/usr/lib/gcc/x86_64-linux-gnu/4.7/include/avxintrin.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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 | /* Copyright (C) 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 11.0. */
#ifndef _IMMINTRIN_H_INCLUDED
# error "Never use <avxintrin.h> directly; include <immintrin.h> instead."
#endif
/* Internal data types for implementing the intrinsics. */
typedef double __v4df __attribute__ ((__vector_size__ (32)));
typedef float __v8sf __attribute__ ((__vector_size__ (32)));
typedef long long __v4di __attribute__ ((__vector_size__ (32)));
typedef int __v8si __attribute__ ((__vector_size__ (32)));
typedef short __v16hi __attribute__ ((__vector_size__ (32)));
typedef char __v32qi __attribute__ ((__vector_size__ (32)));
/* The Intel API is flexible enough that we must allow aliasing with other
vector types, and their scalar components. */
typedef float __m256 __attribute__ ((__vector_size__ (32),
__may_alias__));
typedef long long __m256i __attribute__ ((__vector_size__ (32),
__may_alias__));
typedef double __m256d __attribute__ ((__vector_size__ (32),
__may_alias__));
/* Compare predicates for scalar and packed compare intrinsics. */
/* Equal (ordered, non-signaling) */
#define _CMP_EQ_OQ 0x00
/* Less-than (ordered, signaling) */
#define _CMP_LT_OS 0x01
/* Less-than-or-equal (ordered, signaling) */
#define _CMP_LE_OS 0x02
/* Unordered (non-signaling) */
#define _CMP_UNORD_Q 0x03
/* Not-equal (unordered, non-signaling) */
#define _CMP_NEQ_UQ 0x04
/* Not-less-than (unordered, signaling) */
#define _CMP_NLT_US 0x05
/* Not-less-than-or-equal (unordered, signaling) */
#define _CMP_NLE_US 0x06
/* Ordered (nonsignaling) */
#define _CMP_ORD_Q 0x07
/* Equal (unordered, non-signaling) */
#define _CMP_EQ_UQ 0x08
/* Not-greater-than-or-equal (unordered, signaling) */
#define _CMP_NGE_US 0x09
/* Not-greater-than (unordered, signaling) */
#define _CMP_NGT_US 0x0a
/* False (ordered, non-signaling) */
#define _CMP_FALSE_OQ 0x0b
/* Not-equal (ordered, non-signaling) */
#define _CMP_NEQ_OQ 0x0c
/* Greater-than-or-equal (ordered, signaling) */
#define _CMP_GE_OS 0x0d
/* Greater-than (ordered, signaling) */
#define _CMP_GT_OS 0x0e
/* True (unordered, non-signaling) */
#define _CMP_TRUE_UQ 0x0f
/* Equal (ordered, signaling) */
#define _CMP_EQ_OS 0x10
/* Less-than (ordered, non-signaling) */
#define _CMP_LT_OQ 0x11
/* Less-than-or-equal (ordered, non-signaling) */
#define _CMP_LE_OQ 0x12
/* Unordered (signaling) */
#define _CMP_UNORD_S 0x13
/* Not-equal (unordered, signaling) */
#define _CMP_NEQ_US 0x14
/* Not-less-than (unordered, non-signaling) */
#define _CMP_NLT_UQ 0x15
/* Not-less-than-or-equal (unordered, non-signaling) */
#define _CMP_NLE_UQ 0x16
/* Ordered (signaling) */
#define _CMP_ORD_S 0x17
/* Equal (unordered, signaling) */
#define _CMP_EQ_US 0x18
/* Not-greater-than-or-equal (unordered, non-signaling) */
#define _CMP_NGE_UQ 0x19
/* Not-greater-than (unordered, non-signaling) */
#define _CMP_NGT_UQ 0x1a
/* False (ordered, signaling) */
#define _CMP_FALSE_OS 0x1b
/* Not-equal (ordered, signaling) */
#define _CMP_NEQ_OS 0x1c
/* Greater-than-or-equal (ordered, non-signaling) */
#define _CMP_GE_OQ 0x1d
/* Greater-than (ordered, non-signaling) */
#define _CMP_GT_OQ 0x1e
/* True (unordered, signaling) */
#define _CMP_TRUE_US 0x1f
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_add_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_addpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_add_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_addps256 ((__v8sf)__A, (__v8sf)__B);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_addsub_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_addsubpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_addsub_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_addsubps256 ((__v8sf)__A, (__v8sf)__B);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_and_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_andpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_and_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_andps256 ((__v8sf)__A, (__v8sf)__B);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_andnot_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_andnpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_andnot_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_andnps256 ((__v8sf)__A, (__v8sf)__B);
}
/* Double/single precision floating point blend instructions - select
data from 2 sources using constant/variable mask. */
#ifdef __OPTIMIZE__
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_blend_pd (__m256d __X, __m256d __Y, const int __M)
{
return (__m256d) __builtin_ia32_blendpd256 ((__v4df)__X,
(__v4df)__Y,
__M);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_blend_ps (__m256 __X, __m256 __Y, const int __M)
{
return (__m256) __builtin_ia32_blendps256 ((__v8sf)__X,
(__v8sf)__Y,
__M);
}
#else
#define _mm256_blend_pd(X, Y, M) \
((__m256d) __builtin_ia32_blendpd256 ((__v4df)(__m256d)(X), \
(__v4df)(__m256d)(Y), (int)(M)))
#define _mm256_blend_ps(X, Y, M) \
((__m256) __builtin_ia32_blendps256 ((__v8sf)(__m256)(X), \
(__v8sf)(__m256)(Y), (int)(M)))
#endif
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_blendv_pd (__m256d __X, __m256d __Y, __m256d __M)
{
return (__m256d) __builtin_ia32_blendvpd256 ((__v4df)__X,
(__v4df)__Y,
(__v4df)__M);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_blendv_ps (__m256 __X, __m256 __Y, __m256 __M)
{
return (__m256) __builtin_ia32_blendvps256 ((__v8sf)__X,
(__v8sf)__Y,
(__v8sf)__M);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_div_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_divpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_div_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_divps256 ((__v8sf)__A, (__v8sf)__B);
}
/* Dot product instructions with mask-defined summing and zeroing parts
of result. */
#ifdef __OPTIMIZE__
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_dp_ps (__m256 __X, __m256 __Y, const int __M)
{
return (__m256) __builtin_ia32_dpps256 ((__v8sf)__X,
(__v8sf)__Y,
__M);
}
#else
#define _mm256_dp_ps(X, Y, M) \
((__m256) __builtin_ia32_dpps256 ((__v8sf)(__m256)(X), \
(__v8sf)(__m256)(Y), (int)(M)))
#endif
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_hadd_pd (__m256d __X, __m256d __Y)
{
return (__m256d) __builtin_ia32_haddpd256 ((__v4df)__X, (__v4df)__Y);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_hadd_ps (__m256 __X, __m256 __Y)
{
return (__m256) __builtin_ia32_haddps256 ((__v8sf)__X, (__v8sf)__Y);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_hsub_pd (__m256d __X, __m256d __Y)
{
return (__m256d) __builtin_ia32_hsubpd256 ((__v4df)__X, (__v4df)__Y);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_hsub_ps (__m256 __X, __m256 __Y)
{
return (__m256) __builtin_ia32_hsubps256 ((__v8sf)__X, (__v8sf)__Y);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_max_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_maxpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_max_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_maxps256 ((__v8sf)__A, (__v8sf)__B);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_min_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_minpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_min_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_minps256 ((__v8sf)__A, (__v8sf)__B);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mul_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_mulpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mul_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_mulps256 ((__v8sf)__A, (__v8sf)__B);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_or_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_orpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_or_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_orps256 ((__v8sf)__A, (__v8sf)__B);
}
#ifdef __OPTIMIZE__
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_shuffle_pd (__m256d __A, __m256d __B, const int __mask)
{
return (__m256d) __builtin_ia32_shufpd256 ((__v4df)__A, (__v4df)__B,
__mask);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_shuffle_ps (__m256 __A, __m256 __B, const int __mask)
{
return (__m256) __builtin_ia32_shufps256 ((__v8sf)__A, (__v8sf)__B,
__mask);
}
#else
#define _mm256_shuffle_pd(A, B, N) \
((__m256d)__builtin_ia32_shufpd256 ((__v4df)(__m256d)(A), \
(__v4df)(__m256d)(B), (int)(N)))
#define _mm256_shuffle_ps(A, B, N) \
((__m256) __builtin_ia32_shufps256 ((__v8sf)(__m256)(A), \
(__v8sf)(__m256)(B), (int)(N)))
#endif
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_sub_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_subpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_sub_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_subps256 ((__v8sf)__A, (__v8sf)__B);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_xor_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_xorpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_xor_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_xorps256 ((__v8sf)__A, (__v8sf)__B);
}
#ifdef __OPTIMIZE__
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmp_pd (__m128d __X, __m128d __Y, const int __P)
{
return (__m128d) __builtin_ia32_cmppd ((__v2df)__X, (__v2df)__Y, __P);
}
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmp_ps (__m128 __X, __m128 __Y, const int __P)
{
return (__m128) __builtin_ia32_cmpps ((__v4sf)__X, (__v4sf)__Y, __P);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cmp_pd (__m256d __X, __m256d __Y, const int __P)
{
return (__m256d) __builtin_ia32_cmppd256 ((__v4df)__X, (__v4df)__Y,
__P);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cmp_ps (__m256 __X, __m256 __Y, const int __P)
{
return (__m256) __builtin_ia32_cmpps256 ((__v8sf)__X, (__v8sf)__Y,
__P);
}
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmp_sd (__m128d __X, __m128d __Y, const int __P)
{
return (__m128d) __builtin_ia32_cmpsd ((__v2df)__X, (__v2df)__Y, __P);
}
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmp_ss (__m128 __X, __m128 __Y, const int __P)
{
return (__m128) __builtin_ia32_cmpss ((__v4sf)__X, (__v4sf)__Y, __P);
}
#else
#define _mm_cmp_pd(X, Y, P) \
((__m128d) __builtin_ia32_cmppd ((__v2df)(__m128d)(X), \
(__v2df)(__m128d)(Y), (int)(P)))
#define _mm_cmp_ps(X, Y, P) \
((__m128) __builtin_ia32_cmpps ((__v4sf)(__m128)(X), \
(__v4sf)(__m128)(Y), (int)(P)))
#define _mm256_cmp_pd(X, Y, P) \
((__m256d) __builtin_ia32_cmppd256 ((__v4df)(__m256d)(X), \
(__v4df)(__m256d)(Y), (int)(P)))
#define _mm256_cmp_ps(X, Y, P) \
((__m256) __builtin_ia32_cmpps256 ((__v8sf)(__m256)(X), \
(__v8sf)(__m256)(Y), (int)(P)))
#define _mm_cmp_sd(X, Y, P) \
((__m128d) __builtin_ia32_cmpsd ((__v2df)(__m128d)(X), \
(__v2df)(__m128d)(Y), (int)(P)))
#define _mm_cmp_ss(X, Y, P) \
((__m128) __builtin_ia32_cmpss ((__v4sf)(__m128)(X), \
(__v4sf)(__m128)(Y), (int)(P)))
#endif
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cvtepi32_pd (__m128i __A)
{
return (__m256d)__builtin_ia32_cvtdq2pd256 ((__v4si) __A);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cvtepi32_ps (__m256i __A)
{
return (__m256)__builtin_ia32_cvtdq2ps256 ((__v8si) __A);
}
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cvtpd_ps (__m256d __A)
{
return (__m128)__builtin_ia32_cvtpd2ps256 ((__v4df) __A);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cvtps_epi32 (__m256 __A)
{
return (__m256i)__builtin_ia32_cvtps2dq256 ((__v8sf) __A);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cvtps_pd (__m128 __A)
{
return (__m256d)__builtin_ia32_cvtps2pd256 ((__v4sf) __A);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cvttpd_epi32 (__m256d __A)
{
return (__m128i)__builtin_ia32_cvttpd2dq256 ((__v4df) __A);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cvtpd_epi32 (__m256d __A)
{
return (__m128i)__builtin_ia32_cvtpd2dq256 ((__v4df) __A);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_cvttps_epi32 (__m256 __A)
{
return (__m256i)__builtin_ia32_cvttps2dq256 ((__v8sf) __A);
}
#ifdef __OPTIMIZE__
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_extractf128_pd (__m256d __X, const int __N)
{
return (__m128d) __builtin_ia32_vextractf128_pd256 ((__v4df)__X, __N);
}
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_extractf128_ps (__m256 __X, const int __N)
{
return (__m128) __builtin_ia32_vextractf128_ps256 ((__v8sf)__X, __N);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_extractf128_si256 (__m256i __X, const int __N)
{
return (__m128i) __builtin_ia32_vextractf128_si256 ((__v8si)__X, __N);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_extract_epi32 (__m256i __X, int const __N)
{
__m128i __Y = _mm256_extractf128_si256 (__X, __N >> 2);
return _mm_extract_epi32 (__Y, __N % 4);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_extract_epi16 (__m256i __X, int const __N)
{
__m128i __Y = _mm256_extractf128_si256 (__X, __N >> 3);
return _mm_extract_epi16 (__Y, __N % 8);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_extract_epi8 (__m256i __X, int const __N)
{
__m128i __Y = _mm256_extractf128_si256 (__X, __N >> 4);
return _mm_extract_epi8 (__Y, __N % 16);
}
#ifdef __x86_64__
extern __inline long long __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_extract_epi64 (__m256i __X, const int __N)
{
__m128i __Y = _mm256_extractf128_si256 (__X, __N >> 1);
return _mm_extract_epi64 (__Y, __N % 2);
}
#endif
#else
#define _mm256_extractf128_pd(X, N) \
((__m128d) __builtin_ia32_vextractf128_pd256 ((__v4df)(__m256d)(X), \
(int)(N)))
#define _mm256_extractf128_ps(X, N) \
((__m128) __builtin_ia32_vextractf128_ps256 ((__v8sf)(__m256)(X), \
(int)(N)))
#define _mm256_extractf128_si256(X, N) \
((__m128i) __builtin_ia32_vextractf128_si256 ((__v8si)(__m256i)(X), \
(int)(N)))
#define _mm256_extract_epi32(X, N) \
(__extension__ \
({ \
__m128i __Y = _mm256_extractf128_si256 ((X), (N) >> 2); \
_mm_extract_epi32 (__Y, (N) % 4); \
}))
#define _mm256_extract_epi16(X, N) \
(__extension__ \
({ \
__m128i __Y = _mm256_extractf128_si256 ((X), (N) >> 3); \
_mm_extract_epi16 (__Y, (N) % 8); \
}))
#define _mm256_extract_epi8(X, N) \
(__extension__ \
({ \
__m128i __Y = _mm256_extractf128_si256 ((X), (N) >> 4); \
_mm_extract_epi8 (__Y, (N) % 16); \
}))
#ifdef __x86_64__
#define _mm256_extract_epi64(X, N) \
(__extension__ \
({ \
__m128i __Y = _mm256_extractf128_si256 ((X), (N) >> 1); \
_mm_extract_epi64 (__Y, (N) % 2); \
}))
#endif
#endif
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_zeroall (void)
{
__builtin_ia32_vzeroall ();
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_zeroupper (void)
{
__builtin_ia32_vzeroupper ();
}
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_permutevar_pd (__m128d __A, __m128i __C)
{
return (__m128d) __builtin_ia32_vpermilvarpd ((__v2df)__A,
(__v2di)__C);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_permutevar_pd (__m256d __A, __m256i __C)
{
return (__m256d) __builtin_ia32_vpermilvarpd256 ((__v4df)__A,
(__v4di)__C);
}
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_permutevar_ps (__m128 __A, __m128i __C)
{
return (__m128) __builtin_ia32_vpermilvarps ((__v4sf)__A,
(__v4si)__C);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_permutevar_ps (__m256 __A, __m256i __C)
{
return (__m256) __builtin_ia32_vpermilvarps256 ((__v8sf)__A,
(__v8si)__C);
}
#ifdef __OPTIMIZE__
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_permute_pd (__m128d __X, const int __C)
{
return (__m128d) __builtin_ia32_vpermilpd ((__v2df)__X, __C);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_permute_pd (__m256d __X, const int __C)
{
return (__m256d) __builtin_ia32_vpermilpd256 ((__v4df)__X, __C);
}
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_permute_ps (__m128 __X, const int __C)
{
return (__m128) __builtin_ia32_vpermilps ((__v4sf)__X, __C);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_permute_ps (__m256 __X, const int __C)
{
return (__m256) __builtin_ia32_vpermilps256 ((__v8sf)__X, __C);
}
#else
#define _mm_permute_pd(X, C) \
((__m128d) __builtin_ia32_vpermilpd ((__v2df)(__m128d)(X), (int)(C)))
#define _mm256_permute_pd(X, C) \
((__m256d) __builtin_ia32_vpermilpd256 ((__v4df)(__m256d)(X), (int)(C)))
#define _mm_permute_ps(X, C) \
((__m128) __builtin_ia32_vpermilps ((__v4sf)(__m128)(X), (int)(C)))
#define _mm256_permute_ps(X, C) \
((__m256) __builtin_ia32_vpermilps256 ((__v8sf)(__m256)(X), (int)(C)))
#endif
#ifdef __OPTIMIZE__
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_permute2f128_pd (__m256d __X, __m256d __Y, const int __C)
{
return (__m256d) __builtin_ia32_vperm2f128_pd256 ((__v4df)__X,
(__v4df)__Y,
__C);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_permute2f128_ps (__m256 __X, __m256 __Y, const int __C)
{
return (__m256) __builtin_ia32_vperm2f128_ps256 ((__v8sf)__X,
(__v8sf)__Y,
__C);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_permute2f128_si256 (__m256i __X, __m256i __Y, const int __C)
{
return (__m256i) __builtin_ia32_vperm2f128_si256 ((__v8si)__X,
(__v8si)__Y,
__C);
}
#else
#define _mm256_permute2f128_pd(X, Y, C) \
((__m256d) __builtin_ia32_vperm2f128_pd256 ((__v4df)(__m256d)(X), \
(__v4df)(__m256d)(Y), \
(int)(C)))
#define _mm256_permute2f128_ps(X, Y, C) \
((__m256) __builtin_ia32_vperm2f128_ps256 ((__v8sf)(__m256)(X), \
(__v8sf)(__m256)(Y), \
(int)(C)))
#define _mm256_permute2f128_si256(X, Y, C) \
((__m256i) __builtin_ia32_vperm2f128_si256 ((__v8si)(__m256i)(X), \
(__v8si)(__m256i)(Y), \
(int)(C)))
#endif
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_broadcast_ss (float const *__X)
{
return (__m128) __builtin_ia32_vbroadcastss (__X);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_broadcast_sd (double const *__X)
{
return (__m256d) __builtin_ia32_vbroadcastsd256 (__X);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_broadcast_ss (float const *__X)
{
return (__m256) __builtin_ia32_vbroadcastss256 (__X);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_broadcast_pd (__m128d const *__X)
{
return (__m256d) __builtin_ia32_vbroadcastf128_pd256 (__X);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_broadcast_ps (__m128 const *__X)
{
return (__m256) __builtin_ia32_vbroadcastf128_ps256 (__X);
}
#ifdef __OPTIMIZE__
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_insertf128_pd (__m256d __X, __m128d __Y, const int __O)
{
return (__m256d) __builtin_ia32_vinsertf128_pd256 ((__v4df)__X,
(__v2df)__Y,
__O);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_insertf128_ps (__m256 __X, __m128 __Y, const int __O)
{
return (__m256) __builtin_ia32_vinsertf128_ps256 ((__v8sf)__X,
(__v4sf)__Y,
__O);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_insertf128_si256 (__m256i __X, __m128i __Y, const int __O)
{
return (__m256i) __builtin_ia32_vinsertf128_si256 ((__v8si)__X,
(__v4si)__Y,
__O);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_insert_epi32 (__m256i __X, int __D, int const __N)
{
__m128i __Y = _mm256_extractf128_si256 (__X, __N >> 2);
__Y = _mm_insert_epi32 (__Y, __D, __N % 4);
return _mm256_insertf128_si256 (__X, __Y, __N >> 2);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_insert_epi16 (__m256i __X, int __D, int const __N)
{
__m128i __Y = _mm256_extractf128_si256 (__X, __N >> 3);
__Y = _mm_insert_epi16 (__Y, __D, __N % 8);
return _mm256_insertf128_si256 (__X, __Y, __N >> 3);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_insert_epi8 (__m256i __X, int __D, int const __N)
{
__m128i __Y = _mm256_extractf128_si256 (__X, __N >> 4);
__Y = _mm_insert_epi8 (__Y, __D, __N % 16);
return _mm256_insertf128_si256 (__X, __Y, __N >> 4);
}
#ifdef __x86_64__
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_insert_epi64 (__m256i __X, long long __D, int const __N)
{
__m128i __Y = _mm256_extractf128_si256 (__X, __N >> 1);
__Y = _mm_insert_epi64 (__Y, __D, __N % 2);
return _mm256_insertf128_si256 (__X, __Y, __N >> 1);
}
#endif
#else
#define _mm256_insertf128_pd(X, Y, O) \
((__m256d) __builtin_ia32_vinsertf128_pd256 ((__v4df)(__m256d)(X), \
(__v2df)(__m128d)(Y), \
(int)(O)))
#define _mm256_insertf128_ps(X, Y, O) \
((__m256) __builtin_ia32_vinsertf128_ps256 ((__v8sf)(__m256)(X), \
(__v4sf)(__m128)(Y), \
(int)(O)))
#define _mm256_insertf128_si256(X, Y, O) \
((__m256i) __builtin_ia32_vinsertf128_si256 ((__v8si)(__m256i)(X), \
(__v4si)(__m128i)(Y), \
(int)(O)))
#define _mm256_insert_epi32(X, D, N) \
(__extension__ \
({ \
__m128i __Y = _mm256_extractf128_si256 ((X), (N) >> 2); \
__Y = _mm_insert_epi32 (__Y, (D), (N) % 4); \
_mm256_insertf128_si256 ((X), __Y, (N) >> 2); \
}))
#define _mm256_insert_epi16(X, D, N) \
(__extension__ \
({ \
__m128i __Y = _mm256_extractf128_si256 ((X), (N) >> 3); \
__Y = _mm_insert_epi16 (__Y, (D), (N) % 8); \
_mm256_insertf128_si256 ((X), __Y, (N) >> 3); \
}))
#define _mm256_insert_epi8(X, D, N) \
(__extension__ \
({ \
__m128i __Y = _mm256_extractf128_si256 ((X), (N) >> 4); \
__Y = _mm_insert_epi8 (__Y, (D), (N) % 16); \
_mm256_insertf128_si256 ((X), __Y, (N) >> 4); \
}))
#ifdef __x86_64__
#define _mm256_insert_epi64(X, D, N) \
(__extension__ \
({ \
__m128i __Y = _mm256_extractf128_si256 ((X), (N) >> 1); \
__Y = _mm_insert_epi64 (__Y, (D), (N) % 2); \
_mm256_insertf128_si256 ((X), __Y, (N) >> 1); \
}))
#endif
#endif
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_load_pd (double const *__P)
{
return *(__m256d *)__P;
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_store_pd (double *__P, __m256d __A)
{
*(__m256d *)__P = __A;
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_load_ps (float const *__P)
{
return *(__m256 *)__P;
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_store_ps (float *__P, __m256 __A)
{
*(__m256 *)__P = __A;
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_loadu_pd (double const *__P)
{
return (__m256d) __builtin_ia32_loadupd256 (__P);
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_storeu_pd (double *__P, __m256d __A)
{
__builtin_ia32_storeupd256 (__P, (__v4df)__A);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_loadu_ps (float const *__P)
{
return (__m256) __builtin_ia32_loadups256 (__P);
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_storeu_ps (float *__P, __m256 __A)
{
__builtin_ia32_storeups256 (__P, (__v8sf)__A);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_load_si256 (__m256i const *__P)
{
return *__P;
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_store_si256 (__m256i *__P, __m256i __A)
{
*__P = __A;
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_loadu_si256 (__m256i const *__P)
{
return (__m256i) __builtin_ia32_loaddqu256 ((char const *)__P);
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_storeu_si256 (__m256i *__P, __m256i __A)
{
__builtin_ia32_storedqu256 ((char *)__P, (__v32qi)__A);
}
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskload_pd (double const *__P, __m128i __M)
{
return (__m128d) __builtin_ia32_maskloadpd ((const __v2df *)__P,
(__v2di)__M);
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskstore_pd (double *__P, __m128i __M, __m128d __A)
{
__builtin_ia32_maskstorepd ((__v2df *)__P, (__v2di)__M, (__v2df)__A);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskload_pd (double const *__P, __m256i __M)
{
return (__m256d) __builtin_ia32_maskloadpd256 ((const __v4df *)__P,
(__v4di)__M);
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskstore_pd (double *__P, __m256i __M, __m256d __A)
{
__builtin_ia32_maskstorepd256 ((__v4df *)__P, (__v4di)__M, (__v4df)__A);
}
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskload_ps (float const *__P, __m128i __M)
{
return (__m128) __builtin_ia32_maskloadps ((const __v4sf *)__P,
(__v4si)__M);
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskstore_ps (float *__P, __m128i __M, __m128 __A)
{
__builtin_ia32_maskstoreps ((__v4sf *)__P, (__v4si)__M, (__v4sf)__A);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskload_ps (float const *__P, __m256i __M)
{
return (__m256) __builtin_ia32_maskloadps256 ((const __v8sf *)__P,
(__v8si)__M);
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskstore_ps (float *__P, __m256i __M, __m256 __A)
{
__builtin_ia32_maskstoreps256 ((__v8sf *)__P, (__v8si)__M, (__v8sf)__A);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_movehdup_ps (__m256 __X)
{
return (__m256) __builtin_ia32_movshdup256 ((__v8sf)__X);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_moveldup_ps (__m256 __X)
{
return (__m256) __builtin_ia32_movsldup256 ((__v8sf)__X);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_movedup_pd (__m256d __X)
{
return (__m256d) __builtin_ia32_movddup256 ((__v4df)__X);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_lddqu_si256 (__m256i const *__P)
{
return (__m256i) __builtin_ia32_lddqu256 ((char const *)__P);
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_stream_si256 (__m256i *__A, __m256i __B)
{
__builtin_ia32_movntdq256 ((__v4di *)__A, (__v4di)__B);
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_stream_pd (double *__A, __m256d __B)
{
__builtin_ia32_movntpd256 (__A, (__v4df)__B);
}
extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_stream_ps (float *__P, __m256 __A)
{
__builtin_ia32_movntps256 (__P, (__v8sf)__A);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_rcp_ps (__m256 __A)
{
return (__m256) __builtin_ia32_rcpps256 ((__v8sf)__A);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_rsqrt_ps (__m256 __A)
{
return (__m256) __builtin_ia32_rsqrtps256 ((__v8sf)__A);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_sqrt_pd (__m256d __A)
{
return (__m256d) __builtin_ia32_sqrtpd256 ((__v4df)__A);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_sqrt_ps (__m256 __A)
{
return (__m256) __builtin_ia32_sqrtps256 ((__v8sf)__A);
}
#ifdef __OPTIMIZE__
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_round_pd (__m256d __V, const int __M)
{
return (__m256d) __builtin_ia32_roundpd256 ((__v4df)__V, __M);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_round_ps (__m256 __V, const int __M)
{
return (__m256) __builtin_ia32_roundps256 ((__v8sf)__V, __M);
}
#else
#define _mm256_round_pd(V, M) \
((__m256d) __builtin_ia32_roundpd256 ((__v4df)(__m256d)(V), (int)(M)))
#define _mm256_round_ps(V, M) \
((__m256) __builtin_ia32_roundps256 ((__v8sf)(__m256)(V), (int)(M)))
#endif
#define _mm256_ceil_pd(V) _mm256_round_pd ((V), _MM_FROUND_CEIL)
#define _mm256_floor_pd(V) _mm256_round_pd ((V), _MM_FROUND_FLOOR)
#define _mm256_ceil_ps(V) _mm256_round_ps ((V), _MM_FROUND_CEIL)
#define _mm256_floor_ps(V) _mm256_round_ps ((V), _MM_FROUND_FLOOR)
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_unpackhi_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_unpckhpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_unpacklo_pd (__m256d __A, __m256d __B)
{
return (__m256d) __builtin_ia32_unpcklpd256 ((__v4df)__A, (__v4df)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_unpackhi_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_unpckhps256 ((__v8sf)__A, (__v8sf)__B);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_unpacklo_ps (__m256 __A, __m256 __B)
{
return (__m256) __builtin_ia32_unpcklps256 ((__v8sf)__A, (__v8sf)__B);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_testz_pd (__m128d __M, __m128d __V)
{
return __builtin_ia32_vtestzpd ((__v2df)__M, (__v2df)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_testc_pd (__m128d __M, __m128d __V)
{
return __builtin_ia32_vtestcpd ((__v2df)__M, (__v2df)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_testnzc_pd (__m128d __M, __m128d __V)
{
return __builtin_ia32_vtestnzcpd ((__v2df)__M, (__v2df)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_testz_ps (__m128 __M, __m128 __V)
{
return __builtin_ia32_vtestzps ((__v4sf)__M, (__v4sf)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_testc_ps (__m128 __M, __m128 __V)
{
return __builtin_ia32_vtestcps ((__v4sf)__M, (__v4sf)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_testnzc_ps (__m128 __M, __m128 __V)
{
return __builtin_ia32_vtestnzcps ((__v4sf)__M, (__v4sf)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_testz_pd (__m256d __M, __m256d __V)
{
return __builtin_ia32_vtestzpd256 ((__v4df)__M, (__v4df)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_testc_pd (__m256d __M, __m256d __V)
{
return __builtin_ia32_vtestcpd256 ((__v4df)__M, (__v4df)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_testnzc_pd (__m256d __M, __m256d __V)
{
return __builtin_ia32_vtestnzcpd256 ((__v4df)__M, (__v4df)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_testz_ps (__m256 __M, __m256 __V)
{
return __builtin_ia32_vtestzps256 ((__v8sf)__M, (__v8sf)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_testc_ps (__m256 __M, __m256 __V)
{
return __builtin_ia32_vtestcps256 ((__v8sf)__M, (__v8sf)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_testnzc_ps (__m256 __M, __m256 __V)
{
return __builtin_ia32_vtestnzcps256 ((__v8sf)__M, (__v8sf)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_testz_si256 (__m256i __M, __m256i __V)
{
return __builtin_ia32_ptestz256 ((__v4di)__M, (__v4di)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_testc_si256 (__m256i __M, __m256i __V)
{
return __builtin_ia32_ptestc256 ((__v4di)__M, (__v4di)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_testnzc_si256 (__m256i __M, __m256i __V)
{
return __builtin_ia32_ptestnzc256 ((__v4di)__M, (__v4di)__V);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_movemask_pd (__m256d __A)
{
return __builtin_ia32_movmskpd256 ((__v4df)__A);
}
extern __inline int __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_movemask_ps (__m256 __A)
{
return __builtin_ia32_movmskps256 ((__v8sf)__A);
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_setzero_pd (void)
{
return __extension__ (__m256d){ 0.0, 0.0, 0.0, 0.0 };
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_setzero_ps (void)
{
return __extension__ (__m256){ 0.0, 0.0, 0.0, 0.0,
0.0, 0.0, 0.0, 0.0 };
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_setzero_si256 (void)
{
return __extension__ (__m256i)(__v4di){ 0, 0, 0, 0 };
}
/* Create the vector [A B C D]. */
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_set_pd (double __A, double __B, double __C, double __D)
{
return __extension__ (__m256d){ __D, __C, __B, __A };
}
/* Create the vector [A B C D E F G H]. */
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_set_ps (float __A, float __B, float __C, float __D,
float __E, float __F, float __G, float __H)
{
return __extension__ (__m256){ __H, __G, __F, __E,
__D, __C, __B, __A };
}
/* Create the vector [A B C D E F G H]. */
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_set_epi32 (int __A, int __B, int __C, int __D,
int __E, int __F, int __G, int __H)
{
return __extension__ (__m256i)(__v8si){ __H, __G, __F, __E,
__D, __C, __B, __A };
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_set_epi16 (short __q15, short __q14, short __q13, short __q12,
short __q11, short __q10, short __q09, short __q08,
short __q07, short __q06, short __q05, short __q04,
short __q03, short __q02, short __q01, short __q00)
{
return __extension__ (__m256i)(__v16hi){
__q00, __q01, __q02, __q03, __q04, __q05, __q06, __q07,
__q08, __q09, __q10, __q11, __q12, __q13, __q14, __q15
};
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_set_epi8 (char __q31, char __q30, char __q29, char __q28,
char __q27, char __q26, char __q25, char __q24,
char __q23, char __q22, char __q21, char __q20,
char __q19, char __q18, char __q17, char __q16,
char __q15, char __q14, char __q13, char __q12,
char __q11, char __q10, char __q09, char __q08,
char __q07, char __q06, char __q05, char __q04,
char __q03, char __q02, char __q01, char __q00)
{
return __extension__ (__m256i)(__v32qi){
__q00, __q01, __q02, __q03, __q04, __q05, __q06, __q07,
__q08, __q09, __q10, __q11, __q12, __q13, __q14, __q15,
__q16, __q17, __q18, __q19, __q20, __q21, __q22, __q23,
__q24, __q25, __q26, __q27, __q28, __q29, __q30, __q31
};
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_set_epi64x (long long __A, long long __B, long long __C,
long long __D)
{
return __extension__ (__m256i)(__v4di){ __D, __C, __B, __A };
}
/* Create a vector with all elements equal to A. */
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_set1_pd (double __A)
{
return __extension__ (__m256d){ __A, __A, __A, __A };
}
/* Create a vector with all elements equal to A. */
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_set1_ps (float __A)
{
return __extension__ (__m256){ __A, __A, __A, __A,
__A, __A, __A, __A };
}
/* Create a vector with all elements equal to A. */
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_set1_epi32 (int __A)
{
return __extension__ (__m256i)(__v8si){ __A, __A, __A, __A,
__A, __A, __A, __A };
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_set1_epi16 (short __A)
{
return _mm256_set_epi16 (__A, __A, __A, __A, __A, __A, __A, __A,
__A, __A, __A, __A, __A, __A, __A, __A);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_set1_epi8 (char __A)
{
return _mm256_set_epi8 (__A, __A, __A, __A, __A, __A, __A, __A,
__A, __A, __A, __A, __A, __A, __A, __A,
__A, __A, __A, __A, __A, __A, __A, __A,
__A, __A, __A, __A, __A, __A, __A, __A);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_set1_epi64x (long long __A)
{
return __extension__ (__m256i)(__v4di){ __A, __A, __A, __A };
}
/* Create vectors of elements in the reversed order from the
_mm256_set_XXX functions. */
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_setr_pd (double __A, double __B, double __C, double __D)
{
return _mm256_set_pd (__D, __C, __B, __A);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_setr_ps (float __A, float __B, float __C, float __D,
float __E, float __F, float __G, float __H)
{
return _mm256_set_ps (__H, __G, __F, __E, __D, __C, __B, __A);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_setr_epi32 (int __A, int __B, int __C, int __D,
int __E, int __F, int __G, int __H)
{
return _mm256_set_epi32 (__H, __G, __F, __E, __D, __C, __B, __A);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_setr_epi16 (short __q15, short __q14, short __q13, short __q12,
short __q11, short __q10, short __q09, short __q08,
short __q07, short __q06, short __q05, short __q04,
short __q03, short __q02, short __q01, short __q00)
{
return _mm256_set_epi16 (__q00, __q01, __q02, __q03,
__q04, __q05, __q06, __q07,
__q08, __q09, __q10, __q11,
__q12, __q13, __q14, __q15);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_setr_epi8 (char __q31, char __q30, char __q29, char __q28,
char __q27, char __q26, char __q25, char __q24,
char __q23, char __q22, char __q21, char __q20,
char __q19, char __q18, char __q17, char __q16,
char __q15, char __q14, char __q13, char __q12,
char __q11, char __q10, char __q09, char __q08,
char __q07, char __q06, char __q05, char __q04,
char __q03, char __q02, char __q01, char __q00)
{
return _mm256_set_epi8 (__q00, __q01, __q02, __q03,
__q04, __q05, __q06, __q07,
__q08, __q09, __q10, __q11,
__q12, __q13, __q14, __q15,
__q16, __q17, __q18, __q19,
__q20, __q21, __q22, __q23,
__q24, __q25, __q26, __q27,
__q28, __q29, __q30, __q31);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_setr_epi64x (long long __A, long long __B, long long __C,
long long __D)
{
return _mm256_set_epi64x (__D, __C, __B, __A);
}
/* Casts between various SP, DP, INT vector types. Note that these do no
conversion of values, they just change the type. */
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_castpd_ps (__m256d __A)
{
return (__m256) __A;
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_castpd_si256 (__m256d __A)
{
return (__m256i) __A;
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_castps_pd (__m256 __A)
{
return (__m256d) __A;
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_castps_si256(__m256 __A)
{
return (__m256i) __A;
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_castsi256_ps (__m256i __A)
{
return (__m256) __A;
}
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_castsi256_pd (__m256i __A)
{
return (__m256d) __A;
}
extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_castpd256_pd128 (__m256d __A)
{
return (__m128d) __builtin_ia32_pd_pd256 ((__v4df)__A);
}
extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_castps256_ps128 (__m256 __A)
{
return (__m128) __builtin_ia32_ps_ps256 ((__v8sf)__A);
}
extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_castsi256_si128 (__m256i __A)
{
return (__m128i) __builtin_ia32_si_si256 ((__v8si)__A);
}
/* When cast is done from a 128 to 256-bit type, the low 128 bits of
the 256-bit result contain source parameter value and the upper 128
bits of the result are undefined. Those intrinsics shouldn't
generate any extra moves. */
extern __inline __m256d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_castpd128_pd256 (__m128d __A)
{
return (__m256d) __builtin_ia32_pd256_pd ((__v2df)__A);
}
extern __inline __m256 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_castps128_ps256 (__m128 __A)
{
return (__m256) __builtin_ia32_ps256_ps ((__v4sf)__A);
}
extern __inline __m256i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_castsi128_si256 (__m128i __A)
{
return (__m256i) __builtin_ia32_si256_si ((__v4si)__A);
}
|