/usr/lib/gcc/x86_64-linux-gnu/4.6/include/smmintrin.h is in gcc-4.6 4.6.4-6ubuntu2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 | /* Copyright (C) 2007, 2008, 2009, 2010 Free Software Foundation, Inc.
This file is part of GCC.
GCC 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, or (at your option)
any later version.
GCC 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.
Under Section 7 of GPL version 3, you are granted additional
permissions described in the GCC Runtime Library Exception, version
3.1, as published by the Free Software Foundation.
You should have received a copy of the GNU General Public License and
a copy of the GCC Runtime Library Exception along with this program;
see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
<http://www.gnu.org/licenses/>.
/* Implemented from the specification included in the Intel C++ Compiler
User Guide and Reference, version 10.0. */
#ifndef _SMMINTRIN_H_INCLUDED
#define _SMMINTRIN_H_INCLUDED
#ifndef __SSE4_1__
# error "SSE4.1 instruction set not enabled"
#else
/* We need definitions from the SSSE3, SSE3, SSE2 and SSE header
files. */
#include <tmmintrin.h>
/* Rounding mode macros. */
#define _MM_FROUND_TO_NEAREST_INT 0x00
#define _MM_FROUND_TO_NEG_INF 0x01
#define _MM_FROUND_TO_POS_INF 0x02
#define _MM_FROUND_TO_ZERO 0x03
#define _MM_FROUND_CUR_DIRECTION 0x04
#define _MM_FROUND_RAISE_EXC 0x00
#define _MM_FROUND_NO_EXC 0x08
#define _MM_FROUND_NINT \
(_MM_FROUND_TO_NEAREST_INT | _MM_FROUND_RAISE_EXC)
#define _MM_FROUND_FLOOR \
(_MM_FROUND_TO_NEG_INF | _MM_FROUND_RAISE_EXC)
#define _MM_FROUND_CEIL \
(_MM_FROUND_TO_POS_INF | _MM_FROUND_RAISE_EXC)
#define _MM_FROUND_TRUNC \
(_MM_FROUND_TO_ZERO | _MM_FROUND_RAISE_EXC)
#define _MM_FROUND_RINT \
(_MM_FROUND_CUR_DIRECTION | _MM_FROUND_RAISE_EXC)
#define _MM_FROUND_NEARBYINT \
(_MM_FROUND_CUR_DIRECTION | _MM_FROUND_NO_EXC)
/* Test Instruction */
/* Packed integer 128-bit bitwise comparison. Return 1 if
(__V & __M) == 0. */
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_testz_si128 (__m128i __M, __m128i __V)
{
return __builtin_ia32_ptestz128 ((__v2di)__M, (__v2di)__V);
}
/* Packed integer 128-bit bitwise comparison. Return 1 if
(__V & ~__M) == 0. */
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_testc_si128 (__m128i __M, __m128i __V)
{
return __builtin_ia32_ptestc128 ((__v2di)__M, (__v2di)__V);
}
/* Packed integer 128-bit bitwise comparison. Return 1 if
(__V & __M) != 0 && (__V & ~__M) != 0. */
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_testnzc_si128 (__m128i __M, __m128i __V)
{
return __builtin_ia32_ptestnzc128 ((__v2di)__M, (__v2di)__V);
}
/* Macros for packed integer 128-bit comparison intrinsics. */
#define _mm_test_all_zeros(M, V) _mm_testz_si128 ((M), (V))
#define _mm_test_all_ones(V) \
_mm_testc_si128 ((V), _mm_cmpeq_epi32 ((V), (V)))
#define _mm_test_mix_ones_zeros(M, V) _mm_testnzc_si128 ((M), (V))
/* Packed/scalar double precision floating point rounding. */
#ifdef __OPTIMIZE__
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_round_pd (__m128d __V, const int __M)
{
return (__m128d) __builtin_ia32_roundpd ((__v2df)__V, __M);
}
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_round_sd(__m128d __D, __m128d __V, const int __M)
{
return (__m128d) __builtin_ia32_roundsd ((__v2df)__D,
(__v2df)__V,
__M);
}
#else
#define _mm_round_pd(V, M) \
((__m128d) __builtin_ia32_roundpd ((__v2df)(__m128d)(V), (int)(M)))
#define _mm_round_sd(D, V, M) \
((__m128d) __builtin_ia32_roundsd ((__v2df)(__m128d)(D), \
(__v2df)(__m128d)(V), (int)(M)))
#endif
/* Packed/scalar single precision floating point rounding. */
#ifdef __OPTIMIZE__
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_round_ps (__m128 __V, const int __M)
{
return (__m128) __builtin_ia32_roundps ((__v4sf)__V, __M);
}
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_round_ss (__m128 __D, __m128 __V, const int __M)
{
return (__m128) __builtin_ia32_roundss ((__v4sf)__D,
(__v4sf)__V,
__M);
}
#else
#define _mm_round_ps(V, M) \
((__m128) __builtin_ia32_roundps ((__v4sf)(__m128)(V), (int)(M)))
#define _mm_round_ss(D, V, M) \
((__m128) __builtin_ia32_roundss ((__v4sf)(__m128)(D), \
(__v4sf)(__m128)(V), (int)(M)))
#endif
/* Macros for ceil/floor intrinsics. */
#define _mm_ceil_pd(V) _mm_round_pd ((V), _MM_FROUND_CEIL)
#define _mm_ceil_sd(D, V) _mm_round_sd ((D), (V), _MM_FROUND_CEIL)
#define _mm_floor_pd(V) _mm_round_pd((V), _MM_FROUND_FLOOR)
#define _mm_floor_sd(D, V) _mm_round_sd ((D), (V), _MM_FROUND_FLOOR)
#define _mm_ceil_ps(V) _mm_round_ps ((V), _MM_FROUND_CEIL)
#define _mm_ceil_ss(D, V) _mm_round_ss ((D), (V), _MM_FROUND_CEIL)
#define _mm_floor_ps(V) _mm_round_ps ((V), _MM_FROUND_FLOOR)
#define _mm_floor_ss(D, V) _mm_round_ss ((D), (V), _MM_FROUND_FLOOR)
/* SSE4.1 */
/* Integer blend instructions - select data from 2 sources using
constant/variable mask. */
#ifdef __OPTIMIZE__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blend_epi16 (__m128i __X, __m128i __Y, const int __M)
{
return (__m128i) __builtin_ia32_pblendw128 ((__v8hi)__X,
(__v8hi)__Y,
__M);
}
#else
#define _mm_blend_epi16(X, Y, M) \
((__m128i) __builtin_ia32_pblendw128 ((__v8hi)(__m128i)(X), \
(__v8hi)(__m128i)(Y), (int)(M)))
#endif
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blendv_epi8 (__m128i __X, __m128i __Y, __m128i __M)
{
return (__m128i) __builtin_ia32_pblendvb128 ((__v16qi)__X,
(__v16qi)__Y,
(__v16qi)__M);
}
/* Single precision floating point blend instructions - select data
from 2 sources using constant/variable mask. */
#ifdef __OPTIMIZE__
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blend_ps (__m128 __X, __m128 __Y, const int __M)
{
return (__m128) __builtin_ia32_blendps ((__v4sf)__X,
(__v4sf)__Y,
__M);
}
#else
#define _mm_blend_ps(X, Y, M) \
((__m128) __builtin_ia32_blendps ((__v4sf)(__m128)(X), \
(__v4sf)(__m128)(Y), (int)(M)))
#endif
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blendv_ps (__m128 __X, __m128 __Y, __m128 __M)
{
return (__m128) __builtin_ia32_blendvps ((__v4sf)__X,
(__v4sf)__Y,
(__v4sf)__M);
}
/* Double precision floating point blend instructions - select data
from 2 sources using constant/variable mask. */
#ifdef __OPTIMIZE__
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blend_pd (__m128d __X, __m128d __Y, const int __M)
{
return (__m128d) __builtin_ia32_blendpd ((__v2df)__X,
(__v2df)__Y,
__M);
}
#else
#define _mm_blend_pd(X, Y, M) \
((__m128d) __builtin_ia32_blendpd ((__v2df)(__m128d)(X), \
(__v2df)(__m128d)(Y), (int)(M)))
#endif
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_blendv_pd (__m128d __X, __m128d __Y, __m128d __M)
{
return (__m128d) __builtin_ia32_blendvpd ((__v2df)__X,
(__v2df)__Y,
(__v2df)__M);
}
/* Dot product instructions with mask-defined summing and zeroing parts
of result. */
#ifdef __OPTIMIZE__
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_dp_ps (__m128 __X, __m128 __Y, const int __M)
{
return (__m128) __builtin_ia32_dpps ((__v4sf)__X,
(__v4sf)__Y,
__M);
}
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_dp_pd (__m128d __X, __m128d __Y, const int __M)
{
return (__m128d) __builtin_ia32_dppd ((__v2df)__X,
(__v2df)__Y,
__M);
}
#else
#define _mm_dp_ps(X, Y, M) \
((__m128) __builtin_ia32_dpps ((__v4sf)(__m128)(X), \
(__v4sf)(__m128)(Y), (int)(M)))
#define _mm_dp_pd(X, Y, M) \
((__m128d) __builtin_ia32_dppd ((__v2df)(__m128d)(X), \
(__v2df)(__m128d)(Y), (int)(M)))
#endif
/* Packed integer 64-bit comparison, zeroing or filling with ones
corresponding parts of result. */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_epi64 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_pcmpeqq ((__v2di)__X, (__v2di)__Y);
}
/* Min/max packed integer instructions. */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_epi8 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_pminsb128 ((__v16qi)__X, (__v16qi)__Y);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_epi8 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_pmaxsb128 ((__v16qi)__X, (__v16qi)__Y);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_epu16 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_pminuw128 ((__v8hi)__X, (__v8hi)__Y);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_epu16 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_pmaxuw128 ((__v8hi)__X, (__v8hi)__Y);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_epi32 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_pminsd128 ((__v4si)__X, (__v4si)__Y);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_epi32 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_pmaxsd128 ((__v4si)__X, (__v4si)__Y);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_epu32 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_pminud128 ((__v4si)__X, (__v4si)__Y);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_epu32 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_pmaxud128 ((__v4si)__X, (__v4si)__Y);
}
/* Packed integer 32-bit multiplication with truncation of upper
halves of results. */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mullo_epi32 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_pmulld128 ((__v4si)__X, (__v4si)__Y);
}
/* Packed integer 32-bit multiplication of 2 pairs of operands
with two 64-bit results. */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mul_epi32 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_pmuldq128 ((__v4si)__X, (__v4si)__Y);
}
/* Insert single precision float into packed single precision array
element selected by index N. The bits [7-6] of N define S
index, the bits [5-4] define D index, and bits [3-0] define
zeroing mask for D. */
#ifdef __OPTIMIZE__
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_insert_ps (__m128 __D, __m128 __S, const int __N)
{
return (__m128) __builtin_ia32_insertps128 ((__v4sf)__D,
(__v4sf)__S,
__N);
}
#else
#define _mm_insert_ps(D, S, N) \
((__m128) __builtin_ia32_insertps128 ((__v4sf)(__m128)(D), \
(__v4sf)(__m128)(S), (int)(N)))
#endif
/* Helper macro to create the N value for _mm_insert_ps. */
#define _MM_MK_INSERTPS_NDX(S, D, M) (((S) << 6) | ((D) << 4) | (M))
/* Extract binary representation of single precision float from packed
single precision array element of X selected by index N. */
#ifdef __OPTIMIZE__
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_ps (__m128 __X, const int __N)
{
union { int i; float f; } __tmp;
__tmp.f = __builtin_ia32_vec_ext_v4sf ((__v4sf)__X, __N);
return __tmp.i;
}
#else
#define _mm_extract_ps(X, N) \
(__extension__ \
({ \
union { int i; float f; } __tmp; \
__tmp.f = __builtin_ia32_vec_ext_v4sf ((__v4sf)(__m128)(X), (int)(N)); \
__tmp.i; \
}))
#endif
/* Extract binary representation of single precision float into
D from packed single precision array element of S selected
by index N. */
#define _MM_EXTRACT_FLOAT(D, S, N) \
{ (D) = __builtin_ia32_vec_ext_v4sf ((__v4sf)(S), (N)); }
/* Extract specified single precision float element into the lower
part of __m128. */
#define _MM_PICK_OUT_PS(X, N) \
_mm_insert_ps (_mm_setzero_ps (), (X), \
_MM_MK_INSERTPS_NDX ((N), 0, 0x0e))
/* Insert integer, S, into packed integer array element of D
selected by index N. */
#ifdef __OPTIMIZE__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_insert_epi8 (__m128i __D, int __S, const int __N)
{
return (__m128i) __builtin_ia32_vec_set_v16qi ((__v16qi)__D,
__S, __N);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_insert_epi32 (__m128i __D, int __S, const int __N)
{
return (__m128i) __builtin_ia32_vec_set_v4si ((__v4si)__D,
__S, __N);
}
#ifdef __x86_64__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_insert_epi64 (__m128i __D, long long __S, const int __N)
{
return (__m128i) __builtin_ia32_vec_set_v2di ((__v2di)__D,
__S, __N);
}
#endif
#else
#define _mm_insert_epi8(D, S, N) \
((__m128i) __builtin_ia32_vec_set_v16qi ((__v16qi)(__m128i)(D), \
(int)(S), (int)(N)))
#define _mm_insert_epi32(D, S, N) \
((__m128i) __builtin_ia32_vec_set_v4si ((__v4si)(__m128i)(D), \
(int)(S), (int)(N)))
#ifdef __x86_64__
#define _mm_insert_epi64(D, S, N) \
((__m128i) __builtin_ia32_vec_set_v2di ((__v2di)(__m128i)(D), \
(long long)(S), (int)(N)))
#endif
#endif
/* Extract integer from packed integer array element of X selected by
index N. */
#ifdef __OPTIMIZE__
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_epi8 (__m128i __X, const int __N)
{
return (unsigned char) __builtin_ia32_vec_ext_v16qi ((__v16qi)__X, __N);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_epi32 (__m128i __X, const int __N)
{
return __builtin_ia32_vec_ext_v4si ((__v4si)__X, __N);
}
#ifdef __x86_64__
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_extract_epi64 (__m128i __X, const int __N)
{
return __builtin_ia32_vec_ext_v2di ((__v2di)__X, __N);
}
#endif
#else
#define _mm_extract_epi8(X, N) \
((int) (unsigned char) __builtin_ia32_vec_ext_v16qi ((__v16qi)(__m128i)(X), (int)(N)))
#define _mm_extract_epi32(X, N) \
((int) __builtin_ia32_vec_ext_v4si ((__v4si)(__m128i)(X), (int)(N)))
#ifdef __x86_64__
#define _mm_extract_epi64(X, N) \
((long long) __builtin_ia32_vec_ext_v2di ((__v2di)(__m128i)(X), (int)(N)))
#endif
#endif
/* Return horizontal packed word minimum and its index in bits [15:0]
and bits [18:16] respectively. */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_minpos_epu16 (__m128i __X)
{
return (__m128i) __builtin_ia32_phminposuw128 ((__v8hi)__X);
}
/* Packed integer sign-extension. */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi8_epi32 (__m128i __X)
{
return (__m128i) __builtin_ia32_pmovsxbd128 ((__v16qi)__X);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi16_epi32 (__m128i __X)
{
return (__m128i) __builtin_ia32_pmovsxwd128 ((__v8hi)__X);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi8_epi64 (__m128i __X)
{
return (__m128i) __builtin_ia32_pmovsxbq128 ((__v16qi)__X);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi32_epi64 (__m128i __X)
{
return (__m128i) __builtin_ia32_pmovsxdq128 ((__v4si)__X);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi16_epi64 (__m128i __X)
{
return (__m128i) __builtin_ia32_pmovsxwq128 ((__v8hi)__X);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepi8_epi16 (__m128i __X)
{
return (__m128i) __builtin_ia32_pmovsxbw128 ((__v16qi)__X);
}
/* Packed integer zero-extension. */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepu8_epi32 (__m128i __X)
{
return (__m128i) __builtin_ia32_pmovzxbd128 ((__v16qi)__X);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepu16_epi32 (__m128i __X)
{
return (__m128i) __builtin_ia32_pmovzxwd128 ((__v8hi)__X);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepu8_epi64 (__m128i __X)
{
return (__m128i) __builtin_ia32_pmovzxbq128 ((__v16qi)__X);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepu32_epi64 (__m128i __X)
{
return (__m128i) __builtin_ia32_pmovzxdq128 ((__v4si)__X);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepu16_epi64 (__m128i __X)
{
return (__m128i) __builtin_ia32_pmovzxwq128 ((__v8hi)__X);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtepu8_epi16 (__m128i __X)
{
return (__m128i) __builtin_ia32_pmovzxbw128 ((__v16qi)__X);
}
/* Pack 8 double words from 2 operands into 8 words of result with
unsigned saturation. */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_packus_epi32 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_packusdw128 ((__v4si)__X, (__v4si)__Y);
}
/* Sum absolute 8-bit integer difference of adjacent groups of 4
byte integers in the first 2 operands. Starting offsets within
operands are determined by the 3rd mask operand. */
#ifdef __OPTIMIZE__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mpsadbw_epu8 (__m128i __X, __m128i __Y, const int __M)
{
return (__m128i) __builtin_ia32_mpsadbw128 ((__v16qi)__X,
(__v16qi)__Y, __M);
}
#else
#define _mm_mpsadbw_epu8(X, Y, M) \
((__m128i) __builtin_ia32_mpsadbw128 ((__v16qi)(__m128i)(X), \
(__v16qi)(__m128i)(Y), (int)(M)))
#endif
/* Load double quadword using non-temporal aligned hint. */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_stream_load_si128 (__m128i *__X)
{
return (__m128i) __builtin_ia32_movntdqa ((__v2di *) __X);
}
#ifdef __SSE4_2__
/* These macros specify the source data format. */
#define _SIDD_UBYTE_OPS 0x00
#define _SIDD_UWORD_OPS 0x01
#define _SIDD_SBYTE_OPS 0x02
#define _SIDD_SWORD_OPS 0x03
/* These macros specify the comparison operation. */
#define _SIDD_CMP_EQUAL_ANY 0x00
#define _SIDD_CMP_RANGES 0x04
#define _SIDD_CMP_EQUAL_EACH 0x08
#define _SIDD_CMP_EQUAL_ORDERED 0x0c
/* These macros specify the the polarity. */
#define _SIDD_POSITIVE_POLARITY 0x00
#define _SIDD_NEGATIVE_POLARITY 0x10
#define _SIDD_MASKED_POSITIVE_POLARITY 0x20
#define _SIDD_MASKED_NEGATIVE_POLARITY 0x30
/* These macros specify the output selection in _mm_cmpXstri (). */
#define _SIDD_LEAST_SIGNIFICANT 0x00
#define _SIDD_MOST_SIGNIFICANT 0x40
/* These macros specify the output selection in _mm_cmpXstrm (). */
#define _SIDD_BIT_MASK 0x00
#define _SIDD_UNIT_MASK 0x40
/* Intrinsics for text/string processing. */
#ifdef __OPTIMIZE__
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistrm (__m128i __X, __m128i __Y, const int __M)
{
return (__m128i) __builtin_ia32_pcmpistrm128 ((__v16qi)__X,
(__v16qi)__Y,
__M);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistri (__m128i __X, __m128i __Y, const int __M)
{
return __builtin_ia32_pcmpistri128 ((__v16qi)__X,
(__v16qi)__Y,
__M);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestrm (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
return (__m128i) __builtin_ia32_pcmpestrm128 ((__v16qi)__X, __LX,
(__v16qi)__Y, __LY,
__M);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestri (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
return __builtin_ia32_pcmpestri128 ((__v16qi)__X, __LX,
(__v16qi)__Y, __LY,
__M);
}
#else
#define _mm_cmpistrm(X, Y, M) \
((__m128i) __builtin_ia32_pcmpistrm128 ((__v16qi)(__m128i)(X), \
(__v16qi)(__m128i)(Y), (int)(M)))
#define _mm_cmpistri(X, Y, M) \
((int) __builtin_ia32_pcmpistri128 ((__v16qi)(__m128i)(X), \
(__v16qi)(__m128i)(Y), (int)(M)))
#define _mm_cmpestrm(X, LX, Y, LY, M) \
((__m128i) __builtin_ia32_pcmpestrm128 ((__v16qi)(__m128i)(X), \
(int)(LX), (__v16qi)(__m128i)(Y), \
(int)(LY), (int)(M)))
#define _mm_cmpestri(X, LX, Y, LY, M) \
((int) __builtin_ia32_pcmpestri128 ((__v16qi)(__m128i)(X), (int)(LX), \
(__v16qi)(__m128i)(Y), (int)(LY), \
(int)(M)))
#endif
/* Intrinsics for text/string processing and reading values of
EFlags. */
#ifdef __OPTIMIZE__
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistra (__m128i __X, __m128i __Y, const int __M)
{
return __builtin_ia32_pcmpistria128 ((__v16qi)__X,
(__v16qi)__Y,
__M);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistrc (__m128i __X, __m128i __Y, const int __M)
{
return __builtin_ia32_pcmpistric128 ((__v16qi)__X,
(__v16qi)__Y,
__M);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistro (__m128i __X, __m128i __Y, const int __M)
{
return __builtin_ia32_pcmpistrio128 ((__v16qi)__X,
(__v16qi)__Y,
__M);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistrs (__m128i __X, __m128i __Y, const int __M)
{
return __builtin_ia32_pcmpistris128 ((__v16qi)__X,
(__v16qi)__Y,
__M);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpistrz (__m128i __X, __m128i __Y, const int __M)
{
return __builtin_ia32_pcmpistriz128 ((__v16qi)__X,
(__v16qi)__Y,
__M);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestra (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
return __builtin_ia32_pcmpestria128 ((__v16qi)__X, __LX,
(__v16qi)__Y, __LY,
__M);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestrc (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
return __builtin_ia32_pcmpestric128 ((__v16qi)__X, __LX,
(__v16qi)__Y, __LY,
__M);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestro (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
return __builtin_ia32_pcmpestrio128 ((__v16qi)__X, __LX,
(__v16qi)__Y, __LY,
__M);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestrs (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
return __builtin_ia32_pcmpestris128 ((__v16qi)__X, __LX,
(__v16qi)__Y, __LY,
__M);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpestrz (__m128i __X, int __LX, __m128i __Y, int __LY, const int __M)
{
return __builtin_ia32_pcmpestriz128 ((__v16qi)__X, __LX,
(__v16qi)__Y, __LY,
__M);
}
#else
#define _mm_cmpistra(X, Y, M) \
((int) __builtin_ia32_pcmpistria128 ((__v16qi)(__m128i)(X), \
(__v16qi)(__m128i)(Y), (int)(M)))
#define _mm_cmpistrc(X, Y, M) \
((int) __builtin_ia32_pcmpistric128 ((__v16qi)(__m128i)(X), \
(__v16qi)(__m128i)(Y), (int)(M)))
#define _mm_cmpistro(X, Y, M) \
((int) __builtin_ia32_pcmpistrio128 ((__v16qi)(__m128i)(X), \
(__v16qi)(__m128i)(Y), (int)(M)))
#define _mm_cmpistrs(X, Y, M) \
((int) __builtin_ia32_pcmpistris128 ((__v16qi)(__m128i)(X), \
(__v16qi)(__m128i)(Y), (int)(M)))
#define _mm_cmpistrz(X, Y, M) \
((int) __builtin_ia32_pcmpistriz128 ((__v16qi)(__m128i)(X), \
(__v16qi)(__m128i)(Y), (int)(M)))
#define _mm_cmpestra(X, LX, Y, LY, M) \
((int) __builtin_ia32_pcmpestria128 ((__v16qi)(__m128i)(X), (int)(LX), \
(__v16qi)(__m128i)(Y), (int)(LY), \
(int)(M)))
#define _mm_cmpestrc(X, LX, Y, LY, M) \
((int) __builtin_ia32_pcmpestric128 ((__v16qi)(__m128i)(X), (int)(LX), \
(__v16qi)(__m128i)(Y), (int)(LY), \
(int)(M)))
#define _mm_cmpestro(X, LX, Y, LY, M) \
((int) __builtin_ia32_pcmpestrio128 ((__v16qi)(__m128i)(X), (int)(LX), \
(__v16qi)(__m128i)(Y), (int)(LY), \
(int)(M)))
#define _mm_cmpestrs(X, LX, Y, LY, M) \
((int) __builtin_ia32_pcmpestris128 ((__v16qi)(__m128i)(X), (int)(LX), \
(__v16qi)(__m128i)(Y), (int)(LY), \
(int)(M)))
#define _mm_cmpestrz(X, LX, Y, LY, M) \
((int) __builtin_ia32_pcmpestriz128 ((__v16qi)(__m128i)(X), (int)(LX), \
(__v16qi)(__m128i)(Y), (int)(LY), \
(int)(M)))
#endif
/* Packed integer 64-bit comparison, zeroing or filling with ones
corresponding parts of result. */
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_epi64 (__m128i __X, __m128i __Y)
{
return (__m128i) __builtin_ia32_pcmpgtq ((__v2di)__X, (__v2di)__Y);
}
#ifdef __POPCNT__
#include <popcntintrin.h>
#endif
/* Accumulate CRC32 (polynomial 0x11EDC6F41) value. */
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_crc32_u8 (unsigned int __C, unsigned char __V)
{
return __builtin_ia32_crc32qi (__C, __V);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_crc32_u16 (unsigned int __C, unsigned short __V)
{
return __builtin_ia32_crc32hi (__C, __V);
}
extern __inline unsigned int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_crc32_u32 (unsigned int __C, unsigned int __V)
{
return __builtin_ia32_crc32si (__C, __V);
}
#ifdef __x86_64__
extern __inline unsigned long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_crc32_u64 (unsigned long long __C, unsigned long long __V)
{
return __builtin_ia32_crc32di (__C, __V);
}
#endif
#endif /* __SSE4_2__ */
#endif /* __SSE4_1__ */
#endif /* _SMMINTRIN_H_INCLUDED */
|