2020-2-capstone-design2 / 2015104175

Go to a project
Toggle navigation Toggle navigation pinning
Switch branch/tag
avx512-fma-intrinsics-upgrade.ll 36.9 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 
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx512f | FileCheck %s

declare <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)
declare <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32)

define <16 x float> @test_x86_vfnmadd_ps_z(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2) {
; CHECK-LABEL: test_x86_vfnmadd_ps_z:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfnmadd213ps {{.*#+}} zmm0 = -(zmm1 * zmm0) + zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfnmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 4) nounwind
  ret <16 x float> %res
}
declare <16 x float> @llvm.x86.avx512.mask.vfnmadd.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32) nounwind readnone

define <16 x float> @test_mask_vfnmadd_ps(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask) {
; CHECK-LABEL: test_mask_vfnmadd_ps:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmadd132ps {{.*#+}} zmm0 {%k1} = -(zmm0 * zmm1) + zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfnmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 4) nounwind
  ret <16 x float> %res
}

define <8 x double> @test_x86_vfnmadd_pd_z(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_x86_vfnmadd_pd_z:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfnmadd213pd {{.*#+}} zmm0 = -(zmm1 * zmm0) + zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 4) nounwind
  ret <8 x double> %res
}
declare <8 x double> @llvm.x86.avx512.mask.vfnmadd.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32) nounwind readnone

define <8 x double> @test_mask_vfnmadd_pd(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_vfnmadd_pd:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmadd132pd {{.*#+}} zmm0 {%k1} = -(zmm0 * zmm1) + zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 4) nounwind
  ret <8 x double> %res
}

define <16 x float> @test_x86_vfnmsubps_z(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2) {
; CHECK-LABEL: test_x86_vfnmsubps_z:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfnmsub213ps {{.*#+}} zmm0 = -(zmm1 * zmm0) - zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 4) nounwind
  ret <16 x float> %res
}
declare <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32) nounwind readnone

define <16 x float> @test_mask_vfnmsub_ps(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask) {
; CHECK-LABEL: test_mask_vfnmsub_ps:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmsub132ps {{.*#+}} zmm0 {%k1} = -(zmm0 * zmm1) - zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 4) nounwind
  ret <16 x float> %res
}

define <8 x double> @test_x86_vfnmsubpd_z(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_x86_vfnmsubpd_z:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfnmsub213pd {{.*#+}} zmm0 = -(zmm1 * zmm0) - zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 4) nounwind
  ret <8 x double> %res
}
declare <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32) nounwind readnone

define <8 x double> @test_mask_vfnmsub_pd(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_vfnmsub_pd:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmsub132pd {{.*#+}} zmm0 {%k1} = -(zmm0 * zmm1) - zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 4) nounwind
  ret <8 x double> %res
}

define <16 x float> @test_x86_vfmaddsubps_z(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2) {
; CHECK-LABEL: test_x86_vfmaddsubps_z:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmaddsub213ps {{.*#+}} zmm0 = (zmm1 * zmm0) +/- zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmaddsub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 4) nounwind
  ret <16 x float> %res
}

define <16 x float> @test_mask_fmaddsub_ps(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask) {
; CHECK-LABEL: test_mask_fmaddsub_ps:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub132ps {{.*#+}} zmm0 {%k1} = (zmm0 * zmm1) +/- zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmaddsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask, i32 4)
  ret <16 x float> %res
}

declare <16 x float> @llvm.x86.avx512.mask.vfmaddsub.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32) nounwind readnone

define <8 x double> @test_x86_vfmaddsubpd_z(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_x86_vfmaddsubpd_z:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmaddsub213pd {{.*#+}} zmm0 = (zmm1 * zmm0) +/- zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmaddsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 4) nounwind
  ret <8 x double> %res
}
declare <8 x double> @llvm.x86.avx512.mask.vfmaddsub.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32) nounwind readnone

define <8 x double> @test_mask_vfmaddsub_pd(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_vfmaddsub_pd:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub132pd {{.*#+}} zmm0 {%k1} = (zmm0 * zmm1) +/- zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmaddsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 4) nounwind
  ret <8 x double> %res
}

define <8 x double>@test_int_x86_avx512_mask_vfmaddsub_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask_vfmaddsub_pd_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub132pd {{.*#+}} zmm0 {%k1} = (zmm0 * zmm1) +/- zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmaddsub.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 4)
  ret <8 x double> %res
}

declare <8 x double> @llvm.x86.avx512.mask3.vfmaddsub.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32)

define <8 x double>@test_int_x86_avx512_mask3_vfmaddsub_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmaddsub_pd_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub231pd {{.*#+}} zmm2 {%k1} = (zmm0 * zmm1) +/- zmm2
; CHECK-NEXT:    vmovapd %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask3.vfmaddsub.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 4)
  ret <8 x double> %res
}

declare <8 x double> @llvm.x86.avx512.maskz.vfmaddsub.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32)

define <8 x double>@test_int_x86_avx512_maskz_vfmaddsub_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_maskz_vfmaddsub_pd_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub213pd {{.*#+}} zmm0 {%k1} {z} = (zmm1 * zmm0) +/- zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.maskz.vfmaddsub.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 4)
  ret <8 x double> %res
}

define <16 x float>@test_int_x86_avx512_mask_vfmaddsub_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask_vfmaddsub_ps_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub132ps {{.*#+}} zmm0 {%k1} = (zmm0 * zmm1) +/- zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmaddsub.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 4)
  ret <16 x float> %res
}

declare <16 x float> @llvm.x86.avx512.mask3.vfmaddsub.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)

define <16 x float>@test_int_x86_avx512_mask3_vfmaddsub_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmaddsub_ps_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub231ps {{.*#+}} zmm2 {%k1} = (zmm0 * zmm1) +/- zmm2
; CHECK-NEXT:    vmovaps %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask3.vfmaddsub.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 4)
  ret <16 x float> %res
}

declare <16 x float> @llvm.x86.avx512.maskz.vfmaddsub.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)

define <16 x float>@test_int_x86_avx512_maskz_vfmaddsub_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_maskz_vfmaddsub_ps_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub213ps {{.*#+}} zmm0 {%k1} {z} = (zmm1 * zmm0) +/- zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.maskz.vfmaddsub.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 4)
  ret <16 x float> %res
}

declare <8 x double> @llvm.x86.avx512.mask3.vfmsubadd.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32)

define <8 x double>@test_int_x86_avx512_mask3_vfmsubadd_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmsubadd_pd_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmsubadd231pd {{.*#+}} zmm2 {%k1} = (zmm0 * zmm1) -/+ zmm2
; CHECK-NEXT:    vmovapd %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask3.vfmsubadd.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 4)
  ret <8 x double> %res
}

declare <16 x float> @llvm.x86.avx512.mask3.vfmsubadd.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)

define <16 x float>@test_int_x86_avx512_mask3_vfmsubadd_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmsubadd_ps_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmsubadd231ps {{.*#+}} zmm2 {%k1} = (zmm0 * zmm1) -/+ zmm2
; CHECK-NEXT:    vmovaps %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask3.vfmsubadd.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 4)
  ret <16 x float> %res
}

define <16 x float> @test_mask_round_vfmadd512_ps_rrb_rne(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask) {
; CHECK-LABEL: test_mask_round_vfmadd512_ps_rrb_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd132ps {rn-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 8) nounwind
  ret <16 x float> %res
}

define <16 x float> @test_mask_round_vfmadd512_ps_rrb_rtn(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask) {
; CHECK-LABEL: test_mask_round_vfmadd512_ps_rrb_rtn:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd132ps {rd-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 9) nounwind
  ret <16 x float> %res
}

define <16 x float> @test_mask_round_vfmadd512_ps_rrb_rtp(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask) {
; CHECK-LABEL: test_mask_round_vfmadd512_ps_rrb_rtp:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd132ps {ru-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 10) nounwind
  ret <16 x float> %res
}

define <16 x float> @test_mask_round_vfmadd512_ps_rrb_rtz(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask) {
; CHECK-LABEL: test_mask_round_vfmadd512_ps_rrb_rtz:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd132ps {rz-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 11) nounwind
  ret <16 x float> %res
}

define <16 x float> @test_mask_round_vfmadd512_ps_rrb_current(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask) {
; CHECK-LABEL: test_mask_round_vfmadd512_ps_rrb_current:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd132ps {{.*#+}} zmm0 {%k1} = (zmm0 * zmm1) + zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 4) nounwind
  ret <16 x float> %res
}

define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_rne(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2) {
; CHECK-LABEL: test_mask_round_vfmadd512_ps_rrbz_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213ps {rn-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 8) nounwind
  ret <16 x float> %res
}

define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_rtn(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2) {
; CHECK-LABEL: test_mask_round_vfmadd512_ps_rrbz_rtn:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213ps {rd-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 9) nounwind
  ret <16 x float> %res
}

define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_rtp(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2) {
; CHECK-LABEL: test_mask_round_vfmadd512_ps_rrbz_rtp:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213ps {ru-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 10) nounwind
  ret <16 x float> %res
}

define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_rtz(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2) {
; CHECK-LABEL: test_mask_round_vfmadd512_ps_rrbz_rtz:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213ps {rz-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 11) nounwind
  ret <16 x float> %res
}

define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_current(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2) {
; CHECK-LABEL: test_mask_round_vfmadd512_ps_rrbz_current:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213ps {{.*#+}} zmm0 = (zmm1 * zmm0) + zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 4) nounwind
  ret <16 x float> %res
}

declare <8 x double> @llvm.x86.avx512.mask3.vfmsub.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32)

define <8 x double>@test_int_x86_avx512_mask3_vfmsub_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmsub_pd_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmsub231pd {{.*#+}} zmm2 {%k1} = (zmm0 * zmm1) - zmm2
; CHECK-NEXT:    vmovapd %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask3.vfmsub.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 4)
  ret <8 x double> %res
}

declare <16 x float> @llvm.x86.avx512.mask3.vfmsub.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)

define <16 x float>@test_int_x86_avx512_mask3_vfmsub_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmsub_ps_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmsub231ps {{.*#+}} zmm2 {%k1} = (zmm0 * zmm1) - zmm2
; CHECK-NEXT:    vmovaps %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask3.vfmsub.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 4)
  ret <16 x float> %res
}

define <8 x double> @test_mask_round_vfmadd512_pd_rrb_rne(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_round_vfmadd512_pd_rrb_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd132pd {rn-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 8) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfmadd512_pd_rrb_rtn(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_round_vfmadd512_pd_rrb_rtn:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd132pd {rd-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 9) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfmadd512_pd_rrb_rtp(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_round_vfmadd512_pd_rrb_rtp:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd132pd {ru-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 10) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfmadd512_pd_rrb_rtz(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_round_vfmadd512_pd_rrb_rtz:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd132pd {rz-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 11) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfmadd512_pd_rrb_current(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_round_vfmadd512_pd_rrb_current:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd132pd {{.*#+}} zmm0 {%k1} = (zmm0 * zmm1) + zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 4) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_rne(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_mask_round_vfmadd512_pd_rrbz_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213pd {rn-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 8) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_rtn(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_mask_round_vfmadd512_pd_rrbz_rtn:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213pd {rd-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 9) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_rtp(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_mask_round_vfmadd512_pd_rrbz_rtp:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213pd {ru-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 10) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_rtz(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_mask_round_vfmadd512_pd_rrbz_rtz:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213pd {rz-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 11) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_current(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_mask_round_vfmadd512_pd_rrbz_current:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd213pd {{.*#+}} zmm0 = (zmm1 * zmm0) + zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 4) nounwind
  ret <8 x double> %res
}

define <8 x double>@test_int_x86_avx512_mask_vfmadd_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask_vfmadd_pd_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd132pd {{.*#+}} zmm0 {%k1} = (zmm0 * zmm1) + zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 4)
  ret <8 x double> %res
}

declare <8 x double> @llvm.x86.avx512.mask3.vfmadd.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32)

define <8 x double>@test_int_x86_avx512_mask3_vfmadd_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmadd_pd_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd231pd {{.*#+}} zmm2 {%k1} = (zmm0 * zmm1) + zmm2
; CHECK-NEXT:    vmovapd %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask3.vfmadd.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 4)
  ret <8 x double> %res
}

declare <8 x double> @llvm.x86.avx512.maskz.vfmadd.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32)

define <8 x double>@test_int_x86_avx512_maskz_vfmadd_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_maskz_vfmadd_pd_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd213pd {{.*#+}} zmm0 {%k1} {z} = (zmm1 * zmm0) + zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.maskz.vfmadd.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 4)
  ret <8 x double> %res
}

define <16 x float>@test_int_x86_avx512_mask_vfmadd_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask_vfmadd_ps_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd132ps {{.*#+}} zmm0 {%k1} = (zmm0 * zmm1) + zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 4)
  ret <16 x float> %res
}

declare <16 x float> @llvm.x86.avx512.mask3.vfmadd.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)

define <16 x float>@test_int_x86_avx512_mask3_vfmadd_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmadd_ps_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd231ps {{.*#+}} zmm2 {%k1} = (zmm0 * zmm1) + zmm2
; CHECK-NEXT:    vmovaps %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask3.vfmadd.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 4)
  ret <16 x float> %res
}

declare <16 x float> @llvm.x86.avx512.maskz.vfmadd.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)

define <16 x float>@test_int_x86_avx512_maskz_vfmadd_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_maskz_vfmadd_ps_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmadd213ps {{.*#+}} zmm0 {%k1} {z} = (zmm1 * zmm0) + zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.maskz.vfmadd.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 4)
  ret <16 x float> %res
}


define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_rne(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_round_vfnmsub512_pd_rrb_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmsub132pd {rn-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 8) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_rtn(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_round_vfnmsub512_pd_rrb_rtn:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmsub132pd {rd-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 9) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_rtp(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_round_vfnmsub512_pd_rrb_rtp:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmsub132pd {ru-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 10) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_rtz(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_round_vfnmsub512_pd_rrb_rtz:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmsub132pd {rz-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 11) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_current(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask) {
; CHECK-LABEL: test_mask_round_vfnmsub512_pd_rrb_current:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmsub132pd {{.*#+}} zmm0 {%k1} = -(zmm0 * zmm1) - zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 4) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_rne(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_mask_round_vfnmsub512_pd_rrbz_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfnmsub213pd {rn-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 8) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_rtn(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_mask_round_vfnmsub512_pd_rrbz_rtn:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfnmsub213pd {rd-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 9) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_rtp(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_mask_round_vfnmsub512_pd_rrbz_rtp:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfnmsub213pd {ru-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 10) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_rtz(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_mask_round_vfnmsub512_pd_rrbz_rtz:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfnmsub213pd {rz-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 11) nounwind
  ret <8 x double> %res
}

define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_current(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2) {
; CHECK-LABEL: test_mask_round_vfnmsub512_pd_rrbz_current:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfnmsub213pd {{.*#+}} zmm0 = -(zmm1 * zmm0) - zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 4) nounwind
  ret <8 x double> %res
}

define <8 x double>@test_int_x86_avx512_mask_vfnmsub_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask_vfnmsub_pd_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmsub132pd {{.*#+}} zmm0 {%k1} = -(zmm0 * zmm1) - zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 4)
  ret <8 x double> %res
}

declare <8 x double> @llvm.x86.avx512.mask3.vfnmsub.pd.512(<8 x double>, <8 x double>, <8 x double>, i8, i32)

define <8 x double>@test_int_x86_avx512_mask3_vfnmsub_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfnmsub_pd_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmsub231pd {{.*#+}} zmm2 {%k1} = -(zmm0 * zmm1) - zmm2
; CHECK-NEXT:    vmovapd %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask3.vfnmsub.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 4)
  ret <8 x double> %res
}

define <16 x float>@test_int_x86_avx512_mask_vfnmsub_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask_vfnmsub_ps_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmsub132ps {{.*#+}} zmm0 {%k1} = -(zmm0 * zmm1) - zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 4)
  ret <16 x float> %res
}

declare <16 x float> @llvm.x86.avx512.mask3.vfnmsub.ps.512(<16 x float>, <16 x float>, <16 x float>, i16, i32)

define <16 x float>@test_int_x86_avx512_mask3_vfnmsub_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfnmsub_ps_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmsub231ps {{.*#+}} zmm2 {%k1} = -(zmm0 * zmm1) - zmm2
; CHECK-NEXT:    vmovaps %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask3.vfnmsub.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 4)
  ret <16 x float> %res
}

define <8 x double>@test_int_x86_avx512_mask_vfnmadd_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask_vfnmadd_pd_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmadd132pd {{.*#+}} zmm0 {%k1} = -(zmm0 * zmm1) + zmm2
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfnmadd.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 4)
  ret <8 x double> %res
}

define <16 x float>@test_int_x86_avx512_mask_vfnmadd_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask_vfnmadd_ps_512:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfnmadd132ps {{.*#+}} zmm0 {%k1} = -(zmm0 * zmm1) + zmm2
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfnmadd.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 4)
  ret <16 x float> %res
}

define <8 x double>@test_int_x86_avx512_mask_vfmaddsub_pd_512_rne(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask_vfmaddsub_pd_512_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub132pd {rn-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask.vfmaddsub.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 8)
  ret <8 x double> %res
}

define <8 x double>@test_int_x86_avx512_mask3_vfmaddsub_pd_512_rne(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmaddsub_pd_512_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub231pd {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; CHECK-NEXT:    vmovapd %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask3.vfmaddsub.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 8)
  ret <8 x double> %res
}

define <8 x double>@test_int_x86_avx512_maskz_vfmaddsub_pd_512_rne(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_maskz_vfmaddsub_pd_512_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub213pd {rn-sae}, %zmm2, %zmm1, %zmm0 {%k1} {z}
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.maskz.vfmaddsub.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 8)
  ret <8 x double> %res
}

define <16 x float>@test_int_x86_avx512_mask_vfmaddsub_ps_512_rne(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask_vfmaddsub_ps_512_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub132ps {rn-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask.vfmaddsub.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 8)
  ret <16 x float> %res
}

define <16 x float>@test_int_x86_avx512_mask3_vfmaddsub_ps_512_rne(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmaddsub_ps_512_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub231ps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; CHECK-NEXT:    vmovaps %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask3.vfmaddsub.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 8)
  ret <16 x float> %res
}

define <16 x float>@test_int_x86_avx512_maskz_vfmaddsub_ps_512_rne(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_maskz_vfmaddsub_ps_512_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmaddsub213ps {rn-sae}, %zmm2, %zmm1, %zmm0 {%k1} {z}
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.maskz.vfmaddsub.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 8)
  ret <16 x float> %res
}

define <8 x double>@test_int_x86_avx512_mask3_vfmsubadd_pd_512_rne(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmsubadd_pd_512_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmsubadd231pd {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; CHECK-NEXT:    vmovapd %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <8 x double> @llvm.x86.avx512.mask3.vfmsubadd.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 8)
  ret <8 x double> %res
}

define <16 x float>@test_int_x86_avx512_mask3_vfmsubadd_ps_512_rne(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmsubadd_ps_512_rne:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    kmovw %edi, %k1
; CHECK-NEXT:    vfmsubadd231ps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; CHECK-NEXT:    vmovaps %zmm2, %zmm0
; CHECK-NEXT:    retq
  %res = call <16 x float> @llvm.x86.avx512.mask3.vfmsubadd.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 8)
  ret <16 x float> %res
}