; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -instcombine -S | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"

declare <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>, <4 x float>, <4 x float>, i8, i32)

define <4 x float> @test_add_ss(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: @test_add_ss(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fadd float [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x float> [[A]], float [[TMP3]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP4]]
;
  %1 = insertelement <4 x float> %b, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float> %a, <4 x float> %3, <4 x float> undef, i8 -1, i32 4)
  ret <4 x float> %4
}

define <4 x float> @test_add_ss_round(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: @test_add_ss_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> undef, i8 -1, i32 8)
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
  %1 = insertelement <4 x float> %b, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float> %a, <4 x float> %3, <4 x float> undef, i8 -1, i32 8)
  ret <4 x float> %4
}

define <4 x float> @test_add_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_add_ss_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fadd float [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i1> [[TMP4]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], float [[TMP3]], float [[TMP6]]
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x float> [[A]], float [[TMP7]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP8]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float> %a, <4 x float> %b, <4 x float> %3, i8 %mask, i32 4)
  ret <4 x float> %4
}

define <4 x float> @test_add_ss_mask_round(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_add_ss_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> [[C:%.*]], i8 [[MASK:%.*]], i32 8)
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float> %a, <4 x float> %b, <4 x float> %3, i8 %mask, i32 8)
  ret <4 x float> %4
}

define float @test_add_ss_1(float %a, float %b) {
; CHECK-LABEL: @test_add_ss_1(
; CHECK-NEXT:    ret float 1.000000e+00
;
  %1 = insertelement <4 x float> undef, float %a, i32 0
  %2 = insertelement <4 x float> %1, float 1.000000e+00, i32 1
  %3 = insertelement <4 x float> %2, float 2.000000e+00, i32 2
  %4 = insertelement <4 x float> %3, float 3.000000e+00, i32 3
  %5 = insertelement <4 x float> undef, float %b, i32 0
  %6 = insertelement <4 x float> %5, float 4.000000e+00, i32 1
  %7 = insertelement <4 x float> %6, float 5.000000e+00, i32 2
  %8 = insertelement <4 x float> %7, float 6.000000e+00, i32 3
  %9 = tail call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float> %4, <4 x float> %8, <4 x float> undef, i8 -1, i32 8)
  %10 = extractelement <4 x float> %9, i32 1
  ret float %10
}

declare <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>, <2 x double>, <2 x double>, i8, i32)

define <2 x double> @test_add_sd(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: @test_add_sd(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fadd double [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <2 x double> [[A]], double [[TMP3]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP4]]
;
  %1 = insertelement <2 x double> %b, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double> %a, <2 x double> %1, <2 x double> undef, i8 -1, i32 4)
  ret <2 x double> %2
}

define <2 x double> @test_add_sd_round(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: @test_add_sd_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> undef, i8 -1, i32 8)
; CHECK-NEXT:    ret <2 x double> [[TMP1]]
;
  %1 = insertelement <2 x double> %b, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double> %a, <2 x double> %1, <2 x double> undef, i8 -1, i32 8)
  ret <2 x double> %2
}

define <2 x double> @test_add_sd_mask(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_add_sd_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fadd double [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i1> [[TMP4]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], double [[TMP3]], double [[TMP6]]
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x double> [[A]], double [[TMP7]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP8]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double> %a, <2 x double> %b, <2 x double> %1, i8 %mask, i32 4)
  ret <2 x double> %2
}

define <2 x double> @test_add_sd_mask_round(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_add_sd_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> [[C:%.*]], i8 [[MASK:%.*]], i32 8)
; CHECK-NEXT:    ret <2 x double> [[TMP1]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double> %a, <2 x double> %b, <2 x double> %1, i8 %mask, i32 8)
  ret <2 x double> %2
}

define double @test_add_sd_1(double %a, double %b) {
; CHECK-LABEL: @test_add_sd_1(
; CHECK-NEXT:    ret double 1.000000e+00
;
  %1 = insertelement <2 x double> undef, double %a, i32 0
  %2 = insertelement <2 x double> %1, double 1.000000e+00, i32 1
  %3 = insertelement <2 x double> undef, double %b, i32 0
  %4 = insertelement <2 x double> %3, double 2.000000e+00, i32 1
  %5 = tail call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double> %2, <2 x double> %4, <2 x double> undef, i8 -1, i32 8)
  %6 = extractelement <2 x double> %5, i32 1
  ret double %6
}

declare <4 x float> @llvm.x86.avx512.mask.sub.ss.round(<4 x float>, <4 x float>, <4 x float>, i8, i32)

define <4 x float> @test_sub_ss(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: @test_sub_ss(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fsub float [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x float> [[A]], float [[TMP3]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP4]]
;
  %1 = insertelement <4 x float> %b, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.sub.ss.round(<4 x float> %a, <4 x float> %3, <4 x float> undef, i8 -1, i32 4)
  ret <4 x float> %4
}

define <4 x float> @test_sub_ss_round(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: @test_sub_ss_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x float> @llvm.x86.avx512.mask.sub.ss.round(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> undef, i8 -1, i32 8)
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
  %1 = insertelement <4 x float> %b, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.sub.ss.round(<4 x float> %a, <4 x float> %3, <4 x float> undef, i8 -1, i32 8)
  ret <4 x float> %4
}

define <4 x float> @test_sub_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_sub_ss_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fsub float [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i1> [[TMP4]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], float [[TMP3]], float [[TMP6]]
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x float> [[A]], float [[TMP7]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP8]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.sub.ss.round(<4 x float> %a, <4 x float> %b, <4 x float> %3, i8 %mask, i32 4)
  ret <4 x float> %4
}

define <4 x float> @test_sub_ss_mask_round(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_sub_ss_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x float> @llvm.x86.avx512.mask.sub.ss.round(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> [[C:%.*]], i8 [[MASK:%.*]], i32 8)
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.sub.ss.round(<4 x float> %a, <4 x float> %b, <4 x float> %3, i8 %mask, i32 8)
  ret <4 x float> %4
}

define float @test_sub_ss_1(float %a, float %b) {
; CHECK-LABEL: @test_sub_ss_1(
; CHECK-NEXT:    ret float 1.000000e+00
;
  %1 = insertelement <4 x float> undef, float %a, i32 0
  %2 = insertelement <4 x float> %1, float 1.000000e+00, i32 1
  %3 = insertelement <4 x float> %2, float 2.000000e+00, i32 2
  %4 = insertelement <4 x float> %3, float 3.000000e+00, i32 3
  %5 = insertelement <4 x float> undef, float %b, i32 0
  %6 = insertelement <4 x float> %5, float 4.000000e+00, i32 1
  %7 = insertelement <4 x float> %6, float 5.000000e+00, i32 2
  %8 = insertelement <4 x float> %7, float 6.000000e+00, i32 3
  %9 = tail call <4 x float> @llvm.x86.avx512.mask.sub.ss.round(<4 x float> %4, <4 x float> %8, <4 x float> undef, i8 -1, i32 8)
  %10 = extractelement <4 x float> %9, i32 1
  ret float %10
}

declare <2 x double> @llvm.x86.avx512.mask.sub.sd.round(<2 x double>, <2 x double>, <2 x double>, i8, i32)

define <2 x double> @test_sub_sd(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: @test_sub_sd(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fsub double [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <2 x double> [[A]], double [[TMP3]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP4]]
;
  %1 = insertelement <2 x double> %b, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.sub.sd.round(<2 x double> %a, <2 x double> %1, <2 x double> undef, i8 -1, i32 4)
  ret <2 x double> %2
}

define <2 x double> @test_sub_sd_round(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: @test_sub_sd_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <2 x double> @llvm.x86.avx512.mask.sub.sd.round(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> undef, i8 -1, i32 8)
; CHECK-NEXT:    ret <2 x double> [[TMP1]]
;
  %1 = insertelement <2 x double> %b, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.sub.sd.round(<2 x double> %a, <2 x double> %1, <2 x double> undef, i8 -1, i32 8)
  ret <2 x double> %2
}

define <2 x double> @test_sub_sd_mask(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_sub_sd_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fsub double [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i1> [[TMP4]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], double [[TMP3]], double [[TMP6]]
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x double> [[A]], double [[TMP7]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP8]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.sub.sd.round(<2 x double> %a, <2 x double> %b, <2 x double> %1, i8 %mask, i32 4)
  ret <2 x double> %2
}

define <2 x double> @test_sub_sd_mask_round(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_sub_sd_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <2 x double> @llvm.x86.avx512.mask.sub.sd.round(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> [[C:%.*]], i8 [[MASK:%.*]], i32 8)
; CHECK-NEXT:    ret <2 x double> [[TMP1]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.sub.sd.round(<2 x double> %a, <2 x double> %b, <2 x double> %1, i8 %mask, i32 8)
  ret <2 x double> %2
}

define double @test_sub_sd_1(double %a, double %b) {
; CHECK-LABEL: @test_sub_sd_1(
; CHECK-NEXT:    ret double 1.000000e+00
;
  %1 = insertelement <2 x double> undef, double %a, i32 0
  %2 = insertelement <2 x double> %1, double 1.000000e+00, i32 1
  %3 = insertelement <2 x double> undef, double %b, i32 0
  %4 = insertelement <2 x double> %3, double 2.000000e+00, i32 1
  %5 = tail call <2 x double> @llvm.x86.avx512.mask.sub.sd.round(<2 x double> %2, <2 x double> %4, <2 x double> undef, i8 -1, i32 8)
  %6 = extractelement <2 x double> %5, i32 1
  ret double %6
}

declare <4 x float> @llvm.x86.avx512.mask.mul.ss.round(<4 x float>, <4 x float>, <4 x float>, i8, i32)

define <4 x float> @test_mul_ss(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: @test_mul_ss(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fmul float [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x float> [[A]], float [[TMP3]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP4]]
;
  %1 = insertelement <4 x float> %b, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.mul.ss.round(<4 x float> %a, <4 x float> %3, <4 x float> undef, i8 -1, i32 4)
  ret <4 x float> %4
}

define <4 x float> @test_mul_ss_round(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: @test_mul_ss_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x float> @llvm.x86.avx512.mask.mul.ss.round(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> undef, i8 -1, i32 8)
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
  %1 = insertelement <4 x float> %b, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.mul.ss.round(<4 x float> %a, <4 x float> %3, <4 x float> undef, i8 -1, i32 8)
  ret <4 x float> %4
}

define <4 x float> @test_mul_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mul_ss_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fmul float [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i1> [[TMP4]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], float [[TMP3]], float [[TMP6]]
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x float> [[A]], float [[TMP7]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP8]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.mul.ss.round(<4 x float> %a, <4 x float> %b, <4 x float> %3, i8 %mask, i32 4)
  ret <4 x float> %4
}

define <4 x float> @test_mul_ss_mask_round(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mul_ss_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x float> @llvm.x86.avx512.mask.mul.ss.round(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> [[C:%.*]], i8 [[MASK:%.*]], i32 8)
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.mul.ss.round(<4 x float> %a, <4 x float> %b, <4 x float> %3, i8 %mask, i32 8)
  ret <4 x float> %4
}

define float @test_mul_ss_1(float %a, float %b) {
; CHECK-LABEL: @test_mul_ss_1(
; CHECK-NEXT:    ret float 1.000000e+00
;
  %1 = insertelement <4 x float> undef, float %a, i32 0
  %2 = insertelement <4 x float> %1, float 1.000000e+00, i32 1
  %3 = insertelement <4 x float> %2, float 2.000000e+00, i32 2
  %4 = insertelement <4 x float> %3, float 3.000000e+00, i32 3
  %5 = insertelement <4 x float> undef, float %b, i32 0
  %6 = insertelement <4 x float> %5, float 4.000000e+00, i32 1
  %7 = insertelement <4 x float> %6, float 5.000000e+00, i32 2
  %8 = insertelement <4 x float> %7, float 6.000000e+00, i32 3
  %9 = tail call <4 x float> @llvm.x86.avx512.mask.mul.ss.round(<4 x float> %4, <4 x float> %8, <4 x float> undef, i8 -1, i32 8)
  %10 = extractelement <4 x float> %9, i32 1
  ret float %10
}

declare <2 x double> @llvm.x86.avx512.mask.mul.sd.round(<2 x double>, <2 x double>, <2 x double>, i8, i32)

define <2 x double> @test_mul_sd(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: @test_mul_sd(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fmul double [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <2 x double> [[A]], double [[TMP3]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP4]]
;
  %1 = insertelement <2 x double> %b, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.mul.sd.round(<2 x double> %a, <2 x double> %1, <2 x double> undef, i8 -1, i32 4)
  ret <2 x double> %2
}

define <2 x double> @test_mul_sd_round(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: @test_mul_sd_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <2 x double> @llvm.x86.avx512.mask.mul.sd.round(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> undef, i8 -1, i32 8)
; CHECK-NEXT:    ret <2 x double> [[TMP1]]
;
  %1 = insertelement <2 x double> %b, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.mul.sd.round(<2 x double> %a, <2 x double> %1, <2 x double> undef, i8 -1, i32 8)
  ret <2 x double> %2
}

define <2 x double> @test_mul_sd_mask(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mul_sd_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fmul double [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i1> [[TMP4]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], double [[TMP3]], double [[TMP6]]
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x double> [[A]], double [[TMP7]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP8]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.mul.sd.round(<2 x double> %a, <2 x double> %b, <2 x double> %1, i8 %mask, i32 4)
  ret <2 x double> %2
}

define <2 x double> @test_mul_sd_mask_round(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mul_sd_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <2 x double> @llvm.x86.avx512.mask.mul.sd.round(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> [[C:%.*]], i8 [[MASK:%.*]], i32 8)
; CHECK-NEXT:    ret <2 x double> [[TMP1]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.mul.sd.round(<2 x double> %a, <2 x double> %b, <2 x double> %1, i8 %mask, i32 8)
  ret <2 x double> %2
}

define double @test_mul_sd_1(double %a, double %b) {
; CHECK-LABEL: @test_mul_sd_1(
; CHECK-NEXT:    ret double 1.000000e+00
;
  %1 = insertelement <2 x double> undef, double %a, i32 0
  %2 = insertelement <2 x double> %1, double 1.000000e+00, i32 1
  %3 = insertelement <2 x double> undef, double %b, i32 0
  %4 = insertelement <2 x double> %3, double 2.000000e+00, i32 1
  %5 = tail call <2 x double> @llvm.x86.avx512.mask.mul.sd.round(<2 x double> %2, <2 x double> %4, <2 x double> undef, i8 -1, i32 8)
  %6 = extractelement <2 x double> %5, i32 1
  ret double %6
}

declare <4 x float> @llvm.x86.avx512.mask.div.ss.round(<4 x float>, <4 x float>, <4 x float>, i8, i32)

define <4 x float> @test_div_ss(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: @test_div_ss(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fdiv float [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x float> [[A]], float [[TMP3]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP4]]
;
  %1 = insertelement <4 x float> %b, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.div.ss.round(<4 x float> %a, <4 x float> %3, <4 x float> undef, i8 -1, i32 4)
  ret <4 x float> %4
}

define <4 x float> @test_div_ss_round(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: @test_div_ss_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x float> @llvm.x86.avx512.mask.div.ss.round(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> undef, i8 -1, i32 8)
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
  %1 = insertelement <4 x float> %b, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.div.ss.round(<4 x float> %a, <4 x float> %3, <4 x float> undef, i8 -1, i32 8)
  ret <4 x float> %4
}

define <4 x float> @test_div_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_div_ss_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fdiv float [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i1> [[TMP4]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], float [[TMP3]], float [[TMP6]]
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x float> [[A]], float [[TMP7]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP8]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.div.ss.round(<4 x float> %a, <4 x float> %b, <4 x float> %3, i8 %mask, i32 4)
  ret <4 x float> %4
}

define <4 x float> @test_div_ss_mask_round(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_div_ss_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x float> @llvm.x86.avx512.mask.div.ss.round(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> [[C:%.*]], i8 [[MASK:%.*]], i32 8)
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.div.ss.round(<4 x float> %a, <4 x float> %b, <4 x float> %3, i8 %mask, i32 8)
  ret <4 x float> %4
}

define float @test_div_ss_1(float %a, float %b) {
; CHECK-LABEL: @test_div_ss_1(
; CHECK-NEXT:    ret float 1.000000e+00
;
  %1 = insertelement <4 x float> undef, float %a, i32 0
  %2 = insertelement <4 x float> %1, float 1.000000e+00, i32 1
  %3 = insertelement <4 x float> %2, float 2.000000e+00, i32 2
  %4 = insertelement <4 x float> %3, float 3.000000e+00, i32 3
  %5 = insertelement <4 x float> undef, float %b, i32 0
  %6 = insertelement <4 x float> %5, float 4.000000e+00, i32 1
  %7 = insertelement <4 x float> %6, float 5.000000e+00, i32 2
  %8 = insertelement <4 x float> %7, float 6.000000e+00, i32 3
  %9 = tail call <4 x float> @llvm.x86.avx512.mask.div.ss.round(<4 x float> %4, <4 x float> %8, <4 x float> undef, i8 -1, i32 8)
  %10 = extractelement <4 x float> %9, i32 1
  ret float %10
}

declare <2 x double> @llvm.x86.avx512.mask.div.sd.round(<2 x double>, <2 x double>, <2 x double>, i8, i32)

define <2 x double> @test_div_sd(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: @test_div_sd(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fdiv double [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <2 x double> [[A]], double [[TMP3]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP4]]
;
  %1 = insertelement <2 x double> %b, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.div.sd.round(<2 x double> %a, <2 x double> %1, <2 x double> undef, i8 -1, i32 4)
  ret <2 x double> %2
}

define <2 x double> @test_div_sd_round(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: @test_div_sd_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <2 x double> @llvm.x86.avx512.mask.div.sd.round(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> undef, i8 -1, i32 8)
; CHECK-NEXT:    ret <2 x double> [[TMP1]]
;
  %1 = insertelement <2 x double> %b, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.div.sd.round(<2 x double> %a, <2 x double> %1, <2 x double> undef, i8 -1, i32 8)
  ret <2 x double> %2
}

define <2 x double> @test_div_sd_mask(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_div_sd_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = fdiv double [[TMP1]], [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i1> [[TMP4]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP5]], double [[TMP3]], double [[TMP6]]
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x double> [[A]], double [[TMP7]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP8]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.div.sd.round(<2 x double> %a, <2 x double> %b, <2 x double> %1, i8 %mask, i32 4)
  ret <2 x double> %2
}

define <2 x double> @test_div_sd_mask_round(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_div_sd_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <2 x double> @llvm.x86.avx512.mask.div.sd.round(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> [[C:%.*]], i8 [[MASK:%.*]], i32 8)
; CHECK-NEXT:    ret <2 x double> [[TMP1]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.div.sd.round(<2 x double> %a, <2 x double> %b, <2 x double> %1, i8 %mask, i32 8)
  ret <2 x double> %2
}

define double @test_div_sd_1(double %a, double %b) {
; CHECK-LABEL: @test_div_sd_1(
; CHECK-NEXT:    ret double 1.000000e+00
;
  %1 = insertelement <2 x double> undef, double %a, i32 0
  %2 = insertelement <2 x double> %1, double 1.000000e+00, i32 1
  %3 = insertelement <2 x double> undef, double %b, i32 0
  %4 = insertelement <2 x double> %3, double 2.000000e+00, i32 1
  %5 = tail call <2 x double> @llvm.x86.avx512.mask.div.sd.round(<2 x double> %2, <2 x double> %4, <2 x double> undef, i8 -1, i32 8)
  %6 = extractelement <2 x double> %5, i32 1
  ret double %6
}

declare <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float>, <4 x float>, <4 x float>, i8, i32)

define <4 x float> @test_max_ss(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: @test_max_ss(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> undef, i8 -1, i32 4)
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
  %1 = insertelement <4 x float> %b, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float> %a, <4 x float> %3, <4 x float> undef, i8 -1, i32 4)
  ret <4 x float> %4
}

define <4 x float> @test_max_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_max_ss_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> [[C:%.*]], i8 [[MASK:%.*]], i32 4)
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float> %a, <4 x float> %b, <4 x float> %3, i8 %mask, i32 4)
  ret <4 x float> %4
}

define float @test_max_ss_1(float %a, float %b) {
; CHECK-LABEL: @test_max_ss_1(
; CHECK-NEXT:    ret float 1.000000e+00
;
  %1 = insertelement <4 x float> undef, float %a, i32 0
  %2 = insertelement <4 x float> %1, float 1.000000e+00, i32 1
  %3 = insertelement <4 x float> %2, float 2.000000e+00, i32 2
  %4 = insertelement <4 x float> %3, float 3.000000e+00, i32 3
  %5 = insertelement <4 x float> undef, float %b, i32 0
  %6 = insertelement <4 x float> %5, float 4.000000e+00, i32 1
  %7 = insertelement <4 x float> %6, float 5.000000e+00, i32 2
  %8 = insertelement <4 x float> %7, float 6.000000e+00, i32 3
  %9 = tail call <4 x float> @llvm.x86.avx512.mask.max.ss.round(<4 x float> %4, <4 x float> %8, <4 x float> undef, i8 -1, i32 8)
  %10 = extractelement <4 x float> %9, i32 1
  ret float %10
}

declare <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double>, <2 x double>, <2 x double>, i8, i32)

define <2 x double> @test_max_sd(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: @test_max_sd(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> undef, i8 -1, i32 4)
; CHECK-NEXT:    ret <2 x double> [[TMP1]]
;
  %1 = insertelement <2 x double> %b, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double> %a, <2 x double> %1, <2 x double> undef, i8 -1, i32 4)
  ret <2 x double> %2
}

define <2 x double> @test_max_sd_mask(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_max_sd_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> [[C:%.*]], i8 [[MASK:%.*]], i32 4)
; CHECK-NEXT:    ret <2 x double> [[TMP1]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double> %a, <2 x double> %b, <2 x double> %1, i8 %mask, i32 4)
  ret <2 x double> %2
}

define double @test_max_sd_1(double %a, double %b) {
; CHECK-LABEL: @test_max_sd_1(
; CHECK-NEXT:    ret double 1.000000e+00
;
  %1 = insertelement <2 x double> undef, double %a, i32 0
  %2 = insertelement <2 x double> %1, double 1.000000e+00, i32 1
  %3 = insertelement <2 x double> undef, double %b, i32 0
  %4 = insertelement <2 x double> %3, double 2.000000e+00, i32 1
  %5 = tail call <2 x double> @llvm.x86.avx512.mask.max.sd.round(<2 x double> %2, <2 x double> %4, <2 x double> undef, i8 -1, i32 8)
  %6 = extractelement <2 x double> %5, i32 1
  ret double %6
}

declare <4 x float> @llvm.x86.avx512.mask.min.ss.round(<4 x float>, <4 x float>, <4 x float>, i8, i32)

define <4 x float> @test_min_ss(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: @test_min_ss(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x float> @llvm.x86.avx512.mask.min.ss.round(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> undef, i8 -1, i32 4)
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
  %1 = insertelement <4 x float> %b, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.min.ss.round(<4 x float> %a, <4 x float> %3, <4 x float> undef, i8 -1, i32 4)
  ret <4 x float> %4
}

define <4 x float> @test_min_ss_mask(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_min_ss_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x float> @llvm.x86.avx512.mask.min.ss.round(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x float> [[C:%.*]], i8 [[MASK:%.*]], i32 4)
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = tail call <4 x float> @llvm.x86.avx512.mask.min.ss.round(<4 x float> %a, <4 x float> %b, <4 x float> %3, i8 %mask, i32 4)
  ret <4 x float> %4
}

define float @test_min_ss_1(float %a, float %b) {
; CHECK-LABEL: @test_min_ss_1(
; CHECK-NEXT:    ret float 1.000000e+00
;
  %1 = insertelement <4 x float> undef, float %a, i32 0
  %2 = insertelement <4 x float> %1, float 1.000000e+00, i32 1
  %3 = insertelement <4 x float> %2, float 2.000000e+00, i32 2
  %4 = insertelement <4 x float> %3, float 3.000000e+00, i32 3
  %5 = insertelement <4 x float> undef, float %b, i32 0
  %6 = insertelement <4 x float> %5, float 4.000000e+00, i32 1
  %7 = insertelement <4 x float> %6, float 5.000000e+00, i32 2
  %8 = insertelement <4 x float> %7, float 6.000000e+00, i32 3
  %9 = tail call <4 x float> @llvm.x86.avx512.mask.min.ss.round(<4 x float> %4, <4 x float> %8, <4 x float> undef, i8 -1, i32 8)
  %10 = extractelement <4 x float> %9, i32 1
  ret float %10
}

declare <2 x double> @llvm.x86.avx512.mask.min.sd.round(<2 x double>, <2 x double>, <2 x double>, i8, i32)

define <2 x double> @test_min_sd(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: @test_min_sd(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <2 x double> @llvm.x86.avx512.mask.min.sd.round(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> undef, i8 -1, i32 4)
; CHECK-NEXT:    ret <2 x double> [[TMP1]]
;
  %1 = insertelement <2 x double> %b, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.min.sd.round(<2 x double> %a, <2 x double> %1, <2 x double> undef, i8 -1, i32 4)
  ret <2 x double> %2
}

define <2 x double> @test_min_sd_mask(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_min_sd_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call <2 x double> @llvm.x86.avx512.mask.min.sd.round(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], <2 x double> [[C:%.*]], i8 [[MASK:%.*]], i32 4)
; CHECK-NEXT:    ret <2 x double> [[TMP1]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = tail call <2 x double> @llvm.x86.avx512.mask.min.sd.round(<2 x double> %a, <2 x double> %b, <2 x double> %1, i8 %mask, i32 4)
  ret <2 x double> %2
}

define double @test_min_sd_1(double %a, double %b) {
; CHECK-LABEL: @test_min_sd_1(
; CHECK-NEXT:    ret double 1.000000e+00
;
  %1 = insertelement <2 x double> undef, double %a, i32 0
  %2 = insertelement <2 x double> %1, double 1.000000e+00, i32 1
  %3 = insertelement <2 x double> undef, double %b, i32 0
  %4 = insertelement <2 x double> %3, double 2.000000e+00, i32 1
  %5 = tail call <2 x double> @llvm.x86.avx512.mask.min.sd.round(<2 x double> %2, <2 x double> %4, <2 x double> undef, i8 -1, i32 8)
  %6 = extractelement <2 x double> %5, i32 1
  ret double %6
}

declare i8 @llvm.x86.avx512.mask.cmp.ss(<4 x float>, <4 x float>, i32, i8, i32)

define i8 @test_cmp_ss(<4 x float> %a, <4 x float> %b, i8 %mask) {
; CHECK-LABEL: @test_cmp_ss(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call i8 @llvm.x86.avx512.mask.cmp.ss(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], i32 3, i8 [[MASK:%.*]], i32 4)
; CHECK-NEXT:    ret i8 [[TMP1]]
;
  %1 = insertelement <4 x float> %a, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = insertelement <4 x float> %b, float 4.000000e+00, i32 1
  %5 = insertelement <4 x float> %4, float 5.000000e+00, i32 2
  %6 = insertelement <4 x float> %5, float 6.000000e+00, i32 3
  %7 = tail call i8 @llvm.x86.avx512.mask.cmp.ss(<4 x float> %3, <4 x float> %6, i32 3, i8 %mask, i32 4)
  ret i8 %7
}

declare i8 @llvm.x86.avx512.mask.cmp.sd(<2 x double>, <2 x double>, i32, i8, i32)

define i8 @test_cmp_sd(<2 x double> %a, <2 x double> %b, i8 %mask) {
; CHECK-LABEL: @test_cmp_sd(
; CHECK-NEXT:    [[TMP1:%.*]] = tail call i8 @llvm.x86.avx512.mask.cmp.sd(<2 x double> [[A:%.*]], <2 x double> [[B:%.*]], i32 3, i8 [[MASK:%.*]], i32 4)
; CHECK-NEXT:    ret i8 [[TMP1]]
;
  %1 = insertelement <2 x double> %a, double 1.000000e+00, i32 1
  %2 = insertelement <2 x double> %b, double 2.000000e+00, i32 1
  %3 = tail call i8 @llvm.x86.avx512.mask.cmp.sd(<2 x double> %1, <2 x double> %2, i32 3, i8 %mask, i32 4)
  ret i8 %3
}

define i64 @test(float %f, double %d) {
; CHECK-LABEL: @test(
; CHECK-NEXT:    [[V03:%.*]] = insertelement <4 x float> undef, float [[F:%.*]], i32 0
; CHECK-NEXT:    [[TMP0:%.*]] = tail call i32 @llvm.x86.avx512.vcvtss2si32(<4 x float> [[V03]], i32 4)
; CHECK-NEXT:    [[V13:%.*]] = insertelement <4 x float> undef, float [[F]], i32 0
; CHECK-NEXT:    [[TMP1:%.*]] = tail call i64 @llvm.x86.avx512.vcvtss2si64(<4 x float> [[V13]], i32 4)
; CHECK-NEXT:    [[V23:%.*]] = insertelement <4 x float> undef, float [[F]], i32 0
; CHECK-NEXT:    [[TMP2:%.*]] = tail call i32 @llvm.x86.avx512.cvttss2si(<4 x float> [[V23]], i32 4)
; CHECK-NEXT:    [[V33:%.*]] = insertelement <4 x float> undef, float [[F]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = tail call i64 @llvm.x86.avx512.cvttss2si64(<4 x float> [[V33]], i32 4)
; CHECK-NEXT:    [[V41:%.*]] = insertelement <2 x double> undef, double [[D:%.*]], i32 0
; CHECK-NEXT:    [[TMP4:%.*]] = tail call i32 @llvm.x86.avx512.vcvtsd2si32(<2 x double> [[V41]], i32 4)
; CHECK-NEXT:    [[V51:%.*]] = insertelement <2 x double> undef, double [[D]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = tail call i64 @llvm.x86.avx512.vcvtsd2si64(<2 x double> [[V51]], i32 4)
; CHECK-NEXT:    [[V61:%.*]] = insertelement <2 x double> undef, double [[D]], i32 0
; CHECK-NEXT:    [[TMP6:%.*]] = tail call i32 @llvm.x86.avx512.cvttsd2si(<2 x double> [[V61]], i32 4)
; CHECK-NEXT:    [[V71:%.*]] = insertelement <2 x double> undef, double [[D]], i32 0
; CHECK-NEXT:    [[TMP7:%.*]] = tail call i64 @llvm.x86.avx512.cvttsd2si64(<2 x double> [[V71]], i32 4)
; CHECK-NEXT:    [[TMP8:%.*]] = add i32 [[TMP0]], [[TMP2]]
; CHECK-NEXT:    [[TMP9:%.*]] = add i32 [[TMP4]], [[TMP6]]
; CHECK-NEXT:    [[TMP10:%.*]] = add i32 [[TMP8]], [[TMP9]]
; CHECK-NEXT:    [[TMP11:%.*]] = sext i32 [[TMP10]] to i64
; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[TMP1]], [[TMP3]]
; CHECK-NEXT:    [[TMP13:%.*]] = add i64 [[TMP5]], [[TMP7]]
; CHECK-NEXT:    [[TMP14:%.*]] = add i64 [[TMP12]], [[TMP13]]
; CHECK-NEXT:    [[TMP15:%.*]] = add i64 [[TMP14]], [[TMP11]]
; CHECK-NEXT:    ret i64 [[TMP15]]
;
  %v00 = insertelement <4 x float> undef, float %f, i32 0
  %v01 = insertelement <4 x float> %v00, float 0.000000e+00, i32 1
  %v02 = insertelement <4 x float> %v01, float 0.000000e+00, i32 2
  %v03 = insertelement <4 x float> %v02, float 0.000000e+00, i32 3
  %tmp0 = tail call i32 @llvm.x86.avx512.vcvtss2si32(<4 x float> %v03, i32 4)
  %v10 = insertelement <4 x float> undef, float %f, i32 0
  %v11 = insertelement <4 x float> %v10, float 0.000000e+00, i32 1
  %v12 = insertelement <4 x float> %v11, float 0.000000e+00, i32 2
  %v13 = insertelement <4 x float> %v12, float 0.000000e+00, i32 3
  %tmp1 = tail call i64 @llvm.x86.avx512.vcvtss2si64(<4 x float> %v13, i32 4)
  %v20 = insertelement <4 x float> undef, float %f, i32 0
  %v21 = insertelement <4 x float> %v20, float 0.000000e+00, i32 1
  %v22 = insertelement <4 x float> %v21, float 0.000000e+00, i32 2
  %v23 = insertelement <4 x float> %v22, float 0.000000e+00, i32 3
  %tmp2 = tail call i32 @llvm.x86.avx512.cvttss2si(<4 x float> %v23, i32 4)
  %v30 = insertelement <4 x float> undef, float %f, i32 0
  %v31 = insertelement <4 x float> %v30, float 0.000000e+00, i32 1
  %v32 = insertelement <4 x float> %v31, float 0.000000e+00, i32 2
  %v33 = insertelement <4 x float> %v32, float 0.000000e+00, i32 3
  %tmp3 = tail call i64 @llvm.x86.avx512.cvttss2si64(<4 x float> %v33, i32 4)
  %v40 = insertelement <2 x double> undef, double %d, i32 0
  %v41 = insertelement <2 x double> %v40, double 0.000000e+00, i32 1
  %tmp4 = tail call i32 @llvm.x86.avx512.vcvtsd2si32(<2 x double> %v41, i32 4)
  %v50 = insertelement <2 x double> undef, double %d, i32 0
  %v51 = insertelement <2 x double> %v50, double 0.000000e+00, i32 1
  %tmp5 = tail call i64 @llvm.x86.avx512.vcvtsd2si64(<2 x double> %v51, i32 4)
  %v60 = insertelement <2 x double> undef, double %d, i32 0
  %v61 = insertelement <2 x double> %v60, double 0.000000e+00, i32 1
  %tmp6 = tail call i32 @llvm.x86.avx512.cvttsd2si(<2 x double> %v61, i32 4)
  %v70 = insertelement <2 x double> undef, double %d, i32 0
  %v71 = insertelement <2 x double> %v70, double 0.000000e+00, i32 1
  %tmp7 = tail call i64 @llvm.x86.avx512.cvttsd2si64(<2 x double> %v71, i32 4)
  %tmp8 = add i32 %tmp0, %tmp2
  %tmp9 = add i32 %tmp4, %tmp6
  %tmp10 = add i32 %tmp8, %tmp9
  %tmp11 = sext i32 %tmp10 to i64
  %tmp12 = add i64 %tmp1, %tmp3
  %tmp13 = add i64 %tmp5, %tmp7
  %tmp14 = add i64 %tmp12, %tmp13
  %tmp15 = add i64 %tmp11, %tmp14
  ret i64 %tmp15
}

declare i32 @llvm.x86.avx512.vcvtss2si32(<4 x float>, i32)
declare i64 @llvm.x86.avx512.vcvtss2si64(<4 x float>, i32)
declare i32 @llvm.x86.avx512.cvttss2si(<4 x float>, i32)
declare i64 @llvm.x86.avx512.cvttss2si64(<4 x float>, i32)
declare i32 @llvm.x86.avx512.vcvtsd2si32(<2 x double>, i32)
declare i64 @llvm.x86.avx512.vcvtsd2si64(<2 x double>, i32)
declare i32 @llvm.x86.avx512.cvttsd2si(<2 x double>, i32)
declare i64 @llvm.x86.avx512.cvttsd2si64(<2 x double>, i32)

define i64 @test2(float %f, double %d) {
; CHECK-LABEL: @test2(
; CHECK-NEXT:    [[V03:%.*]] = insertelement <4 x float> undef, float [[F:%.*]], i32 0
; CHECK-NEXT:    [[TMP0:%.*]] = tail call i32 @llvm.x86.avx512.vcvtss2usi32(<4 x float> [[V03]], i32 4)
; CHECK-NEXT:    [[V13:%.*]] = insertelement <4 x float> undef, float [[F]], i32 0
; CHECK-NEXT:    [[TMP1:%.*]] = tail call i64 @llvm.x86.avx512.vcvtss2usi64(<4 x float> [[V13]], i32 4)
; CHECK-NEXT:    [[V23:%.*]] = insertelement <4 x float> undef, float [[F]], i32 0
; CHECK-NEXT:    [[TMP2:%.*]] = tail call i32 @llvm.x86.avx512.cvttss2usi(<4 x float> [[V23]], i32 4)
; CHECK-NEXT:    [[V33:%.*]] = insertelement <4 x float> undef, float [[F]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = tail call i64 @llvm.x86.avx512.cvttss2usi64(<4 x float> [[V33]], i32 4)
; CHECK-NEXT:    [[V41:%.*]] = insertelement <2 x double> undef, double [[D:%.*]], i32 0
; CHECK-NEXT:    [[TMP4:%.*]] = tail call i32 @llvm.x86.avx512.vcvtsd2usi32(<2 x double> [[V41]], i32 4)
; CHECK-NEXT:    [[V51:%.*]] = insertelement <2 x double> undef, double [[D]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = tail call i64 @llvm.x86.avx512.vcvtsd2usi64(<2 x double> [[V51]], i32 4)
; CHECK-NEXT:    [[V61:%.*]] = insertelement <2 x double> undef, double [[D]], i32 0
; CHECK-NEXT:    [[TMP6:%.*]] = tail call i32 @llvm.x86.avx512.cvttsd2usi(<2 x double> [[V61]], i32 4)
; CHECK-NEXT:    [[V71:%.*]] = insertelement <2 x double> undef, double [[D]], i32 0
; CHECK-NEXT:    [[TMP7:%.*]] = tail call i64 @llvm.x86.avx512.cvttsd2usi64(<2 x double> [[V71]], i32 4)
; CHECK-NEXT:    [[TMP8:%.*]] = add i32 [[TMP0]], [[TMP2]]
; CHECK-NEXT:    [[TMP9:%.*]] = add i32 [[TMP4]], [[TMP6]]
; CHECK-NEXT:    [[TMP10:%.*]] = add i32 [[TMP8]], [[TMP9]]
; CHECK-NEXT:    [[TMP11:%.*]] = sext i32 [[TMP10]] to i64
; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[TMP1]], [[TMP3]]
; CHECK-NEXT:    [[TMP13:%.*]] = add i64 [[TMP5]], [[TMP7]]
; CHECK-NEXT:    [[TMP14:%.*]] = add i64 [[TMP12]], [[TMP13]]
; CHECK-NEXT:    [[TMP15:%.*]] = add i64 [[TMP14]], [[TMP11]]
; CHECK-NEXT:    ret i64 [[TMP15]]
;
  %v00 = insertelement <4 x float> undef, float %f, i32 0
  %v01 = insertelement <4 x float> %v00, float 0.000000e+00, i32 1
  %v02 = insertelement <4 x float> %v01, float 0.000000e+00, i32 2
  %v03 = insertelement <4 x float> %v02, float 0.000000e+00, i32 3
  %tmp0 = tail call i32 @llvm.x86.avx512.vcvtss2usi32(<4 x float> %v03, i32 4)
  %v10 = insertelement <4 x float> undef, float %f, i32 0
  %v11 = insertelement <4 x float> %v10, float 0.000000e+00, i32 1
  %v12 = insertelement <4 x float> %v11, float 0.000000e+00, i32 2
  %v13 = insertelement <4 x float> %v12, float 0.000000e+00, i32 3
  %tmp1 = tail call i64 @llvm.x86.avx512.vcvtss2usi64(<4 x float> %v13, i32 4)
  %v20 = insertelement <4 x float> undef, float %f, i32 0
  %v21 = insertelement <4 x float> %v20, float 0.000000e+00, i32 1
  %v22 = insertelement <4 x float> %v21, float 0.000000e+00, i32 2
  %v23 = insertelement <4 x float> %v22, float 0.000000e+00, i32 3
  %tmp2 = tail call i32 @llvm.x86.avx512.cvttss2usi(<4 x float> %v23, i32 4)
  %v30 = insertelement <4 x float> undef, float %f, i32 0
  %v31 = insertelement <4 x float> %v30, float 0.000000e+00, i32 1
  %v32 = insertelement <4 x float> %v31, float 0.000000e+00, i32 2
  %v33 = insertelement <4 x float> %v32, float 0.000000e+00, i32 3
  %tmp3 = tail call i64 @llvm.x86.avx512.cvttss2usi64(<4 x float> %v33, i32 4)
  %v40 = insertelement <2 x double> undef, double %d, i32 0
  %v41 = insertelement <2 x double> %v40, double 0.000000e+00, i32 1
  %tmp4 = tail call i32 @llvm.x86.avx512.vcvtsd2usi32(<2 x double> %v41, i32 4)
  %v50 = insertelement <2 x double> undef, double %d, i32 0
  %v51 = insertelement <2 x double> %v50, double 0.000000e+00, i32 1
  %tmp5 = tail call i64 @llvm.x86.avx512.vcvtsd2usi64(<2 x double> %v51, i32 4)
  %v60 = insertelement <2 x double> undef, double %d, i32 0
  %v61 = insertelement <2 x double> %v60, double 0.000000e+00, i32 1
  %tmp6 = tail call i32 @llvm.x86.avx512.cvttsd2usi(<2 x double> %v61, i32 4)
  %v70 = insertelement <2 x double> undef, double %d, i32 0
  %v71 = insertelement <2 x double> %v70, double 0.000000e+00, i32 1
  %tmp7 = tail call i64 @llvm.x86.avx512.cvttsd2usi64(<2 x double> %v71, i32 4)
  %tmp8 = add i32 %tmp0, %tmp2
  %tmp9 = add i32 %tmp4, %tmp6
  %tmp10 = add i32 %tmp8, %tmp9
  %tmp11 = sext i32 %tmp10 to i64
  %tmp12 = add i64 %tmp1, %tmp3
  %tmp13 = add i64 %tmp5, %tmp7
  %tmp14 = add i64 %tmp12, %tmp13
  %tmp15 = add i64 %tmp11, %tmp14
  ret i64 %tmp15
}

declare i32 @llvm.x86.avx512.vcvtss2usi32(<4 x float>, i32)
declare i64 @llvm.x86.avx512.vcvtss2usi64(<4 x float>, i32)
declare i32 @llvm.x86.avx512.cvttss2usi(<4 x float>, i32)
declare i64 @llvm.x86.avx512.cvttss2usi64(<4 x float>, i32)
declare i32 @llvm.x86.avx512.vcvtsd2usi32(<2 x double>, i32)
declare i64 @llvm.x86.avx512.vcvtsd2usi64(<2 x double>, i32)
declare i32 @llvm.x86.avx512.cvttsd2usi(<2 x double>, i32)
declare i64 @llvm.x86.avx512.cvttsd2usi64(<2 x double>, i32)

declare <4 x float> @llvm.x86.avx512.mask.rndscale.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32, i32)
declare <2 x double> @llvm.x86.avx512.mask.rndscale.sd(<2 x double>, <2 x double>, <2 x double>, i8, i32, i32)
declare <4 x float> @llvm.x86.avx512.mask.rndscale.ps.128(<4 x float>, i32, <4 x float>, i8)
declare <8 x float> @llvm.x86.avx512.mask.rndscale.ps.256(<8 x float>, i32, <8 x float>, i8)
declare <16 x float> @llvm.x86.avx512.mask.rndscale.ps.512(<16 x float>, i32, <16 x float>, i16, i32)
declare <2 x double> @llvm.x86.avx512.mask.rndscale.pd.128(<2 x double>, i32, <2 x double>, i8)
declare <4 x double> @llvm.x86.avx512.mask.rndscale.pd.256(<4 x double>, i32, <4 x double>, i8)
declare <8 x double> @llvm.x86.avx512.mask.rndscale.pd.512(<8 x double>, i32, <8 x double>, i8, i32)

define <4 x float> @test_rndscale_ss_floor(<4 x float> %src0, <4 x float> %src1, <4 x float> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_ss_floor(
; CHECK-NEXT:    [[TMP1:%.*]] = and i8 [[K:%.*]], 1
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i8 [[TMP1]], 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[SRC1:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call float @llvm.floor.f32(float [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[DST:%.*]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = select i1 [[TMP2]], float [[TMP5]], float [[TMP4]]
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x float> [[SRC0:%.*]], float [[TMP6]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP7]]
;
  %1 = call <4 x float> @llvm.x86.avx512.mask.rndscale.ss(<4 x float> %src0, <4 x float> %src1, <4 x float> %dst, i8 %k, i32 1, i32 4)
  ret <4 x float> %1
}

define <4 x float> @test_rndscale_ss_ceil(<4 x float> %src0, <4 x float> %src1, <4 x float> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_ss_ceil(
; CHECK-NEXT:    [[TMP1:%.*]] = and i8 [[K:%.*]], 1
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i8 [[TMP1]], 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[SRC1:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call float @llvm.ceil.f32(float [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[DST:%.*]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = select i1 [[TMP2]], float [[TMP5]], float [[TMP4]]
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x float> [[SRC0:%.*]], float [[TMP6]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP7]]
;
  %1 = call <4 x float> @llvm.x86.avx512.mask.rndscale.ss(<4 x float> %src0, <4 x float> %src1, <4 x float> %dst, i8 %k, i32 2, i32 4)
  ret <4 x float> %1
}

define <2 x double> @test_rndscale_sd_floor(<2 x double> %src0, <2 x double> %src1, <2 x double> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_sd_floor(
; CHECK-NEXT:    [[TMP1:%.*]] = and i8 [[K:%.*]], 1
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i8 [[TMP1]], 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[SRC1:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call double @llvm.floor.f64(double [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x double> [[DST:%.*]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = select i1 [[TMP2]], double [[TMP5]], double [[TMP4]]
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <2 x double> [[SRC0:%.*]], double [[TMP6]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP7]]
;
  %1 = call <2 x double> @llvm.x86.avx512.mask.rndscale.sd(<2 x double> %src0, <2 x double> %src1, <2 x double> %dst, i8 %k, i32 1, i32 4)
  ret <2 x double> %1
}

define <2 x double> @test_rndscale_sd_ceil(<2 x double> %src0, <2 x double> %src1, <2 x double> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_sd_ceil(
; CHECK-NEXT:    [[TMP1:%.*]] = and i8 [[K:%.*]], 1
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i8 [[TMP1]], 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[SRC1:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call double @llvm.ceil.f64(double [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x double> [[DST:%.*]], i64 0
; CHECK-NEXT:    [[TMP6:%.*]] = select i1 [[TMP2]], double [[TMP5]], double [[TMP4]]
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <2 x double> [[SRC0:%.*]], double [[TMP6]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP7]]
;
  %1 = call <2 x double> @llvm.x86.avx512.mask.rndscale.sd(<2 x double> %src0, <2 x double> %src1, <2 x double> %dst, i8 %k, i32 2, i32 4)
  ret <2 x double> %1
}

define <4 x float> @test_rndscale_ps_128_floor(<4 x float> %src, <4 x float> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_ps_128_floor(
; CHECK-NEXT:    [[TMP1:%.*]] = call <4 x float> @llvm.floor.v4f32(<4 x float> [[SRC:%.*]])
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[K:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[TMP4:%.*]] = select <4 x i1> [[TMP3]], <4 x float> [[TMP1]], <4 x float> [[DST:%.*]]
; CHECK-NEXT:    ret <4 x float> [[TMP4]]
;
  %1 = call <4 x float> @llvm.x86.avx512.mask.rndscale.ps.128(<4 x float> %src, i32 1, <4 x float> %dst, i8 %k)
  ret <4 x float> %1
}

define <4 x float> @test_rndscale_ps_128_ceil(<4 x float> %src, <4 x float> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_ps_128_ceil(
; CHECK-NEXT:    [[TMP1:%.*]] = call <4 x float> @llvm.ceil.v4f32(<4 x float> [[SRC:%.*]])
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[K:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[TMP4:%.*]] = select <4 x i1> [[TMP3]], <4 x float> [[TMP1]], <4 x float> [[DST:%.*]]
; CHECK-NEXT:    ret <4 x float> [[TMP4]]
;
  %1 = call <4 x float> @llvm.x86.avx512.mask.rndscale.ps.128(<4 x float> %src, i32 2, <4 x float> %dst, i8 %k)
  ret <4 x float> %1
}

define <8 x float> @test_rndscale_ps_256_floor(<8 x float> %src, <8 x float> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_ps_256_floor(
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x float> @llvm.floor.v8f32(<8 x float> [[SRC:%.*]])
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[K:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x float> [[TMP1]], <8 x float> [[DST:%.*]]
; CHECK-NEXT:    ret <8 x float> [[TMP3]]
;
  %1 = call <8 x float> @llvm.x86.avx512.mask.rndscale.ps.256(<8 x float> %src, i32 1, <8 x float> %dst, i8 %k)
  ret <8 x float> %1
}

define <8 x float> @test_rndscale_ps_256_ceil(<8 x float> %src, <8 x float> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_ps_256_ceil(
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x float> @llvm.ceil.v8f32(<8 x float> [[SRC:%.*]])
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[K:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x float> [[TMP1]], <8 x float> [[DST:%.*]]
; CHECK-NEXT:    ret <8 x float> [[TMP3]]
;
  %1 = call <8 x float> @llvm.x86.avx512.mask.rndscale.ps.256(<8 x float> %src, i32 2, <8 x float> %dst, i8 %k)
  ret <8 x float> %1
}

define <16 x float> @test_rndscale_ps_512_floor(<16 x float> %src, <16 x float> %dst, i16 %k) {
; CHECK-LABEL: @test_rndscale_ps_512_floor(
; CHECK-NEXT:    [[TMP1:%.*]] = call <16 x float> @llvm.floor.v16f32(<16 x float> [[SRC:%.*]])
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[K:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[DST:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.mask.rndscale.ps.512(<16 x float> %src, i32 1, <16 x float> %dst, i16 %k, i32 4)
  ret <16 x float> %1
}

define <16 x float> @test_rndscale_ps_512_ceil(<16 x float> %src, <16 x float> %dst, i16 %k) {
; CHECK-LABEL: @test_rndscale_ps_512_ceil(
; CHECK-NEXT:    [[TMP1:%.*]] = call <16 x float> @llvm.ceil.v16f32(<16 x float> [[SRC:%.*]])
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[K:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[DST:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.mask.rndscale.ps.512(<16 x float> %src, i32 2, <16 x float> %dst, i16 %k, i32 4)
  ret <16 x float> %1
}

define <2 x double> @test_rndscale_pd_128_floor(<2 x double> %src, <2 x double> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_pd_128_floor(
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x double> @llvm.floor.v2f64(<2 x double> [[SRC:%.*]])
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[K:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> undef, <2 x i32> <i32 0, i32 1>
; CHECK-NEXT:    [[TMP4:%.*]] = select <2 x i1> [[TMP3]], <2 x double> [[TMP1]], <2 x double> [[DST:%.*]]
; CHECK-NEXT:    ret <2 x double> [[TMP4]]
;
  %1 = call <2 x double> @llvm.x86.avx512.mask.rndscale.pd.128(<2 x double> %src, i32 1, <2 x double> %dst, i8 %k)
  ret <2 x double> %1
}

define <2 x double> @test_rndscale_pd_128_ceil(<2 x double> %src, <2 x double> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_pd_128_ceil(
; CHECK-NEXT:    [[TMP1:%.*]] = call <2 x double> @llvm.ceil.v2f64(<2 x double> [[SRC:%.*]])
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[K:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> undef, <2 x i32> <i32 0, i32 1>
; CHECK-NEXT:    [[TMP4:%.*]] = select <2 x i1> [[TMP3]], <2 x double> [[TMP1]], <2 x double> [[DST:%.*]]
; CHECK-NEXT:    ret <2 x double> [[TMP4]]
;
  %1 = call <2 x double> @llvm.x86.avx512.mask.rndscale.pd.128(<2 x double> %src, i32 2, <2 x double> %dst, i8 %k)
  ret <2 x double> %1
}

define <4 x double> @test_rndscale_pd_256_floor(<4 x double> %src, <4 x double> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_pd_256_floor(
; CHECK-NEXT:    [[TMP1:%.*]] = call <4 x double> @llvm.floor.v4f64(<4 x double> [[SRC:%.*]])
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[K:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[TMP4:%.*]] = select <4 x i1> [[TMP3]], <4 x double> [[TMP1]], <4 x double> [[DST:%.*]]
; CHECK-NEXT:    ret <4 x double> [[TMP4]]
;
  %1 = call <4 x double> @llvm.x86.avx512.mask.rndscale.pd.256(<4 x double> %src, i32 1, <4 x double> %dst, i8 %k)
  ret <4 x double> %1
}

define <4 x double> @test_rndscale_pd_256_ceil(<4 x double> %src, <4 x double> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_pd_256_ceil(
; CHECK-NEXT:    [[TMP1:%.*]] = call <4 x double> @llvm.ceil.v4f64(<4 x double> [[SRC:%.*]])
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[K:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[TMP4:%.*]] = select <4 x i1> [[TMP3]], <4 x double> [[TMP1]], <4 x double> [[DST:%.*]]
; CHECK-NEXT:    ret <4 x double> [[TMP4]]
;
  %1 = call <4 x double> @llvm.x86.avx512.mask.rndscale.pd.256(<4 x double> %src, i32 2, <4 x double> %dst, i8 %k)
  ret <4 x double> %1
}

define <8 x double> @test_rndscale_pd_512_floor(<8 x double> %src, <8 x double> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_pd_512_floor(
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x double> @llvm.floor.v8f64(<8 x double> [[SRC:%.*]])
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[K:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[DST:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.mask.rndscale.pd.512(<8 x double> %src, i32 1, <8 x double> %dst, i8 %k, i32 4)
  ret <8 x double> %1
}

define <8 x double> @test_rndscale_pd_512_ceil(<8 x double> %src, <8 x double> %dst, i8 %k) {
; CHECK-LABEL: @test_rndscale_pd_512_ceil(
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x double> @llvm.ceil.v8f64(<8 x double> [[SRC:%.*]])
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[K:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[DST:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.mask.rndscale.pd.512(<8 x double> %src, i32 2, <8 x double> %dst, i8 %k, i32 4)
  ret <8 x double> %1
}

declare float @llvm.fma.f32(float, float, float) #1

define <4 x float> @test_mask_vfmadd_ss(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mask_vfmadd_ss(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i32 0
; CHECK-NEXT:    [[TMP4:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], float [[TMP4]], float [[TMP1]]
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x float> [[A]], float [[TMP7]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP8]]
;
  %1 = insertelement <4 x float> %b, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = insertelement <4 x float> %c, float 4.000000e+00, i32 1
  %5 = insertelement <4 x float> %4, float 5.000000e+00, i32 2
  %6 = insertelement <4 x float> %5, float 6.000000e+00, i32 3
  %7 = extractelement <4 x float> %a, i64 0
  %8 = extractelement <4 x float> %3, i64 0
  %9 = extractelement <4 x float> %6, i64 0
  %10 = call float @llvm.fma.f32(float %7, float %8, float %9)
  %11 = bitcast i8 %mask to <8 x i1>
  %12 = extractelement <8 x i1> %11, i64 0
  %13 = select i1 %12, float %10, float %7
  %14 = insertelement <4 x float> %a, float %13, i64 0
  ret <4 x float> %14
}

define float @test_mask_vfmadd_ss_0(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mask_vfmadd_ss_0(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], float [[TMP4]], float [[TMP1]]
; CHECK-NEXT:    ret float [[TMP7]]
;
  %1 = insertelement <4 x float> %a, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = extractelement <4 x float> %3, i64 0
  %5 = extractelement <4 x float> %b, i64 0
  %6 = extractelement <4 x float> %c, i64 0
  %7 = call float @llvm.fma.f32(float %4, float %5, float %6)
  %8 = bitcast i8 %mask to <8 x i1>
  %9 = extractelement <8 x i1> %8, i64 0
  %10 = select i1 %9, float %7, float %4
  %11 = insertelement <4 x float> %3, float %10, i64 0
  %12 = extractelement <4 x float> %11, i32 0
  ret float %12
}

define float @test_mask_vfmadd_ss_1(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mask_vfmadd_ss_1(
; CHECK-NEXT:    ret float 1.000000e+00
;
  %1 = insertelement <4 x float> %a, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = extractelement <4 x float> %3, i64 0
  %5 = extractelement <4 x float> %b, i64 0
  %6 = extractelement <4 x float> %c, i64 0
  %7 = call float @llvm.fma.f32(float %4, float %5, float %6)
  %8 = bitcast i8 %mask to <8 x i1>
  %9 = extractelement <8 x i1> %8, i64 0
  %10 = select i1 %9, float %7, float %4
  %11 = insertelement <4 x float> %3, float %10, i64 0
  %12 = extractelement <4 x float> %11, i32 1
  ret float %12
}

declare double @llvm.fma.f64(double, double, double) #1

define <2 x double> @test_mask_vfmadd_sd(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mask_vfmadd_sd(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], double [[TMP4]], double [[TMP1]]
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x double> [[A]], double [[TMP7]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP8]]
;
  %1 = insertelement <2 x double> %b, double 1.000000e+00, i32 1
  %2 = insertelement <2 x double> %c, double 2.000000e+00, i32 1
  %3 = extractelement <2 x double> %a, i64 0
  %4 = extractelement <2 x double> %1, i64 0
  %5 = extractelement <2 x double> %2, i64 0
  %6 = call double @llvm.fma.f64(double %3, double %4, double %5)
  %7 = bitcast i8 %mask to <8 x i1>
  %8 = extractelement <8 x i1> %7, i64 0
  %9 = select i1 %8, double %6, double %3
  %10 = insertelement <2 x double> %a, double %9, i64 0
  ret <2 x double> %10
}

define double @test_mask_vfmadd_sd_0(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mask_vfmadd_sd_0(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], double [[TMP4]], double [[TMP1]]
; CHECK-NEXT:    ret double [[TMP7]]
;
  %1 = insertelement <2 x double> %a, double 1.000000e+00, i32 1
  %2 = extractelement <2 x double> %1, i64 0
  %3 = extractelement <2 x double> %b, i64 0
  %4 = extractelement <2 x double> %c, i64 0
  %5 = call double @llvm.fma.f64(double %2, double %3, double %4)
  %6 = bitcast i8 %mask to <8 x i1>
  %7 = extractelement <8 x i1> %6, i64 0
  %8 = select i1 %7, double %5, double %2
  %9 = insertelement <2 x double> %1, double %8, i64 0
  %10 = extractelement <2 x double> %9, i32 0
  ret double %10
}

define double @test_mask_vfmadd_sd_1(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mask_vfmadd_sd_1(
; CHECK-NEXT:    ret double 1.000000e+00
;
  %1 = insertelement <2 x double> %a, double 1.000000e+00, i32 1
  %2 = extractelement <2 x double> %1, i64 0
  %3 = extractelement <2 x double> %b, i64 0
  %4 = extractelement <2 x double> %c, i64 0
  %5 = call double @llvm.fma.f64(double %2, double %3, double %4)
  %6 = bitcast i8 %mask to <8 x i1>
  %7 = extractelement <8 x i1> %6, i64 0
  %8 = select i1 %7, double %5, double %2
  %9 = insertelement <2 x double> %1, double %8, i64 0
  %10 = extractelement <2 x double> %9, i32 1
  ret double %10
}

define <4 x float> @test_maskz_vfmadd_ss(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_maskz_vfmadd_ss(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i32 0
; CHECK-NEXT:    [[TMP4:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], float [[TMP4]], float 0.000000e+00
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x float> [[A]], float [[TMP7]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP8]]
;
  %1 = insertelement <4 x float> %b, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = insertelement <4 x float> %c, float 4.000000e+00, i32 1
  %5 = insertelement <4 x float> %4, float 5.000000e+00, i32 2
  %6 = insertelement <4 x float> %5, float 6.000000e+00, i32 3
  %7 = extractelement <4 x float> %a, i64 0
  %8 = extractelement <4 x float> %3, i64 0
  %9 = extractelement <4 x float> %6, i64 0
  %10 = call float @llvm.fma.f32(float %7, float %8, float %9)
  %11 = bitcast i8 %mask to <8 x i1>
  %12 = extractelement <8 x i1> %11, i64 0
  %13 = select i1 %12, float %10, float 0.000000e+00
  %14 = insertelement <4 x float> %a, float %13, i64 0
  ret <4 x float> %14
}

define float @test_maskz_vfmadd_ss_0(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_maskz_vfmadd_ss_0(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], float [[TMP4]], float 0.000000e+00
; CHECK-NEXT:    ret float [[TMP7]]
;
  %1 = insertelement <4 x float> %a, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = extractelement <4 x float> %3, i64 0
  %5 = extractelement <4 x float> %b, i64 0
  %6 = extractelement <4 x float> %c, i64 0
  %7 = call float @llvm.fma.f32(float %4, float %5, float %6)
  %8 = bitcast i8 %mask to <8 x i1>
  %9 = extractelement <8 x i1> %8, i64 0
  %10 = select i1 %9, float %7, float 0.000000e+00
  %11 = insertelement <4 x float> %3, float %10, i64 0
  %12 = extractelement <4 x float> %11, i32 0
  ret float %12
}

define float @test_maskz_vfmadd_ss_1(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_maskz_vfmadd_ss_1(
; CHECK-NEXT:    ret float 1.000000e+00
;
  %1 = insertelement <4 x float> %a, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = extractelement <4 x float> %3, i64 0
  %5 = extractelement <4 x float> %b, i64 0
  %6 = extractelement <4 x float> %c, i64 0
  %7 = call float @llvm.fma.f32(float %4, float %5, float %6)
  %8 = bitcast i8 %mask to <8 x i1>
  %9 = extractelement <8 x i1> %8, i64 0
  %10 = select i1 %9, float %7, float 0.000000e+00
  %11 = insertelement <4 x float> %3, float %10, i64 0
  %12 = extractelement <4 x float> %11, i32 1
  ret float %12
}

define <2 x double> @test_maskz_vfmadd_sd(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_maskz_vfmadd_sd(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], double [[TMP4]], double 0.000000e+00
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x double> [[A]], double [[TMP7]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP8]]
;
  %1 = insertelement <2 x double> %b, double 1.000000e+00, i32 1
  %2 = insertelement <2 x double> %c, double 2.000000e+00, i32 1
  %3 = extractelement <2 x double> %a, i64 0
  %4 = extractelement <2 x double> %1, i64 0
  %5 = extractelement <2 x double> %2, i64 0
  %6 = call double @llvm.fma.f64(double %3, double %4, double %5)
  %7 = bitcast i8 %mask to <8 x i1>
  %8 = extractelement <8 x i1> %7, i64 0
  %9 = select i1 %8, double %6, double 0.000000e+00
  %10 = insertelement <2 x double> %a, double %9, i64 0
  ret <2 x double> %10
}

define double @test_maskz_vfmadd_sd_0(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_maskz_vfmadd_sd_0(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], double [[TMP4]], double 0.000000e+00
; CHECK-NEXT:    ret double [[TMP7]]
;
  %1 = insertelement <2 x double> %a, double 1.000000e+00, i32 1
  %2 = extractelement <2 x double> %1, i64 0
  %3 = extractelement <2 x double> %b, i64 0
  %4 = extractelement <2 x double> %c, i64 0
  %5 = call double @llvm.fma.f64(double %2, double %3, double %4)
  %6 = bitcast i8 %mask to <8 x i1>
  %7 = extractelement <8 x i1> %6, i64 0
  %8 = select i1 %7, double %5, double 0.000000e+00
  %9 = insertelement <2 x double> %1, double %8, i64 0
  %10 = extractelement <2 x double> %9, i32 0
  ret double %10
}

define double @test_maskz_vfmadd_sd_1(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_maskz_vfmadd_sd_1(
; CHECK-NEXT:    ret double 1.000000e+00
;
  %1 = insertelement <2 x double> %a, double 1.000000e+00, i32 1
  %2 = extractelement <2 x double> %1, i64 0
  %3 = extractelement <2 x double> %b, i64 0
  %4 = extractelement <2 x double> %c, i64 0
  %5 = call double @llvm.fma.f64(double %2, double %3, double %4)
  %6 = bitcast i8 %mask to <8 x i1>
  %7 = extractelement <8 x i1> %6, i64 0
  %8 = select i1 %7, double %5, double 0.000000e+00
  %9 = insertelement <2 x double> %1, double %8, i64 0
  %10 = extractelement <2 x double> %9, i32 1
  ret double %10
}

define <4 x float> @test_mask3_vfmadd_ss(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfmadd_ss(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], float [[TMP4]], float [[TMP3]]
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <4 x float> [[C]], float [[TMP7]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP8]]
;
  %1 = insertelement <4 x float> %a, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = insertelement <4 x float> %b, float 4.000000e+00, i32 1
  %5 = insertelement <4 x float> %4, float 5.000000e+00, i32 2
  %6 = insertelement <4 x float> %5, float 6.000000e+00, i32 3
  %7 = extractelement <4 x float> %3, i64 0
  %8 = extractelement <4 x float> %6, i64 0
  %9 = extractelement <4 x float> %c, i64 0
  %10 = call float @llvm.fma.f32(float %7, float %8, float %9)
  %11 = bitcast i8 %mask to <8 x i1>
  %12 = extractelement <8 x i1> %11, i64 0
  %13 = select i1 %12, float %10, float %9
  %14 = insertelement <4 x float> %c, float %13, i64 0
  ret <4 x float> %14
}

define float @test_mask3_vfmadd_ss_0(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfmadd_ss_0(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i32 0
; CHECK-NEXT:    [[TMP4:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], float [[TMP4]], float [[TMP3]]
; CHECK-NEXT:    ret float [[TMP7]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = extractelement <4 x float> %a, i64 0
  %5 = extractelement <4 x float> %b, i64 0
  %6 = extractelement <4 x float> %3, i64 0
  %7 = call float @llvm.fma.f32(float %4, float %5, float %6)
  %8 = bitcast i8 %mask to <8 x i1>
  %9 = extractelement <8 x i1> %8, i64 0
  %10 = select i1 %9, float %7, float %6
  %11 = insertelement <4 x float> %3, float %10, i64 0
  %12 = extractelement <4 x float> %11, i32 0
  ret float %12
}

define float @test_mask3_vfmadd_ss_1(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfmadd_ss_1(
; CHECK-NEXT:    ret float 1.000000e+00
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = extractelement <4 x float> %a, i64 0
  %5 = extractelement <4 x float> %b, i64 0
  %6 = extractelement <4 x float> %3, i64 0
  %7 = call float @llvm.fma.f32(float %4, float %5, float %6)
  %8 = bitcast i8 %mask to <8 x i1>
  %9 = extractelement <8 x i1> %8, i64 0
  %10 = select i1 %9, float %7, float %6
  %11 = insertelement <4 x float> %3, float %10, i64 0
  %12 = extractelement <4 x float> %11, i32 1
  ret float %12
}

define <2 x double> @test_mask3_vfmadd_sd(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfmadd_sd(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], double [[TMP4]], double [[TMP3]]
; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x double> [[C]], double [[TMP7]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP8]]
;
  %1 = insertelement <2 x double> %a, double 1.000000e+00, i32 1
  %2 = insertelement <2 x double> %b, double 2.000000e+00, i32 1
  %3 = extractelement <2 x double> %1, i64 0
  %4 = extractelement <2 x double> %2, i64 0
  %5 = extractelement <2 x double> %c, i64 0
  %6 = call double @llvm.fma.f64(double %3, double %4, double %5)
  %7 = bitcast i8 %mask to <8 x i1>
  %8 = extractelement <8 x i1> %7, i64 0
  %9 = select i1 %8, double %6, double %5
  %10 = insertelement <2 x double> %c, double %9, i64 0
  ret <2 x double> %10
}

define double @test_mask3_vfmadd_sd_0(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfmadd_sd_0(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP3]])
; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i1> [[TMP5]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[TMP6]], double [[TMP4]], double [[TMP3]]
; CHECK-NEXT:    ret double [[TMP7]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = extractelement <2 x double> %a, i64 0
  %3 = extractelement <2 x double> %b, i64 0
  %4 = extractelement <2 x double> %1, i64 0
  %5 = call double @llvm.fma.f64(double %2, double %3, double %4)
  %6 = bitcast i8 %mask to <8 x i1>
  %7 = extractelement <8 x i1> %6, i64 0
  %8 = select i1 %7, double %5, double %4
  %9 = insertelement <2 x double> %1, double %8, i64 0
  %10 = extractelement <2 x double> %9, i32 0
  ret double %10
}

define double @test_mask3_vfmadd_sd_1(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfmadd_sd_1(
; CHECK-NEXT:    ret double 1.000000e+00
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = extractelement <2 x double> %a, i64 0
  %3 = extractelement <2 x double> %b, i64 0
  %4 = extractelement <2 x double> %1, i64 0
  %5 = call double @llvm.fma.f64(double %2, double %3, double %4)
  %6 = bitcast i8 %mask to <8 x i1>
  %7 = extractelement <8 x i1> %6, i64 0
  %8 = select i1 %7, double %5, double %4
  %9 = insertelement <2 x double> %1, double %8, i64 0
  %10 = extractelement <2 x double> %9, i32 1
  ret double %10
}

define <4 x float> @test_mask3_vfmsub_ss(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfmsub_ss(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = fsub float -0.000000e+00, [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP4]])
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <8 x i1> [[TMP7]], i64 0
; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[TMP8]], float [[TMP5]], float [[TMP6]]
; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <4 x float> [[C]], float [[TMP9]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP10]]
;
  %1 = insertelement <4 x float> %a, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = insertelement <4 x float> %b, float 4.000000e+00, i32 1
  %5 = insertelement <4 x float> %4, float 5.000000e+00, i32 2
  %6 = insertelement <4 x float> %5, float 6.000000e+00, i32 3
  %7 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
  %8 = extractelement <4 x float> %3, i64 0
  %9 = extractelement <4 x float> %6, i64 0
  %10 = extractelement <4 x float> %7, i64 0
  %11 = call float @llvm.fma.f32(float %8, float %9, float %10)
  %12 = extractelement <4 x float> %c, i64 0
  %13 = bitcast i8 %mask to <8 x i1>
  %14 = extractelement <8 x i1> %13, i64 0
  %15 = select i1 %14, float %11, float %12
  %16 = insertelement <4 x float> %c, float %15, i64 0
  ret <4 x float> %16
}

define float @test_mask3_vfmsub_ss_0(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfmsub_ss_0(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[C:%.*]], i32 0
; CHECK-NEXT:    [[TMP4:%.*]] = fsub float -0.000000e+00, [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = call float @llvm.fma.f32(float [[TMP1]], float [[TMP2]], float [[TMP4]])
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[C]], i32 0
; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <8 x i1> [[TMP7]], i64 0
; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[TMP8]], float [[TMP5]], float [[TMP6]]
; CHECK-NEXT:    ret float [[TMP9]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %3
  %5 = extractelement <4 x float> %a, i64 0
  %6 = extractelement <4 x float> %b, i64 0
  %7 = extractelement <4 x float> %4, i64 0
  %8 = call float @llvm.fma.f32(float %5, float %6, float %7)
  %9 = extractelement <4 x float> %3, i64 0
  %10 = bitcast i8 %mask to <8 x i1>
  %11 = extractelement <8 x i1> %10, i64 0
  %12 = select i1 %11, float %8, float %9
  %13 = insertelement <4 x float> %3, float %12, i64 0
  %14 = extractelement <4 x float> %13, i32 0
  ret float %14
}

define float @test_mask3_vfmsub_ss_1(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfmsub_ss_1(
; CHECK-NEXT:    ret float 1.000000e+00
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %3
  %5 = extractelement <4 x float> %a, i64 0
  %6 = extractelement <4 x float> %b, i64 0
  %7 = extractelement <4 x float> %4, i64 0
  %8 = call float @llvm.fma.f32(float %5, float %6, float %7)
  %9 = extractelement <4 x float> %3, i64 0
  %10 = bitcast i8 %mask to <8 x i1>
  %11 = extractelement <8 x i1> %10, i64 0
  %12 = select i1 %11, float %8, float %9
  %13 = insertelement <4 x float> %3, float %12, i64 0
  %14 = extractelement <4 x float> %13, i32 1
  ret float %14
}

define <2 x double> @test_mask3_vfmsub_sd(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfmsub_sd(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = fsub double -0.000000e+00, [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP4]])
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[C]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <8 x i1> [[TMP7]], i64 0
; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[TMP8]], double [[TMP5]], double [[TMP6]]
; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <2 x double> [[C]], double [[TMP9]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP10]]
;
  %1 = insertelement <2 x double> %a, double 1.000000e+00, i32 1
  %2 = insertelement <2 x double> %b, double 2.000000e+00, i32 1
  %3 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %c
  %4 = extractelement <2 x double> %1, i64 0
  %5 = extractelement <2 x double> %2, i64 0
  %6 = extractelement <2 x double> %3, i64 0
  %7 = call double @llvm.fma.f64(double %4, double %5, double %6)
  %8 = extractelement <2 x double> %c, i64 0
  %9 = bitcast i8 %mask to <8 x i1>
  %10 = extractelement <8 x i1> %9, i64 0
  %11 = select i1 %10, double %7, double %8
  %12 = insertelement <2 x double> %c, double %11, i64 0
  ret <2 x double> %12
}

define double @test_mask3_vfmsub_sd_0(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfmsub_sd_0(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = fsub double -0.000000e+00, [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = call double @llvm.fma.f64(double [[TMP1]], double [[TMP2]], double [[TMP4]])
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[C]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <8 x i1> [[TMP7]], i64 0
; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[TMP8]], double [[TMP5]], double [[TMP6]]
; CHECK-NEXT:    ret double [[TMP9]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %1
  %3 = extractelement <2 x double> %a, i64 0
  %4 = extractelement <2 x double> %b, i64 0
  %5 = extractelement <2 x double> %2, i64 0
  %6 = call double @llvm.fma.f64(double %3, double %4, double %5)
  %7 = extractelement <2 x double> %1, i64 0
  %8 = bitcast i8 %mask to <8 x i1>
  %9 = extractelement <8 x i1> %8, i64 0
  %10 = select i1 %9, double %6, double %7
  %11 = insertelement <2 x double> %1, double %10, i64 0
  %12 = extractelement <2 x double> %11, i32 0
  ret double %12
}

define double @test_mask3_vfmsub_sd_1(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfmsub_sd_1(
; CHECK-NEXT:    ret double 1.000000e+00
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %1
  %3 = extractelement <2 x double> %a, i64 0
  %4 = extractelement <2 x double> %b, i64 0
  %5 = extractelement <2 x double> %2, i64 0
  %6 = call double @llvm.fma.f64(double %3, double %4, double %5)
  %7 = extractelement <2 x double> %1, i64 0
  %8 = bitcast i8 %mask to <8 x i1>
  %9 = extractelement <8 x i1> %8, i64 0
  %10 = select i1 %9, double %6, double %7
  %11 = insertelement <2 x double> %1, double %10, i64 0
  %12 = extractelement <2 x double> %11, i32 1
  ret double %12
}

define <4 x float> @test_mask3_vfnmsub_ss(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfnmsub_ss(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = fsub float -0.000000e+00, [[TMP1]]
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP5:%.*]] = fsub float -0.000000e+00, [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = call float @llvm.fma.f32(float [[TMP2]], float [[TMP3]], float [[TMP5]])
; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <4 x float> [[C]], i64 0
; CHECK-NEXT:    [[TMP8:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <8 x i1> [[TMP8]], i64 0
; CHECK-NEXT:    [[TMP10:%.*]] = select i1 [[TMP9]], float [[TMP6]], float [[TMP7]]
; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <4 x float> [[C]], float [[TMP10]], i64 0
; CHECK-NEXT:    ret <4 x float> [[TMP11]]
;
  %1 = insertelement <4 x float> %a, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = insertelement <4 x float> %b, float 4.000000e+00, i32 1
  %5 = insertelement <4 x float> %4, float 5.000000e+00, i32 2
  %6 = insertelement <4 x float> %5, float 6.000000e+00, i32 3
  %7 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %3
  %8 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
  %9 = extractelement <4 x float> %7, i64 0
  %10 = extractelement <4 x float> %6, i64 0
  %11 = extractelement <4 x float> %8, i64 0
  %12 = call float @llvm.fma.f32(float %9, float %10, float %11)
  %13 = extractelement <4 x float> %c, i64 0
  %14 = bitcast i8 %mask to <8 x i1>
  %15 = extractelement <8 x i1> %14, i64 0
  %16 = select i1 %15, float %12, float %13
  %17 = insertelement <4 x float> %c, float %16, i64 0
  ret <4 x float> %17
}

define float @test_mask3_vfnmsub_ss_0(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfnmsub_ss_0(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x float> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = fsub float -0.000000e+00, [[TMP1]]
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[C:%.*]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = fsub float -0.000000e+00, [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = call float @llvm.fma.f32(float [[TMP2]], float [[TMP3]], float [[TMP5]])
; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <4 x float> [[C]], i32 0
; CHECK-NEXT:    [[TMP8:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <8 x i1> [[TMP8]], i64 0
; CHECK-NEXT:    [[TMP10:%.*]] = select i1 [[TMP9]], float [[TMP6]], float [[TMP7]]
; CHECK-NEXT:    ret float [[TMP10]]
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %a
  %5 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %3
  %6 = extractelement <4 x float> %4, i64 0
  %7 = extractelement <4 x float> %b, i64 0
  %8 = extractelement <4 x float> %5, i64 0
  %9 = call float @llvm.fma.f32(float %6, float %7, float %8)
  %10 = extractelement <4 x float> %3, i64 0
  %11 = bitcast i8 %mask to <8 x i1>
  %12 = extractelement <8 x i1> %11, i64 0
  %13 = select i1 %12, float %9, float %10
  %14 = insertelement <4 x float> %3, float %13, i64 0
  %15 = extractelement <4 x float> %14, i32 0
  ret float %15
}

define float @test_mask3_vfnmsub_ss_1(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfnmsub_ss_1(
; CHECK-NEXT:    ret float 1.000000e+00
;
  %1 = insertelement <4 x float> %c, float 1.000000e+00, i32 1
  %2 = insertelement <4 x float> %1, float 2.000000e+00, i32 2
  %3 = insertelement <4 x float> %2, float 3.000000e+00, i32 3
  %4 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %a
  %5 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %3
  %6 = extractelement <4 x float> %4, i64 0
  %7 = extractelement <4 x float> %b, i64 0
  %8 = extractelement <4 x float> %5, i64 0
  %9 = call float @llvm.fma.f32(float %6, float %7, float %8)
  %10 = extractelement <4 x float> %3, i64 0
  %11 = bitcast i8 %mask to <8 x i1>
  %12 = extractelement <8 x i1> %11, i64 0
  %13 = select i1 %12, float %9, float %10
  %14 = insertelement <4 x float> %3, float %13, i64 0
  %15 = extractelement <4 x float> %14, i32 1
  ret float %15
}

define <2 x double> @test_mask3_vfnmsub_sd(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfnmsub_sd(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = fsub double -0.000000e+00, [[TMP1]]
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP5:%.*]] = fsub double -0.000000e+00, [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = call double @llvm.fma.f64(double [[TMP2]], double [[TMP3]], double [[TMP5]])
; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <2 x double> [[C]], i64 0
; CHECK-NEXT:    [[TMP8:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <8 x i1> [[TMP8]], i64 0
; CHECK-NEXT:    [[TMP10:%.*]] = select i1 [[TMP9]], double [[TMP6]], double [[TMP7]]
; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <2 x double> [[C]], double [[TMP10]], i64 0
; CHECK-NEXT:    ret <2 x double> [[TMP11]]
;
  %1 = insertelement <2 x double> %a, double 1.000000e+00, i32 1
  %2 = insertelement <2 x double> %b, double 2.000000e+00, i32 1
  %3 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %1
  %4 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %c
  %5 = extractelement <2 x double> %3, i64 0
  %6 = extractelement <2 x double> %2, i64 0
  %7 = extractelement <2 x double> %4, i64 0
  %8 = call double @llvm.fma.f64(double %5, double %6, double %7)
  %9 = extractelement <2 x double> %c, i64 0
  %10 = bitcast i8 %mask to <8 x i1>
  %11 = extractelement <8 x i1> %10, i64 0
  %12 = select i1 %11, double %8, double %9
  %13 = insertelement <2 x double> %c, double %12, i64 0
  ret <2 x double> %13
}

define double @test_mask3_vfnmsub_sd_0(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfnmsub_sd_0(
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x double> [[A:%.*]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = fsub double -0.000000e+00, [[TMP1]]
; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x double> [[B:%.*]], i64 0
; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x double> [[C:%.*]], i64 0
; CHECK-NEXT:    [[TMP5:%.*]] = fsub double -0.000000e+00, [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = call double @llvm.fma.f64(double [[TMP2]], double [[TMP3]], double [[TMP5]])
; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <2 x double> [[C]], i64 0
; CHECK-NEXT:    [[TMP8:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <8 x i1> [[TMP8]], i64 0
; CHECK-NEXT:    [[TMP10:%.*]] = select i1 [[TMP9]], double [[TMP6]], double [[TMP7]]
; CHECK-NEXT:    ret double [[TMP10]]
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %a
  %3 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %1
  %4 = extractelement <2 x double> %2, i64 0
  %5 = extractelement <2 x double> %b, i64 0
  %6 = extractelement <2 x double> %3, i64 0
  %7 = call double @llvm.fma.f64(double %4, double %5, double %6)
  %8 = extractelement <2 x double> %1, i64 0
  %9 = bitcast i8 %mask to <8 x i1>
  %10 = extractelement <8 x i1> %9, i64 0
  %11 = select i1 %10, double %7, double %8
  %12 = insertelement <2 x double> %1, double %11, i64 0
  %13 = extractelement <2 x double> %12, i32 0
  ret double %13
}

define double @test_mask3_vfnmsub_sd_1(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mask3_vfnmsub_sd_1(
; CHECK-NEXT:    ret double 1.000000e+00
;
  %1 = insertelement <2 x double> %c, double 1.000000e+00, i32 1
  %2 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %a
  %3 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %1
  %4 = extractelement <2 x double> %2, i64 0
  %5 = extractelement <2 x double> %b, i64 0
  %6 = extractelement <2 x double> %3, i64 0
  %7 = call double @llvm.fma.f64(double %4, double %5, double %6)
  %8 = extractelement <2 x double> %1, i64 0
  %9 = bitcast i8 %mask to <8 x i1>
  %10 = extractelement <8 x i1> %9, i64 0
  %11 = select i1 %10, double %7, double %8
  %12 = insertelement <2 x double> %1, double %11, i64 0
  %13 = extractelement <2 x double> %12, i32 1
  ret double %13
}

declare <8 x i32> @llvm.x86.avx2.permd(<8 x i32>, <8 x i32>)

define <8 x i32> @identity_test_permvar_si_256(<8 x i32> %a0) {
; CHECK-LABEL: @identity_test_permvar_si_256(
; CHECK-NEXT:    ret <8 x i32> [[A0:%.*]]
;
  %1 = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>)
  ret <8 x i32> %1
}

define <8 x i32> @identity_test_permvar_si_256_mask(<8 x i32> %a0, <8 x i32> %passthru, i8 %mask) {
; CHECK-LABEL: @identity_test_permvar_si_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP2:%.*]] = select <8 x i1> [[TMP1]], <8 x i32> [[A0:%.*]], <8 x i32> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x i32> [[TMP2]]
;
  %1 = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i32> %1, <8 x i32> %passthru
  ret <8 x i32> %3
}

define <8 x i32> @zero_test_permvar_si_256(<8 x i32> %a0) {
; CHECK-LABEL: @zero_test_permvar_si_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[A0:%.*]], <8 x i32> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:    ret <8 x i32> [[TMP1]]
;
  %1 = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> zeroinitializer)
  ret <8 x i32> %1
}

define <8 x i32> @zero_test_permvar_si_256_mask(<8 x i32> %a0, <8 x i32> %passthru, i8 %mask) {
; CHECK-LABEL: @zero_test_permvar_si_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[A0:%.*]], <8 x i32> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x i32> [[TMP1]], <8 x i32> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x i32> [[TMP3]]
;
  %1 = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> zeroinitializer)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i32> %1, <8 x i32> %passthru
  ret <8 x i32> %3
}

define <8 x i32> @shuffle_test_permvar_si_256(<8 x i32> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_si_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[A0:%.*]], <8 x i32> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <8 x i32> [[TMP1]]
;
  %1 = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  ret <8 x i32> %1
}

define <8 x i32> @shuffle_test_permvar_si_256_mask(<8 x i32> %a0, <8 x i32> %passthru, i8 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_si_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[A0:%.*]], <8 x i32> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x i32> [[TMP1]], <8 x i32> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x i32> [[TMP3]]
;
  %1 = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i32> %1, <8 x i32> %passthru
  ret <8 x i32> %3
}

define <8 x i32> @undef_test_permvar_si_256(<8 x i32> %a0) {
; CHECK-LABEL: @undef_test_permvar_si_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[A0:%.*]], <8 x i32> undef, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <8 x i32> [[TMP1]]
;
  %1 = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  ret <8 x i32> %1
}

define <8 x i32> @undef_test_permvar_si_256_mask(<8 x i32> %a0, <8 x i32> %passthru, i8 %mask) {
; CHECK-LABEL: @undef_test_permvar_si_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[A0:%.*]], <8 x i32> undef, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x i32> [[TMP1]], <8 x i32> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x i32> [[TMP3]]
;
  %1 = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i32> %1, <8 x i32> %passthru
  ret <8 x i32> %3
}

declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x i32>)

define <8 x float> @identity_test_permvar_sf_256(<8 x float> %a0) {
; CHECK-LABEL: @identity_test_permvar_sf_256(
; CHECK-NEXT:    ret <8 x float> [[A0:%.*]]
;
  %1 = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>)
  ret <8 x float> %1
}

define <8 x float> @identity_test_permvar_sf_256_mask(<8 x float> %a0, <8 x float> %passthru, i8 %mask) {
; CHECK-LABEL: @identity_test_permvar_sf_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP2:%.*]] = select <8 x i1> [[TMP1]], <8 x float> [[A0:%.*]], <8 x float> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x float> [[TMP2]]
;
  %1 = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x float> %1, <8 x float> %passthru
  ret <8 x float> %3
}

define <8 x float> @zero_test_permvar_sf_256(<8 x float> %a0) {
; CHECK-LABEL: @zero_test_permvar_sf_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x float> [[A0:%.*]], <8 x float> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:    ret <8 x float> [[TMP1]]
;
  %1 = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> zeroinitializer)
  ret <8 x float> %1
}

define <8 x float> @zero_test_permvar_sf_256_mask(<8 x float> %a0, <8 x float> %passthru, i8 %mask) {
; CHECK-LABEL: @zero_test_permvar_sf_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x float> [[A0:%.*]], <8 x float> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x float> [[TMP1]], <8 x float> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x float> [[TMP3]]
;
  %1 = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> zeroinitializer)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x float> %1, <8 x float> %passthru
  ret <8 x float> %3
}

define <8 x float> @shuffle_test_permvar_sf_256(<8 x float> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_sf_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x float> [[A0:%.*]], <8 x float> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <8 x float> [[TMP1]]
;
  %1 = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  ret <8 x float> %1
}

define <8 x float> @shuffle_test_permvar_sf_256_mask(<8 x float> %a0, <8 x float> %passthru, i8 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_sf_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x float> [[A0:%.*]], <8 x float> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x float> [[TMP1]], <8 x float> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x float> [[TMP3]]
;
  %1 = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x float> %1, <8 x float> %passthru
  ret <8 x float> %3
}

define <8 x float> @undef_test_permvar_sf_256(<8 x float> %a0) {
; CHECK-LABEL: @undef_test_permvar_sf_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x float> [[A0:%.*]], <8 x float> undef, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <8 x float> [[TMP1]]
;
  %1 = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  ret <8 x float> %1
}

define <8 x float> @undef_test_permvar_sf_256_mask(<8 x float> %a0, <8 x float> %passthru, i8 %mask) {
; CHECK-LABEL: @undef_test_permvar_sf_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x float> [[A0:%.*]], <8 x float> undef, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x float> [[TMP1]], <8 x float> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x float> [[TMP3]]
;
  %1 = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x float> %1, <8 x float> %passthru
  ret <8 x float> %3
}

declare <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64>, <4 x i64>)

define <4 x i64> @identity_test_permvar_di_256(<4 x i64> %a0) {
; CHECK-LABEL: @identity_test_permvar_di_256(
; CHECK-NEXT:    ret <4 x i64> [[A0:%.*]]
;
  %1 = call <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64> %a0, <4 x i64> <i64 0, i64 1, i64 2, i64 3>)
  ret <4 x i64> %1
}

define <4 x i64> @identity_test_permvar_di_256_mask(<4 x i64> %a0, <4 x i64> %passthru, i8 %mask) {
; CHECK-LABEL: @identity_test_permvar_di_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[EXTRACT:%.*]] = shufflevector <8 x i1> [[TMP1]], <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[EXTRACT]], <4 x i64> [[A0:%.*]], <4 x i64> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <4 x i64> [[TMP2]]
;
  %1 = call <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64> %a0, <4 x i64> <i64 0, i64 1, i64 2, i64 3>)
  %2 = bitcast i8 %mask to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %3 = select <4 x i1> %extract, <4 x i64> %1, <4 x i64> %passthru
  ret <4 x i64> %3
}

define <4 x i64> @zero_test_permvar_di_256(<4 x i64> %a0) {
; CHECK-LABEL: @zero_test_permvar_di_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i64> [[A0:%.*]], <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:    ret <4 x i64> [[TMP1]]
;
  %1 = call <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64> %a0, <4 x i64> zeroinitializer)
  ret <4 x i64> %1
}

define <4 x i64> @zero_test_permvar_di_256_mask(<4 x i64> %a0, <4 x i64> %passthru, i8 %mask) {
; CHECK-LABEL: @zero_test_permvar_di_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i64> [[A0:%.*]], <4 x i64> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[EXTRACT:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[TMP3:%.*]] = select <4 x i1> [[EXTRACT]], <4 x i64> [[TMP1]], <4 x i64> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <4 x i64> [[TMP3]]
;
  %1 = call <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64> %a0, <4 x i64> zeroinitializer)
  %2 = bitcast i8 %mask to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %3 = select <4 x i1> %extract, <4 x i64> %1, <4 x i64> %passthru
  ret <4 x i64> %3
}

define <4 x i64> @shuffle_test_permvar_di_256(<4 x i64> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_di_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i64> [[A0:%.*]], <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <4 x i64> [[TMP1]]
;
  %1 = call <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64> %a0, <4 x i64> <i64 3, i64 2, i64 1, i64 0>)
  ret <4 x i64> %1
}

define <4 x i64> @shuffle_test_permvar_di_256_mask(<4 x i64> %a0, <4 x i64> %passthru, i8 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_di_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i64> [[A0:%.*]], <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[EXTRACT:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[TMP3:%.*]] = select <4 x i1> [[EXTRACT]], <4 x i64> [[TMP1]], <4 x i64> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <4 x i64> [[TMP3]]
;
  %1 = call <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64> %a0, <4 x i64> <i64 3, i64 2, i64 1, i64 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %3 = select <4 x i1> %extract, <4 x i64> %1, <4 x i64> %passthru
  ret <4 x i64> %3
}

define <4 x i64> @undef_test_permvar_di_256(<4 x i64> %a0) {
; CHECK-LABEL: @undef_test_permvar_di_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i64> [[A0:%.*]], <4 x i64> undef, <4 x i32> <i32 undef, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <4 x i64> [[TMP1]]
;
  %1 = call <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64> %a0, <4 x i64> <i64 undef, i64 2, i64 1, i64 0>)
  ret <4 x i64> %1
}

define <4 x i64> @undef_test_permvar_di_256_mask(<4 x i64> %a0, <4 x i64> %passthru, i8 %mask) {
; CHECK-LABEL: @undef_test_permvar_di_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i64> [[A0:%.*]], <4 x i64> undef, <4 x i32> <i32 undef, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[EXTRACT:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[TMP3:%.*]] = select <4 x i1> [[EXTRACT]], <4 x i64> [[TMP1]], <4 x i64> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <4 x i64> [[TMP3]]
;
  %1 = call <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64> %a0, <4 x i64> <i64 undef, i64 2, i64 1, i64 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %3 = select <4 x i1> %extract, <4 x i64> %1, <4 x i64> %passthru
  ret <4 x i64> %3
}

declare <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double>, <4 x i64>)

define <4 x double> @identity_test_permvar_df_256(<4 x double> %a0) {
; CHECK-LABEL: @identity_test_permvar_df_256(
; CHECK-NEXT:    ret <4 x double> [[A0:%.*]]
;
  %1 = call <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double> %a0, <4 x i64> <i64 0, i64 1, i64 2, i64 3>)
  ret <4 x double> %1
}

define <4 x double> @identity_test_permvar_df_256_mask(<4 x double> %a0, <4 x double> %passthru, i8 %mask) {
; CHECK-LABEL: @identity_test_permvar_df_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[EXTRACT:%.*]] = shufflevector <8 x i1> [[TMP1]], <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[EXTRACT]], <4 x double> [[A0:%.*]], <4 x double> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <4 x double> [[TMP2]]
;
  %1 = call <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double> %a0, <4 x i64> <i64 0, i64 1, i64 2, i64 3>)
  %2 = bitcast i8 %mask to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %3 = select <4 x i1> %extract, <4 x double> %1, <4 x double> %passthru
  ret <4 x double> %3
}

define <4 x double> @zero_test_permvar_df_256(<4 x double> %a0) {
; CHECK-LABEL: @zero_test_permvar_df_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x double> [[A0:%.*]], <4 x double> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:    ret <4 x double> [[TMP1]]
;
  %1 = call <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double> %a0, <4 x i64> zeroinitializer)
  ret <4 x double> %1
}

define <4 x double> @zero_test_permvar_df_256_mask(<4 x double> %a0, <4 x double> %passthru, i8 %mask) {
; CHECK-LABEL: @zero_test_permvar_df_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x double> [[A0:%.*]], <4 x double> undef, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[EXTRACT:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[TMP3:%.*]] = select <4 x i1> [[EXTRACT]], <4 x double> [[TMP1]], <4 x double> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <4 x double> [[TMP3]]
;
  %1 = call <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double> %a0, <4 x i64> zeroinitializer)
  %2 = bitcast i8 %mask to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %3 = select <4 x i1> %extract, <4 x double> %1, <4 x double> %passthru
  ret <4 x double> %3
}

define <4 x double> @shuffle_test_permvar_df_256(<4 x double> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_df_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x double> [[A0:%.*]], <4 x double> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <4 x double> [[TMP1]]
;
  %1 = call <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double> %a0, <4 x i64> <i64 3, i64 2, i64 1, i64 0>)
  ret <4 x double> %1
}

define <4 x double> @shuffle_test_permvar_df_256_mask(<4 x double> %a0, <4 x double> %passthru, i8 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_df_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x double> [[A0:%.*]], <4 x double> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[EXTRACT:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[TMP3:%.*]] = select <4 x i1> [[EXTRACT]], <4 x double> [[TMP1]], <4 x double> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <4 x double> [[TMP3]]
;
  %1 = call <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double> %a0, <4 x i64> <i64 3, i64 2, i64 1, i64 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %3 = select <4 x i1> %extract, <4 x double> %1, <4 x double> %passthru
  ret <4 x double> %3
}

define <4 x double> @undef_test_permvar_df_256(<4 x double> %a0) {
; CHECK-LABEL: @undef_test_permvar_df_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x double> [[A0:%.*]], <4 x double> undef, <4 x i32> <i32 undef, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <4 x double> [[TMP1]]
;
  %1 = call <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double> %a0, <4 x i64> <i64 undef, i64 2, i64 1, i64 0>)
  ret <4 x double> %1
}

define <4 x double> @undef_test_permvar_df_256_mask(<4 x double> %a0, <4 x double> %passthru, i8 %mask) {
; CHECK-LABEL: @undef_test_permvar_df_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x double> [[A0:%.*]], <4 x double> undef, <4 x i32> <i32 undef, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[EXTRACT:%.*]] = shufflevector <8 x i1> [[TMP2]], <8 x i1> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[TMP3:%.*]] = select <4 x i1> [[EXTRACT]], <4 x double> [[TMP1]], <4 x double> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <4 x double> [[TMP3]]
;
  %1 = call <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double> %a0, <4 x i64> <i64 undef, i64 2, i64 1, i64 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %3 = select <4 x i1> %extract, <4 x double> %1, <4 x double> %passthru
  ret <4 x double> %3
}

declare <16 x i32> @llvm.x86.avx512.permvar.si.512(<16 x i32>, <16 x i32>)

define <16 x i32> @identity_test_permvar_si_512(<16 x i32> %a0) {
; CHECK-LABEL: @identity_test_permvar_si_512(
; CHECK-NEXT:    ret <16 x i32> [[A0:%.*]]
;
  %1 = call <16 x i32> @llvm.x86.avx512.permvar.si.512(<16 x i32> %a0, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>)
  ret <16 x i32> %1
}

define <16 x i32> @identity_test_permvar_si_512_mask(<16 x i32> %a0, <16 x i32> %passthru, i16 %mask) {
; CHECK-LABEL: @identity_test_permvar_si_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP2:%.*]] = select <16 x i1> [[TMP1]], <16 x i32> [[A0:%.*]], <16 x i32> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x i32> [[TMP2]]
;
  %1 = call <16 x i32> @llvm.x86.avx512.permvar.si.512(<16 x i32> %a0, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i32> %1, <16 x i32> %passthru
  ret <16 x i32> %3
}

define <16 x i32> @zero_test_permvar_si_512(<16 x i32> %a0) {
; CHECK-LABEL: @zero_test_permvar_si_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i32> [[A0:%.*]], <16 x i32> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:    ret <16 x i32> [[TMP1]]
;
  %1 = call <16 x i32> @llvm.x86.avx512.permvar.si.512(<16 x i32> %a0, <16 x i32> zeroinitializer)
  ret <16 x i32> %1
}

define <16 x i32> @zero_test_permvar_si_512_mask(<16 x i32> %a0, <16 x i32> %passthru, i16 %mask) {
; CHECK-LABEL: @zero_test_permvar_si_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i32> [[A0:%.*]], <16 x i32> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x i32> [[TMP1]], <16 x i32> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x i32> [[TMP3]]
;
  %1 = call <16 x i32> @llvm.x86.avx512.permvar.si.512(<16 x i32> %a0, <16 x i32> zeroinitializer)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i32> %1, <16 x i32> %passthru
  ret <16 x i32> %3
}

define <16 x i32> @shuffle_test_permvar_si_512(<16 x i32> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_si_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i32> [[A0:%.*]], <16 x i32> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <16 x i32> [[TMP1]]
;
  %1 = call <16 x i32> @llvm.x86.avx512.permvar.si.512(<16 x i32> %a0, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  ret <16 x i32> %1
}

define <16 x i32> @shuffle_test_permvar_si_512_mask(<16 x i32> %a0, <16 x i32> %passthru, i16 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_si_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i32> [[A0:%.*]], <16 x i32> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x i32> [[TMP1]], <16 x i32> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x i32> [[TMP3]]
;
  %1 = call <16 x i32> @llvm.x86.avx512.permvar.si.512(<16 x i32> %a0, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i32> %1, <16 x i32> %passthru
  ret <16 x i32> %3
}

define <16 x i32> @undef_test_permvar_si_512(<16 x i32> %a0) {
; CHECK-LABEL: @undef_test_permvar_si_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i32> [[A0:%.*]], <16 x i32> undef, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <16 x i32> [[TMP1]]
;
  %1 = call <16 x i32> @llvm.x86.avx512.permvar.si.512(<16 x i32> %a0, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  ret <16 x i32> %1
}

define <16 x i32> @undef_test_permvar_si_512_mask(<16 x i32> %a0, <16 x i32> %passthru, i16 %mask) {
; CHECK-LABEL: @undef_test_permvar_si_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i32> [[A0:%.*]], <16 x i32> undef, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x i32> [[TMP1]], <16 x i32> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x i32> [[TMP3]]
;
  %1 = call <16 x i32> @llvm.x86.avx512.permvar.si.512(<16 x i32> %a0, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i32> %1, <16 x i32> %passthru
  ret <16 x i32> %3
}

declare <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float>, <16 x i32>)

define <16 x float> @identity_test_permvar_sf_512(<16 x float> %a0) {
; CHECK-LABEL: @identity_test_permvar_sf_512(
; CHECK-NEXT:    ret <16 x float> [[A0:%.*]]
;
  %1 = call <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float> %a0, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>)
  ret <16 x float> %1
}

define <16 x float> @identity_test_permvar_sf_512_mask(<16 x float> %a0, <16 x float> %passthru, i16 %mask) {
; CHECK-LABEL: @identity_test_permvar_sf_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP2:%.*]] = select <16 x i1> [[TMP1]], <16 x float> [[A0:%.*]], <16 x float> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP2]]
;
  %1 = call <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float> %a0, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %passthru
  ret <16 x float> %3
}

define <16 x float> @zero_test_permvar_sf_512(<16 x float> %a0) {
; CHECK-LABEL: @zero_test_permvar_sf_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x float> [[A0:%.*]], <16 x float> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:    ret <16 x float> [[TMP1]]
;
  %1 = call <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float> %a0, <16 x i32> zeroinitializer)
  ret <16 x float> %1
}

define <16 x float> @zero_test_permvar_sf_512_mask(<16 x float> %a0, <16 x float> %passthru, i16 %mask) {
; CHECK-LABEL: @zero_test_permvar_sf_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x float> [[A0:%.*]], <16 x float> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float> %a0, <16 x i32> zeroinitializer)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %passthru
  ret <16 x float> %3
}

define <16 x float> @shuffle_test_permvar_sf_512(<16 x float> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_sf_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x float> [[A0:%.*]], <16 x float> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <16 x float> [[TMP1]]
;
  %1 = call <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float> %a0, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  ret <16 x float> %1
}

define <16 x float> @shuffle_test_permvar_sf_512_mask(<16 x float> %a0, <16 x float> %passthru, i16 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_sf_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x float> [[A0:%.*]], <16 x float> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float> %a0, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %passthru
  ret <16 x float> %3
}

define <16 x float> @undef_test_permvar_sf_512(<16 x float> %a0) {
; CHECK-LABEL: @undef_test_permvar_sf_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x float> [[A0:%.*]], <16 x float> undef, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <16 x float> [[TMP1]]
;
  %1 = call <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float> %a0, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  ret <16 x float> %1
}

define <16 x float> @undef_test_permvar_sf_512_mask(<16 x float> %a0, <16 x float> %passthru, i16 %mask) {
; CHECK-LABEL: @undef_test_permvar_sf_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x float> [[A0:%.*]], <16 x float> undef, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float> %a0, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %passthru
  ret <16 x float> %3
}

declare <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64>, <8 x i64>)

define <8 x i64> @identity_test_permvar_di_512(<8 x i64> %a0) {
; CHECK-LABEL: @identity_test_permvar_di_512(
; CHECK-NEXT:    ret <8 x i64> [[A0:%.*]]
;
  %1 = call <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64> %a0, <8 x i64> <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>)
  ret <8 x i64> %1
}

define <8 x i64> @identity_test_permvar_di_512_mask(<8 x i64> %a0, <8 x i64> %passthru, i8 %mask) {
; CHECK-LABEL: @identity_test_permvar_di_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP2:%.*]] = select <8 x i1> [[TMP1]], <8 x i64> [[A0:%.*]], <8 x i64> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x i64> [[TMP2]]
;
  %1 = call <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64> %a0, <8 x i64> <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i64> %1, <8 x i64> %passthru
  ret <8 x i64> %3
}

define <8 x i64> @zero_test_permvar_di_512(<8 x i64> %a0) {
; CHECK-LABEL: @zero_test_permvar_di_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i64> [[A0:%.*]], <8 x i64> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:    ret <8 x i64> [[TMP1]]
;
  %1 = call <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64> %a0, <8 x i64> zeroinitializer)
  ret <8 x i64> %1
}

define <8 x i64> @zero_test_permvar_di_512_mask(<8 x i64> %a0, <8 x i64> %passthru, i8 %mask) {
; CHECK-LABEL: @zero_test_permvar_di_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i64> [[A0:%.*]], <8 x i64> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x i64> [[TMP1]], <8 x i64> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x i64> [[TMP3]]
;
  %1 = call <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64> %a0, <8 x i64> zeroinitializer)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i64> %1, <8 x i64> %passthru
  ret <8 x i64> %3
}

define <8 x i64> @shuffle_test_permvar_di_512(<8 x i64> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_di_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i64> [[A0:%.*]], <8 x i64> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <8 x i64> [[TMP1]]
;
  %1 = call <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64> %a0, <8 x i64> <i64 7, i64 6, i64 5, i64 4, i64 3, i64 2, i64 1, i64 0>)
  ret <8 x i64> %1
}

define <8 x i64> @shuffle_test_permvar_di_512_mask(<8 x i64> %a0, <8 x i64> %passthru, i8 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_di_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i64> [[A0:%.*]], <8 x i64> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x i64> [[TMP1]], <8 x i64> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x i64> [[TMP3]]
;
  %1 = call <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64> %a0, <8 x i64> <i64 7, i64 6, i64 5, i64 4, i64 3, i64 2, i64 1, i64 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i64> %1, <8 x i64> %passthru
  ret <8 x i64> %3
}

define <8 x i64> @undef_test_permvar_di_512(<8 x i64> %a0) {
; CHECK-LABEL: @undef_test_permvar_di_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i64> [[A0:%.*]], <8 x i64> undef, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <8 x i64> [[TMP1]]
;
  %1 = call <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64> %a0, <8 x i64> <i64 undef, i64 6, i64 5, i64 4, i64 3, i64 2, i64 1, i64 0>)
  ret <8 x i64> %1
}

define <8 x i64> @undef_test_permvar_di_512_mask(<8 x i64> %a0, <8 x i64> %passthru, i8 %mask) {
; CHECK-LABEL: @undef_test_permvar_di_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i64> [[A0:%.*]], <8 x i64> undef, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x i64> [[TMP1]], <8 x i64> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x i64> [[TMP3]]
;
  %1 = call <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64> %a0, <8 x i64> <i64 undef, i64 6, i64 5, i64 4, i64 3, i64 2, i64 1, i64 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i64> %1, <8 x i64> %passthru
  ret <8 x i64> %3
}

declare <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double>, <8 x i64>)

define <8 x double> @identity_test_permvar_df_512(<8 x double> %a0) {
; CHECK-LABEL: @identity_test_permvar_df_512(
; CHECK-NEXT:    ret <8 x double> [[A0:%.*]]
;
  %1 = call <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double> %a0, <8 x i64> <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>)
  ret <8 x double> %1
}

define <8 x double> @identity_test_permvar_df_512_mask(<8 x double> %a0, <8 x double> %passthru, i8 %mask) {
; CHECK-LABEL: @identity_test_permvar_df_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP2:%.*]] = select <8 x i1> [[TMP1]], <8 x double> [[A0:%.*]], <8 x double> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP2]]
;
  %1 = call <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double> %a0, <8 x i64> <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x double> %1, <8 x double> %passthru
  ret <8 x double> %3
}

define <8 x double> @zero_test_permvar_df_512(<8 x double> %a0) {
; CHECK-LABEL: @zero_test_permvar_df_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x double> [[A0:%.*]], <8 x double> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:    ret <8 x double> [[TMP1]]
;
  %1 = call <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double> %a0, <8 x i64> zeroinitializer)
  ret <8 x double> %1
}

define <8 x double> @zero_test_permvar_df_512_mask(<8 x double> %a0, <8 x double> %passthru, i8 %mask) {
; CHECK-LABEL: @zero_test_permvar_df_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x double> [[A0:%.*]], <8 x double> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double> %a0, <8 x i64> zeroinitializer)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x double> %1, <8 x double> %passthru
  ret <8 x double> %3
}

define <8 x double> @shuffle_test_permvar_df_512(<8 x double> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_df_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x double> [[A0:%.*]], <8 x double> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <8 x double> [[TMP1]]
;
  %1 = call <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double> %a0, <8 x i64> <i64 7, i64 6, i64 5, i64 4, i64 3, i64 2, i64 1, i64 0>)
  ret <8 x double> %1
}

define <8 x double> @shuffle_test_permvar_df_512_mask(<8 x double> %a0, <8 x double> %passthru, i8 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_df_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x double> [[A0:%.*]], <8 x double> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double> %a0, <8 x i64> <i64 7, i64 6, i64 5, i64 4, i64 3, i64 2, i64 1, i64 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x double> %1, <8 x double> %passthru
  ret <8 x double> %3
}

define <8 x double> @undef_test_permvar_df_512(<8 x double> %a0) {
; CHECK-LABEL: @undef_test_permvar_df_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x double> [[A0:%.*]], <8 x double> undef, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <8 x double> [[TMP1]]
;
  %1 = call <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double> %a0, <8 x i64> <i64 undef, i64 6, i64 5, i64 4, i64 3, i64 2, i64 1, i64 0>)
  ret <8 x double> %1
}

define <8 x double> @undef_test_permvar_df_512_mask(<8 x double> %a0, <8 x double> %passthru, i8 %mask) {
; CHECK-LABEL: @undef_test_permvar_df_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x double> [[A0:%.*]], <8 x double> undef, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double> %a0, <8 x i64> <i64 undef, i64 6, i64 5, i64 4, i64 3, i64 2, i64 1, i64 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x double> %1, <8 x double> %passthru
  ret <8 x double> %3
}

declare <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16>, <8 x i16>)

define <8 x i16> @identity_test_permvar_hi_128(<8 x i16> %a0) {
; CHECK-LABEL: @identity_test_permvar_hi_128(
; CHECK-NEXT:    ret <8 x i16> [[A0:%.*]]
;
  %1 = call <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16> %a0, <8 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
  ret <8 x i16> %1
}

define <8 x i16> @identity_test_permvar_hi_128_mask(<8 x i16> %a0, <8 x i16> %passthru, i8 %mask) {
; CHECK-LABEL: @identity_test_permvar_hi_128_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP2:%.*]] = select <8 x i1> [[TMP1]], <8 x i16> [[A0:%.*]], <8 x i16> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x i16> [[TMP2]]
;
  %1 = call <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16> %a0, <8 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passthru
  ret <8 x i16> %3
}

define <8 x i16> @zero_test_permvar_hi_128(<8 x i16> %a0) {
; CHECK-LABEL: @zero_test_permvar_hi_128(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i16> [[A0:%.*]], <8 x i16> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:    ret <8 x i16> [[TMP1]]
;
  %1 = call <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16> %a0, <8 x i16> zeroinitializer)
  ret <8 x i16> %1
}

define <8 x i16> @zero_test_permvar_hi_128_mask(<8 x i16> %a0, <8 x i16> %passthru, i8 %mask) {
; CHECK-LABEL: @zero_test_permvar_hi_128_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i16> [[A0:%.*]], <8 x i16> undef, <8 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x i16> [[TMP1]], <8 x i16> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x i16> [[TMP3]]
;
  %1 = call <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16> %a0, <8 x i16> zeroinitializer)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passthru
  ret <8 x i16> %3
}

define <8 x i16> @shuffle_test_permvar_hi_128(<8 x i16> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_hi_128(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i16> [[A0:%.*]], <8 x i16> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <8 x i16> [[TMP1]]
;
  %1 = call <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16> %a0, <8 x i16> <i16 7, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 0>)
  ret <8 x i16> %1
}

define <8 x i16> @shuffle_test_permvar_hi_128_mask(<8 x i16> %a0, <8 x i16> %passthru, i8 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_hi_128_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i16> [[A0:%.*]], <8 x i16> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x i16> [[TMP1]], <8 x i16> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x i16> [[TMP3]]
;
  %1 = call <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16> %a0, <8 x i16> <i16 7, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passthru
  ret <8 x i16> %3
}

define <8 x i16> @undef_test_permvar_hi_128(<8 x i16> %a0) {
; CHECK-LABEL: @undef_test_permvar_hi_128(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i16> [[A0:%.*]], <8 x i16> undef, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <8 x i16> [[TMP1]]
;
  %1 = call <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16> %a0, <8 x i16> <i16 undef, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 0>)
  ret <8 x i16> %1
}

define <8 x i16> @undef_test_permvar_hi_128_mask(<8 x i16> %a0, <8 x i16> %passthru, i8 %mask) {
; CHECK-LABEL: @undef_test_permvar_hi_128_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i16> [[A0:%.*]], <8 x i16> undef, <8 x i32> <i32 undef, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x i16> [[TMP1]], <8 x i16> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <8 x i16> [[TMP3]]
;
  %1 = call <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16> %a0, <8 x i16> <i16 undef, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 0>)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passthru
  ret <8 x i16> %3
}

declare <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16>, <16 x i16>)

define <16 x i16> @identity_test_permvar_hi_256(<16 x i16> %a0) {
; CHECK-LABEL: @identity_test_permvar_hi_256(
; CHECK-NEXT:    ret <16 x i16> [[A0:%.*]]
;
  %1 = call <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16> %a0, <16 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>)
  ret <16 x i16> %1
}

define <16 x i16> @identity_test_permvar_hi_256_mask(<16 x i16> %a0, <16 x i16> %passthru, i16 %mask) {
; CHECK-LABEL: @identity_test_permvar_hi_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP2:%.*]] = select <16 x i1> [[TMP1]], <16 x i16> [[A0:%.*]], <16 x i16> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x i16> [[TMP2]]
;
  %1 = call <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16> %a0, <16 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15>)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passthru
  ret <16 x i16> %3
}

define <16 x i16> @zero_test_permvar_hi_256(<16 x i16> %a0) {
; CHECK-LABEL: @zero_test_permvar_hi_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i16> [[A0:%.*]], <16 x i16> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:    ret <16 x i16> [[TMP1]]
;
  %1 = call <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16> %a0, <16 x i16> zeroinitializer)
  ret <16 x i16> %1
}

define <16 x i16> @zero_test_permvar_hi_256_mask(<16 x i16> %a0, <16 x i16> %passthru, i16 %mask) {
; CHECK-LABEL: @zero_test_permvar_hi_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i16> [[A0:%.*]], <16 x i16> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x i16> [[TMP1]], <16 x i16> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x i16> [[TMP3]]
;
  %1 = call <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16> %a0, <16 x i16> zeroinitializer)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passthru
  ret <16 x i16> %3
}

define <16 x i16> @shuffle_test_permvar_hi_256(<16 x i16> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_hi_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i16> [[A0:%.*]], <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <16 x i16> [[TMP1]]
;
  %1 = call <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16> %a0, <16 x i16> <i16 15, i16 14, i16 13, i16 12, i16 11, i16 10, i16 9, i16 8, i16 7, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 0>)
  ret <16 x i16> %1
}

define <16 x i16> @shuffle_test_permvar_hi_256_mask(<16 x i16> %a0, <16 x i16> %passthru, i16 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_hi_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i16> [[A0:%.*]], <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x i16> [[TMP1]], <16 x i16> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x i16> [[TMP3]]
;
  %1 = call <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16> %a0, <16 x i16> <i16 15, i16 14, i16 13, i16 12, i16 11, i16 10, i16 9, i16 8, i16 7, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 0>)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passthru
  ret <16 x i16> %3
}

define <16 x i16> @undef_test_permvar_hi_256(<16 x i16> %a0) {
; CHECK-LABEL: @undef_test_permvar_hi_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i16> [[A0:%.*]], <16 x i16> undef, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <16 x i16> [[TMP1]]
;
  %1 = call <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16> %a0, <16 x i16> <i16 undef, i16 14, i16 13, i16 12, i16 11, i16 10, i16 9, i16 8, i16 7, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 0>)
  ret <16 x i16> %1
}

define <16 x i16> @undef_test_permvar_hi_256_mask(<16 x i16> %a0, <16 x i16> %passthru, i16 %mask) {
; CHECK-LABEL: @undef_test_permvar_hi_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i16> [[A0:%.*]], <16 x i16> undef, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x i16> [[TMP1]], <16 x i16> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x i16> [[TMP3]]
;
  %1 = call <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16> %a0, <16 x i16> <i16 undef, i16 14, i16 13, i16 12, i16 11, i16 10, i16 9, i16 8, i16 7, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 0>)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passthru
  ret <16 x i16> %3
}

declare <32 x i16> @llvm.x86.avx512.permvar.hi.512(<32 x i16>, <32 x i16>)

define <32 x i16> @identity_test_permvar_hi_512(<32 x i16> %a0) {
; CHECK-LABEL: @identity_test_permvar_hi_512(
; CHECK-NEXT:    ret <32 x i16> [[A0:%.*]]
;
  %1 = call <32 x i16> @llvm.x86.avx512.permvar.hi.512(<32 x i16> %a0, <32 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 20, i16 21, i16 22, i16 23, i16 24, i16 25, i16 26, i16 27, i16 28, i16 29, i16 30, i16 31>)
  ret <32 x i16> %1
}

define <32 x i16> @identity_test_permvar_hi_512_mask(<32 x i16> %a0, <32 x i16> %passthru, i32 %mask) {
; CHECK-LABEL: @identity_test_permvar_hi_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i32 [[MASK:%.*]] to <32 x i1>
; CHECK-NEXT:    [[TMP2:%.*]] = select <32 x i1> [[TMP1]], <32 x i16> [[A0:%.*]], <32 x i16> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <32 x i16> [[TMP2]]
;
  %1 = call <32 x i16> @llvm.x86.avx512.permvar.hi.512(<32 x i16> %a0, <32 x i16> <i16 0, i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 20, i16 21, i16 22, i16 23, i16 24, i16 25, i16 26, i16 27, i16 28, i16 29, i16 30, i16 31>)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %passthru
  ret <32 x i16> %3
}

define <32 x i16> @zero_test_permvar_hi_512(<32 x i16> %a0) {
; CHECK-LABEL: @zero_test_permvar_hi_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i16> [[A0:%.*]], <32 x i16> undef, <32 x i32> zeroinitializer
; CHECK-NEXT:    ret <32 x i16> [[TMP1]]
;
  %1 = call <32 x i16> @llvm.x86.avx512.permvar.hi.512(<32 x i16> %a0, <32 x i16> zeroinitializer)
  ret <32 x i16> %1
}

define <32 x i16> @zero_test_permvar_hi_512_mask(<32 x i16> %a0, <32 x i16> %passthru, i32 %mask) {
; CHECK-LABEL: @zero_test_permvar_hi_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i16> [[A0:%.*]], <32 x i16> undef, <32 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i32 [[MASK:%.*]] to <32 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <32 x i1> [[TMP2]], <32 x i16> [[TMP1]], <32 x i16> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <32 x i16> [[TMP3]]
;
  %1 = call <32 x i16> @llvm.x86.avx512.permvar.hi.512(<32 x i16> %a0, <32 x i16> zeroinitializer)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %passthru
  ret <32 x i16> %3
}

define <32 x i16> @shuffle_test_permvar_hi_512(<32 x i16> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_hi_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i16> [[A0:%.*]], <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <32 x i16> [[TMP1]]
;
  %1 = call <32 x i16> @llvm.x86.avx512.permvar.hi.512(<32 x i16> %a0, <32 x i16> <i16 31, i16 30, i16 29, i16 28, i16 27, i16 26, i16 25, i16 24, i16 23, i16 22, i16 21, i16 20, i16 19, i16 18, i16 17, i16 16, i16 15, i16 14, i16 13, i16 12, i16 11, i16 10, i16 9, i16 8, i16 7, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 0>)
  ret <32 x i16> %1
}

define <32 x i16> @shuffle_test_permvar_hi_512_mask(<32 x i16> %a0, <32 x i16> %passthru, i32 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_hi_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i16> [[A0:%.*]], <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i32 [[MASK:%.*]] to <32 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <32 x i1> [[TMP2]], <32 x i16> [[TMP1]], <32 x i16> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <32 x i16> [[TMP3]]
;
  %1 = call <32 x i16> @llvm.x86.avx512.permvar.hi.512(<32 x i16> %a0, <32 x i16> <i16 31, i16 30, i16 29, i16 28, i16 27, i16 26, i16 25, i16 24, i16 23, i16 22, i16 21, i16 20, i16 19, i16 18, i16 17, i16 16, i16 15, i16 14, i16 13, i16 12, i16 11, i16 10, i16 9, i16 8, i16 7, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 0>)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %passthru
  ret <32 x i16> %3
}

define <32 x i16> @undef_test_permvar_hi_512(<32 x i16> %a0) {
; CHECK-LABEL: @undef_test_permvar_hi_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i16> [[A0:%.*]], <32 x i16> undef, <32 x i32> <i32 undef, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <32 x i16> [[TMP1]]
;
  %1 = call <32 x i16> @llvm.x86.avx512.permvar.hi.512(<32 x i16> %a0, <32 x i16> <i16 undef, i16 30, i16 29, i16 28, i16 27, i16 26, i16 25, i16 24, i16 23, i16 22, i16 21, i16 20, i16 19, i16 18, i16 17, i16 16, i16 15, i16 14, i16 13, i16 12, i16 11, i16 10, i16 9, i16 8, i16 7, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 0>)
  ret <32 x i16> %1
}

define <32 x i16> @undef_test_permvar_hi_512_mask(<32 x i16> %a0, <32 x i16> %passthru, i32 %mask) {
; CHECK-LABEL: @undef_test_permvar_hi_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i16> [[A0:%.*]], <32 x i16> undef, <32 x i32> <i32 undef, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i32 [[MASK:%.*]] to <32 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <32 x i1> [[TMP2]], <32 x i16> [[TMP1]], <32 x i16> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <32 x i16> [[TMP3]]
;
  %1 = call <32 x i16> @llvm.x86.avx512.permvar.hi.512(<32 x i16> %a0, <32 x i16> <i16 undef, i16 30, i16 29, i16 28, i16 27, i16 26, i16 25, i16 24, i16 23, i16 22, i16 21, i16 20, i16 19, i16 18, i16 17, i16 16, i16 15, i16 14, i16 13, i16 12, i16 11, i16 10, i16 9, i16 8, i16 7, i16 6, i16 5, i16 4, i16 3, i16 2, i16 1, i16 0>)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i16> %1, <32 x i16> %passthru
  ret <32 x i16> %3
}

declare <16 x i8> @llvm.x86.avx512.permvar.qi.128(<16 x i8>, <16 x i8>)

define <16 x i8> @identity_test_permvar_qi_128(<16 x i8> %a0) {
; CHECK-LABEL: @identity_test_permvar_qi_128(
; CHECK-NEXT:    ret <16 x i8> [[A0:%.*]]
;
  %1 = call <16 x i8> @llvm.x86.avx512.permvar.qi.128(<16 x i8> %a0, <16 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15>)
  ret <16 x i8> %1
}

define <16 x i8> @identity_test_permvar_qi_128_mask(<16 x i8> %a0, <16 x i8> %passthru, i16 %mask) {
; CHECK-LABEL: @identity_test_permvar_qi_128_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP2:%.*]] = select <16 x i1> [[TMP1]], <16 x i8> [[A0:%.*]], <16 x i8> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x i8> [[TMP2]]
;
  %1 = call <16 x i8> @llvm.x86.avx512.permvar.qi.128(<16 x i8> %a0, <16 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15>)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passthru
  ret <16 x i8> %3
}

define <16 x i8> @zero_test_permvar_qi_128(<16 x i8> %a0) {
; CHECK-LABEL: @zero_test_permvar_qi_128(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i8> [[A0:%.*]], <16 x i8> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:    ret <16 x i8> [[TMP1]]
;
  %1 = call <16 x i8> @llvm.x86.avx512.permvar.qi.128(<16 x i8> %a0, <16 x i8> zeroinitializer)
  ret <16 x i8> %1
}

define <16 x i8> @zero_test_permvar_qi_128_mask(<16 x i8> %a0, <16 x i8> %passthru, i16 %mask) {
; CHECK-LABEL: @zero_test_permvar_qi_128_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i8> [[A0:%.*]], <16 x i8> undef, <16 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x i8> [[TMP1]], <16 x i8> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x i8> [[TMP3]]
;
  %1 = call <16 x i8> @llvm.x86.avx512.permvar.qi.128(<16 x i8> %a0, <16 x i8> zeroinitializer)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passthru
  ret <16 x i8> %3
}

define <16 x i8> @shuffle_test_permvar_qi_128(<16 x i8> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_qi_128(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i8> [[A0:%.*]], <16 x i8> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <16 x i8> [[TMP1]]
;
  %1 = call <16 x i8> @llvm.x86.avx512.permvar.qi.128(<16 x i8> %a0, <16 x i8> <i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  ret <16 x i8> %1
}

define <16 x i8> @shuffle_test_permvar_qi_128_mask(<16 x i8> %a0, <16 x i8> %passthru, i16 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_qi_128_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i8> [[A0:%.*]], <16 x i8> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x i8> [[TMP1]], <16 x i8> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x i8> [[TMP3]]
;
  %1 = call <16 x i8> @llvm.x86.avx512.permvar.qi.128(<16 x i8> %a0, <16 x i8> <i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passthru
  ret <16 x i8> %3
}

define <16 x i8> @undef_test_permvar_qi_128(<16 x i8> %a0) {
; CHECK-LABEL: @undef_test_permvar_qi_128(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i8> [[A0:%.*]], <16 x i8> undef, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <16 x i8> [[TMP1]]
;
  %1 = call <16 x i8> @llvm.x86.avx512.permvar.qi.128(<16 x i8> %a0, <16 x i8> <i8 undef, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  ret <16 x i8> %1
}

define <16 x i8> @undef_test_permvar_qi_128_mask(<16 x i8> %a0, <16 x i8> %passthru, i16 %mask) {
; CHECK-LABEL: @undef_test_permvar_qi_128_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i8> [[A0:%.*]], <16 x i8> undef, <16 x i32> <i32 undef, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x i8> [[TMP1]], <16 x i8> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <16 x i8> [[TMP3]]
;
  %1 = call <16 x i8> @llvm.x86.avx512.permvar.qi.128(<16 x i8> %a0, <16 x i8> <i8 undef, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passthru
  ret <16 x i8> %3
}

declare <32 x i8> @llvm.x86.avx512.permvar.qi.256(<32 x i8>, <32 x i8>)

define <32 x i8> @identity_test_permvar_qi_256(<32 x i8> %a0) {
; CHECK-LABEL: @identity_test_permvar_qi_256(
; CHECK-NEXT:    ret <32 x i8> [[A0:%.*]]
;
  %1 = call <32 x i8> @llvm.x86.avx512.permvar.qi.256(<32 x i8> %a0, <32 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 20, i8 21, i8 22, i8 23, i8 24, i8 25, i8 26, i8 27, i8 28, i8 29, i8 30, i8 31>)
  ret <32 x i8> %1
}

define <32 x i8> @identity_test_permvar_qi_256_mask(<32 x i8> %a0, <32 x i8> %passthru, i32 %mask) {
; CHECK-LABEL: @identity_test_permvar_qi_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i32 [[MASK:%.*]] to <32 x i1>
; CHECK-NEXT:    [[TMP2:%.*]] = select <32 x i1> [[TMP1]], <32 x i8> [[A0:%.*]], <32 x i8> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <32 x i8> [[TMP2]]
;
  %1 = call <32 x i8> @llvm.x86.avx512.permvar.qi.256(<32 x i8> %a0, <32 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 20, i8 21, i8 22, i8 23, i8 24, i8 25, i8 26, i8 27, i8 28, i8 29, i8 30, i8 31>)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passthru
  ret <32 x i8> %3
}

define <32 x i8> @zero_test_permvar_qi_256(<32 x i8> %a0) {
; CHECK-LABEL: @zero_test_permvar_qi_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i8> [[A0:%.*]], <32 x i8> undef, <32 x i32> zeroinitializer
; CHECK-NEXT:    ret <32 x i8> [[TMP1]]
;
  %1 = call <32 x i8> @llvm.x86.avx512.permvar.qi.256(<32 x i8> %a0, <32 x i8> zeroinitializer)
  ret <32 x i8> %1
}

define <32 x i8> @zero_test_permvar_qi_256_mask(<32 x i8> %a0, <32 x i8> %passthru, i32 %mask) {
; CHECK-LABEL: @zero_test_permvar_qi_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i8> [[A0:%.*]], <32 x i8> undef, <32 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i32 [[MASK:%.*]] to <32 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <32 x i1> [[TMP2]], <32 x i8> [[TMP1]], <32 x i8> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <32 x i8> [[TMP3]]
;
  %1 = call <32 x i8> @llvm.x86.avx512.permvar.qi.256(<32 x i8> %a0, <32 x i8> zeroinitializer)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passthru
  ret <32 x i8> %3
}

define <32 x i8> @shuffle_test_permvar_qi_256(<32 x i8> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_qi_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i8> [[A0:%.*]], <32 x i8> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <32 x i8> [[TMP1]]
;
  %1 = call <32 x i8> @llvm.x86.avx512.permvar.qi.256(<32 x i8> %a0, <32 x i8> <i8 31, i8 30, i8 29, i8 28, i8 27, i8 26, i8 25, i8 24, i8 23, i8 22, i8 21, i8 20, i8 19, i8 18, i8 17, i8 16, i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  ret <32 x i8> %1
}

define <32 x i8> @shuffle_test_permvar_qi_256_mask(<32 x i8> %a0, <32 x i8> %passthru, i32 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_qi_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i8> [[A0:%.*]], <32 x i8> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i32 [[MASK:%.*]] to <32 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <32 x i1> [[TMP2]], <32 x i8> [[TMP1]], <32 x i8> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <32 x i8> [[TMP3]]
;
  %1 = call <32 x i8> @llvm.x86.avx512.permvar.qi.256(<32 x i8> %a0, <32 x i8> <i8 31, i8 30, i8 29, i8 28, i8 27, i8 26, i8 25, i8 24, i8 23, i8 22, i8 21, i8 20, i8 19, i8 18, i8 17, i8 16, i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passthru
  ret <32 x i8> %3
}

define <32 x i8> @undef_test_permvar_qi_256(<32 x i8> %a0) {
; CHECK-LABEL: @undef_test_permvar_qi_256(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i8> [[A0:%.*]], <32 x i8> undef, <32 x i32> <i32 undef, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <32 x i8> [[TMP1]]
;
  %1 = call <32 x i8> @llvm.x86.avx512.permvar.qi.256(<32 x i8> %a0, <32 x i8> <i8 undef, i8 30, i8 29, i8 28, i8 27, i8 26, i8 25, i8 24, i8 23, i8 22, i8 21, i8 20, i8 19, i8 18, i8 17, i8 16, i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  ret <32 x i8> %1
}

define <32 x i8> @undef_test_permvar_qi_256_mask(<32 x i8> %a0, <32 x i8> %passthru, i32 %mask) {
; CHECK-LABEL: @undef_test_permvar_qi_256_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i8> [[A0:%.*]], <32 x i8> undef, <32 x i32> <i32 undef, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i32 [[MASK:%.*]] to <32 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <32 x i1> [[TMP2]], <32 x i8> [[TMP1]], <32 x i8> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <32 x i8> [[TMP3]]
;
  %1 = call <32 x i8> @llvm.x86.avx512.permvar.qi.256(<32 x i8> %a0, <32 x i8> <i8 undef, i8 30, i8 29, i8 28, i8 27, i8 26, i8 25, i8 24, i8 23, i8 22, i8 21, i8 20, i8 19, i8 18, i8 17, i8 16, i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passthru
  ret <32 x i8> %3
}

declare <64 x i8> @llvm.x86.avx512.permvar.qi.512(<64 x i8>, <64 x i8>)

define <64 x i8> @identity_test_permvar_qi_512(<64 x i8> %a0) {
; CHECK-LABEL: @identity_test_permvar_qi_512(
; CHECK-NEXT:    ret <64 x i8> [[A0:%.*]]
;
  %1 = call <64 x i8> @llvm.x86.avx512.permvar.qi.512(<64 x i8> %a0, <64 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 20, i8 21, i8 22, i8 23, i8 24, i8 25, i8 26, i8 27, i8 28, i8 29, i8 30, i8 31, i8 32, i8 33, i8 34, i8 35, i8 36, i8 37, i8 38, i8 39, i8 40, i8 41, i8 42, i8 43, i8 44, i8 45, i8 46, i8 47, i8 48, i8 49, i8 50, i8 51, i8 52, i8 53, i8 54, i8 55, i8 56, i8 57, i8 58, i8 59, i8 60, i8 61, i8 62, i8 63>)
  ret <64 x i8> %1
}

define <64 x i8> @identity_test_permvar_qi_512_mask(<64 x i8> %a0, <64 x i8> %passthru, i64 %mask) {
; CHECK-LABEL: @identity_test_permvar_qi_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i64 [[MASK:%.*]] to <64 x i1>
; CHECK-NEXT:    [[TMP2:%.*]] = select <64 x i1> [[TMP1]], <64 x i8> [[A0:%.*]], <64 x i8> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <64 x i8> [[TMP2]]
;
  %1 = call <64 x i8> @llvm.x86.avx512.permvar.qi.512(<64 x i8> %a0, <64 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 20, i8 21, i8 22, i8 23, i8 24, i8 25, i8 26, i8 27, i8 28, i8 29, i8 30, i8 31, i8 32, i8 33, i8 34, i8 35, i8 36, i8 37, i8 38, i8 39, i8 40, i8 41, i8 42, i8 43, i8 44, i8 45, i8 46, i8 47, i8 48, i8 49, i8 50, i8 51, i8 52, i8 53, i8 54, i8 55, i8 56, i8 57, i8 58, i8 59, i8 60, i8 61, i8 62, i8 63>)
  %2 = bitcast i64 %mask to <64 x i1>
  %3 = select <64 x i1> %2, <64 x i8> %1, <64 x i8> %passthru
  ret <64 x i8> %3
}

define <64 x i8> @zero_test_permvar_qi_512(<64 x i8> %a0) {
; CHECK-LABEL: @zero_test_permvar_qi_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <64 x i8> [[A0:%.*]], <64 x i8> undef, <64 x i32> zeroinitializer
; CHECK-NEXT:    ret <64 x i8> [[TMP1]]
;
  %1 = call <64 x i8> @llvm.x86.avx512.permvar.qi.512(<64 x i8> %a0, <64 x i8> zeroinitializer)
  ret <64 x i8> %1
}

define <64 x i8> @zero_test_permvar_qi_512_mask(<64 x i8> %a0, <64 x i8> %passthru, i64 %mask) {
; CHECK-LABEL: @zero_test_permvar_qi_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <64 x i8> [[A0:%.*]], <64 x i8> undef, <64 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i64 [[MASK:%.*]] to <64 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <64 x i1> [[TMP2]], <64 x i8> [[TMP1]], <64 x i8> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <64 x i8> [[TMP3]]
;
  %1 = call <64 x i8> @llvm.x86.avx512.permvar.qi.512(<64 x i8> %a0, <64 x i8> zeroinitializer)
  %2 = bitcast i64 %mask to <64 x i1>
  %3 = select <64 x i1> %2, <64 x i8> %1, <64 x i8> %passthru
  ret <64 x i8> %3
}

define <64 x i8> @shuffle_test_permvar_qi_512(<64 x i8> %a0) {
; CHECK-LABEL: @shuffle_test_permvar_qi_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <64 x i8> [[A0:%.*]], <64 x i8> undef, <64 x i32> <i32 63, i32 62, i32 61, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <64 x i8> [[TMP1]]
;
  %1 = call <64 x i8> @llvm.x86.avx512.permvar.qi.512(<64 x i8> %a0, <64 x i8> <i8 63, i8 62, i8 61, i8 60, i8 59, i8 58, i8 57, i8 56, i8 55, i8 54, i8 53, i8 52, i8 51, i8 50, i8 49, i8 48, i8 47, i8 46, i8 45, i8 44, i8 43, i8 42, i8 41, i8 40, i8 39, i8 38, i8 37, i8 36, i8 35, i8 34, i8 33, i8 32, i8 31, i8 30, i8 29, i8 28, i8 27, i8 26, i8 25, i8 24, i8 23, i8 22, i8 21, i8 20, i8 19, i8 18, i8 17, i8 16, i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  ret <64 x i8> %1
}

define <64 x i8> @shuffle_test_permvar_qi_512_mask(<64 x i8> %a0, <64 x i8> %passthru, i64 %mask) {
; CHECK-LABEL: @shuffle_test_permvar_qi_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <64 x i8> [[A0:%.*]], <64 x i8> undef, <64 x i32> <i32 63, i32 62, i32 61, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i64 [[MASK:%.*]] to <64 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <64 x i1> [[TMP2]], <64 x i8> [[TMP1]], <64 x i8> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <64 x i8> [[TMP3]]
;
  %1 = call <64 x i8> @llvm.x86.avx512.permvar.qi.512(<64 x i8> %a0, <64 x i8> <i8 63, i8 62, i8 61, i8 60, i8 59, i8 58, i8 57, i8 56, i8 55, i8 54, i8 53, i8 52, i8 51, i8 50, i8 49, i8 48, i8 47, i8 46, i8 45, i8 44, i8 43, i8 42, i8 41, i8 40, i8 39, i8 38, i8 37, i8 36, i8 35, i8 34, i8 33, i8 32, i8 31, i8 30, i8 29, i8 28, i8 27, i8 26, i8 25, i8 24, i8 23, i8 22, i8 21, i8 20, i8 19, i8 18, i8 17, i8 16, i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  %2 = bitcast i64 %mask to <64 x i1>
  %3 = select <64 x i1> %2, <64 x i8> %1, <64 x i8> %passthru
  ret <64 x i8> %3
}

define <64 x i8> @undef_test_permvar_qi_512(<64 x i8> %a0) {
; CHECK-LABEL: @undef_test_permvar_qi_512(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <64 x i8> [[A0:%.*]], <64 x i8> undef, <64 x i32> <i32 undef, i32 62, i32 61, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    ret <64 x i8> [[TMP1]]
;
  %1 = call <64 x i8> @llvm.x86.avx512.permvar.qi.512(<64 x i8> %a0, <64 x i8> <i8 undef, i8 62, i8 61, i8 60, i8 59, i8 58, i8 57, i8 56, i8 55, i8 54, i8 53, i8 52, i8 51, i8 50, i8 49, i8 48, i8 47, i8 46, i8 45, i8 44, i8 43, i8 42, i8 41, i8 40, i8 39, i8 38, i8 37, i8 36, i8 35, i8 34, i8 33, i8 32, i8 31, i8 30, i8 29, i8 28, i8 27, i8 26, i8 25, i8 24, i8 23, i8 22, i8 21, i8 20, i8 19, i8 18, i8 17, i8 16, i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  ret <64 x i8> %1
}

define <64 x i8> @undef_test_permvar_qi_512_mask(<64 x i8> %a0, <64 x i8> %passthru, i64 %mask) {
; CHECK-LABEL: @undef_test_permvar_qi_512_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <64 x i8> [[A0:%.*]], <64 x i8> undef, <64 x i32> <i32 undef, i32 62, i32 61, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i64 [[MASK:%.*]] to <64 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <64 x i1> [[TMP2]], <64 x i8> [[TMP1]], <64 x i8> [[PASSTHRU:%.*]]
; CHECK-NEXT:    ret <64 x i8> [[TMP3]]
;
  %1 = call <64 x i8> @llvm.x86.avx512.permvar.qi.512(<64 x i8> %a0, <64 x i8> <i8 undef, i8 62, i8 61, i8 60, i8 59, i8 58, i8 57, i8 56, i8 55, i8 54, i8 53, i8 52, i8 51, i8 50, i8 49, i8 48, i8 47, i8 46, i8 45, i8 44, i8 43, i8 42, i8 41, i8 40, i8 39, i8 38, i8 37, i8 36, i8 35, i8 34, i8 33, i8 32, i8 31, i8 30, i8 29, i8 28, i8 27, i8 26, i8 25, i8 24, i8 23, i8 22, i8 21, i8 20, i8 19, i8 18, i8 17, i8 16, i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>)
  %2 = bitcast i64 %mask to <64 x i1>
  %3 = select <64 x i1> %2, <64 x i8> %1, <64 x i8> %passthru
  ret <64 x i8> %3
}

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

define <16 x float> @test_add_ps(<16 x float> %a, <16 x float> %b) {
; CHECK-LABEL: @test_add_ps(
; CHECK-NEXT:    [[TMP1:%.*]] = fadd <16 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP1]]
;
  %1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a, <16 x float> %b, i32 4)
  ret <16 x float> %1
}

define <16 x float> @test_add_ps_round(<16 x float> %a, <16 x float> %b) {
; CHECK-LABEL: @test_add_ps_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> [[A:%.*]], <16 x float> [[B:%.*]], i32 8)
; CHECK-NEXT:    ret <16 x float> [[TMP1]]
;
  %1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a, <16 x float> %b, i32 8)
  ret <16 x float> %1
}

define <16 x float> @test_add_ps_mask(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask) {
; CHECK-LABEL: @test_add_ps_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = fadd <16 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[C:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a, <16 x float> %b, i32 4)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %c
  ret <16 x float> %3
}

define <16 x float> @test_add_ps_mask_round(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask) {
; CHECK-LABEL: @test_add_ps_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> [[A:%.*]], <16 x float> [[B:%.*]], i32 8)
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[C:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a, <16 x float> %b, i32 8)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %c
  ret <16 x float> %3
}

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

define <8 x double> @test_add_pd(<8 x double> %a, <8 x double> %b) {
; CHECK-LABEL: @test_add_pd(
; CHECK-NEXT:    [[TMP1:%.*]] = fadd <8 x double> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP1]]
;
  %1 = call <8 x double> @llvm.x86.avx512.add.pd.512(<8 x double> %a, <8 x double> %b, i32 4)
  ret <8 x double> %1
}

define <8 x double> @test_add_pd_round(<8 x double> %a, <8 x double> %b) {
; CHECK-LABEL: @test_add_pd_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x double> @llvm.x86.avx512.add.pd.512(<8 x double> [[A:%.*]], <8 x double> [[B:%.*]], i32 8)
; CHECK-NEXT:    ret <8 x double> [[TMP1]]
;
  %1 = call <8 x double> @llvm.x86.avx512.add.pd.512(<8 x double> %a, <8 x double> %b, i32 8)
  ret <8 x double> %1
}

define <8 x double> @test_add_pd_mask(<8 x double> %a, <8 x double> %b, <8 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_add_pd_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = fadd <8 x double> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[C:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.add.pd.512(<8 x double> %a, <8 x double> %b, i32 4)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x double> %1, <8 x double> %c
  ret <8 x double> %3
}

define <8 x double> @test_add_pd_mask_round(<8 x double> %a, <8 x double> %b, <8 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_add_pd_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x double> @llvm.x86.avx512.add.pd.512(<8 x double> [[A:%.*]], <8 x double> [[B:%.*]], i32 8)
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[C:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.add.pd.512(<8 x double> %a, <8 x double> %b, i32 8)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x double> %1, <8 x double> %c
  ret <8 x double> %3
}

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

define <16 x float> @test_sub_ps(<16 x float> %a, <16 x float> %b) {
; CHECK-LABEL: @test_sub_ps(
; CHECK-NEXT:    [[TMP1:%.*]] = fsub <16 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP1]]
;
  %1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a, <16 x float> %b, i32 4)
  ret <16 x float> %1
}

define <16 x float> @test_sub_ps_round(<16 x float> %a, <16 x float> %b) {
; CHECK-LABEL: @test_sub_ps_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> [[A:%.*]], <16 x float> [[B:%.*]], i32 8)
; CHECK-NEXT:    ret <16 x float> [[TMP1]]
;
  %1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a, <16 x float> %b, i32 8)
  ret <16 x float> %1
}

define <16 x float> @test_sub_ps_mask(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask) {
; CHECK-LABEL: @test_sub_ps_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = fsub <16 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[C:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a, <16 x float> %b, i32 4)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %c
  ret <16 x float> %3
}

define <16 x float> @test_sub_ps_mask_round(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask) {
; CHECK-LABEL: @test_sub_ps_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> [[A:%.*]], <16 x float> [[B:%.*]], i32 8)
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[C:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a, <16 x float> %b, i32 8)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %c
  ret <16 x float> %3
}

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

define <8 x double> @test_sub_pd(<8 x double> %a, <8 x double> %b) {
; CHECK-LABEL: @test_sub_pd(
; CHECK-NEXT:    [[TMP1:%.*]] = fsub <8 x double> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP1]]
;
  %1 = call <8 x double> @llvm.x86.avx512.sub.pd.512(<8 x double> %a, <8 x double> %b, i32 4)
  ret <8 x double> %1
}

define <8 x double> @test_sub_pd_round(<8 x double> %a, <8 x double> %b) {
; CHECK-LABEL: @test_sub_pd_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x double> @llvm.x86.avx512.sub.pd.512(<8 x double> [[A:%.*]], <8 x double> [[B:%.*]], i32 8)
; CHECK-NEXT:    ret <8 x double> [[TMP1]]
;
  %1 = call <8 x double> @llvm.x86.avx512.sub.pd.512(<8 x double> %a, <8 x double> %b, i32 8)
  ret <8 x double> %1
}

define <8 x double> @test_sub_pd_mask(<8 x double> %a, <8 x double> %b, <8 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_sub_pd_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = fsub <8 x double> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[C:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.sub.pd.512(<8 x double> %a, <8 x double> %b, i32 4)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x double> %1, <8 x double> %c
  ret <8 x double> %3
}

define <8 x double> @test_sub_pd_mask_round(<8 x double> %a, <8 x double> %b, <8 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_sub_pd_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x double> @llvm.x86.avx512.sub.pd.512(<8 x double> [[A:%.*]], <8 x double> [[B:%.*]], i32 8)
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[C:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.sub.pd.512(<8 x double> %a, <8 x double> %b, i32 8)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x double> %1, <8 x double> %c
  ret <8 x double> %3
}

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

define <16 x float> @test_mul_ps(<16 x float> %a, <16 x float> %b) {
; CHECK-LABEL: @test_mul_ps(
; CHECK-NEXT:    [[TMP1:%.*]] = fmul <16 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP1]]
;
  %1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a, <16 x float> %b, i32 4)
  ret <16 x float> %1
}

define <16 x float> @test_mul_ps_round(<16 x float> %a, <16 x float> %b) {
; CHECK-LABEL: @test_mul_ps_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> [[A:%.*]], <16 x float> [[B:%.*]], i32 8)
; CHECK-NEXT:    ret <16 x float> [[TMP1]]
;
  %1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a, <16 x float> %b, i32 8)
  ret <16 x float> %1
}

define <16 x float> @test_mul_ps_mask(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask) {
; CHECK-LABEL: @test_mul_ps_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = fmul <16 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[C:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a, <16 x float> %b, i32 4)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %c
  ret <16 x float> %3
}

define <16 x float> @test_mul_ps_mask_round(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask) {
; CHECK-LABEL: @test_mul_ps_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> [[A:%.*]], <16 x float> [[B:%.*]], i32 8)
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[C:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a, <16 x float> %b, i32 8)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %c
  ret <16 x float> %3
}

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

define <8 x double> @test_mul_pd(<8 x double> %a, <8 x double> %b) {
; CHECK-LABEL: @test_mul_pd(
; CHECK-NEXT:    [[TMP1:%.*]] = fmul <8 x double> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP1]]
;
  %1 = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> %a, <8 x double> %b, i32 4)
  ret <8 x double> %1
}

define <8 x double> @test_mul_pd_round(<8 x double> %a, <8 x double> %b) {
; CHECK-LABEL: @test_mul_pd_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> [[A:%.*]], <8 x double> [[B:%.*]], i32 8)
; CHECK-NEXT:    ret <8 x double> [[TMP1]]
;
  %1 = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> %a, <8 x double> %b, i32 8)
  ret <8 x double> %1
}

define <8 x double> @test_mul_pd_mask(<8 x double> %a, <8 x double> %b, <8 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mul_pd_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = fmul <8 x double> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[C:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> %a, <8 x double> %b, i32 4)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x double> %1, <8 x double> %c
  ret <8 x double> %3
}

define <8 x double> @test_mul_pd_mask_round(<8 x double> %a, <8 x double> %b, <8 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_mul_pd_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> [[A:%.*]], <8 x double> [[B:%.*]], i32 8)
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[C:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> %a, <8 x double> %b, i32 8)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x double> %1, <8 x double> %c
  ret <8 x double> %3
}

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

define <16 x float> @test_div_ps(<16 x float> %a, <16 x float> %b) {
; CHECK-LABEL: @test_div_ps(
; CHECK-NEXT:    [[TMP1:%.*]] = fdiv <16 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP1]]
;
  %1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a, <16 x float> %b, i32 4)
  ret <16 x float> %1
}

define <16 x float> @test_div_ps_round(<16 x float> %a, <16 x float> %b) {
; CHECK-LABEL: @test_div_ps_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> [[A:%.*]], <16 x float> [[B:%.*]], i32 8)
; CHECK-NEXT:    ret <16 x float> [[TMP1]]
;
  %1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a, <16 x float> %b, i32 8)
  ret <16 x float> %1
}

define <16 x float> @test_div_ps_mask(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask) {
; CHECK-LABEL: @test_div_ps_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = fdiv <16 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[C:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a, <16 x float> %b, i32 4)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %c
  ret <16 x float> %3
}

define <16 x float> @test_div_ps_mask_round(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask) {
; CHECK-LABEL: @test_div_ps_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> [[A:%.*]], <16 x float> [[B:%.*]], i32 8)
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16 [[MASK:%.*]] to <16 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <16 x i1> [[TMP2]], <16 x float> [[TMP1]], <16 x float> [[C:%.*]]
; CHECK-NEXT:    ret <16 x float> [[TMP3]]
;
  %1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a, <16 x float> %b, i32 8)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %c
  ret <16 x float> %3
}

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

define <8 x double> @test_div_pd(<8 x double> %a, <8 x double> %b) {
; CHECK-LABEL: @test_div_pd(
; CHECK-NEXT:    [[TMP1:%.*]] = fdiv <8 x double> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP1]]
;
  %1 = call <8 x double> @llvm.x86.avx512.div.pd.512(<8 x double> %a, <8 x double> %b, i32 4)
  ret <8 x double> %1
}

define <8 x double> @test_div_pd_round(<8 x double> %a, <8 x double> %b) {
; CHECK-LABEL: @test_div_pd_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x double> @llvm.x86.avx512.div.pd.512(<8 x double> [[A:%.*]], <8 x double> [[B:%.*]], i32 8)
; CHECK-NEXT:    ret <8 x double> [[TMP1]]
;
  %1 = call <8 x double> @llvm.x86.avx512.div.pd.512(<8 x double> %a, <8 x double> %b, i32 8)
  ret <8 x double> %1
}

define <8 x double> @test_div_pd_mask(<8 x double> %a, <8 x double> %b, <8 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_div_pd_mask(
; CHECK-NEXT:    [[TMP1:%.*]] = fdiv <8 x double> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[C:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.div.pd.512(<8 x double> %a, <8 x double> %b, i32 4)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x double> %1, <8 x double> %c
  ret <8 x double> %3
}

define <8 x double> @test_div_pd_mask_round(<8 x double> %a, <8 x double> %b, <8 x double> %c, i8 %mask) {
; CHECK-LABEL: @test_div_pd_mask_round(
; CHECK-NEXT:    [[TMP1:%.*]] = call <8 x double> @llvm.x86.avx512.div.pd.512(<8 x double> [[A:%.*]], <8 x double> [[B:%.*]], i32 8)
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i8 [[MASK:%.*]] to <8 x i1>
; CHECK-NEXT:    [[TMP3:%.*]] = select <8 x i1> [[TMP2]], <8 x double> [[TMP1]], <8 x double> [[C:%.*]]
; CHECK-NEXT:    ret <8 x double> [[TMP3]]
;
  %1 = call <8 x double> @llvm.x86.avx512.div.pd.512(<8 x double> %a, <8 x double> %b, i32 8)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x double> %1, <8 x double> %c
  ret <8 x double> %3
}

declare i32 @llvm.x86.avx512.vcomi.ss(<4 x float>, <4 x float>, i32, i32)

define i32 @test_comi_ss_0(float %a, float %b) {
; CHECK-LABEL: @test_comi_ss_0(
; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x float> undef, float [[A:%.*]], i32 0
; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x float> undef, float [[B:%.*]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = tail call i32 @llvm.x86.avx512.vcomi.ss(<4 x float> [[TMP1]], <4 x float> [[TMP2]], i32 0, i32 4)
; CHECK-NEXT:    ret i32 [[TMP3]]
;
  %1 = insertelement <4 x float> undef, float %a, i32 0
  %2 = insertelement <4 x float> %1, float 1.000000e+00, i32 1
  %3 = insertelement <4 x float> %2, float 2.000000e+00, i32 2
  %4 = insertelement <4 x float> %3, float 3.000000e+00, i32 3
  %5 = insertelement <4 x float> undef, float %b, i32 0
  %6 = insertelement <4 x float> %5, float 4.000000e+00, i32 1
  %7 = insertelement <4 x float> %6, float 5.000000e+00, i32 2
  %8 = insertelement <4 x float> %7, float 6.000000e+00, i32 3
  %9 = tail call i32 @llvm.x86.avx512.vcomi.ss(<4 x float> %4, <4 x float> %8, i32 0, i32 4)
  ret i32 %9
}

declare i32 @llvm.x86.avx512.vcomi.sd(<2 x double>, <2 x double>, i32, i32)

define i32 @test_comi_sd_0(double %a, double %b) {
; CHECK-LABEL: @test_comi_sd_0(
; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x double> undef, double [[A:%.*]], i32 0
; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x double> undef, double [[B:%.*]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = tail call i32 @llvm.x86.avx512.vcomi.sd(<2 x double> [[TMP1]], <2 x double> [[TMP2]], i32 0, i32 4)
; CHECK-NEXT:    ret i32 [[TMP3]]
;
  %1 = insertelement <2 x double> undef, double %a, i32 0
  %2 = insertelement <2 x double> %1, double 1.000000e+00, i32 1
  %3 = insertelement <2 x double> undef, double %b, i32 0
  %4 = insertelement <2 x double> %3, double 2.000000e+00, i32 1
  %5 = tail call i32 @llvm.x86.avx512.vcomi.sd(<2 x double> %2, <2 x double> %4, i32 0, i32 4)
  ret i32 %5
}