6 ; xmm4 = (W[I-15+1] >> 3) ^ (W[I-15+1] >> 7) ^ (W[I-15+1] << 14)
- pslld xmm2, 11 ; xmm2 = W[I-15] << 25
- pslld xmm6, 11 ; xmm6 = W[I-15+1] << 25
- pxor xmm0, xmm1 ; xmm0 = (W[I-15] >> 3) ^ (W[I-15] >> 7) ^ (W[I-15] << 14) ^ (W[I-15] >> 18)
- pxor xmm4, xmm5 ; xmm4 = (W[I-15+1] >> 3) ^ (W[I-15+1] >> 7) ^ (W[I-15+1] << 14) ^ (W[I-15+1] >> 18)
- pxor xmm0, xmm2 ; xmm0 = (W[I-15] >> 3) ^ (W[I-15] >> 7) ^ (W[I-15] << 14) ^ (W[I-15] >> 18) ^ (W[I-15] << 25)
- pxor xmm4, xmm6 ; xmm4 = (W[I-15+1] >> 3) ^ (W[I-15+1] >> 7) ^ (W[I-15+1] << 14) ^ (W[I-15+1] >> 18) ^ (W[I-15+1] << 25)
-
- movdqa xmm3, [r11-(2-%1)*16] ; xmm3 = W[I-2]
- movdqa xmm7, [r11-(2-(%1+1))*16] ; xmm7 = W[I-2+1]
-
- paddd xmm0, [r11-(16-%1)*16] ; xmm0 = s0(W[I-15]) + W[I-16]
- paddd xmm4, [r11-(16-(%1+1))*16] ; xmm4 = s0(W[I-15+1]) + W[I-16+1]
+%define SHA_CALC_W_PARA 2
+%define SHA_CALC_W_UNROLL 8
-;;;;;;;;;;;;;;;;;;
+%define SHA_ROUND_LOOP_UNROLL 16
+
+%ifidn __YASM_OBJFMT__, macho64
+extern _sha256_consts_m128i
+extern _sha256_init
+%else
+extern sha256_consts_m128i
+extern sha256_init
+%endif
+
+%ifidn __YASM_OBJFMT__, macho64
+global _sha256_sse2_64_new
+%else
+global sha256_sse2_64_new
+%endif
+
+%define sr1 xmm6
+%define sr2 xmm1
+%define sr3 xmm2
+%define sr4 xmm13
+
+%define rA xmm7
+%define rB xmm5
+%define rC xmm4
+%define rD xmm3
+%define rE xmm0
+%define rF xmm8
+%define rG xmm9
+%define rH xmm10
+
+%macro sha_round_blk 0
+ movdqa sr1, [data+rax] ; T1 = w;
+ ;movdqa sr1, xmm11
+ movdqa sr2, rE ; sr2 = rE
+
+ pandn sr2, rG ; sr2 = ~rE & rG
+ movdqa sr3, rF ; sr3 = rF
+
+ paddd sr1, rH ; T1 = h + sha256_consts_m128i[i] + w;
+ movdqa rH, rG ; rH = rG
+
+ pand sr3, rE ; sr3 = rE & rF
+ movdqa rG, rF ; rG = rF
+
+%ifidn __YASM_OBJFMT__, macho64
+ paddd sr1, [rcx+rax]
+%else
+ paddd sr1, sha256_consts_m128i[rax] ; T1 = sha256_consts_m128i[i] + w;
+%endif
+ pxor sr2, sr3 ; sr2 = (rE & rF) ^ (~rE & rG) = Ch (e, f, g)
+
+ movdqa rF, rE ; rF = rE
+ paddd sr1, sr2 ; T1 = h + Ch (e, f, g) + sha256_consts_m128i[i] + w;
+
+ movdqa sr2, rE ; sr2 = rE
+ psrld rE, 6 ; e >> 6
+
+ movdqa sr3, rE ; e >> 6
+ pslld sr2, 7 ; e << 7
+
+ psrld sr3, 5 ; e >> 11
+ pxor rE, sr2 ; e >> 6 ^ e << 7
+
+ pslld sr2, 14 ; e << 21
+ pxor rE, sr3 ; e >> 6 ^ e << 7 ^ e >> 11
+
+ psrld sr3, 14 ; e >> 25
+ pxor rE, sr2 ; e >> 6 ^ e << 7 ^ e >> 11 ^ e << 21
+
+ pslld sr2, 5 ; e << 26
+ pxor rE, sr3 ; e >> 6 ^ e << 7 ^ e >> 11 ^ e << 21 ^ e >> 25
+
+ pxor rE, sr2 ; e >> 6 ^ e << 7 ^ e >> 11 ^ e << 21 ^ e >> 25 ^ e << 26
+ movdqa sr2, rB ; sr2 = rB
+
+ paddd sr1, rE ; sr1 = h + BIGSIGMA1_256(e) + Ch (e, f, g) + sha256_consts_m128i[i] + w;
+ movdqa rE, rD ; rE = rD
+
+ movdqa rD, rC ; rD = rC
+ paddd rE, sr1 ; rE = rD + T1
+
+ movdqa sr3, rC ; sr3 = rC
+ pand rC, rA ; rC = rC & rA
+
+ pand sr3, rB ; sr3 = rB & rC
+ pand sr2, rA ; sr2 = rB & rA
+
+ pxor sr2, rC ; sr2 = (rB & rA) ^ (rC & rA)
+ movdqa rC, rB ; rC = rB
- movdqa xmm2, xmm3 ; xmm2 = W[I-2]
- movdqa xmm6, xmm7 ; xmm6 = W[I-2+1]
- psrld xmm3, 10 ; xmm3 = W[I-2] >> 10
- psrld xmm7, 10 ; xmm7 = W[I-2+1] >> 10
- movdqa xmm1, xmm3 ; xmm1 = W[I-2] >> 10
- movdqa xmm5, xmm7 ; xmm5 = W[I-2+1] >> 10
-
- paddd xmm0, [r11-(7-%1)*16] ; xmm0 = s0(W[I-15]) + W[I-16] + W[I-7]
-
- pslld xmm2, 13 ; xmm2 = W[I-2] << 13
- pslld xmm6, 13 ; xmm6 = W[I-2+1] << 13
- psrld xmm1, 7 ; xmm1 = W[I-2] >> 17
- psrld xmm5, 7 ; xmm5 = W[I-2+1] >> 17
-
- paddd xmm4, [r11-(7-(%1+1))*16] ; xmm4 = s0(W[I-15+1]) + W[I-16+1] + W[I-7+1]
-
- pxor xmm3, xmm1 ; xmm3 = (W[I-2] >> 10) ^ (W[I-2] >> 17)
- pxor xmm7, xmm5 ; xmm7 = (W[I-2+1] >> 10) ^ (W[I-2+1] >> 17)
- psrld xmm1, 2 ; xmm1 = W[I-2] >> 19
- psrld xmm5, 2 ; xmm5 = W[I-2+1] >> 19
- pxor xmm3, xmm2 ; xmm3 = (W[I-2] >> 10) ^ (W[I-2] >> 17) ^ (W[I-2] << 13)
- pxor xmm7, xmm6 ; xmm7 = (W[I-2+1] >> 10) ^ (W[I-2+1] >> 17) ^ (W[I-2+1] << 13)
- pslld xmm2, 2 ; xmm2 = W[I-2] << 15
- pslld xmm6, 2 ; xmm6 = W[I-2+1] << 15
- pxor xmm3, xmm1 ; xmm3 = (W[I-2] >> 10) ^ (W[I-2] >> 17) ^ (W[I-2] << 13) ^ (W[I-2] >> 19)
- pxor xmm7, xmm5 ; xmm7 = (W[I-2+1] >> 10) ^ (W[I-2+1] >> 17) ^ (W[I-2+1] << 13) ^ (W[I-2+1] >> 19)
- pxor xmm3, xmm2 ; xmm3 = (W[I-2] >> 10) ^ (W[I-2] >> 17) ^ (W[I-2] << 13) ^ (W[I-2] >> 19) ^ (W[I-2] << 15)
- pxor xmm7, xmm6 ; xmm7 = (W[I-2+1] >> 10) ^ (W[I-2+1] >> 17) ^ (W[I-2+1] << 13) ^ (W[I-2+1] >> 19) ^ (W[I-2+1] << 15)
-
- paddd xmm0, xmm3 ; xmm0 = s0(W[I-15]) + W[I-16] + s1(W[I-2]) + W[I-7]
- paddd xmm4, xmm7 ; xmm4 = s0(W[I-15+1]) + W[I-16+1] + s1(W[I-2+1]) + W[I-7+1]
- movdqa [r11+(%1*16)], xmm0
- movdqa [r11+((%1+1)*16)], xmm4
+ pxor sr2, sr3 ; sr2 = (rB & rA) ^ (rC & rA) ^ (rB & rC)
+ movdqa rB, rA ; rB = rA
+
+ paddd sr1, sr2 ; sr1 = T1 + (rB & rA) ^ (rC & rA) ^ (rB & rC)
+ lea rax, [rax+16]
+
+ movdqa sr3, rA ; sr3 = rA
+ psrld rA, 2 ; a >> 2
+
+ pslld sr3, 10 ; a << 10
+ movdqa sr2, rA ; a >> 2
+
+ pxor rA, sr3 ; a >> 2 ^ a << 10
+ psrld sr2, 11 ; a >> 13
+
+ pxor rA, sr2 ; a >> 2 ^ a << 10 ^ a >> 13
+ pslld sr3, 9 ; a << 19
+
+ pxor rA, sr3 ; a >> 2 ^ a << 10 ^ a >> 13 ^ a << 19
+ psrld sr2, 9 ; a >> 21
+
+ pxor rA, sr2 ; a >> 2 ^ a << 10 ^ a >> 13 ^ a << 19 ^ a >> 21
+ pslld sr3, 11 ; a << 30
+
+ pxor rA, sr3 ; a >> 2 ^ a << 10 ^ a >> 13 ^ a << 19 ^ a >> 21 ^ a << 30
+ paddd rA, sr1 ; T1 + BIGSIGMA0_256(a) + Maj(a, b, c);
%endmacro
-%assign i 0
-%rep LAB_CALC_UNROLL
- lab_calc_blk i
-%assign i i+LAB_CALC_PARA
-%endrep
+%macro sha_calc_w_blk 1
+ movdqa xmm0, [r11-(15-%1)*16] ; xmm0 = W[I-15]
+ movdqa xmm4, [r11-(15-(%1+1))*16] ; xmm4 = W[I-15+1]
+ movdqa xmm2, xmm0 ; xmm2 = W[I-15]
+ movdqa xmm6, xmm4 ; xmm6 = W[I-15+1]
+ psrld xmm0, 3 ; xmm0 = W[I-15] >> 3
+ psrld xmm4, 3 ; xmm4 = W[I-15+1] >> 3
+ movdqa xmm1, xmm0 ; xmm1 = W[I-15] >> 3
+ movdqa xmm5, xmm4 ; xmm5 = W[I-15+1] >> 3
+ pslld xmm2, 14 ; xmm2 = W[I-15] << 14
+ pslld xmm6, 14 ; xmm6 = W[I-15+1] << 14
+ psrld xmm1, 4 ; xmm1 = W[I-15] >> 7
+ psrld xmm5, 4 ; xmm5 = W[I-15+1] >> 7
+ pxor xmm0, xmm1 ; xmm0 = (W[I-15] >> 3) ^ (W[I-15] >> 7)
+ pxor xmm4, xmm5 ; xmm4 = (W[I-15+1] >> 3) ^ (W[I-15+1] >> 7)
+ psrld xmm1, 11 ; xmm1 = W[I-15] >> 18
+ psrld xmm5, 11 ; xmm5 = W[I-15+1] >> 18
+ pxor xmm0, xmm2 ; xmm0 = (W[I-15] >> 3) ^ (W[I-15] >> 7) ^ (W[I-15] << 14)
+ pxor xmm4, xmm6 ; xmm4 = (W[I-15+1] >> 3) ^ (W[I-15+1] >> 7) ^ (W[I-15+1] << 14)
+ pslld xmm2, 11 ; xmm2 = W[I-15] << 25
+ pslld xmm6, 11 ; xmm6 = W[I-15+1] << 25
+ pxor xmm0, xmm1 ; xmm0 = (W[I-15] >> 3) ^ (W[I-15] >> 7) ^ (W[I-15] << 14) ^ (W[I-15] >> 18)
+ pxor xmm4, xmm5 ; xmm4 = (W[I-15+1] >> 3) ^ (W[I-15+1] >> 7) ^ (W[I-15+1] << 14) ^ (W[I-15+1] >> 18)
+ pxor xmm0, xmm2 ; xmm0 = (W[I-15] >> 3) ^ (W[I-15] >> 7) ^ (W[I-15] << 14) ^ (W[I-15] >> 18) ^ (W[I-15] << 25)
+ pxor xmm4, xmm6 ; xmm4 = (W[I-15+1] >> 3) ^ (W[I-15+1] >> 7) ^ (W[I-15+1] << 14) ^ (W[I-15+1] >> 18) ^ (W[I-15+1] << 25)
+
+ movdqa xmm3, [r11-(2-%1)*16] ; xmm3 = W[I-2]
+ movdqa xmm7, [r11-(2-(%1+1))*16] ; xmm7 = W[I-2+1]
+
+ paddd xmm0, [r11-(16-%1)*16] ; xmm0 = s0(W[I-15]) + W[I-16]
+ paddd xmm4, [r11-(16-(%1+1))*16] ; xmm4 = s0(W[I-15+1]) + W[I-16+1]
- add r11, LAB_CALC_UNROLL*LAB_CALC_PARA*16
- cmp r11, rcx
- jb LAB_CALC
-
- pop rcx
- mov rax, 0
-
-; Load the init values of the message into the hash.
-
- movdqa xmm7, [init]
- pshufd xmm5, xmm7, 0x55 ; xmm5 == b
- pshufd xmm4, xmm7, 0xAA ; xmm4 == c
- pshufd xmm3, xmm7, 0xFF ; xmm3 == d
- pshufd xmm7, xmm7, 0 ; xmm7 == a
-
- movdqa xmm0, [init+4*4]
- pshufd xmm8, xmm0, 0x55 ; xmm8 == f
- pshufd xmm9, xmm0, 0xAA ; xmm9 == g
- pshufd xmm10, xmm0, 0xFF ; xmm10 == h
- pshufd xmm0, xmm0, 0 ; xmm0 == e
-
-LAB_LOOP:
-
-;; T t1 = h + (Rotr32(e, 6) ^ Rotr32(e, 11) ^ Rotr32(e, 25)) + ((e & f) ^ AndNot(e, g)) + Expand32<T>(g_sha256_k[j]) + w[j]
-
-%macro lab_loop_blk 0
- movdqa xmm6, [data+rax*4]
- paddd xmm6, g_4sha256_k[rax*4]
- add rax, 4
-
- paddd xmm6, xmm10 ; +h
-
- movdqa xmm1, xmm0
- movdqa xmm2, xmm9
- pandn xmm1, xmm2 ; ~e & g
-
- movdqa xmm10, xmm2 ; h = g
- movdqa xmm2, xmm8 ; f
- movdqa xmm9, xmm2 ; g = f
-
- pand xmm2, xmm0 ; e & f
- pxor xmm1, xmm2 ; (e & f) ^ (~e & g)
- movdqa xmm8, xmm0 ; f = e
-
- paddd xmm6, xmm1 ; Ch + h + w[i] + k[i]
-
- movdqa xmm1, xmm0
- psrld xmm0, 6
- movdqa xmm2, xmm0
- pslld xmm1, 7
- psrld xmm2, 5
- pxor xmm0, xmm1
- pxor xmm0, xmm2
- pslld xmm1, 14
- psrld xmm2, 14
- pxor xmm0, xmm1
- pxor xmm0, xmm2
- pslld xmm1, 5
- pxor xmm0, xmm1 ; Rotr32(e, 6) ^ Rotr32(e, 11) ^ Rotr32(e, 25)
- paddd xmm6, xmm0 ; xmm6 = t1
-
- movdqa xmm0, xmm3 ; d
- paddd xmm0, xmm6 ; e = d+t1
-
- movdqa xmm1, xmm5 ; =b
- movdqa xmm3, xmm4 ; d = c
- movdqa xmm2, xmm4 ; c
- pand xmm2, xmm5 ; b & c
- pand xmm4, xmm7 ; a & c
- pand xmm1, xmm7 ; a & b
- pxor xmm1, xmm4
- movdqa xmm4, xmm5 ; c = b
- movdqa xmm5, xmm7 ; b = a
- pxor xmm1, xmm2 ; (a & c) ^ (a & d) ^ (c & d)
- paddd xmm6, xmm1 ; t1 + ((a & c) ^ (a & d) ^ (c & d))
-
- movdqa xmm2, xmm7
- psrld xmm7, 2
- movdqa xmm1, xmm7
- pslld xmm2, 10
- psrld xmm1, 11
- pxor xmm7, xmm2
- pxor xmm7, xmm1
- pslld xmm2, 9
- psrld xmm1, 9
- pxor xmm7, xmm2
- pxor xmm7, xmm1
- pslld xmm2, 11
- pxor xmm7, xmm2
- paddd xmm7, xmm6 ; a = t1 + (Rotr32(a, 2) ^ Rotr32(a, 13) ^ Rotr32(a, 22)) + ((a & c) ^ (a & d) ^ (c & d));
+;;;;;;;;;;;;;;;;;;
+
+ movdqa xmm2, xmm3 ; xmm2 = W[I-2]
+ movdqa xmm6, xmm7 ; xmm6 = W[I-2+1]
+ psrld xmm3, 10 ; xmm3 = W[I-2] >> 10
+ psrld xmm7, 10 ; xmm7 = W[I-2+1] >> 10
+ movdqa xmm1, xmm3 ; xmm1 = W[I-2] >> 10
+ movdqa xmm5, xmm7 ; xmm5 = W[I-2+1] >> 10
+
+ paddd xmm0, [r11-(7-%1)*16] ; xmm0 = s0(W[I-15]) + W[I-16] + W[I-7]
+
+ pslld xmm2, 13 ; xmm2 = W[I-2] << 13
+ pslld xmm6, 13 ; xmm6 = W[I-2+1] << 13
+ psrld xmm1, 7 ; xmm1 = W[I-2] >> 17
+ psrld xmm5, 7 ; xmm5 = W[I-2+1] >> 17
+
+ paddd xmm4, [r11-(7-(%1+1))*16] ; xmm4 = s0(W[I-15+1]) + W[I-16+1] + W[I-7+1]
+
+ pxor xmm3, xmm1 ; xmm3 = (W[I-2] >> 10) ^ (W[I-2] >> 17)
+ pxor xmm7, xmm5 ; xmm7 = (W[I-2+1] >> 10) ^ (W[I-2+1] >> 17)
+ psrld xmm1, 2 ; xmm1 = W[I-2] >> 19
+ psrld xmm5, 2 ; xmm5 = W[I-2+1] >> 19
+ pxor xmm3, xmm2 ; xmm3 = (W[I-2] >> 10) ^ (W[I-2] >> 17) ^ (W[I-2] << 13)
+ pxor xmm7, xmm6 ; xmm7 = (W[I-2+1] >> 10) ^ (W[I-2+1] >> 17) ^ (W[I-2+1] << 13)
+ pslld xmm2, 2 ; xmm2 = W[I-2] << 15
+ pslld xmm6, 2 ; xmm6 = W[I-2+1] << 15
+ pxor xmm3, xmm1 ; xmm3 = (W[I-2] >> 10) ^ (W[I-2] >> 17) ^ (W[I-2] << 13) ^ (W[I-2] >> 19)
+ pxor xmm7, xmm5 ; xmm7 = (W[I-2+1] >> 10) ^ (W[I-2+1] >> 17) ^ (W[I-2+1] << 13) ^ (W[I-2+1] >> 19)
+ pxor xmm3, xmm2 ; xmm3 = (W[I-2] >> 10) ^ (W[I-2] >> 17) ^ (W[I-2] << 13) ^ (W[I-2] >> 19) ^ (W[I-2] << 15)
+ pxor xmm7, xmm6 ; xmm7 = (W[I-2+1] >> 10) ^ (W[I-2+1] >> 17) ^ (W[I-2+1] << 13) ^ (W[I-2+1] >> 19) ^ (W[I-2+1] << 15)
+
+ paddd xmm0, xmm3 ; xmm0 = s0(W[I-15]) + W[I-16] + s1(W[I-2]) + W[I-7]
+ paddd xmm4, xmm7 ; xmm4 = s0(W[I-15+1]) + W[I-16+1] + s1(W[I-2+1]) + W[I-7+1]
+ movdqa [r11+(%1*16)], xmm0
+ movdqa [r11+((%1+1)*16)], xmm4
%endmacro
+; _sha256_sse2_64_new hash(rdi), hash1(rsi), data(rdx), init(rcx),
+
+%ifidn __YASM_OBJFMT__, macho64
+_sha256_sse2_64_new:
+%else
+sha256_sse2_64_new:
+%endif
+
+ push rbx
+
+%macro SHA_256 0
+ mov rbx, 64*4 ; rbx is # of SHA-2 rounds
+ mov rax, 16*4 ; rax is where we expand to
+
+ push rbx
+ lea rbx, qword [data+rbx*4]
+ lea r11, qword [data+rax*4]
+
+%%SHA_CALC_W:
+%assign i 0
+%rep SHA_CALC_W_UNROLL
+ sha_calc_w_blk i
+%assign i i+SHA_CALC_W_PARA
+%endrep
+ add r11, SHA_CALC_W_UNROLL*SHA_CALC_W_PARA*16
+ cmp r11, rbx
+ jb %%SHA_CALC_W
+
+ pop rbx
+ mov rax, 0
+ lea rbx, [rbx*4]
+
+ movdqa rA, [init]
+ pshufd rB, rA, 0x55 ; rB == B
+ pshufd rC, rA, 0xAA ; rC == C
+ pshufd rD, rA, 0xFF ; rD == D
+ pshufd rA, rA, 0 ; rA == A
+
+ movdqa rE, [init+4*4]
+ pshufd rF, rE, 0x55 ; rF == F
+ pshufd rG, rE, 0xAA ; rG == G
+ pshufd rH, rE, 0xFF ; rH == H
+ pshufd rE, rE, 0 ; rE == E
+
+%ifidn __YASM_OBJFMT__, macho64
+ lea rcx, [_sha256_consts_m128i wrt rip]
+%endif
+
+%%SHAROUND_LOOP:
%assign i 0
-%rep LAB_LOOP_UNROLL
- lab_loop_blk
+%rep SHA_ROUND_LOOP_UNROLL
+ sha_round_blk
%assign i i+1
%endrep
-
- cmp rax, rcx
- jb LAB_LOOP
+ cmp rax, rbx
+ jb %%SHAROUND_LOOP
; Finished the 64 rounds, calculate hash and save
- movdqa xmm1, [rdx]
- pshufd xmm2, xmm1, 0x55
- pshufd xmm6, xmm1, 0xAA
- pshufd xmm11, xmm1, 0xFF
- pshufd xmm1, xmm1, 0
-
- paddd xmm5, xmm2
- paddd xmm4, xmm6
- paddd xmm3, xmm11
- paddd xmm7, xmm1
-
- movdqa xmm1, [rdx+4*4]
- pshufd xmm2, xmm1, 0x55
- pshufd xmm6, xmm1, 0xAA
- pshufd xmm11, xmm1, 0xFF
- pshufd xmm1, xmm1, 0
-
- paddd xmm8, xmm2
- paddd xmm9, xmm6
- paddd xmm10, xmm11
- paddd xmm0, xmm1
-
- movdqa [hash+0*16], xmm7
- movdqa [hash+1*16], xmm5
- movdqa [hash+2*16], xmm4
- movdqa [hash+3*16], xmm3
- movdqa [hash+4*16], xmm0
- movdqa [hash+5*16], xmm8
- movdqa [hash+6*16], xmm9
- movdqa [hash+7*16], xmm10
+ movdqa sr1, [init]
+ pshufd sr2, sr1, 0x55
+ pshufd sr3, sr1, 0xAA
+ pshufd sr4, sr1, 0xFF
+ pshufd sr1, sr1, 0
+
+ paddd rB, sr2
+ paddd rC, sr3
+ paddd rD, sr4
+ paddd rA, sr1
+
+ movdqa sr1, [init+4*4]
+ pshufd sr2, sr1, 0x55
+ pshufd sr3, sr1, 0xAA
+ pshufd sr4, sr1, 0xFF
+ pshufd sr1, sr1, 0
+
+ paddd rF, sr2
+ paddd rG, sr3
+ paddd rH, sr4
+ paddd rE, sr1
+%endmacro
+
+ SHA_256
+ movdqa [hash1+0*16], rA
+ movdqa [hash1+1*16], rB
+ movdqa [hash1+2*16], rC
+ movdqa [hash1+3*16], rD
+ movdqa [hash1+4*16], rE
+ movdqa [hash1+5*16], rF
+ movdqa [hash1+6*16], rG
+ movdqa [hash1+7*16], rH
+
+ mov data, hash1
+ mov init, sha256_init
+
+ SHA_256
+
+ movdqa [hash+7*16], rH
LAB_RET:
- pop rbx
- ret
+ pop rbx
+ ret