/usr/lib/gcc/x86_64-linux-gnu/4.7/include/mmintrin.h is in gcc-4.7 4.7.2-5.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 | /* Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009
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 9.0. */
#ifndef _MMINTRIN_H_INCLUDED
#define _MMINTRIN_H_INCLUDED
#ifndef __MMX__
# error "MMX instruction set not enabled"
#else
/* The Intel API is flexible enough that we must allow aliasing with other
vector types, and their scalar components. */
typedef int __m64 __attribute__ ((__vector_size__ (8), __may_alias__));
/* Internal data types for implementing the intrinsics. */
typedef int __v2si __attribute__ ((__vector_size__ (8)));
typedef short __v4hi __attribute__ ((__vector_size__ (8)));
typedef char __v8qi __attribute__ ((__vector_size__ (8)));
typedef long long __v1di __attribute__ ((__vector_size__ (8)));
typedef float __v2sf __attribute__ ((__vector_size__ (8)));
/* Empty the multimedia state. */
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_empty (void)
{
__builtin_ia32_emms ();
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_empty (void)
{
_mm_empty ();
}
/* Convert I to a __m64 object. The integer is zero-extended to 64-bits. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi32_si64 (int __i)
{
return (__m64) __builtin_ia32_vec_init_v2si (__i, 0);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_from_int (int __i)
{
return _mm_cvtsi32_si64 (__i);
}
#ifdef __x86_64__
/* Convert I to a __m64 object. */
/* Intel intrinsic. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_from_int64 (long long __i)
{
return (__m64) __i;
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi64_m64 (long long __i)
{
return (__m64) __i;
}
/* Microsoft intrinsic. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi64x_si64 (long long __i)
{
return (__m64) __i;
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_pi64x (long long __i)
{
return (__m64) __i;
}
#endif
/* Convert the lower 32 bits of the __m64 object into an integer. */
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi64_si32 (__m64 __i)
{
return __builtin_ia32_vec_ext_v2si ((__v2si)__i, 0);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_to_int (__m64 __i)
{
return _mm_cvtsi64_si32 (__i);
}
#ifdef __x86_64__
/* Convert the __m64 object to a 64bit integer. */
/* Intel intrinsic. */
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_to_int64 (__m64 __i)
{
return (long long)__i;
}
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtm64_si64 (__m64 __i)
{
return (long long)__i;
}
/* Microsoft intrinsic. */
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsi64_si64x (__m64 __i)
{
return (long long)__i;
}
#endif
/* Pack the four 16-bit values from M1 into the lower four 8-bit values of
the result, and the four 16-bit values from M2 into the upper four 8-bit
values of the result, all with signed saturation. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_packs_pi16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_packsswb ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_packsswb (__m64 __m1, __m64 __m2)
{
return _mm_packs_pi16 (__m1, __m2);
}
/* Pack the two 32-bit values from M1 in to the lower two 16-bit values of
the result, and the two 32-bit values from M2 into the upper two 16-bit
values of the result, all with signed saturation. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_packs_pi32 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_packssdw ((__v2si)__m1, (__v2si)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_packssdw (__m64 __m1, __m64 __m2)
{
return _mm_packs_pi32 (__m1, __m2);
}
/* Pack the four 16-bit values from M1 into the lower four 8-bit values of
the result, and the four 16-bit values from M2 into the upper four 8-bit
values of the result, all with unsigned saturation. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_packs_pu16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_packuswb ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_packuswb (__m64 __m1, __m64 __m2)
{
return _mm_packs_pu16 (__m1, __m2);
}
/* Interleave the four 8-bit values from the high half of M1 with the four
8-bit values from the high half of M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpackhi_pi8 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_punpckhbw ((__v8qi)__m1, (__v8qi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_punpckhbw (__m64 __m1, __m64 __m2)
{
return _mm_unpackhi_pi8 (__m1, __m2);
}
/* Interleave the two 16-bit values from the high half of M1 with the two
16-bit values from the high half of M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpackhi_pi16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_punpckhwd ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_punpckhwd (__m64 __m1, __m64 __m2)
{
return _mm_unpackhi_pi16 (__m1, __m2);
}
/* Interleave the 32-bit value from the high half of M1 with the 32-bit
value from the high half of M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpackhi_pi32 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_punpckhdq ((__v2si)__m1, (__v2si)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_punpckhdq (__m64 __m1, __m64 __m2)
{
return _mm_unpackhi_pi32 (__m1, __m2);
}
/* Interleave the four 8-bit values from the low half of M1 with the four
8-bit values from the low half of M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpacklo_pi8 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_punpcklbw ((__v8qi)__m1, (__v8qi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_punpcklbw (__m64 __m1, __m64 __m2)
{
return _mm_unpacklo_pi8 (__m1, __m2);
}
/* Interleave the two 16-bit values from the low half of M1 with the two
16-bit values from the low half of M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpacklo_pi16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_punpcklwd ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_punpcklwd (__m64 __m1, __m64 __m2)
{
return _mm_unpacklo_pi16 (__m1, __m2);
}
/* Interleave the 32-bit value from the low half of M1 with the 32-bit
value from the low half of M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_unpacklo_pi32 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_punpckldq ((__v2si)__m1, (__v2si)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_punpckldq (__m64 __m1, __m64 __m2)
{
return _mm_unpacklo_pi32 (__m1, __m2);
}
/* Add the 8-bit values in M1 to the 8-bit values in M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_pi8 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_paddb ((__v8qi)__m1, (__v8qi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddb (__m64 __m1, __m64 __m2)
{
return _mm_add_pi8 (__m1, __m2);
}
/* Add the 16-bit values in M1 to the 16-bit values in M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_pi16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_paddw ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddw (__m64 __m1, __m64 __m2)
{
return _mm_add_pi16 (__m1, __m2);
}
/* Add the 32-bit values in M1 to the 32-bit values in M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_pi32 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_paddd ((__v2si)__m1, (__v2si)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddd (__m64 __m1, __m64 __m2)
{
return _mm_add_pi32 (__m1, __m2);
}
/* Add the 64-bit values in M1 to the 64-bit values in M2. */
#ifdef __SSE2__
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_si64 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_paddq ((__v1di)__m1, (__v1di)__m2);
}
#endif
/* Add the 8-bit values in M1 to the 8-bit values in M2 using signed
saturated arithmetic. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_adds_pi8 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_paddsb ((__v8qi)__m1, (__v8qi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddsb (__m64 __m1, __m64 __m2)
{
return _mm_adds_pi8 (__m1, __m2);
}
/* Add the 16-bit values in M1 to the 16-bit values in M2 using signed
saturated arithmetic. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_adds_pi16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_paddsw ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddsw (__m64 __m1, __m64 __m2)
{
return _mm_adds_pi16 (__m1, __m2);
}
/* Add the 8-bit values in M1 to the 8-bit values in M2 using unsigned
saturated arithmetic. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_adds_pu8 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_paddusb ((__v8qi)__m1, (__v8qi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddusb (__m64 __m1, __m64 __m2)
{
return _mm_adds_pu8 (__m1, __m2);
}
/* Add the 16-bit values in M1 to the 16-bit values in M2 using unsigned
saturated arithmetic. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_adds_pu16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_paddusw ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_paddusw (__m64 __m1, __m64 __m2)
{
return _mm_adds_pu16 (__m1, __m2);
}
/* Subtract the 8-bit values in M2 from the 8-bit values in M1. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_pi8 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_psubb ((__v8qi)__m1, (__v8qi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubb (__m64 __m1, __m64 __m2)
{
return _mm_sub_pi8 (__m1, __m2);
}
/* Subtract the 16-bit values in M2 from the 16-bit values in M1. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_pi16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_psubw ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubw (__m64 __m1, __m64 __m2)
{
return _mm_sub_pi16 (__m1, __m2);
}
/* Subtract the 32-bit values in M2 from the 32-bit values in M1. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_pi32 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_psubd ((__v2si)__m1, (__v2si)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubd (__m64 __m1, __m64 __m2)
{
return _mm_sub_pi32 (__m1, __m2);
}
/* Add the 64-bit values in M1 to the 64-bit values in M2. */
#ifdef __SSE2__
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_si64 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_psubq ((__v1di)__m1, (__v1di)__m2);
}
#endif
/* Subtract the 8-bit values in M2 from the 8-bit values in M1 using signed
saturating arithmetic. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_subs_pi8 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_psubsb ((__v8qi)__m1, (__v8qi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubsb (__m64 __m1, __m64 __m2)
{
return _mm_subs_pi8 (__m1, __m2);
}
/* Subtract the 16-bit values in M2 from the 16-bit values in M1 using
signed saturating arithmetic. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_subs_pi16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_psubsw ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubsw (__m64 __m1, __m64 __m2)
{
return _mm_subs_pi16 (__m1, __m2);
}
/* Subtract the 8-bit values in M2 from the 8-bit values in M1 using
unsigned saturating arithmetic. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_subs_pu8 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_psubusb ((__v8qi)__m1, (__v8qi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubusb (__m64 __m1, __m64 __m2)
{
return _mm_subs_pu8 (__m1, __m2);
}
/* Subtract the 16-bit values in M2 from the 16-bit values in M1 using
unsigned saturating arithmetic. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_subs_pu16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_psubusw ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psubusw (__m64 __m1, __m64 __m2)
{
return _mm_subs_pu16 (__m1, __m2);
}
/* Multiply four 16-bit values in M1 by four 16-bit values in M2 producing
four 32-bit intermediate results, which are then summed by pairs to
produce two 32-bit results. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_madd_pi16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_pmaddwd ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pmaddwd (__m64 __m1, __m64 __m2)
{
return _mm_madd_pi16 (__m1, __m2);
}
/* Multiply four signed 16-bit values in M1 by four signed 16-bit values in
M2 and produce the high 16 bits of the 32-bit results. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mulhi_pi16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_pmulhw ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pmulhw (__m64 __m1, __m64 __m2)
{
return _mm_mulhi_pi16 (__m1, __m2);
}
/* Multiply four 16-bit values in M1 by four 16-bit values in M2 and produce
the low 16 bits of the results. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mullo_pi16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_pmullw ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pmullw (__m64 __m1, __m64 __m2)
{
return _mm_mullo_pi16 (__m1, __m2);
}
/* Shift four 16-bit values in M left by COUNT. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sll_pi16 (__m64 __m, __m64 __count)
{
return (__m64) __builtin_ia32_psllw ((__v4hi)__m, (__v4hi)__count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psllw (__m64 __m, __m64 __count)
{
return _mm_sll_pi16 (__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_slli_pi16 (__m64 __m, int __count)
{
return (__m64) __builtin_ia32_psllwi ((__v4hi)__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psllwi (__m64 __m, int __count)
{
return _mm_slli_pi16 (__m, __count);
}
/* Shift two 32-bit values in M left by COUNT. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sll_pi32 (__m64 __m, __m64 __count)
{
return (__m64) __builtin_ia32_pslld ((__v2si)__m, (__v2si)__count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pslld (__m64 __m, __m64 __count)
{
return _mm_sll_pi32 (__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_slli_pi32 (__m64 __m, int __count)
{
return (__m64) __builtin_ia32_pslldi ((__v2si)__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pslldi (__m64 __m, int __count)
{
return _mm_slli_pi32 (__m, __count);
}
/* Shift the 64-bit value in M left by COUNT. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sll_si64 (__m64 __m, __m64 __count)
{
return (__m64) __builtin_ia32_psllq ((__v1di)__m, (__v1di)__count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psllq (__m64 __m, __m64 __count)
{
return _mm_sll_si64 (__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_slli_si64 (__m64 __m, int __count)
{
return (__m64) __builtin_ia32_psllqi ((__v1di)__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psllqi (__m64 __m, int __count)
{
return _mm_slli_si64 (__m, __count);
}
/* Shift four 16-bit values in M right by COUNT; shift in the sign bit. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sra_pi16 (__m64 __m, __m64 __count)
{
return (__m64) __builtin_ia32_psraw ((__v4hi)__m, (__v4hi)__count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psraw (__m64 __m, __m64 __count)
{
return _mm_sra_pi16 (__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srai_pi16 (__m64 __m, int __count)
{
return (__m64) __builtin_ia32_psrawi ((__v4hi)__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrawi (__m64 __m, int __count)
{
return _mm_srai_pi16 (__m, __count);
}
/* Shift two 32-bit values in M right by COUNT; shift in the sign bit. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_sra_pi32 (__m64 __m, __m64 __count)
{
return (__m64) __builtin_ia32_psrad ((__v2si)__m, (__v2si)__count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrad (__m64 __m, __m64 __count)
{
return _mm_sra_pi32 (__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srai_pi32 (__m64 __m, int __count)
{
return (__m64) __builtin_ia32_psradi ((__v2si)__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psradi (__m64 __m, int __count)
{
return _mm_srai_pi32 (__m, __count);
}
/* Shift four 16-bit values in M right by COUNT; shift in zeros. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srl_pi16 (__m64 __m, __m64 __count)
{
return (__m64) __builtin_ia32_psrlw ((__v4hi)__m, (__v4hi)__count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrlw (__m64 __m, __m64 __count)
{
return _mm_srl_pi16 (__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srli_pi16 (__m64 __m, int __count)
{
return (__m64) __builtin_ia32_psrlwi ((__v4hi)__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrlwi (__m64 __m, int __count)
{
return _mm_srli_pi16 (__m, __count);
}
/* Shift two 32-bit values in M right by COUNT; shift in zeros. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srl_pi32 (__m64 __m, __m64 __count)
{
return (__m64) __builtin_ia32_psrld ((__v2si)__m, (__v2si)__count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrld (__m64 __m, __m64 __count)
{
return _mm_srl_pi32 (__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srli_pi32 (__m64 __m, int __count)
{
return (__m64) __builtin_ia32_psrldi ((__v2si)__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrldi (__m64 __m, int __count)
{
return _mm_srli_pi32 (__m, __count);
}
/* Shift the 64-bit value in M left by COUNT; shift in zeros. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srl_si64 (__m64 __m, __m64 __count)
{
return (__m64) __builtin_ia32_psrlq ((__v1di)__m, (__v1di)__count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrlq (__m64 __m, __m64 __count)
{
return _mm_srl_si64 (__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_srli_si64 (__m64 __m, int __count)
{
return (__m64) __builtin_ia32_psrlqi ((__v1di)__m, __count);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_psrlqi (__m64 __m, int __count)
{
return _mm_srli_si64 (__m, __count);
}
/* Bit-wise AND the 64-bit values in M1 and M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_and_si64 (__m64 __m1, __m64 __m2)
{
return __builtin_ia32_pand (__m1, __m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pand (__m64 __m1, __m64 __m2)
{
return _mm_and_si64 (__m1, __m2);
}
/* Bit-wise complement the 64-bit value in M1 and bit-wise AND it with the
64-bit value in M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_andnot_si64 (__m64 __m1, __m64 __m2)
{
return __builtin_ia32_pandn (__m1, __m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pandn (__m64 __m1, __m64 __m2)
{
return _mm_andnot_si64 (__m1, __m2);
}
/* Bit-wise inclusive OR the 64-bit values in M1 and M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_or_si64 (__m64 __m1, __m64 __m2)
{
return __builtin_ia32_por (__m1, __m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_por (__m64 __m1, __m64 __m2)
{
return _mm_or_si64 (__m1, __m2);
}
/* Bit-wise exclusive OR the 64-bit values in M1 and M2. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_xor_si64 (__m64 __m1, __m64 __m2)
{
return __builtin_ia32_pxor (__m1, __m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pxor (__m64 __m1, __m64 __m2)
{
return _mm_xor_si64 (__m1, __m2);
}
/* Compare eight 8-bit values. The result of the comparison is 0xFF if the
test is true and zero if false. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_pi8 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_pcmpeqb ((__v8qi)__m1, (__v8qi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pcmpeqb (__m64 __m1, __m64 __m2)
{
return _mm_cmpeq_pi8 (__m1, __m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_pi8 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_pcmpgtb ((__v8qi)__m1, (__v8qi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pcmpgtb (__m64 __m1, __m64 __m2)
{
return _mm_cmpgt_pi8 (__m1, __m2);
}
/* Compare four 16-bit values. The result of the comparison is 0xFFFF if
the test is true and zero if false. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_pi16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_pcmpeqw ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pcmpeqw (__m64 __m1, __m64 __m2)
{
return _mm_cmpeq_pi16 (__m1, __m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_pi16 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_pcmpgtw ((__v4hi)__m1, (__v4hi)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pcmpgtw (__m64 __m1, __m64 __m2)
{
return _mm_cmpgt_pi16 (__m1, __m2);
}
/* Compare two 32-bit values. The result of the comparison is 0xFFFFFFFF if
the test is true and zero if false. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpeq_pi32 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_pcmpeqd ((__v2si)__m1, (__v2si)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pcmpeqd (__m64 __m1, __m64 __m2)
{
return _mm_cmpeq_pi32 (__m1, __m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmpgt_pi32 (__m64 __m1, __m64 __m2)
{
return (__m64) __builtin_ia32_pcmpgtd ((__v2si)__m1, (__v2si)__m2);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_m_pcmpgtd (__m64 __m1, __m64 __m2)
{
return _mm_cmpgt_pi32 (__m1, __m2);
}
/* Creates a 64-bit zero. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setzero_si64 (void)
{
return (__m64)0LL;
}
/* Creates a vector of two 32-bit values; I0 is least significant. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_pi32 (int __i1, int __i0)
{
return (__m64) __builtin_ia32_vec_init_v2si (__i0, __i1);
}
/* Creates a vector of four 16-bit values; W0 is least significant. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_pi16 (short __w3, short __w2, short __w1, short __w0)
{
return (__m64) __builtin_ia32_vec_init_v4hi (__w0, __w1, __w2, __w3);
}
/* Creates a vector of eight 8-bit values; B0 is least significant. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set_pi8 (char __b7, char __b6, char __b5, char __b4,
char __b3, char __b2, char __b1, char __b0)
{
return (__m64) __builtin_ia32_vec_init_v8qi (__b0, __b1, __b2, __b3,
__b4, __b5, __b6, __b7);
}
/* Similar, but with the arguments in reverse order. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setr_pi32 (int __i0, int __i1)
{
return _mm_set_pi32 (__i1, __i0);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setr_pi16 (short __w0, short __w1, short __w2, short __w3)
{
return _mm_set_pi16 (__w3, __w2, __w1, __w0);
}
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_setr_pi8 (char __b0, char __b1, char __b2, char __b3,
char __b4, char __b5, char __b6, char __b7)
{
return _mm_set_pi8 (__b7, __b6, __b5, __b4, __b3, __b2, __b1, __b0);
}
/* Creates a vector of two 32-bit values, both elements containing I. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set1_pi32 (int __i)
{
return _mm_set_pi32 (__i, __i);
}
/* Creates a vector of four 16-bit values, all elements containing W. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set1_pi16 (short __w)
{
return _mm_set_pi16 (__w, __w, __w, __w);
}
/* Creates a vector of eight 8-bit values, all elements containing B. */
extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_set1_pi8 (char __b)
{
return _mm_set_pi8 (__b, __b, __b, __b, __b, __b, __b, __b);
}
#endif /* __MMX__ */
#endif /* _MMINTRIN_H_INCLUDED */
|