llvm-project/llvm/test/CodeGen/X86/masked_memop.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-apple-darwin -mattr=avx < %s | FileCheck %s --check-prefix=AVX  --check-prefix=AVX1
; RUN: llc -mtriple=x86_64-apple-darwin -mattr=avx2 < %s | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
; RUN: llc -mtriple=x86_64-apple-darwin -mattr=avx512f < %s | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc -mtriple=x86_64-apple-darwin -mattr=avx512f,avx512bw,avx512vl < %s | FileCheck %s --check-prefix=AVX512 --check-prefix=SKX

; To test for the case where masked load/store is not legal, we should add a run with a target
; that does not have AVX, but that case should probably be a separate test file using less tests
; because it takes over 1.2 seconds to codegen these tests on Haswell 4GHz if there's no maskmov.

define <1 x double> @loadv1(<1 x i64> %trigger, <1 x double>* %addr, <1 x double> %dst) {
; AVX-LABEL: loadv1:
; AVX:       ## BB#0:
; AVX-NEXT:    testq %rdi, %rdi
; AVX-NEXT:    ## implicit-def: %xmm1
; AVX-NEXT:    je LBB0_1
; AVX-NEXT:  ## BB#2: ## %else
; AVX-NEXT:    testq %rdi, %rdi
; AVX-NEXT:    jne LBB0_3
; AVX-NEXT:  LBB0_4: ## %else
; AVX-NEXT:    vmovaps %xmm1, %xmm0
; AVX-NEXT:    retq
; AVX-NEXT:  LBB0_1: ## %cond.load
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    testq %rdi, %rdi
; AVX-NEXT:    je LBB0_4
; AVX-NEXT:  LBB0_3: ## %else
; AVX-NEXT:    vmovaps %xmm0, %xmm1
; AVX-NEXT:    vmovaps %xmm1, %xmm0
; AVX-NEXT:    retq
;
; AVX512F-LABEL: loadv1:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    testq %rdi, %rdi
; AVX512F-NEXT:    ## implicit-def: %xmm1
; AVX512F-NEXT:    jne LBB0_2
; AVX512F-NEXT:  ## BB#1: ## %cond.load
; AVX512F-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX512F-NEXT:  LBB0_2: ## %else
; AVX512F-NEXT:    testq %rdi, %rdi
; AVX512F-NEXT:    sete %al
; AVX512F-NEXT:    kmovw %eax, %k1
; AVX512F-NEXT:    vmovsd %xmm1, %xmm0, %xmm0 {%k1}
; AVX512F-NEXT:    retq
;
; SKX-LABEL: loadv1:
; SKX:       ## BB#0:
; SKX-NEXT:    testq %rdi, %rdi
; SKX-NEXT:    ## implicit-def: %xmm1
; SKX-NEXT:    jne LBB0_2
; SKX-NEXT:  ## BB#1: ## %cond.load
; SKX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; SKX-NEXT:  LBB0_2: ## %else
; SKX-NEXT:    testq %rdi, %rdi
; SKX-NEXT:    sete %al
; SKX-NEXT:    kmovd %eax, %k1
; SKX-NEXT:    vmovsd %xmm1, %xmm0, %xmm0 {%k1}
; SKX-NEXT:    retq
  %mask = icmp eq <1 x i64> %trigger, zeroinitializer
  %res = call <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>* %addr, i32 4, <1 x i1>%mask, <1 x double>%dst)
  ret <1 x double> %res
}
declare <1 x double> @llvm.masked.load.v1f64.p0v1f64(<1 x double>*, i32, <1 x i1>, <1 x double>)

define void @storev1(<1 x i32> %trigger, <1 x i32>* %addr, <1 x i32> %val) {
; AVX-LABEL: storev1:
; AVX:       ## BB#0:
; AVX-NEXT:    testl %edi, %edi
; AVX-NEXT:    je LBB1_1
; AVX-NEXT:  ## BB#2: ## %else
; AVX-NEXT:    retq
; AVX-NEXT:  LBB1_1: ## %cond.store
; AVX-NEXT:    movl %edx, (%rsi)
; AVX-NEXT:    retq
;
; AVX512-LABEL: storev1:
; AVX512:       ## BB#0:
; AVX512-NEXT:    testl %edi, %edi
; AVX512-NEXT:    je LBB1_1
; AVX512-NEXT:  ## BB#2: ## %else
; AVX512-NEXT:    retq
; AVX512-NEXT:  LBB1_1: ## %cond.store
; AVX512-NEXT:    movl %edx, (%rsi)
; AVX512-NEXT:    retq
  %mask = icmp eq <1 x i32> %trigger, zeroinitializer
  call void @llvm.masked.store.v1i32.p0v1i32(<1 x i32>%val, <1 x i32>* %addr, i32 4, <1 x i1>%mask)
  ret void
}
declare void @llvm.masked.store.v1i32.p0v1i32(<1 x i32>, <1 x i32>*, i32, <1 x i1>)

define <2 x double> @test6(<2 x i64> %trigger, <2 x double>* %addr, <2 x double> %dst) {
; AVX-LABEL: test6:
; AVX:       ## BB#0:
; AVX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX-NEXT:    vmaskmovpd (%rdi), %xmm0, %xmm2
; AVX-NEXT:    vblendvpd %xmm0, %xmm2, %xmm1, %xmm0
; AVX-NEXT:    retq
;
; AVX512F-LABEL: test6:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX512F-NEXT:    vmaskmovpd (%rdi), %xmm0, %xmm2
; AVX512F-NEXT:    vblendvpd %xmm0, %xmm2, %xmm1, %xmm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test6:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT:    vpcmpeqq %xmm2, %xmm0, %k1
; SKX-NEXT:    vblendmpd (%rdi), %xmm1, %xmm0 {%k1}
; SKX-NEXT:    retq
  %mask = icmp eq <2 x i64> %trigger, zeroinitializer
  %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1>%mask, <2 x double>%dst)
  ret <2 x double> %res
}

define <4 x float> @test7(<4 x i32> %trigger, <4 x float>* %addr, <4 x float> %dst) {
; AVX-LABEL: test7:
; AVX:       ## BB#0:
; AVX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX-NEXT:    vpcmpeqd %xmm2, %xmm0, %xmm0
; AVX-NEXT:    vmaskmovps (%rdi), %xmm0, %xmm2
; AVX-NEXT:    vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; AVX-NEXT:    retq
;
; AVX512F-LABEL: test7:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT:    vpcmpeqd %xmm2, %xmm0, %xmm0
; AVX512F-NEXT:    vmaskmovps (%rdi), %xmm0, %xmm2
; AVX512F-NEXT:    vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test7:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT:    vpcmpeqd %xmm2, %xmm0, %k1
; SKX-NEXT:    vblendmps (%rdi), %xmm1, %xmm0 {%k1}
; SKX-NEXT:    retq
  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
  %res = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %addr, i32 4, <4 x i1>%mask, <4 x float>%dst)
  ret <4 x float> %res
}

define <4 x i32> @test8(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %dst) {
; AVX1-LABEL: test8:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT:    vpcmpeqd %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vmaskmovps (%rdi), %xmm0, %xmm2
; AVX1-NEXT:    vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test8:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT:    vpcmpeqd %xmm2, %xmm0, %xmm0
; AVX2-NEXT:    vpmaskmovd (%rdi), %xmm0, %xmm2
; AVX2-NEXT:    vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test8:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT:    vpcmpeqd %xmm2, %xmm0, %xmm0
; AVX512F-NEXT:    vpmaskmovd (%rdi), %xmm0, %xmm2
; AVX512F-NEXT:    vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test8:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT:    vpcmpeqd %xmm2, %xmm0, %k1
; SKX-NEXT:    vpblendmd (%rdi), %xmm1, %xmm0 {%k1}
; SKX-NEXT:    retq
  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
  %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1>%mask, <4 x i32>%dst)
  ret <4 x i32> %res
}

define void @test9(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
; AVX1-LABEL: test9:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT:    vpcmpeqd %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vmaskmovps %xmm1, %xmm0, (%rdi)
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test9:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT:    vpcmpeqd %xmm2, %xmm0, %xmm0
; AVX2-NEXT:    vpmaskmovd %xmm1, %xmm0, (%rdi)
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test9:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT:    vpcmpeqd %xmm2, %xmm0, %xmm0
; AVX512F-NEXT:    vpmaskmovd %xmm1, %xmm0, (%rdi)
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test9:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT:    vpcmpeqd %xmm2, %xmm0, %k1
; SKX-NEXT:    vmovdqu32 %xmm1, (%rdi) {%k1}
; SKX-NEXT:    retq
  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1>%mask)
  ret void
}

define <4 x double> @test10(<4 x i32> %trigger, <4 x double>* %addr, <4 x double> %dst) {
; AVX1-LABEL: test10:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT:    vpcmpeqd %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vpmovsxdq %xmm0, %xmm2
; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; AVX1-NEXT:    vpmovsxdq %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
; AVX1-NEXT:    vmaskmovpd (%rdi), %ymm0, %ymm2
; AVX1-NEXT:    vblendvpd %ymm0, %ymm2, %ymm1, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test10:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT:    vpcmpeqd %xmm2, %xmm0, %xmm0
; AVX2-NEXT:    vpmovsxdq %xmm0, %ymm0
; AVX2-NEXT:    vmaskmovpd (%rdi), %ymm0, %ymm2
; AVX2-NEXT:    vblendvpd %ymm0, %ymm2, %ymm1, %ymm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test10:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT:    vpcmpeqd %xmm2, %xmm0, %xmm0
; AVX512F-NEXT:    vpmovsxdq %xmm0, %ymm0
; AVX512F-NEXT:    vmaskmovpd (%rdi), %ymm0, %ymm2
; AVX512F-NEXT:    vblendvpd %ymm0, %ymm2, %ymm1, %ymm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test10:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT:    vpcmpeqd %xmm2, %xmm0, %k1
; SKX-NEXT:    vblendmpd (%rdi), %ymm1, %ymm0 {%k1}
; SKX-NEXT:    retq
  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
  %res = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* %addr, i32 32, <4 x i1>%mask, <4 x double>%dst)
  ret <4 x double> %res
}

define <4 x double> @test10b(<4 x i32> %trigger, <4 x double>* %addr, <4 x double> %dst) {
; AVX1-LABEL: test10b:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpmovsxdq %xmm0, %xmm1
; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; AVX1-NEXT:    vpmovsxdq %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT:    vmaskmovpd (%rdi), %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test10b:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vpmovsxdq %xmm0, %ymm0
; AVX2-NEXT:    vmaskmovpd (%rdi), %ymm0, %ymm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test10b:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX512F-NEXT:    vpcmpeqd %xmm1, %xmm0, %xmm0
; AVX512F-NEXT:    vpmovsxdq %xmm0, %ymm0
; AVX512F-NEXT:    vmaskmovpd (%rdi), %ymm0, %ymm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test10b:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; SKX-NEXT:    vpcmpeqd %xmm1, %xmm0, %k1
; SKX-NEXT:    vmovapd (%rdi), %ymm0 {%k1} {z}
; SKX-NEXT:    retq
  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
  %res = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* %addr, i32 32, <4 x i1>%mask, <4 x double>zeroinitializer)
  ret <4 x double> %res
}

define <8 x float> @test11a(<8 x i32> %trigger, <8 x float>* %addr, <8 x float> %dst) {
; AVX1-LABEL: test11a:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT:    vpcmpeqd %xmm3, %xmm2, %xmm2
; AVX1-NEXT:    vpcmpeqd %xmm3, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT:    vmaskmovps (%rdi), %ymm0, %ymm2
; AVX1-NEXT:    vblendvps %ymm0, %ymm2, %ymm1, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test11a:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT:    vpcmpeqd %ymm2, %ymm0, %ymm0
; AVX2-NEXT:    vmaskmovps (%rdi), %ymm0, %ymm2
; AVX2-NEXT:    vblendvps %ymm0, %ymm2, %ymm1, %ymm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test11a:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    ## kill: %ymm1<def> %ymm1<kill> %zmm1<def>
; AVX512F-NEXT:    ## kill: %ymm0<def> %ymm0<kill> %zmm0<def>
; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT:    vpcmpeqd %zmm2, %zmm0, %k0
; AVX512F-NEXT:    kshiftlw $8, %k0, %k0
; AVX512F-NEXT:    kshiftrw $8, %k0, %k1
; AVX512F-NEXT:    vblendmps (%rdi), %zmm1, %zmm0 {%k1}
; AVX512F-NEXT:    ## kill: %ymm0<def> %ymm0<kill> %zmm0<kill>
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test11a:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT:    vpcmpeqd %ymm2, %ymm0, %k1
; SKX-NEXT:    vblendmps (%rdi), %ymm1, %ymm0 {%k1}
; SKX-NEXT:    retq
  %mask = icmp eq <8 x i32> %trigger, zeroinitializer
  %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 32, <8 x i1>%mask, <8 x float>%dst)
  ret <8 x float> %res
}

define <8 x i32> @test11b(<8 x i1> %mask, <8 x i32>* %addr, <8 x i32> %dst) {
; AVX1-LABEL: test11b:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm2 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX1-NEXT:    vpslld $31, %xmm2, %xmm2
; AVX1-NEXT:    vpsrad $31, %xmm2, %xmm2
; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
; AVX1-NEXT:    vpslld $31, %xmm0, %xmm0
; AVX1-NEXT:    vpsrad $31, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
; AVX1-NEXT:    vmaskmovps (%rdi), %ymm0, %ymm2
; AVX1-NEXT:    vblendvps %ymm0, %ymm2, %ymm1, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test11b:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT:    vpslld $31, %ymm0, %ymm0
; AVX2-NEXT:    vpsrad $31, %ymm0, %ymm0
; AVX2-NEXT:    vpmaskmovd (%rdi), %ymm0, %ymm2
; AVX2-NEXT:    vblendvps %ymm0, %ymm2, %ymm1, %ymm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test11b:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    ## kill: %ymm1<def> %ymm1<kill> %zmm1<def>
; AVX512F-NEXT:    vpmovsxwq %xmm0, %zmm0
; AVX512F-NEXT:    vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT:    vptestmq %zmm0, %zmm0, %k1
; AVX512F-NEXT:    vpblendmd (%rdi), %zmm1, %zmm0 {%k1}
; AVX512F-NEXT:    ## kill: %ymm0<def> %ymm0<kill> %zmm0<kill>
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test11b:
; SKX:       ## BB#0:
; SKX-NEXT:    vpsllw $15, %xmm0, %xmm0
; SKX-NEXT:    vpmovw2m %xmm0, %k1
; SKX-NEXT:    vpblendmd (%rdi), %ymm1, %ymm0 {%k1}
; SKX-NEXT:    retq
  %res = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* %addr, i32 4, <8 x i1>%mask, <8 x i32>%dst)
  ret <8 x i32> %res
}

define <8 x float> @test11c(<8 x i1> %mask, <8 x float>* %addr) {
; AVX1-LABEL: test11c:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX1-NEXT:    vpslld $31, %xmm1, %xmm1
; AVX1-NEXT:    vpsrad $31, %xmm1, %xmm1
; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
; AVX1-NEXT:    vpslld $31, %xmm0, %xmm0
; AVX1-NEXT:    vpsrad $31, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT:    vmaskmovps (%rdi), %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test11c:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT:    vpslld $31, %ymm0, %ymm0
; AVX2-NEXT:    vpsrad $31, %ymm0, %ymm0
; AVX2-NEXT:    vmaskmovps (%rdi), %ymm0, %ymm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test11c:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpmovsxwq %xmm0, %zmm0
; AVX512F-NEXT:    vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT:    vptestmq %zmm0, %zmm0, %k1
; AVX512F-NEXT:    vmovups (%rdi), %zmm0 {%k1} {z}
; AVX512F-NEXT:    ## kill: %ymm0<def> %ymm0<kill> %zmm0<kill>
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test11c:
; SKX:       ## BB#0:
; SKX-NEXT:    vpsllw $15, %xmm0, %xmm0
; SKX-NEXT:    vpmovw2m %xmm0, %k1
; SKX-NEXT:    vmovaps (%rdi), %ymm0 {%k1} {z}
; SKX-NEXT:    retq
  %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 32, <8 x i1> %mask, <8 x float> zeroinitializer)
  ret <8 x float> %res
}

define <8 x i32> @test11d(<8 x i1> %mask, <8 x i32>* %addr) {
; AVX1-LABEL: test11d:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX1-NEXT:    vpslld $31, %xmm1, %xmm1
; AVX1-NEXT:    vpsrad $31, %xmm1, %xmm1
; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
; AVX1-NEXT:    vpslld $31, %xmm0, %xmm0
; AVX1-NEXT:    vpsrad $31, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT:    vmaskmovps (%rdi), %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test11d:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT:    vpslld $31, %ymm0, %ymm0
; AVX2-NEXT:    vpsrad $31, %ymm0, %ymm0
; AVX2-NEXT:    vpmaskmovd (%rdi), %ymm0, %ymm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test11d:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpmovsxwq %xmm0, %zmm0
; AVX512F-NEXT:    vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT:    vptestmq %zmm0, %zmm0, %k1
; AVX512F-NEXT:    vmovdqu32 (%rdi), %zmm0 {%k1} {z}
; AVX512F-NEXT:    ## kill: %ymm0<def> %ymm0<kill> %zmm0<kill>
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test11d:
; SKX:       ## BB#0:
; SKX-NEXT:    vpsllw $15, %xmm0, %xmm0
; SKX-NEXT:    vpmovw2m %xmm0, %k1
; SKX-NEXT:    vmovdqu32 (%rdi), %ymm0 {%k1} {z}
; SKX-NEXT:    retq
  %res = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* %addr, i32 4, <8 x i1> %mask, <8 x i32> zeroinitializer)
  ret <8 x i32> %res
}

define void @test12(<8 x i32> %trigger, <8 x i32>* %addr, <8 x i32> %val) {
; AVX1-LABEL: test12:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT:    vpcmpeqd %xmm3, %xmm2, %xmm2
; AVX1-NEXT:    vpcmpeqd %xmm3, %xmm0, %xmm0
; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT:    vmaskmovps %ymm1, %ymm0, (%rdi)
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test12:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT:    vpcmpeqd %ymm2, %ymm0, %ymm0
; AVX2-NEXT:    vpmaskmovd %ymm1, %ymm0, (%rdi)
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test12:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    ## kill: %ymm1<def> %ymm1<kill> %zmm1<def>
; AVX512F-NEXT:    ## kill: %ymm0<def> %ymm0<kill> %zmm0<def>
; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT:    vpcmpeqd %zmm2, %zmm0, %k0
; AVX512F-NEXT:    kshiftlw $8, %k0, %k0
; AVX512F-NEXT:    kshiftrw $8, %k0, %k1
; AVX512F-NEXT:    vmovdqu32 %zmm1, (%rdi) {%k1}
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test12:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT:    vpcmpeqd %ymm2, %ymm0, %k1
; SKX-NEXT:    vmovdqu32 %ymm1, (%rdi) {%k1}
; SKX-NEXT:    vzeroupper
; SKX-NEXT:    retq
  %mask = icmp eq <8 x i32> %trigger, zeroinitializer
  call void @llvm.masked.store.v8i32.p0v8i32(<8 x i32>%val, <8 x i32>* %addr, i32 4, <8 x i1>%mask)
  ret void
}

define void @test14(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %val) {
; AVX1-LABEL: test14:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm2[2,3],xmm0[4,5],xmm2[6,7]
; AVX1-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX1-NEXT:    vmaskmovps %xmm1, %xmm0, (%rdi)
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test14:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; AVX2-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX2-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX2-NEXT:    vmaskmovps %xmm1, %xmm0, (%rdi)
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test14:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; AVX512F-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX512F-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX512F-NEXT:    vmaskmovps %xmm1, %xmm0, (%rdi)
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test14:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; SKX-NEXT:    vpcmpeqq %xmm2, %xmm0, %k1
; SKX-NEXT:    vmovups %xmm1, (%rdi) {%k1}
; SKX-NEXT:    retq
  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
  call void @llvm.masked.store.v2f32.p0v2f32(<2 x float>%val, <2 x float>* %addr, i32 4, <2 x i1>%mask)
  ret void
}

define void @test15(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %val) {
; AVX1-LABEL: test15:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm2[2,3],xmm0[4,5],xmm2[6,7]
; AVX1-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX1-NEXT:    vmaskmovps %xmm1, %xmm0, (%rdi)
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test15:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; AVX2-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX2-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX2-NEXT:    vpmaskmovd %xmm1, %xmm0, (%rdi)
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test15:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; AVX512F-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX512F-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX512F-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX512F-NEXT:    vpmaskmovd %xmm1, %xmm0, (%rdi)
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test15:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; SKX-NEXT:    vpcmpeqq %xmm2, %xmm0, %k1
; SKX-NEXT:    vpmovqd %xmm1, (%rdi) {%k1}
; SKX-NEXT:    retq
  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
  call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>%val, <2 x i32>* %addr, i32 4, <2 x i1>%mask)
  ret void
}

define <2 x float> @test16(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %dst) {
; AVX1-LABEL: test16:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm2[2,3],xmm0[4,5],xmm2[6,7]
; AVX1-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX1-NEXT:    vmaskmovps (%rdi), %xmm0, %xmm2
; AVX1-NEXT:    vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test16:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; AVX2-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX2-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX2-NEXT:    vmaskmovps (%rdi), %xmm0, %xmm2
; AVX2-NEXT:    vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test16:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; AVX512F-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX512F-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX512F-NEXT:    vmaskmovps (%rdi), %xmm0, %xmm2
; AVX512F-NEXT:    vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test16:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; SKX-NEXT:    vpcmpeqq %xmm2, %xmm0, %k1
; SKX-NEXT:    vblendmps (%rdi), %xmm1, %xmm0 {%k1}
; SKX-NEXT:    retq
  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
  %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>%dst)
  ret <2 x float> %res
}

define <2 x i32> @test17(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %dst) {
; AVX1-LABEL: test17:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm2[2,3],xmm0[4,5],xmm2[6,7]
; AVX1-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX1-NEXT:    vmaskmovps (%rdi), %xmm0, %xmm2
; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX1-NEXT:    vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; AVX1-NEXT:    vpmovsxdq %xmm0, %xmm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test17:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; AVX2-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX2-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX2-NEXT:    vpmaskmovd (%rdi), %xmm0, %xmm2
; AVX2-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX2-NEXT:    vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; AVX2-NEXT:    vpmovsxdq %xmm0, %xmm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test17:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; AVX512F-NEXT:    vpcmpeqq %xmm2, %xmm0, %xmm0
; AVX512F-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX512F-NEXT:    vpmaskmovd (%rdi), %xmm0, %xmm2
; AVX512F-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX512F-NEXT:    vblendvps %xmm0, %xmm2, %xmm1, %xmm0
; AVX512F-NEXT:    vpmovsxdq %xmm0, %xmm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test17:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; SKX-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2],xmm2[3]
; SKX-NEXT:    vpcmpeqq %xmm2, %xmm0, %k1
; SKX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm1[0,2,2,3]
; SKX-NEXT:    vmovdqu32 (%rdi), %xmm0 {%k1}
; SKX-NEXT:    vpmovsxdq %xmm0, %xmm0
; SKX-NEXT:    retq
  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
  %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1>%mask, <2 x i32>%dst)
  ret <2 x i32> %res
}

define <2 x float> @test18(<2 x i32> %trigger, <2 x float>* %addr) {
; AVX1-LABEL: test18:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; AVX1-NEXT:    vpcmpeqq %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX1-NEXT:    vmaskmovps (%rdi), %xmm0, %xmm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test18:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
; AVX2-NEXT:    vpcmpeqq %xmm1, %xmm0, %xmm0
; AVX2-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX2-NEXT:    vmaskmovps (%rdi), %xmm0, %xmm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test18:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX512F-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
; AVX512F-NEXT:    vpcmpeqq %xmm1, %xmm0, %xmm0
; AVX512F-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
; AVX512F-NEXT:    vmaskmovps (%rdi), %xmm0, %xmm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test18:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; SKX-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
; SKX-NEXT:    vpcmpeqq %xmm1, %xmm0, %k1
; SKX-NEXT:    vmovups (%rdi), %xmm0 {%k1} {z}
; SKX-NEXT:    retq
  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
  %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>undef)
  ret <2 x float> %res
}

define <4 x float> @load_all(<4 x i32> %trigger, <4 x float>* %addr) {
; AVX-LABEL: load_all:
; AVX:       ## BB#0:
; AVX-NEXT:    vmovups (%rdi), %xmm0
; AVX-NEXT:    retq
;
; AVX512F-LABEL: load_all:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
; AVX512F-NEXT:    vmaskmovps (%rdi), %xmm0, %xmm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: load_all:
; SKX:       ## BB#0:
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    vmovups (%rdi), %xmm0 {%k1} {z}
; SKX-NEXT:    retq
  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
  %res = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %addr, i32 4, <4 x i1><i1 true, i1 true, i1 true, i1 true>, <4 x float>undef)
  ret <4 x float> %res
}

;;; Loads with Constant Masks - these should be optimized to use something other than a variable blend.

; 128-bit FP vectors are supported with AVX.

define <4 x float> @mload_constmask_v4f32(<4 x float>* %addr, <4 x float> %dst) {
; AVX-LABEL: mload_constmask_v4f32:
; AVX:       ## BB#0:
; AVX-NEXT:    vblendps {{.*#+}} xmm0 = mem[0],xmm0[1],mem[2,3]
; AVX-NEXT:    retq
;
; AVX512F-LABEL: mload_constmask_v4f32:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vmovaps {{.*#+}} xmm1 = [4294967295,0,4294967295,4294967295]
; AVX512F-NEXT:    vmaskmovps (%rdi), %xmm1, %xmm2
; AVX512F-NEXT:    vblendvps %xmm1, %xmm2, %xmm0, %xmm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: mload_constmask_v4f32:
; SKX:       ## BB#0:
; SKX-NEXT:    movb $13, %al
; SKX-NEXT:    kmovd %eax, %k1
; SKX-NEXT:    vmovups (%rdi), %xmm0 {%k1}
; SKX-NEXT:    retq
  %res = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %addr, i32 4, <4 x i1> <i1 1, i1 0, i1 1, i1 1>, <4 x float> %dst)
  ret <4 x float> %res
}

; 128-bit integer vectors are supported with AVX2.

define <4 x i32> @mload_constmask_v4i32(<4 x i32>* %addr, <4 x i32> %dst) {
; AVX1-LABEL: mload_constmask_v4i32:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vmovaps {{.*#+}} xmm1 = [0,4294967295,4294967295,4294967295]
; AVX1-NEXT:    vmaskmovps (%rdi), %xmm1, %xmm1
; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5,6,7]
; AVX1-NEXT:    retq
;
; AVX2-LABEL: mload_constmask_v4i32:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [0,4294967295,4294967295,4294967295]
; AVX2-NEXT:    vpmaskmovd (%rdi), %xmm1, %xmm1
; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1,2,3]
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: mload_constmask_v4i32:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vmovdqa {{.*#+}} xmm1 = [0,4294967295,4294967295,4294967295]
; AVX512F-NEXT:    vpmaskmovd (%rdi), %xmm1, %xmm2
; AVX512F-NEXT:    vblendvps %xmm1, %xmm2, %xmm0, %xmm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: mload_constmask_v4i32:
; SKX:       ## BB#0:
; SKX-NEXT:    movb $14, %al
; SKX-NEXT:    kmovd %eax, %k1
; SKX-NEXT:    vmovdqu32 (%rdi), %xmm0 {%k1}
; SKX-NEXT:    retq
  %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> <i1 0, i1 1, i1 1, i1 1>, <4 x i32> %dst)
  ret <4 x i32> %res
}

; 256-bit FP vectors are supported with AVX.

define <8 x float> @mload_constmask_v8f32(<8 x float>* %addr, <8 x float> %dst) {
; AVX-LABEL: mload_constmask_v8f32:
; AVX:       ## BB#0:
; AVX-NEXT:    vmovaps {{.*#+}} ymm1 = [4294967295,4294967295,4294967295,0,0,0,0,0]
; AVX-NEXT:    vmaskmovps (%rdi), %ymm1, %ymm1
; AVX-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0,1,2],ymm0[3,4,5,6,7]
; AVX-NEXT:    retq
;
; AVX512F-LABEL: mload_constmask_v8f32:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    ## kill: %ymm0<def> %ymm0<kill> %zmm0<def>
; AVX512F-NEXT:    movw $7, %ax
; AVX512F-NEXT:    kmovw %eax, %k1
; AVX512F-NEXT:    vmovups (%rdi), %zmm0 {%k1}
; AVX512F-NEXT:    ## kill: %ymm0<def> %ymm0<kill> %zmm0<kill>
; AVX512F-NEXT:    retq
;
; SKX-LABEL: mload_constmask_v8f32:
; SKX:       ## BB#0:
; SKX-NEXT:    movb $7, %al
; SKX-NEXT:    kmovd %eax, %k1
; SKX-NEXT:    vmovups (%rdi), %ymm0 {%k1}
; SKX-NEXT:    retq
  %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> <i1 1, i1 1, i1 1, i1 0, i1 0, i1 0, i1 0, i1 0>, <8 x float> %dst)
  ret <8 x float> %res
}

define <4 x double> @mload_constmask_v4f64(<4 x double>* %addr, <4 x double> %dst) {
; AVX-LABEL: mload_constmask_v4f64:
; AVX:       ## BB#0:
; AVX-NEXT:    vmovapd {{.*#+}} ymm1 = [18446744073709551615,18446744073709551615,18446744073709551615,0]
; AVX-NEXT:    vmaskmovpd (%rdi), %ymm1, %ymm1
; AVX-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0,1,2],ymm0[3]
; AVX-NEXT:    retq
;
; AVX512F-LABEL: mload_constmask_v4f64:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vmovapd {{.*#+}} ymm1 = [18446744073709551615,18446744073709551615,18446744073709551615,0]
; AVX512F-NEXT:    vmaskmovpd (%rdi), %ymm1, %ymm2
; AVX512F-NEXT:    vblendvpd %ymm1, %ymm2, %ymm0, %ymm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: mload_constmask_v4f64:
; SKX:       ## BB#0:
; SKX-NEXT:    movb $7, %al
; SKX-NEXT:    kmovd %eax, %k1
; SKX-NEXT:    vmovupd (%rdi), %ymm0 {%k1}
; SKX-NEXT:    retq
  %res = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* %addr, i32 4, <4 x i1> <i1 1, i1 1, i1 1, i1 0>, <4 x double> %dst)
  ret <4 x double> %res
}

; 256-bit integer vectors are supported with AVX2.

define <8 x i32> @mload_constmask_v8i32(<8 x i32>* %addr, <8 x i32> %dst) {
; AVX-LABEL: mload_constmask_v8i32:
; AVX:       ## BB#0:
; AVX-NEXT:    vblendps {{.*#+}} ymm0 = mem[0,1,2],ymm0[3,4,5,6],mem[7]
; AVX-NEXT:    retq
;
; AVX512F-LABEL: mload_constmask_v8i32:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    ## kill: %ymm0<def> %ymm0<kill> %zmm0<def>
; AVX512F-NEXT:    movw $135, %ax
; AVX512F-NEXT:    kmovw %eax, %k1
; AVX512F-NEXT:    vmovdqu32 (%rdi), %zmm0 {%k1}
; AVX512F-NEXT:    ## kill: %ymm0<def> %ymm0<kill> %zmm0<kill>
; AVX512F-NEXT:    retq
;
; SKX-LABEL: mload_constmask_v8i32:
; SKX:       ## BB#0:
; SKX-NEXT:    movb $-121, %al
; SKX-NEXT:    kmovd %eax, %k1
; SKX-NEXT:    vmovdqu32 (%rdi), %ymm0 {%k1}
; SKX-NEXT:    retq
  %res = call <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>* %addr, i32 4, <8 x i1> <i1 1, i1 1, i1 1, i1 0, i1 0, i1 0, i1 0, i1 1>, <8 x i32> %dst)
  ret <8 x i32> %res
}

define <4 x i64> @mload_constmask_v4i64(<4 x i64>* %addr, <4 x i64> %dst) {
; AVX1-LABEL: mload_constmask_v4i64:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = mem[0],ymm0[1,2],mem[3]
; AVX1-NEXT:    retq
;
; AVX2-LABEL: mload_constmask_v4i64:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vblendps {{.*#+}} ymm0 = mem[0,1],ymm0[2,3,4,5],mem[6,7]
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: mload_constmask_v4i64:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm1 = [18446744073709551615,0,0,18446744073709551615]
; AVX512F-NEXT:    vpmaskmovq (%rdi), %ymm1, %ymm2
; AVX512F-NEXT:    vblendvpd %ymm1, %ymm2, %ymm0, %ymm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: mload_constmask_v4i64:
; SKX:       ## BB#0:
; SKX-NEXT:    movb $9, %al
; SKX-NEXT:    kmovd %eax, %k1
; SKX-NEXT:    vmovdqu64 (%rdi), %ymm0 {%k1}
; SKX-NEXT:    retq
  %res = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* %addr, i32 4, <4 x i1> <i1 1, i1 0, i1 0, i1 1>, <4 x i64> %dst)
  ret <4 x i64> %res
}

; 512-bit FP vectors are supported with AVX512.

define <8 x double> @mload_constmask_v8f64(<8 x double>* %addr, <8 x double> %dst) {
; AVX-LABEL: mload_constmask_v8f64:
; AVX:       ## BB#0:
; AVX-NEXT:    vblendpd {{.*#+}} ymm1 = ymm1[0,1,2],mem[3]
; AVX-NEXT:    vblendpd {{.*#+}} ymm0 = mem[0,1,2],ymm0[3]
; AVX-NEXT:    retq
;
; AVX512F-LABEL: mload_constmask_v8f64:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    movb $-121, %al
; AVX512F-NEXT:    kmovw %eax, %k1
; AVX512F-NEXT:    vmovupd (%rdi), %zmm0 {%k1}
; AVX512F-NEXT:    retq
;
; SKX-LABEL: mload_constmask_v8f64:
; SKX:       ## BB#0:
; SKX-NEXT:    movb $-121, %al
; SKX-NEXT:    kmovd %eax, %k1
; SKX-NEXT:    vmovupd (%rdi), %zmm0 {%k1}
; SKX-NEXT:    retq
  %res = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* %addr, i32 4, <8 x i1> <i1 1, i1 1, i1 1, i1 0, i1 0, i1 0, i1 0, i1 1>, <8 x double> %dst)
  ret <8 x double> %res
}

; If the pass-through operand is undef, no blend is needed.

define <4 x double> @mload_constmask_v4f64_undef_passthrough(<4 x double>* %addr) {
; AVX-LABEL: mload_constmask_v4f64_undef_passthrough:
; AVX:       ## BB#0:
; AVX-NEXT:    vmovapd {{.*#+}} ymm0 = [18446744073709551615,18446744073709551615,18446744073709551615,0]
; AVX-NEXT:    vmaskmovpd (%rdi), %ymm0, %ymm0
; AVX-NEXT:    retq
;
; AVX512F-LABEL: mload_constmask_v4f64_undef_passthrough:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vmovapd {{.*#+}} ymm0 = [18446744073709551615,18446744073709551615,18446744073709551615,0]
; AVX512F-NEXT:    vmaskmovpd (%rdi), %ymm0, %ymm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: mload_constmask_v4f64_undef_passthrough:
; SKX:       ## BB#0:
; SKX-NEXT:    movb $7, %al
; SKX-NEXT:    kmovd %eax, %k1
; SKX-NEXT:    vmovupd (%rdi), %ymm0 {%k1} {z}
; SKX-NEXT:    retq
  %res = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* %addr, i32 4, <4 x i1> <i1 1, i1 1, i1 1, i1 0>, <4 x double> undef)
  ret <4 x double> %res
}

define <4 x i64> @mload_constmask_v4i64_undef_passthrough(<4 x i64>* %addr) {
; AVX1-LABEL: mload_constmask_v4i64_undef_passthrough:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vmovapd {{.*#+}} ymm0 = [0,18446744073709551615,18446744073709551615,0]
; AVX1-NEXT:    vmaskmovpd (%rdi), %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: mload_constmask_v4i64_undef_passthrough:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vmovdqa {{.*#+}} ymm0 = [0,18446744073709551615,18446744073709551615,0]
; AVX2-NEXT:    vpmaskmovq (%rdi), %ymm0, %ymm0
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: mload_constmask_v4i64_undef_passthrough:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm0 = [0,18446744073709551615,18446744073709551615,0]
; AVX512F-NEXT:    vpmaskmovq (%rdi), %ymm0, %ymm0
; AVX512F-NEXT:    retq
;
; SKX-LABEL: mload_constmask_v4i64_undef_passthrough:
; SKX:       ## BB#0:
; SKX-NEXT:    movb $6, %al
; SKX-NEXT:    kmovd %eax, %k1
; SKX-NEXT:    vmovdqu64 (%rdi), %ymm0 {%k1} {z}
; SKX-NEXT:    retq
  %res = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* %addr, i32 4, <4 x i1> <i1 0, i1 1, i1 1, i1 0>, <4 x i64> undef)
  ret <4 x i64> %res
}

define void @test21(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
; AVX1-LABEL: test21:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
; AVX1-NEXT:    vmaskmovps %xmm1, %xmm0, (%rdi)
; AVX1-NEXT:    retq
;
; AVX2-LABEL: test21:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
; AVX2-NEXT:    vpmaskmovd %xmm1, %xmm0, (%rdi)
; AVX2-NEXT:    retq
;
; AVX512F-LABEL: test21:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
; AVX512F-NEXT:    vpmaskmovd %xmm1, %xmm0, (%rdi)
; AVX512F-NEXT:    retq
;
; SKX-LABEL: test21:
; SKX:       ## BB#0:
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    vmovdqu32 %xmm1, (%rdi) {%k1}
; SKX-NEXT:    retq
  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1><i1 true, i1 true, i1 true, i1 true>)
  ret void
}

;  When only one element of the mask is set, reduce to a scalar store.

define void @one_mask_bit_set1(<4 x i32>* %addr, <4 x i32> %val) {
; AVX-LABEL: one_mask_bit_set1:
; AVX:       ## BB#0:
; AVX-NEXT:    vmovss %xmm0, (%rdi)
; AVX-NEXT:    retq
;
; AVX512-LABEL: one_mask_bit_set1:
; AVX512:       ## BB#0:
; AVX512-NEXT:    vmovss %xmm0, (%rdi)
; AVX512-NEXT:    retq
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1><i1 true, i1 false, i1 false, i1 false>)
  ret void
}

; Choose a different element to show that the correct address offset is produced.

define void @one_mask_bit_set2(<4 x float>* %addr, <4 x float> %val) {
; AVX-LABEL: one_mask_bit_set2:
; AVX:       ## BB#0:
; AVX-NEXT:    vextractps $2, %xmm0, 8(%rdi)
; AVX-NEXT:    retq
;
; AVX512-LABEL: one_mask_bit_set2:
; AVX512:       ## BB#0:
; AVX512-NEXT:    vextractps $2, %xmm0, 8(%rdi)
; AVX512-NEXT:    retq
  call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> %val, <4 x float>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>)
  ret void
}

; Choose a different scalar type and a high element of a 256-bit vector because AVX doesn't support those evenly.

define void @one_mask_bit_set3(<4 x i64>* %addr, <4 x i64> %val) {
; AVX-LABEL: one_mask_bit_set3:
; AVX:       ## BB#0:
; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm0
; AVX-NEXT:    vmovlps %xmm0, 16(%rdi)
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    retq
;
; AVX512-LABEL: one_mask_bit_set3:
; AVX512:       ## BB#0:
; AVX512-NEXT:    vextractf128 $1, %ymm0, %xmm0
; AVX512-NEXT:    vmovlps %xmm0, 16(%rdi)
; AVX512-NEXT:    vzeroupper
; AVX512-NEXT:    retq
  call void @llvm.masked.store.v4i64.p0v4i64(<4 x i64> %val, <4 x i64>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>)
  ret void
}

; Choose a different scalar type and a high element of a 256-bit vector because AVX doesn't support those evenly.

define void @one_mask_bit_set4(<4 x double>* %addr, <4 x double> %val) {
; AVX-LABEL: one_mask_bit_set4:
; AVX:       ## BB#0:
; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm0
; AVX-NEXT:    vmovhpd %xmm0, 24(%rdi)
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    retq
;
; AVX512-LABEL: one_mask_bit_set4:
; AVX512:       ## BB#0:
; AVX512-NEXT:    vextractf128 $1, %ymm0, %xmm0
; AVX512-NEXT:    vmovhpd %xmm0, 24(%rdi)
; AVX512-NEXT:    vzeroupper
; AVX512-NEXT:    retq
  call void @llvm.masked.store.v4f64.p0v4f64(<4 x double> %val, <4 x double>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 false, i1 true>)
  ret void
}

; Try a 512-bit vector to make sure AVX doesn't die and AVX512 works as expected.

define void @one_mask_bit_set5(<8 x double>* %addr, <8 x double> %val) {
; AVX-LABEL: one_mask_bit_set5:
; AVX:       ## BB#0:
; AVX-NEXT:    vextractf128 $1, %ymm1, %xmm0
; AVX-NEXT:    vmovlps %xmm0, 48(%rdi)
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    retq
;
; AVX512-LABEL: one_mask_bit_set5:
; AVX512:       ## BB#0:
; AVX512-NEXT:    vextractf32x4 $3, %zmm0, %xmm0
; AVX512-NEXT:    vmovlps %xmm0, 48(%rdi)
; AVX512-NEXT:    vzeroupper
; AVX512-NEXT:    retq
  call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> %val, <8 x double>* %addr, i32 4, <8 x i1><i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 true, i1 false>)
  ret void
}

;  When only one element of the mask is set, reduce to a scalar load.

define <4 x i32> @load_one_mask_bit_set1(<4 x i32>* %addr, <4 x i32> %val) {
; AVX-LABEL: load_one_mask_bit_set1:
; AVX:       ## BB#0:
; AVX-NEXT:    vpinsrd $0, (%rdi), %xmm0, %xmm0
; AVX-NEXT:    retq
;
; AVX512-LABEL: load_one_mask_bit_set1:
; AVX512:       ## BB#0:
; AVX512-NEXT:    vpinsrd $0, (%rdi), %xmm0, %xmm0
; AVX512-NEXT:    retq
  %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1><i1 true, i1 false, i1 false, i1 false>, <4 x i32> %val)
  ret <4 x i32> %res
}

; Choose a different element to show that the correct address offset is produced.

define <4 x float> @load_one_mask_bit_set2(<4 x float>* %addr, <4 x float> %val) {
; AVX-LABEL: load_one_mask_bit_set2:
; AVX:       ## BB#0:
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    retq
;
; AVX512-LABEL: load_one_mask_bit_set2:
; AVX512:       ## BB#0:
; AVX512-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX512-NEXT:    retq
  %res = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>, <4 x float> %val)
  ret <4 x float> %res
}

; Choose a different scalar type and a high element of a 256-bit vector because AVX doesn't support those evenly.

define <4 x i64> @load_one_mask_bit_set3(<4 x i64>* %addr, <4 x i64> %val) {
; AVX1-LABEL: load_one_mask_bit_set3:
; AVX1:       ## BB#0:
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT:    vpinsrq $0, 16(%rdi), %xmm1, %xmm1
; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: load_one_mask_bit_set3:
; AVX2:       ## BB#0:
; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT:    vpinsrq $0, 16(%rdi), %xmm1, %xmm1
; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT:    retq
;
; AVX512-LABEL: load_one_mask_bit_set3:
; AVX512:       ## BB#0:
; AVX512-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX512-NEXT:    vpinsrq $0, 16(%rdi), %xmm1, %xmm1
; AVX512-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512-NEXT:    retq
  %res = call <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 true, i1 false>, <4 x i64> %val)
  ret <4 x i64> %res
}

; Choose a different scalar type and a high element of a 256-bit vector because AVX doesn't support those evenly.

define <4 x double> @load_one_mask_bit_set4(<4 x double>* %addr, <4 x double> %val) {
; AVX-LABEL: load_one_mask_bit_set4:
; AVX:       ## BB#0:
; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm1
; AVX-NEXT:    vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX-NEXT:    retq
;
; AVX512-LABEL: load_one_mask_bit_set4:
; AVX512:       ## BB#0:
; AVX512-NEXT:    vextractf128 $1, %ymm0, %xmm1
; AVX512-NEXT:    vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
; AVX512-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX512-NEXT:    retq
  %res = call <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>* %addr, i32 4, <4 x i1><i1 false, i1 false, i1 false, i1 true>, <4 x double> %val)
  ret <4 x double> %res
}

; Try a 512-bit vector to make sure AVX doesn't die and AVX512 works as expected.

define <8 x double> @load_one_mask_bit_set5(<8 x double>* %addr, <8 x double> %val) {
; AVX-LABEL: load_one_mask_bit_set5:
; AVX:       ## BB#0:
; AVX-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX-NEXT:    vmovsd {{.*#+}} xmm3 = mem[0],zero
; AVX-NEXT:    vmovlhps {{.*#+}} xmm2 = xmm2[0],xmm3[0]
; AVX-NEXT:    vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX-NEXT:    retq
;
; AVX512-LABEL: load_one_mask_bit_set5:
; AVX512:       ## BB#0:
; AVX512-NEXT:    vextractf32x4 $3, %zmm0, %xmm1
; AVX512-NEXT:    vmovhpd {{.*#+}} xmm1 = xmm1[0],mem[0]
; AVX512-NEXT:    vinsertf32x4 $3, %xmm1, %zmm0, %zmm0
; AVX512-NEXT:    retq
  %res = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* %addr, i32 4, <8 x i1><i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 true>, <8 x double> %val)
  ret <8 x double> %res
}

; The mask bit for each data element is the most significant bit of the mask operand, so a compare isn't needed.
; FIXME: The AVX512 code should be improved to use 'vpmovd2m'. Add tests for 512-bit vectors when implementing that.

define void @trunc_mask(<4 x float> %x, <4 x float>* %ptr, <4 x float> %y, <4 x i32> %mask) {
; AVX-LABEL: trunc_mask:
; AVX:       ## BB#0:
; AVX-NEXT:    vmaskmovps %xmm0, %xmm2, (%rdi)
; AVX-NEXT:    retq
;
; AVX512F-LABEL: trunc_mask:
; AVX512F:       ## BB#0:
; AVX512F-NEXT:    vmaskmovps %xmm0, %xmm2, (%rdi)
; AVX512F-NEXT:    retq
;
; SKX-LABEL: trunc_mask:
; SKX:       ## BB#0:
; SKX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; SKX-NEXT:    vpcmpgtd %xmm2, %xmm1, %k1
; SKX-NEXT:    vmovups %xmm0, (%rdi) {%k1}
; SKX-NEXT:    retq
  %bool_mask = icmp slt <4 x i32> %mask, zeroinitializer
  call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> %x, <4 x float>* %ptr, i32 1, <4 x i1> %bool_mask)
  ret void
}

declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
declare <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
declare <4 x i64> @llvm.masked.load.v4i64.p0v4i64(<4 x i64>*, i32, <4 x i1>, <4 x i64>)
declare void @llvm.masked.store.v8i32.p0v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
declare void @llvm.masked.store.v4i64.p0v4i64(<4 x i64>, <4 x i64>*, i32, <4 x i1>)
declare void @llvm.masked.store.v2f32.p0v2f32(<2 x float>, <2 x float>*, i32, <2 x i1>)
declare void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>, <2 x i32>*, i32, <2 x i1>)
declare void @llvm.masked.store.v4f32.p0v4f32(<4 x float>, <4 x float>*, i32, <4 x i1>)
declare <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>*, i32, <8 x i1>, <8 x float>)
declare <8 x i32> @llvm.masked.load.v8i32.p0v8i32(<8 x i32>*, i32, <8 x i1>, <8 x i32>)
declare <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>*, i32, <4 x i1>, <4 x float>)
declare <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>*, i32, <2 x i1>, <2 x float>)
declare <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>*, i32, <8 x i1>, <8 x double>)
declare <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>*, i32, <4 x i1>, <4 x double>)
declare <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>*, i32, <2 x i1>, <2 x double>)
declare void @llvm.masked.store.v8f64.p0v8f64(<8 x double>, <8 x double>*, i32, <8 x i1>)
declare void @llvm.masked.store.v4f64.p0v4f64(<4 x double>, <4 x double>*, i32, <4 x i1>)
declare void @llvm.masked.store.v2f64.p0v2f64(<2 x double>, <2 x double>*, i32, <2 x i1>)
declare void @llvm.masked.store.v2i64.p0v2i64(<2 x i64>, <2 x i64>*, i32, <2 x i1>)