sve-intrinsics-fp-arith.ll 82.4 KB
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 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s 2>%t | FileCheck %s
; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t

; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it.
; WARN-NOT: warning

;
; FABD
;

define <vscale x 8 x half> @fabd_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fabd_h:
; CHECK: fabd z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %a,
                                                                 <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fabd_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fabd_s:
; CHECK: fabd z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %a,
                                                                  <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fabd_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fabd_d:
; CHECK: fabd z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %a,
                                                                   <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FABS
;

define <vscale x 8 x half> @fabs_h(<vscale x 8 x half> %a, <vscale x 8 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: fabs_h:
; CHECK: fabs z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fabs.nxv8f16(<vscale x 8 x half> %a,
                                                                 <vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fabs_s(<vscale x 4 x float> %a, <vscale x 4 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: fabs_s:
; CHECK: fabs z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fabs.nxv4f32(<vscale x 4 x float> %a,
                                                                  <vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fabs_d(<vscale x 2 x double> %a, <vscale x 2 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: fabs_d:
; CHECK: fabs z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fabs.nxv2f64(<vscale x 2 x double> %a,
                                                                   <vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FADD
;

define <vscale x 8 x half> @fadd_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fadd_h:
; CHECK: fadd z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %a,
                                                                 <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fadd_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fadd_s:
; CHECK: fadd z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %a,
                                                                  <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fadd_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fadd_d:
; CHECK: fadd z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %a,
                                                                   <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FCADD
;

define <vscale x 8 x half> @fcadd_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fcadd_h:
; CHECK: fcadd z0.h, p0/m, z0.h, z1.h, #90
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fcadd.nxv8f16(<vscale x 8 x i1> %pg,
                                                                  <vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b,
                                                                  i32 90)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fcadd_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fcadd_s:
; CHECK: fcadd z0.s, p0/m, z0.s, z1.s, #270
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fcadd.nxv4f32(<vscale x 4 x i1> %pg,
                                                                   <vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b,
                                                                   i32 270)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fcadd_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fcadd_d:
; CHECK: fcadd z0.d, p0/m, z0.d, z1.d, #90
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fcadd.nxv2f64(<vscale x 2 x i1> %pg,
                                                                    <vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b,
                                                                    i32 90)
  ret <vscale x 2 x double> %out
}

;
; FCMLA
;

define <vscale x 8 x half> @fcmla_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fcmla_h:
; CHECK: fcmla z0.h, p0/m, z1.h, z2.h, #90
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fcmla.nxv8f16(<vscale x 8 x i1> %pg,
                                                                  <vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b,
                                                                  <vscale x 8 x half> %c,
                                                                  i32 90)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fcmla_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fcmla_s:
; CHECK: fcmla z0.s, p0/m, z1.s, z2.s, #180
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fcmla.nxv4f32(<vscale x 4 x i1> %pg,
                                                                   <vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b,
                                                                   <vscale x 4 x float> %c,
                                                                   i32 180)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fcmla_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
; CHECK-LABEL: fcmla_d:
; CHECK: fcmla z0.d, p0/m, z1.d, z2.d, #270
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fcmla.nxv2f64(<vscale x 2 x i1> %pg,
                                                                    <vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b,
                                                                    <vscale x 2 x double> %c,
                                                                    i32 270)
  ret <vscale x 2 x double> %out
}

;
; FCMLA (Indexed)
;

define <vscale x 8 x half> @fcmla_lane_h(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fcmla_lane_h:
; CHECK: fcmla z0.h, z1.h, z2.h[3], #0
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fcmla.lane.nxv8f16(<vscale x 8 x half> %a,
                                                                       <vscale x 8 x half> %b,
                                                                       <vscale x 8 x half> %c,
                                                                       i32 3,
                                                                       i32 0)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fcmla_lane_s(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fcmla_lane_s:
; CHECK: fcmla z0.s, z1.s, z2.s[1], #90
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fcmla.lane.nxv4f32(<vscale x 4 x float> %a,
                                                                        <vscale x 4 x float> %b,
                                                                        <vscale x 4 x float> %c,
                                                                        i32 1,
                                                                        i32 90)
  ret <vscale x 4 x float> %out
}

;
; FDIV
;

define <vscale x 8 x half> @fdiv_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fdiv_h:
; CHECK: fdiv z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %a,
                                                                 <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fdiv_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fdiv_s:
; CHECK: fdiv z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %a,
                                                                  <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fdiv_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fdiv_d:
; CHECK: fdiv z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %a,
                                                                   <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FDIVR
;

define <vscale x 8 x half> @fdivr_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fdivr_h:
; CHECK: fdivr z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fdivr.nxv8f16(<vscale x 8 x i1> %pg,
                                                                  <vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fdivr_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fdivr_s:
; CHECK: fdivr z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fdivr.nxv4f32(<vscale x 4 x i1> %pg,
                                                                   <vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fdivr_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fdivr_d:
; CHECK: fdivr z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fdivr.nxv2f64(<vscale x 2 x i1> %pg,
                                                                    <vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FEXPA
;

define <vscale x 8 x half> @fexpa_h(<vscale x 8 x i16> %a) {
; CHECK-LABEL: fexpa_h:
; CHECK: fexpa z0.h, z0.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fexpa.x.nxv8f16(<vscale x 8 x i16> %a)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fexpa_s(<vscale x 4 x i32> %a) {
; CHECK-LABEL: fexpa_s:
; CHECK: fexpa z0.s, z0.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fexpa.x.nxv4f32(<vscale x 4 x i32> %a)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fexpa_d(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) {
; CHECK-LABEL: fexpa_d:
; CHECK: fexpa z0.d, z0.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fexpa.x.nxv2f64(<vscale x 2 x i64> %a)
  ret <vscale x 2 x double> %out
}

;
; FMAD
;

define <vscale x 8 x half> @fmad_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fmad_h:
; CHECK: fmad z0.h, p0/m, z1.h, z2.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmad.nxv8f16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %a,
                                                                 <vscale x 8 x half> %b,
                                                                 <vscale x 8 x half> %c)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fmad_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fmad_s:
; CHECK: fmad z0.s, p0/m, z1.s, z2.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmad.nxv4f32(<vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %a,
                                                                  <vscale x 4 x float> %b,
                                                                  <vscale x 4 x float> %c)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fmad_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
; CHECK-LABEL: fmad_d:
; CHECK: fmad z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmad.nxv2f64(<vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %a,
                                                                   <vscale x 2 x double> %b,
                                                                   <vscale x 2 x double> %c)
  ret <vscale x 2 x double> %out
}

;
; FMAX
;

define <vscale x 8 x half> @fmax_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fmax_h:
; CHECK: fmax z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %a,
                                                                 <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fmax_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fmax_s:
; CHECK: fmax z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %a,
                                                                  <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fmax_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fmax_d:
; CHECK: fmax z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %a,
                                                                   <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FMAXNM
;

define <vscale x 8 x half> @fmaxnm_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fmaxnm_h:
; CHECK: fmaxnm z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1> %pg,
                                                                   <vscale x 8 x half> %a,
                                                                   <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fmaxnm_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fmaxnm_s:
; CHECK: fmaxnm z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1> %pg,
                                                                    <vscale x 4 x float> %a,
                                                                    <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fmaxnm_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fmaxnm_d:
; CHECK: fmaxnm z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1> %pg,
                                                                     <vscale x 2 x double> %a,
                                                                     <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FMIN
;

define <vscale x 8 x half> @fmin_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fmin_h:
; CHECK: fmin z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %a,
                                                                 <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fmin_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fmin_s:
; CHECK: fmin z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %a,
                                                                  <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fmin_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fmin_d:
; CHECK: fmin z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %a,
                                                                   <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FMINNM
;

define <vscale x 8 x half> @fminnm_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fminnm_h:
; CHECK: fminnm z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1> %pg,
                                                                   <vscale x 8 x half> %a,
                                                                   <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fminnm_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fminnm_s:
; CHECK: fminnm z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1> %pg,
                                                                    <vscale x 4 x float> %a,
                                                                    <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fminnm_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fminnm_d:
; CHECK: fminnm z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1> %pg,
                                                                     <vscale x 2 x double> %a,
                                                                     <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FMLA
;

define <vscale x 8 x half> @fmla_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fmla_h:
; CHECK: fmla z0.h, p0/m, z1.h, z2.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %a,
                                                                 <vscale x 8 x half> %b,
                                                                 <vscale x 8 x half> %c)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fmla_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fmla_s:
; CHECK: fmla z0.s, p0/m, z1.s, z2.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %a,
                                                                  <vscale x 4 x float> %b,
                                                                  <vscale x 4 x float> %c)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fmla_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
; CHECK-LABEL: fmla_d:
; CHECK: fmla z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %a,
                                                                   <vscale x 2 x double> %b,
                                                                   <vscale x 2 x double> %c)
  ret <vscale x 2 x double> %out
}

;
; FMLA (Indexed)
;

define <vscale x 8 x half> @fmla_lane_h(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fmla_lane_h:
; CHECK: fmla z0.h, z1.h, z2.h[3]
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmla.lane.nxv8f16(<vscale x 8 x half> %a,
                                                                      <vscale x 8 x half> %b,
                                                                      <vscale x 8 x half> %c,
                                                                      i32 3)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fmla_lane_s(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fmla_lane_s:
; CHECK: fmla z0.s, z1.s, z2.s[2]
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmla.lane.nxv4f32(<vscale x 4 x float> %a,
                                                                       <vscale x 4 x float> %b,
                                                                       <vscale x 4 x float> %c,
                                                                       i32 2)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fmla_lane_d(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
; CHECK-LABEL: fmla_lane_d:
; CHECK: fmla z0.d, z1.d, z2.d[1]
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmla.lane.nxv2f64(<vscale x 2 x double> %a,
                                                                        <vscale x 2 x double> %b,
                                                                        <vscale x 2 x double> %c,
                                                                        i32 1)
  ret <vscale x 2 x double> %out
}

;
; FMLS
;

define <vscale x 8 x half> @fmls_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fmls_h:
; CHECK: fmls z0.h, p0/m, z1.h, z2.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %a,
                                                                 <vscale x 8 x half> %b,
                                                                 <vscale x 8 x half> %c)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fmls_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fmls_s:
; CHECK: fmls z0.s, p0/m, z1.s, z2.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %a,
                                                                  <vscale x 4 x float> %b,
                                                                  <vscale x 4 x float> %c)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fmls_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
; CHECK-LABEL: fmls_d:
; CHECK: fmls z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %a,
                                                                   <vscale x 2 x double> %b,
                                                                   <vscale x 2 x double> %c)
  ret <vscale x 2 x double> %out
}

;
; FMLS (Indexed)
;

define <vscale x 8 x half> @fmls_lane_h(<vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fmls_lane_h:
; CHECK: fmls z0.h, z1.h, z2.h[3]
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmls.lane.nxv8f16(<vscale x 8 x half> %a,
                                                                 <vscale x 8 x half> %b,
                                                                 <vscale x 8 x half> %c,
                                                                 i32 3)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fmls_lane_s(<vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fmls_lane_s:
; CHECK: fmls z0.s, z1.s, z2.s[2]
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmls.lane.nxv4f32(<vscale x 4 x float> %a,
                                                                  <vscale x 4 x float> %b,
                                                                  <vscale x 4 x float> %c,
                                                                  i32 2)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fmls_lane_d(<vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
; CHECK-LABEL: fmls_lane_d:
; CHECK: fmls z0.d, z1.d, z2.d[1]
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmls.lane.nxv2f64(<vscale x 2 x double> %a,
                                                                   <vscale x 2 x double> %b,
                                                                   <vscale x 2 x double> %c,
                                                                   i32 1)
  ret <vscale x 2 x double> %out
}

;
; FMSB
;

define <vscale x 8 x half> @fmsb_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fmsb_h:
; CHECK: fmsb z0.h, p0/m, z1.h, z2.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmsb.nxv8f16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %a,
                                                                 <vscale x 8 x half> %b,
                                                                 <vscale x 8 x half> %c)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fmsb_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fmsb_s:
; CHECK: fmsb z0.s, p0/m, z1.s, z2.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmsb.nxv4f32(<vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %a,
                                                                  <vscale x 4 x float> %b,
                                                                  <vscale x 4 x float> %c)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fmsb_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
; CHECK-LABEL: fmsb_d:
; CHECK: fmsb z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmsb.nxv2f64(<vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %a,
                                                                   <vscale x 2 x double> %b,
                                                                   <vscale x 2 x double> %c)
  ret <vscale x 2 x double> %out
}

;
; FMUL
;

define <vscale x 8 x half> @fmul_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fmul_h:
; CHECK: fmul z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %a,
                                                                 <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fmul_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fmul_s:
; CHECK: fmul z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %a,
                                                                  <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fmul_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fmul_d:
; CHECK: fmul z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %a,
                                                                   <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FMUL (Indexed)
;

define <vscale x 8 x half> @fmul_lane_h(<vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fmul_lane_h:
; CHECK: fmul z0.h, z0.h, z1.h[3]
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.lane.nxv8f16(<vscale x 8 x half> %a,
                                                                      <vscale x 8 x half> %b,
                                                                      i32 3)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fmul_lane_s(<vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fmul_lane_s:
; CHECK: fmul z0.s, z0.s, z1.s[2]
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.lane.nxv4f32(<vscale x 4 x float> %a,
                                                                       <vscale x 4 x float> %b,
                                                                       i32 2)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fmul_lane_d(<vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fmul_lane_d:
; CHECK: fmul z0.d, z0.d, z1.d[1]
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.lane.nxv2f64(<vscale x 2 x double> %a,
                                                                        <vscale x 2 x double> %b,
                                                                        i32 1)
  ret <vscale x 2 x double> %out
}

;
; FMULX
;

define <vscale x 8 x half> @fmulx_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fmulx_h:
; CHECK: fmulx z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1> %pg,
                                                                  <vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fmulx_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fmulx_s:
; CHECK: fmulx z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1> %pg,
                                                                   <vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fmulx_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fmulx_d:
; CHECK: fmulx z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1> %pg,
                                                                    <vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FNEG
;

define <vscale x 8 x half> @fneg_h(<vscale x 8 x half> %a, <vscale x 8 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: fneg_h:
; CHECK: fneg z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fneg.nxv8f16(<vscale x 8 x half> %a,
                                                                 <vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fneg_s(<vscale x 4 x float> %a, <vscale x 4 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: fneg_s:
; CHECK: fneg z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fneg.nxv4f32(<vscale x 4 x float> %a,
                                                                  <vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fneg_d(<vscale x 2 x double> %a, <vscale x 2 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: fneg_d:
; CHECK: fneg z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fneg.nxv2f64(<vscale x 2 x double> %a,
                                                                   <vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FNMAD
;

define <vscale x 8 x half> @fnmad_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fnmad_h:
; CHECK: fnmad z0.h, p0/m, z1.h, z2.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fnmad.nxv8f16(<vscale x 8 x i1> %pg,
                                                                  <vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b,
                                                                  <vscale x 8 x half> %c)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fnmad_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fnmad_s:
; CHECK: fnmad z0.s, p0/m, z1.s, z2.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fnmad.nxv4f32(<vscale x 4 x i1> %pg,
                                                                   <vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b,
                                                                   <vscale x 4 x float> %c)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fnmad_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
; CHECK-LABEL: fnmad_d:
; CHECK: fnmad z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fnmad.nxv2f64(<vscale x 2 x i1> %pg,
                                                                    <vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b,
                                                                    <vscale x 2 x double> %c)
  ret <vscale x 2 x double> %out
}

;
; FNMLA
;

define <vscale x 8 x half> @fnmla_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fnmla_h:
; CHECK: fnmla z0.h, p0/m, z1.h, z2.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1> %pg,
                                                                  <vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b,
                                                                  <vscale x 8 x half> %c)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fnmla_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fnmla_s:
; CHECK: fnmla z0.s, p0/m, z1.s, z2.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1> %pg,
                                                                   <vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b,
                                                                   <vscale x 4 x float> %c)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fnmla_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
; CHECK-LABEL: fnmla_d:
; CHECK: fnmla z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1> %pg,
                                                                    <vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b,
                                                                    <vscale x 2 x double> %c)
  ret <vscale x 2 x double> %out
}

;
; FNMLS
;

define <vscale x 8 x half> @fnmls_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fnmls_h:
; CHECK: fnmls z0.h, p0/m, z1.h, z2.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1> %pg,
                                                                  <vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b,
                                                                  <vscale x 8 x half> %c)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fnmls_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fnmls_s:
; CHECK: fnmls z0.s, p0/m, z1.s, z2.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1> %pg,
                                                                   <vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b,
                                                                   <vscale x 4 x float> %c)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fnmls_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
; CHECK-LABEL: fnmls_d:
; CHECK: fnmls z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1> %pg,
                                                                    <vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b,
                                                                    <vscale x 2 x double> %c)
  ret <vscale x 2 x double> %out
}

;
; FNMSB
;

define <vscale x 8 x half> @fnmsb_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b, <vscale x 8 x half> %c) {
; CHECK-LABEL: fnmsb_h:
; CHECK: fnmsb z0.h, p0/m, z1.h, z2.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fnmsb.nxv8f16(<vscale x 8 x i1> %pg,
                                                                  <vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b,
                                                                  <vscale x 8 x half> %c)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fnmsb_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b, <vscale x 4 x float> %c) {
; CHECK-LABEL: fnmsb_s:
; CHECK: fnmsb z0.s, p0/m, z1.s, z2.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fnmsb.nxv4f32(<vscale x 4 x i1> %pg,
                                                                   <vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b,
                                                                   <vscale x 4 x float> %c)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fnmsb_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b, <vscale x 2 x double> %c) {
; CHECK-LABEL: fnmsb_d:
; CHECK: fnmsb z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fnmsb.nxv2f64(<vscale x 2 x i1> %pg,
                                                                    <vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b,
                                                                    <vscale x 2 x double> %c)
  ret <vscale x 2 x double> %out
}

;
; FRECPE
;

define <vscale x 8 x half> @frecpe_h(<vscale x 8 x half> %a) {
; CHECK-LABEL: frecpe_h:
; CHECK: frecpe z0.h, z0.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.frecpe.x.nxv8f16(<vscale x 8 x half> %a)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @frecpe_s(<vscale x 4 x float> %a) {
; CHECK-LABEL: frecpe_s:
; CHECK: frecpe z0.s, z0.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.frecpe.x.nxv4f32(<vscale x 4 x float> %a)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @frecpe_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a) {
; CHECK-LABEL: frecpe_d:
; CHECK: frecpe z0.d, z0.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.frecpe.x.nxv2f64(<vscale x 2 x double> %a)
  ret <vscale x 2 x double> %out
}

;
; FRECPX
;

define <vscale x 8 x half> @frecpx_h(<vscale x 8 x half> %a, <vscale x 8 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: frecpx_h:
; CHECK: frecpx z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.frecpx.nxv8f16(<vscale x 8 x half> %a,
                                                                  <vscale x 8 x i1> %pg,
                                                                  <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @frecpx_s(<vscale x 4 x float> %a, <vscale x 4 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: frecpx_s:
; CHECK: frecpx z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.frecpx.nxv4f32(<vscale x 4 x float> %a,
                                                                   <vscale x 4 x i1> %pg,
                                                                   <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @frecpx_d(<vscale x 2 x double> %a, <vscale x 2 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: frecpx_d:
; CHECK: frecpx z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.frecpx.nxv2f64(<vscale x 2 x double> %a,
                                                                    <vscale x 2 x i1> %pg,
                                                                    <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FRINTA
;

define <vscale x 8 x half> @frinta_h(<vscale x 8 x half> %a, <vscale x 8 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: frinta_h:
; CHECK: frinta z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.frinta.nxv8f16(<vscale x 8 x half> %a,
                                                                   <vscale x 8 x i1> %pg,
                                                                   <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @frinta_s(<vscale x 4 x float> %a, <vscale x 4 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: frinta_s:
; CHECK: frinta z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.frinta.nxv4f32(<vscale x 4 x float> %a,
                                                                    <vscale x 4 x i1> %pg,
                                                                    <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @frinta_d(<vscale x 2 x double> %a, <vscale x 2 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: frinta_d:
; CHECK: frinta z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.frinta.nxv2f64(<vscale x 2 x double> %a,
                                                                     <vscale x 2 x i1> %pg,
                                                                     <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FRINTI
;

define <vscale x 8 x half> @frinti_h(<vscale x 8 x half> %a, <vscale x 8 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: frinti_h:
; CHECK: frinti z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.frinti.nxv8f16(<vscale x 8 x half> %a,
                                                                   <vscale x 8 x i1> %pg,
                                                                   <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @frinti_s(<vscale x 4 x float> %a, <vscale x 4 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: frinti_s:
; CHECK: frinti z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.frinti.nxv4f32(<vscale x 4 x float> %a,
                                                                    <vscale x 4 x i1> %pg,
                                                                    <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @frinti_d(<vscale x 2 x double> %a, <vscale x 2 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: frinti_d:
; CHECK: frinti z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.frinti.nxv2f64(<vscale x 2 x double> %a,
                                                                     <vscale x 2 x i1> %pg,
                                                                     <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FRINTM
;

define <vscale x 8 x half> @frintm_h(<vscale x 8 x half> %a, <vscale x 8 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: frintm_h:
; CHECK: frintm z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.frintm.nxv8f16(<vscale x 8 x half> %a,
                                                                   <vscale x 8 x i1> %pg,
                                                                   <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @frintm_s(<vscale x 4 x float> %a, <vscale x 4 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: frintm_s:
; CHECK: frintm z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.frintm.nxv4f32(<vscale x 4 x float> %a,
                                                                    <vscale x 4 x i1> %pg,
                                                                    <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @frintm_d(<vscale x 2 x double> %a, <vscale x 2 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: frintm_d:
; CHECK: frintm z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.frintm.nxv2f64(<vscale x 2 x double> %a,
                                                                     <vscale x 2 x i1> %pg,
                                                                     <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FRINTN
;

define <vscale x 8 x half> @frintn_h(<vscale x 8 x half> %a, <vscale x 8 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: frintn_h:
; CHECK: frintn z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.frintn.nxv8f16(<vscale x 8 x half> %a,
                                                                   <vscale x 8 x i1> %pg,
                                                                   <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @frintn_s(<vscale x 4 x float> %a, <vscale x 4 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: frintn_s:
; CHECK: frintn z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.frintn.nxv4f32(<vscale x 4 x float> %a,
                                                                    <vscale x 4 x i1> %pg,
                                                                    <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @frintn_d(<vscale x 2 x double> %a, <vscale x 2 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: frintn_d:
; CHECK: frintn z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.frintn.nxv2f64(<vscale x 2 x double> %a,
                                                                     <vscale x 2 x i1> %pg,
                                                                     <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FRINTP
;

define <vscale x 8 x half> @frintp_h(<vscale x 8 x half> %a, <vscale x 8 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: frintp_h:
; CHECK: frintp z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.frintp.nxv8f16(<vscale x 8 x half> %a,
                                                                   <vscale x 8 x i1> %pg,
                                                                   <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @frintp_s(<vscale x 4 x float> %a, <vscale x 4 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: frintp_s:
; CHECK: frintp z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.frintp.nxv4f32(<vscale x 4 x float> %a,
                                                                    <vscale x 4 x i1> %pg,
                                                                    <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @frintp_d(<vscale x 2 x double> %a, <vscale x 2 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: frintp_d:
; CHECK: frintp z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.frintp.nxv2f64(<vscale x 2 x double> %a,
                                                                     <vscale x 2 x i1> %pg,
                                                                     <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FRINTX
;

define <vscale x 8 x half> @frintx_h(<vscale x 8 x half> %a, <vscale x 8 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: frintx_h:
; CHECK: frintx z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.frintx.nxv8f16(<vscale x 8 x half> %a,
                                                                   <vscale x 8 x i1> %pg,
                                                                   <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @frintx_s(<vscale x 4 x float> %a, <vscale x 4 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: frintx_s:
; CHECK: frintx z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.frintx.nxv4f32(<vscale x 4 x float> %a,
                                                                    <vscale x 4 x i1> %pg,
                                                                    <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @frintx_d(<vscale x 2 x double> %a, <vscale x 2 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: frintx_d:
; CHECK: frintx z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.frintx.nxv2f64(<vscale x 2 x double> %a,
                                                                     <vscale x 2 x i1> %pg,
                                                                     <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FRINTZ
;

define <vscale x 8 x half> @frintz_h(<vscale x 8 x half> %a, <vscale x 8 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: frintz_h:
; CHECK: frintz z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.frintz.nxv8f16(<vscale x 8 x half> %a,
                                                                   <vscale x 8 x i1> %pg,
                                                                   <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @frintz_s(<vscale x 4 x float> %a, <vscale x 4 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: frintz_s:
; CHECK: frintz z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.frintz.nxv4f32(<vscale x 4 x float> %a,
                                                                    <vscale x 4 x i1> %pg,
                                                                    <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @frintz_d(<vscale x 2 x double> %a, <vscale x 2 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: frintz_d:
; CHECK: frintz z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.frintz.nxv2f64(<vscale x 2 x double> %a,
                                                                     <vscale x 2 x i1> %pg,
                                                                     <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FRSQRTE
;

define <vscale x 8 x half> @frsqrte_h(<vscale x 8 x half> %a) {
; CHECK-LABEL: frsqrte_h:
; CHECK: frsqrte z0.h, z0.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.frsqrte.x.nxv8f16(<vscale x 8 x half> %a)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @frsqrte_s(<vscale x 4 x float> %a) {
; CHECK-LABEL: frsqrte_s:
; CHECK: frsqrte z0.s, z0.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.frsqrte.x.nxv4f32(<vscale x 4 x float> %a)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @frsqrte_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a) {
; CHECK-LABEL: frsqrte_d:
; CHECK: frsqrte z0.d, z0.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.frsqrte.x.nxv2f64(<vscale x 2 x double> %a)
  ret <vscale x 2 x double> %out
}

;
; FSCALE
;

define <vscale x 8 x half> @fscale_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: fscale_h:
; CHECK: fscale z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fscale.nxv8f16(<vscale x 8 x i1> %pg,
                                                                   <vscale x 8 x half> %a,
                                                                   <vscale x 8 x i16> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fscale_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: fscale_s:
; CHECK: fscale z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fscale.nxv4f32(<vscale x 4 x i1> %pg,
                                                                    <vscale x 4 x float> %a,
                                                                    <vscale x 4 x i32> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fscale_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: fscale_d:
; CHECK: fscale z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fscale.nxv2f64(<vscale x 2 x i1> %pg,
                                                                     <vscale x 2 x double> %a,
                                                                     <vscale x 2 x i64> %b)
  ret <vscale x 2 x double> %out
}

;
; FSQRT
;

define <vscale x 8 x half> @fsqrt_h(<vscale x 8 x half> %a, <vscale x 8 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: fsqrt_h:
; CHECK: fsqrt z0.h, p0/m, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fsqrt.nxv8f16(<vscale x 8 x half> %a,
                                                                  <vscale x 8 x i1> %pg,
                                                                  <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fsqrt_s(<vscale x 4 x float> %a, <vscale x 4 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: fsqrt_s:
; CHECK: fsqrt z0.s, p0/m, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fsqrt.nxv4f32(<vscale x 4 x float> %a,
                                                                   <vscale x 4 x i1> %pg,
                                                                   <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fsqrt_d(<vscale x 2 x double> %a, <vscale x 2 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: fsqrt_d:
; CHECK: fsqrt z0.d, p0/m, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fsqrt.nxv2f64(<vscale x 2 x double> %a,
                                                                    <vscale x 2 x i1> %pg,
                                                                    <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FSUB
;

define <vscale x 8 x half> @fsub_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fsub_h:
; CHECK: fsub z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1> %pg,
                                                                 <vscale x 8 x half> %a,
                                                                 <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fsub_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fsub_s:
; CHECK: fsub z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1> %pg,
                                                                  <vscale x 4 x float> %a,
                                                                  <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fsub_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fsub_d:
; CHECK: fsub z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1> %pg,
                                                                   <vscale x 2 x double> %a,
                                                                   <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FSUBR
;

define <vscale x 8 x half> @fsubr_h(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fsubr_h:
; CHECK: fsubr z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.fsubr.nxv8f16(<vscale x 8 x i1> %pg,
                                                                  <vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @fsubr_s(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fsubr_s:
; CHECK: fsubr z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.fsubr.nxv4f32(<vscale x 4 x i1> %pg,
                                                                   <vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @fsubr_d(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fsubr_d:
; CHECK: fsubr z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.fsubr.nxv2f64(<vscale x 2 x i1> %pg,
                                                                    <vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; FTMAD
;

define <vscale x 8 x half> @ftmad_h(<vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: ftmad_h:
; CHECK: ftmad z0.h, z0.h, z1.h, #0
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.ftmad.x.nxv8f16(<vscale x 8 x half> %a,
                                                                    <vscale x 8 x half> %b,
                                                                    i32 0)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @ftmad_s(<vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: ftmad_s:
; CHECK: ftmad z0.s, z0.s, z1.s, #0
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.ftmad.x.nxv4f32(<vscale x 4 x float> %a,
                                                                     <vscale x 4 x float> %b,
                                                                     i32 0)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @ftmad_d(<vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: ftmad_d:
; CHECK: ftmad z0.d, z0.d, z1.d, #7
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.ftmad.x.nxv2f64(<vscale x 2 x double> %a,
                                                                      <vscale x 2 x double> %b,
                                                                      i32 7)
  ret <vscale x 2 x double> %out
}

;
; FTSMUL
;

define <vscale x 8 x half> @ftsmul_h(<vscale x 8 x half> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: ftsmul_h:
; CHECK: ftsmul z0.h, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.ftsmul.x.nxv8f16(<vscale x 8 x half> %a,
                                                                     <vscale x 8 x i16> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @ftsmul_s(<vscale x 4 x float> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: ftsmul_s:
; CHECK: ftsmul z0.s, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.ftsmul.x.nxv4f32(<vscale x 4 x float> %a,
                                                                      <vscale x 4 x i32> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @ftsmul_d(<vscale x 2 x double> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: ftsmul_d:
; CHECK: ftsmul z0.d, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.ftsmul.x.nxv2f64(<vscale x 2 x double> %a,
                                                                       <vscale x 2 x i64> %b)
  ret <vscale x 2 x double> %out
}

;
; FTSSEL
;

define <vscale x 8 x half> @ftssel_h(<vscale x 8 x half> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: ftssel_h:
; CHECK: ftssel z0.h, z0.h, z1.h
; CHECK-NEXT: ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.ftssel.x.nxv8f16(<vscale x 8 x half> %a,
                                                                     <vscale x 8 x i16> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 4 x float> @ftssel_s(<vscale x 4 x float> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: ftssel_s:
; CHECK: ftssel z0.s, z0.s, z1.s
; CHECK-NEXT: ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.ftssel.x.nxv4f32(<vscale x 4 x float> %a,
                                                                      <vscale x 4 x i32> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @ftssel_d(<vscale x 2 x double> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: ftssel_d:
; CHECK: ftssel z0.d, z0.d, z1.d
; CHECK-NEXT: ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.ftssel.x.nxv2f64(<vscale x 2 x double> %a,
                                                                       <vscale x 2 x i64> %b)
  ret <vscale x 2 x double> %out
}

declare <vscale x 8 x half> @llvm.aarch64.sve.fabd.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fabd.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fabd.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fabs.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fabs.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fabs.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fadd.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fadd.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fadd.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fcadd.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, i32)
declare <vscale x 4 x float> @llvm.aarch64.sve.fcadd.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, i32)
declare <vscale x 2 x double> @llvm.aarch64.sve.fcadd.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, i32)

declare <vscale x 8 x half> @llvm.aarch64.sve.fcmla.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, i32)
declare <vscale x 4 x float> @llvm.aarch64.sve.fcmla.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, i32)
declare <vscale x 2 x double> @llvm.aarch64.sve.fcmla.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, i32)

declare <vscale x 8 x half> @llvm.aarch64.sve.fcmla.lane.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, i32, i32)
declare <vscale x 4 x float> @llvm.aarch64.sve.fcmla.lane.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, i32, i32)

declare <vscale x 8 x half> @llvm.aarch64.sve.fdiv.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fdiv.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fdiv.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fdivr.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fdivr.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fdivr.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fexpa.x.nxv8f16(<vscale x 8 x i16>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fexpa.x.nxv4f32(<vscale x 4 x i32>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fexpa.x.nxv2f64(<vscale x 2 x i64>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fmad.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmad.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmad.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fmax.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmax.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmax.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fmaxnm.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmaxnm.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmaxnm.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fmin.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmin.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmin.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fminnm.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fminnm.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fminnm.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fmla.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmla.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmla.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fmla.lane.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, i32)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmla.lane.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, i32)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmla.lane.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, i32)

declare <vscale x 8 x half> @llvm.aarch64.sve.fmls.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmls.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmls.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fmls.lane.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, i32)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmls.lane.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, i32)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmls.lane.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, i32)

declare <vscale x 8 x half> @llvm.aarch64.sve.fmsb.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmsb.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmsb.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fmul.lane.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, i32)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmul.lane.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, i32)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmul.lane.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, i32)

declare <vscale x 8 x half> @llvm.aarch64.sve.fmulx.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmulx.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmulx.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fneg.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fneg.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fneg.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fnmad.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fnmad.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fnmad.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fnmla.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fnmla.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fnmla.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fnmls.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fnmls.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fnmls.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fnmsb.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fnmsb.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fnmsb.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.frecpe.x.nxv8f16(<vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.frecpe.x.nxv4f32(<vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.frecpe.x.nxv2f64(<vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.frecpx.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.frecpx.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.frecpx.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.frinta.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.frinta.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.frinta.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.frinti.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.frinti.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.frinti.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.frintm.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.frintm.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.frintm.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.frintn.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.frintn.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.frintn.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.frintp.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.frintp.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.frintp.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.frintx.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.frintx.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.frintx.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.frintz.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.frintz.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.frintz.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.frsqrte.x.nxv8f16(<vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.frsqrte.x.nxv4f32(<vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.frsqrte.x.nxv2f64(<vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fscale.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x i16>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fscale.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x i32>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fscale.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x i64>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fsqrt.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fsqrt.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fsqrt.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fsub.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fsub.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fsub.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.fsubr.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fsubr.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fsubr.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)

declare <vscale x 8 x half> @llvm.aarch64.sve.ftmad.x.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, i32)
declare <vscale x 4 x float> @llvm.aarch64.sve.ftmad.x.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, i32)
declare <vscale x 2 x double> @llvm.aarch64.sve.ftmad.x.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, i32)

declare <vscale x 8 x half> @llvm.aarch64.sve.ftsmul.x.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i16>)
declare <vscale x 4 x float> @llvm.aarch64.sve.ftsmul.x.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i32>)
declare <vscale x 2 x double> @llvm.aarch64.sve.ftsmul.x.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i64>)

declare <vscale x 8 x half> @llvm.aarch64.sve.ftssel.x.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i16>)
declare <vscale x 4 x float> @llvm.aarch64.sve.ftssel.x.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i32>)
declare <vscale x 2 x double> @llvm.aarch64.sve.ftssel.x.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i64>)