/usr/share/gccxml-0.9/GCC/3.4/xmmintrin.h is in gccxml 0.9.0+git20140716-2.
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 | /* Copyright (C) 2002, 2003, 2004 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 2, 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.
You should have received a copy of the GNU General Public License
along with GCC; see the file COPYING. If not, write to
the Free Software Foundation, 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA. */
/* As a special exception, if you include this header file into source
files compiled by GCC, this header file does not by itself cause
the resulting executable to be covered by the GNU General Public
License. This exception does not however invalidate any other
reasons why the executable file might be covered by the GNU General
Public License. */
/* Implemented from the specification included in the Intel C++ Compiler
User Guide and Reference, version 8.0. */
#ifndef _XMMINTRIN_H_INCLUDED
#define _XMMINTRIN_H_INCLUDED
#ifndef __SSE__
# error "SSE instruction set not enabled"
#else
/* We need type definitions from the MMX header file. */
#include <mmintrin.h>
/* The data type intended for user use. */
typedef float __m128 __attribute__ ((__mode__(__V4SF__)));
/* Internal data types for implementing the intrinsics. */
typedef float __v4sf __attribute__ ((__mode__(__V4SF__)));
/* Create a selector for use with the SHUFPS instruction. */
#define _MM_SHUFFLE(fp3,fp2,fp1,fp0) \
(((fp3) << 6) | ((fp2) << 4) | ((fp1) << 2) | (fp0))
/* Constants for use with _mm_prefetch. */
enum _mm_hint
{
_MM_HINT_T0 = 3,
_MM_HINT_T1 = 2,
_MM_HINT_T2 = 1,
_MM_HINT_NTA = 0
};
/* Bits in the MXCSR. */
#define _MM_EXCEPT_MASK 0x003f
#define _MM_EXCEPT_INVALID 0x0001
#define _MM_EXCEPT_DENORM 0x0002
#define _MM_EXCEPT_DIV_ZERO 0x0004
#define _MM_EXCEPT_OVERFLOW 0x0008
#define _MM_EXCEPT_UNDERFLOW 0x0010
#define _MM_EXCEPT_INEXACT 0x0020
#define _MM_MASK_MASK 0x1f80
#define _MM_MASK_INVALID 0x0080
#define _MM_MASK_DENORM 0x0100
#define _MM_MASK_DIV_ZERO 0x0200
#define _MM_MASK_OVERFLOW 0x0400
#define _MM_MASK_UNDERFLOW 0x0800
#define _MM_MASK_INEXACT 0x1000
#define _MM_ROUND_MASK 0x6000
#define _MM_ROUND_NEAREST 0x0000
#define _MM_ROUND_DOWN 0x2000
#define _MM_ROUND_UP 0x4000
#define _MM_ROUND_TOWARD_ZERO 0x6000
#define _MM_FLUSH_ZERO_MASK 0x8000
#define _MM_FLUSH_ZERO_ON 0x8000
#define _MM_FLUSH_ZERO_OFF 0x0000
/* Perform the respective operation on the lower SPFP (single-precision
floating-point) values of A and B; the upper three SPFP values are
passed through from A. */
static __inline __m128
_mm_add_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_sub_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_mul_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_div_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_sqrt_ss (__m128 __A)
;
static __inline __m128
_mm_rcp_ss (__m128 __A)
;
static __inline __m128
_mm_rsqrt_ss (__m128 __A)
;
static __inline __m128
_mm_min_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_max_ss (__m128 __A, __m128 __B)
;
/* Perform the respective operation on the four SPFP values in A and B. */
static __inline __m128
_mm_add_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_sub_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_mul_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_div_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_sqrt_ps (__m128 __A)
;
static __inline __m128
_mm_rcp_ps (__m128 __A)
;
static __inline __m128
_mm_rsqrt_ps (__m128 __A)
;
static __inline __m128
_mm_min_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_max_ps (__m128 __A, __m128 __B)
;
/* Perform logical bit-wise operations on 128-bit values. */
static __inline __m128
_mm_and_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_andnot_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_or_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_xor_ps (__m128 __A, __m128 __B)
;
/* Perform a comparison on the lower SPFP values of A and B. If the
comparison is true, place a mask of all ones in the result, otherwise a
mask of zeros. The upper three SPFP values are passed through from A. */
static __inline __m128
_mm_cmpeq_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmplt_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmple_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpgt_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpge_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpneq_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpnlt_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpnle_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpngt_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpnge_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpord_ss (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpunord_ss (__m128 __A, __m128 __B)
;
/* Perform a comparison on the four SPFP values of A and B. For each
element, if the comparison is true, place a mask of all ones in the
result, otherwise a mask of zeros. */
static __inline __m128
_mm_cmpeq_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmplt_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmple_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpgt_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpge_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpneq_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpnlt_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpnle_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpngt_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpnge_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpord_ps (__m128 __A, __m128 __B)
;
static __inline __m128
_mm_cmpunord_ps (__m128 __A, __m128 __B)
;
/* Compare the lower SPFP values of A and B and return 1 if true
and 0 if false. */
static __inline int
_mm_comieq_ss (__m128 __A, __m128 __B)
;
static __inline int
_mm_comilt_ss (__m128 __A, __m128 __B)
;
static __inline int
_mm_comile_ss (__m128 __A, __m128 __B)
;
static __inline int
_mm_comigt_ss (__m128 __A, __m128 __B)
;
static __inline int
_mm_comige_ss (__m128 __A, __m128 __B)
;
static __inline int
_mm_comineq_ss (__m128 __A, __m128 __B)
;
static __inline int
_mm_ucomieq_ss (__m128 __A, __m128 __B)
;
static __inline int
_mm_ucomilt_ss (__m128 __A, __m128 __B)
;
static __inline int
_mm_ucomile_ss (__m128 __A, __m128 __B)
;
static __inline int
_mm_ucomigt_ss (__m128 __A, __m128 __B)
;
static __inline int
_mm_ucomige_ss (__m128 __A, __m128 __B)
;
static __inline int
_mm_ucomineq_ss (__m128 __A, __m128 __B)
;
/* Convert the lower SPFP value to a 32-bit integer according to the current
rounding mode. */
static __inline int
_mm_cvtss_si32 (__m128 __A)
;
static __inline int
_mm_cvt_ss2si (__m128 __A)
;
#ifdef __x86_64__
/* Convert the lower SPFP value to a 32-bit integer according to the current
rounding mode. */
static __inline long long
_mm_cvtss_si64x (__m128 __A)
;
#endif
/* Convert the two lower SPFP values to 32-bit integers according to the
current rounding mode. Return the integers in packed form. */
static __inline __m64
_mm_cvtps_pi32 (__m128 __A)
;
static __inline __m64
_mm_cvt_ps2pi (__m128 __A)
;
/* Truncate the lower SPFP value to a 32-bit integer. */
static __inline int
_mm_cvttss_si32 (__m128 __A)
;
static __inline int
_mm_cvtt_ss2si (__m128 __A)
;
#ifdef __x86_64__
/* Truncate the lower SPFP value to a 32-bit integer. */
static __inline long long
_mm_cvttss_si64x (__m128 __A)
;
#endif
/* Truncate the two lower SPFP values to 32-bit integers. Return the
integers in packed form. */
static __inline __m64
_mm_cvttps_pi32 (__m128 __A)
;
static __inline __m64
_mm_cvtt_ps2pi (__m128 __A)
;
/* Convert B to a SPFP value and insert it as element zero in A. */
static __inline __m128
_mm_cvtsi32_ss (__m128 __A, int __B)
;
static __inline __m128
_mm_cvt_si2ss (__m128 __A, int __B)
;
#ifdef __x86_64__
/* Convert B to a SPFP value and insert it as element zero in A. */
static __inline __m128
_mm_cvtsi64x_ss (__m128 __A, long long __B)
;
#endif
/* Convert the two 32-bit values in B to SPFP form and insert them
as the two lower elements in A. */
static __inline __m128
_mm_cvtpi32_ps (__m128 __A, __m64 __B)
;
static __inline __m128
_mm_cvt_pi2ps (__m128 __A, __m64 __B)
;
/* Convert the four signed 16-bit values in A to SPFP form. */
static __inline __m128
_mm_cvtpi16_ps (__m64 __A)
;
/* Convert the four unsigned 16-bit values in A to SPFP form. */
static __inline __m128
_mm_cvtpu16_ps (__m64 __A)
;
/* Convert the low four signed 8-bit values in A to SPFP form. */
static __inline __m128
_mm_cvtpi8_ps (__m64 __A)
;
/* Convert the low four unsigned 8-bit values in A to SPFP form. */
static __inline __m128
_mm_cvtpu8_ps(__m64 __A)
;
/* Convert the four signed 32-bit values in A and B to SPFP form. */
static __inline __m128
_mm_cvtpi32x2_ps(__m64 __A, __m64 __B)
;
/* Convert the four SPFP values in A to four signed 16-bit integers. */
static __inline __m64
_mm_cvtps_pi16(__m128 __A)
;
/* Convert the four SPFP values in A to four signed 8-bit integers. */
static __inline __m64
_mm_cvtps_pi8(__m128 __A)
;
/* Selects four specific SPFP values from A and B based on MASK. */
#if 0
static __inline __m128
_mm_shuffle_ps (__m128 __A, __m128 __B, int __mask)
;
#else
#define _mm_shuffle_ps(A, B, MASK) \
((__m128) __builtin_ia32_shufps ((__v4sf)(A), (__v4sf)(B), (MASK)))
#endif
/* Selects and interleaves the upper two SPFP values from A and B. */
static __inline __m128
_mm_unpackhi_ps (__m128 __A, __m128 __B)
;
/* Selects and interleaves the lower two SPFP values from A and B. */
static __inline __m128
_mm_unpacklo_ps (__m128 __A, __m128 __B)
;
/* Sets the upper two SPFP values with 64-bits of data loaded from P;
the lower two values are passed through from A. */
static __inline __m128
_mm_loadh_pi (__m128 __A, __m64 const *__P)
;
/* Stores the upper two SPFP values of A into P. */
static __inline void
_mm_storeh_pi (__m64 *__P, __m128 __A)
;
/* Moves the upper two values of B into the lower two values of A. */
static __inline __m128
_mm_movehl_ps (__m128 __A, __m128 __B)
;
/* Moves the lower two values of B into the upper two values of A. */
static __inline __m128
_mm_movelh_ps (__m128 __A, __m128 __B)
;
/* Sets the lower two SPFP values with 64-bits of data loaded from P;
the upper two values are passed through from A. */
static __inline __m128
_mm_loadl_pi (__m128 __A, __m64 const *__P)
;
/* Stores the lower two SPFP values of A into P. */
static __inline void
_mm_storel_pi (__m64 *__P, __m128 __A)
;
/* Creates a 4-bit mask from the most significant bits of the SPFP values. */
static __inline int
_mm_movemask_ps (__m128 __A)
;
/* Return the contents of the control register. */
static __inline unsigned int
_mm_getcsr (void)
;
/* Read exception bits from the control register. */
static __inline unsigned int
_MM_GET_EXCEPTION_STATE (void)
;
static __inline unsigned int
_MM_GET_EXCEPTION_MASK (void)
;
static __inline unsigned int
_MM_GET_ROUNDING_MODE (void)
;
static __inline unsigned int
_MM_GET_FLUSH_ZERO_MODE (void)
;
/* Set the control register to I. */
static __inline void
_mm_setcsr (unsigned int __I)
;
/* Set exception bits in the control register. */
static __inline void
_MM_SET_EXCEPTION_STATE(unsigned int __mask)
;
static __inline void
_MM_SET_EXCEPTION_MASK (unsigned int __mask)
;
static __inline void
_MM_SET_ROUNDING_MODE (unsigned int __mode)
;
static __inline void
_MM_SET_FLUSH_ZERO_MODE (unsigned int __mode)
;
/* Create a vector with element 0 as *P and the rest zero. */
static __inline __m128
_mm_load_ss (float const *__P)
;
/* Create a vector with all four elements equal to *P. */
static __inline __m128
_mm_load1_ps (float const *__P)
;
static __inline __m128
_mm_load_ps1 (float const *__P)
;
/* Load four SPFP values from P. The address must be 16-byte aligned. */
static __inline __m128
_mm_load_ps (float const *__P)
;
/* Load four SPFP values from P. The address need not be 16-byte aligned. */
static __inline __m128
_mm_loadu_ps (float const *__P)
;
/* Load four SPFP values in reverse order. The address must be aligned. */
static __inline __m128
_mm_loadr_ps (float const *__P)
;
/* Create a vector with element 0 as F and the rest zero. */
static __inline __m128
_mm_set_ss (float __F)
;
/* Create a vector with all four elements equal to F. */
static __inline __m128
_mm_set1_ps (float __F)
;
static __inline __m128
_mm_set_ps1 (float __F)
;
/* Create the vector [Z Y X W]. */
static __inline __m128
_mm_set_ps (const float __Z, const float __Y, const float __X, const float __W)
;
/* Create the vector [W X Y Z]. */
static __inline __m128
_mm_setr_ps (float __Z, float __Y, float __X, float __W)
;
/* Create a vector of zeros. */
static __inline __m128
_mm_setzero_ps (void)
;
/* Stores the lower SPFP value. */
static __inline void
_mm_store_ss (float *__P, __m128 __A)
;
/* Store the lower SPFP value across four words. */
static __inline void
_mm_store1_ps (float *__P, __m128 __A)
;
static __inline void
_mm_store_ps1 (float *__P, __m128 __A)
;
/* Store four SPFP values. The address must be 16-byte aligned. */
static __inline void
_mm_store_ps (float *__P, __m128 __A)
;
/* Store four SPFP values. The address need not be 16-byte aligned. */
static __inline void
_mm_storeu_ps (float *__P, __m128 __A)
;
/* Store four SPFP values in reverse order. The address must be aligned. */
static __inline void
_mm_storer_ps (float *__P, __m128 __A)
;
/* Sets the low SPFP value of A from the low value of B. */
static __inline __m128
_mm_move_ss (__m128 __A, __m128 __B)
;
/* Extracts one of the four words of A. The selector N must be immediate. */
#if 0
static __inline int
_mm_extract_pi16 (__m64 __A, int __N)
;
static __inline int
_m_pextrw (__m64 __A, int __N)
;
#else
#define _mm_extract_pi16(A, N) \
__builtin_ia32_pextrw ((__v4hi)(A), (N))
#define _m_pextrw(A, N) _mm_extract_pi16((A), (N))
#endif
/* Inserts word D into one of four words of A. The selector N must be
immediate. */
#if 0
static __inline __m64
_mm_insert_pi16 (__m64 __A, int __D, int __N)
;
static __inline __m64
_m_pinsrw (__m64 __A, int __D, int __N)
;
#else
#define _mm_insert_pi16(A, D, N) \
((__m64) __builtin_ia32_pinsrw ((__v4hi)(A), (D), (N)))
#define _m_pinsrw(A, D, N) _mm_insert_pi16((A), (D), (N))
#endif
/* Compute the element-wise maximum of signed 16-bit values. */
static __inline __m64
_mm_max_pi16 (__m64 __A, __m64 __B)
;
static __inline __m64
_m_pmaxsw (__m64 __A, __m64 __B)
;
/* Compute the element-wise maximum of unsigned 8-bit values. */
static __inline __m64
_mm_max_pu8 (__m64 __A, __m64 __B)
;
static __inline __m64
_m_pmaxub (__m64 __A, __m64 __B)
;
/* Compute the element-wise minimum of signed 16-bit values. */
static __inline __m64
_mm_min_pi16 (__m64 __A, __m64 __B)
;
static __inline __m64
_m_pminsw (__m64 __A, __m64 __B)
;
/* Compute the element-wise minimum of unsigned 8-bit values. */
static __inline __m64
_mm_min_pu8 (__m64 __A, __m64 __B)
;
static __inline __m64
_m_pminub (__m64 __A, __m64 __B)
;
/* Create an 8-bit mask of the signs of 8-bit values. */
static __inline int
_mm_movemask_pi8 (__m64 __A)
;
static __inline int
_m_pmovmskb (__m64 __A)
;
/* Multiply four unsigned 16-bit values in A by four unsigned 16-bit values
in B and produce the high 16 bits of the 32-bit results. */
static __inline __m64
_mm_mulhi_pu16 (__m64 __A, __m64 __B)
;
static __inline __m64
_m_pmulhuw (__m64 __A, __m64 __B)
;
/* Return a combination of the four 16-bit values in A. The selector
must be an immediate. */
#if 0
static __inline __m64
_mm_shuffle_pi16 (__m64 __A, int __N)
;
static __inline __m64
_m_pshufw (__m64 __A, int __N)
;
#else
#define _mm_shuffle_pi16(A, N) \
((__m64) __builtin_ia32_pshufw ((__v4hi)(A), (N)))
#define _m_pshufw(A, N) _mm_shuffle_pi16 ((A), (N))
#endif
/* Conditionally store byte elements of A into P. The high bit of each
byte in the selector N determines whether the corresponding byte from
A is stored. */
static __inline void
_mm_maskmove_si64 (__m64 __A, __m64 __N, char *__P)
;
static __inline void
_m_maskmovq (__m64 __A, __m64 __N, char *__P)
;
/* Compute the rounded averages of the unsigned 8-bit values in A and B. */
static __inline __m64
_mm_avg_pu8 (__m64 __A, __m64 __B)
;
static __inline __m64
_m_pavgb (__m64 __A, __m64 __B)
;
/* Compute the rounded averages of the unsigned 16-bit values in A and B. */
static __inline __m64
_mm_avg_pu16 (__m64 __A, __m64 __B)
;
static __inline __m64
_m_pavgw (__m64 __A, __m64 __B)
;
/* Compute the sum of the absolute differences of the unsigned 8-bit
values in A and B. Return the value in the lower 16-bit word; the
upper words are cleared. */
static __inline __m64
_mm_sad_pu8 (__m64 __A, __m64 __B)
;
static __inline __m64
_m_psadbw (__m64 __A, __m64 __B)
;
/* Loads one cache line from address P to a location "closer" to the
processor. The selector I specifies the type of prefetch operation. */
#if 0
static __inline void
_mm_prefetch (void *__P, enum _mm_hint __I)
;
#else
#define _mm_prefetch(P, I) \
__builtin_prefetch ((P), 0, (I))
#endif
/* Stores the data in A to the address P without polluting the caches. */
static __inline void
_mm_stream_pi (__m64 *__P, __m64 __A)
;
/* Likewise. The address must be 16-byte aligned. */
static __inline void
_mm_stream_ps (float *__P, __m128 __A)
;
/* Guarantees that every preceding store is globally visible before
any subsequent store. */
static __inline void
_mm_sfence (void)
;
/* The execution of the next instruction is delayed by an implementation
specific amount of time. The instruction does not modify the
architectural state. */
static __inline void
_mm_pause (void)
;
/* Transpose the 4x4 matrix composed of row[0-3]. */
#define _MM_TRANSPOSE4_PS(row0, row1, row2, row3) \
do { \
__v4sf __r0 = (row0), __r1 = (row1), __r2 = (row2), __r3 = (row3); \
__v4sf __t0 = __builtin_ia32_shufps (__r0, __r1, 0x44); \
__v4sf __t2 = __builtin_ia32_shufps (__r0, __r1, 0xEE); \
__v4sf __t1 = __builtin_ia32_shufps (__r2, __r3, 0x44); \
__v4sf __t3 = __builtin_ia32_shufps (__r2, __r3, 0xEE); \
(row0) = __builtin_ia32_shufps (__t0, __t1, 0x88); \
(row1) = __builtin_ia32_shufps (__t0, __t1, 0xDD); \
(row2) = __builtin_ia32_shufps (__t2, __t3, 0x88); \
(row3) = __builtin_ia32_shufps (__t2, __t3, 0xDD); \
} while (0)
/* For backward source compatibility. */
#include <emmintrin.h>
#endif /* __SSE__ */
#endif /* _XMMINTRIN_H_INCLUDED */
|