test/CodeGen/X86/masked_gather_scatter.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-unknown-linux-gnu  -mattr=+avx512f < %s | FileCheck %s --check-prefix=ALL --check-prefix=KNL_64
; RUN: llc -mtriple=i386-unknown-linux-gnu  -mattr=+avx512f < %s | FileCheck %s --check-prefix=ALL --check-prefix=KNL_32
; RUN: llc -mtriple=x86_64-unknown-linux-gnu  -mattr=+avx512vl -mattr=+avx512dq < %s | FileCheck %s --check-prefix=ALL --check-prefix=SKX --check-prefix=SKX_SMALL
; RUN: llc -mtriple=x86_64-unknown-linux-gnu  -mattr=+avx512vl -mattr=+avx512dq -code-model=large < %s | FileCheck %s --check-prefix=ALL --check-prefix=SKX --check-prefix=SKX_LARGE
; RUN: llc -mtriple=i386-unknown-linux-gnu  -mattr=+avx512vl -mattr=+avx512dq < %s | FileCheck %s --check-prefix=ALL --check-prefix=SKX_32
; RUN: opt -mtriple=x86_64-apple-darwin -scalarize-masked-mem-intrin -mcpu=corei7-avx -S < %s | FileCheck %s -check-prefix=SCALAR
; RUN: llc -O0 -mtriple=x86_64-unknown-linux-gnu -mcpu=skx < %s -o /dev/null

@glob_array = internal unnamed_addr constant [16 x i32] [i32 1, i32 1, i32 2, i32 3, i32 5, i32 8, i32 13, i32 21, i32 34, i32 55, i32 89, i32 144, i32 233, i32 377, i32 610, i32 987], align 16

; SCALAR-LABEL: test1
; SCALAR:      extractelement <16 x float*>
; SCALAR-NEXT: load float
; SCALAR-NEXT: insertelement <16 x float>
; SCALAR-NEXT: extractelement <16 x float*>
; SCALAR-NEXT: load float

define <16 x float> @test1(float* %base, <16 x i32> %ind) {
; KNL_64-LABEL: test1:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; KNL_64-NEXT:    vmovaps %zmm1, %zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test1:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    kxnorw %k0, %k0, %k1
; KNL_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; KNL_32-NEXT:    vmovaps %zmm1, %zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test1:
; SKX:       # %bb.0:
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; SKX-NEXT:    vmovaps %zmm1, %zmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test1:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; SKX_32-NEXT:    vmovaps %zmm1, %zmm0
; SKX_32-NEXT:    retl

  %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
  %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer

  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind

  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
  ret <16 x float>%res
}

declare <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*>, i32, <16 x i1>, <16 x i32>)
declare <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*>, i32, <16 x i1>, <16 x float>)
declare <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> , i32, <8 x i1> , <8 x i32> )


; SCALAR-LABEL: test2
; SCALAR:      extractelement <16 x float*>
; SCALAR-NEXT: load float
; SCALAR-NEXT: insertelement <16 x float>
; SCALAR-NEXT: br label %else
; SCALAR: else:
; SCALAR-NEXT:  %res.phi.else = phi
; SCALAR-NEXT:  %Mask1 = extractelement <16 x i1> %imask, i32 1
; SCALAR-NEXT:  br i1 %Mask1, label %cond.load1, label %else2

define <16 x float> @test2(float* %base, <16 x i32> %ind, i16 %mask) {
; KNL_64-LABEL: test2:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    kmovw %esi, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; KNL_64-NEXT:    vmovaps %zmm1, %zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test2:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    kmovw {{[0-9]+}}(%esp), %k1
; KNL_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; KNL_32-NEXT:    vmovaps %zmm1, %zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test2:
; SKX:       # %bb.0:
; SKX-NEXT:    kmovw %esi, %k1
; SKX-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; SKX-NEXT:    vmovaps %zmm1, %zmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test2:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    kmovw {{[0-9]+}}(%esp), %k1
; SKX_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; SKX_32-NEXT:    vmovaps %zmm1, %zmm0
; SKX_32-NEXT:    retl

  %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
  %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer

  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
  %imask = bitcast i16 %mask to <16 x i1>
  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> %imask, <16 x float>undef)
  ret <16 x float> %res
}

define <16 x i32> @test3(i32* %base, <16 x i32> %ind, i16 %mask) {
; KNL_64-LABEL: test3:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    kmovw %esi, %k1
; KNL_64-NEXT:    vpgatherdd (%rdi,%zmm0,4), %zmm1 {%k1}
; KNL_64-NEXT:    vmovdqa64 %zmm1, %zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test3:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    kmovw {{[0-9]+}}(%esp), %k1
; KNL_32-NEXT:    vpgatherdd (%eax,%zmm0,4), %zmm1 {%k1}
; KNL_32-NEXT:    vmovdqa64 %zmm1, %zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test3:
; SKX:       # %bb.0:
; SKX-NEXT:    kmovw %esi, %k1
; SKX-NEXT:    vpgatherdd (%rdi,%zmm0,4), %zmm1 {%k1}
; SKX-NEXT:    vmovdqa64 %zmm1, %zmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test3:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    kmovw {{[0-9]+}}(%esp), %k1
; SKX_32-NEXT:    vpgatherdd (%eax,%zmm0,4), %zmm1 {%k1}
; SKX_32-NEXT:    vmovdqa64 %zmm1, %zmm0
; SKX_32-NEXT:    retl

  %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
  %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer

  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i64> %sext_ind
  %imask = bitcast i16 %mask to <16 x i1>
  %res = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> %gep.random, i32 4, <16 x i1> %imask, <16 x i32>undef)
  ret <16 x i32> %res
}


define <16 x i32> @test4(i32* %base, <16 x i32> %ind, i16 %mask) {
; KNL_64-LABEL: test4:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    kmovw %esi, %k1
; KNL_64-NEXT:    kmovw %k1, %k2
; KNL_64-NEXT:    vpgatherdd (%rdi,%zmm0,4), %zmm1 {%k2}
; KNL_64-NEXT:    vmovdqa64 %zmm1, %zmm2
; KNL_64-NEXT:    vpgatherdd (%rdi,%zmm0,4), %zmm2 {%k1}
; KNL_64-NEXT:    vpaddd %zmm2, %zmm1, %zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test4:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    kmovw {{[0-9]+}}(%esp), %k1
; KNL_32-NEXT:    kmovw %k1, %k2
; KNL_32-NEXT:    vpgatherdd (%eax,%zmm0,4), %zmm1 {%k2}
; KNL_32-NEXT:    vmovdqa64 %zmm1, %zmm2
; KNL_32-NEXT:    vpgatherdd (%eax,%zmm0,4), %zmm2 {%k1}
; KNL_32-NEXT:    vpaddd %zmm2, %zmm1, %zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test4:
; SKX:       # %bb.0:
; SKX-NEXT:    kmovw %esi, %k1
; SKX-NEXT:    kmovw %k1, %k2
; SKX-NEXT:    vpgatherdd (%rdi,%zmm0,4), %zmm1 {%k2}
; SKX-NEXT:    vmovdqa64 %zmm1, %zmm2
; SKX-NEXT:    vpgatherdd (%rdi,%zmm0,4), %zmm2 {%k1}
; SKX-NEXT:    vpaddd %zmm2, %zmm1, %zmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test4:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    kmovw {{[0-9]+}}(%esp), %k1
; SKX_32-NEXT:    kmovw %k1, %k2
; SKX_32-NEXT:    vpgatherdd (%eax,%zmm0,4), %zmm1 {%k2}
; SKX_32-NEXT:    vmovdqa64 %zmm1, %zmm2
; SKX_32-NEXT:    vpgatherdd (%eax,%zmm0,4), %zmm2 {%k1}
; SKX_32-NEXT:    vpaddd %zmm2, %zmm1, %zmm0
; SKX_32-NEXT:    retl

  %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
  %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer

  %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
  %imask = bitcast i16 %mask to <16 x i1>
  %gt1 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> %gep.random, i32 4, <16 x i1> %imask, <16 x i32>undef)
  %gt2 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> %gep.random, i32 4, <16 x i1> %imask, <16 x i32>%gt1)
  %res = add <16 x i32> %gt1, %gt2
  ret <16 x i32> %res
}


; SCALAR-LABEL: test5
; SCALAR:        %Mask0 = extractelement <16 x i1> %imask, i32 0
; SCALAR-NEXT:   br i1 %Mask0, label %cond.store, label %else
; SCALAR: cond.store:
; SCALAR-NEXT:  %Elt0 = extractelement <16 x i32> %val, i32 0
; SCALAR-NEXT:  %Ptr0 = extractelement <16 x i32*> %gep.random, i32 0
; SCALAR-NEXT:  store i32 %Elt0, i32* %Ptr0, align 4
; SCALAR-NEXT:  br label %else
; SCALAR: else:
; SCALAR-NEXT: %Mask1 = extractelement <16 x i1> %imask, i32 1
; SCALAR-NEXT:  br i1 %Mask1, label %cond.store1, label %else2

define void @test5(i32* %base, <16 x i32> %ind, i16 %mask, <16 x i32>%val) {
; KNL_64-LABEL: test5:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    kmovw %esi, %k1
; KNL_64-NEXT:    kmovw %k1, %k2
; KNL_64-NEXT:    vpscatterdd %zmm1, (%rdi,%zmm0,4) {%k2}
; KNL_64-NEXT:    vpscatterdd %zmm1, (%rdi,%zmm0,4) {%k1}
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test5:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    kmovw {{[0-9]+}}(%esp), %k1
; KNL_32-NEXT:    kmovw %k1, %k2
; KNL_32-NEXT:    vpscatterdd %zmm1, (%eax,%zmm0,4) {%k2}
; KNL_32-NEXT:    vpscatterdd %zmm1, (%eax,%zmm0,4) {%k1}
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test5:
; SKX:       # %bb.0:
; SKX-NEXT:    kmovw %esi, %k1
; SKX-NEXT:    kmovw %k1, %k2
; SKX-NEXT:    vpscatterdd %zmm1, (%rdi,%zmm0,4) {%k2}
; SKX-NEXT:    vpscatterdd %zmm1, (%rdi,%zmm0,4) {%k1}
; SKX-NEXT:    vzeroupper
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test5:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    kmovw {{[0-9]+}}(%esp), %k1
; SKX_32-NEXT:    kmovw %k1, %k2
; SKX_32-NEXT:    vpscatterdd %zmm1, (%eax,%zmm0,4) {%k2}
; SKX_32-NEXT:    vpscatterdd %zmm1, (%eax,%zmm0,4) {%k1}
; SKX_32-NEXT:    vzeroupper
; SKX_32-NEXT:    retl

  %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
  %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer

  %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
  %imask = bitcast i16 %mask to <16 x i1>
  call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32>%val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
  call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32>%val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
  ret void
}

declare void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> , <8 x i32*> , i32 , <8 x i1> )
declare void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> , <16 x i32*> , i32 , <16 x i1> )


; SCALAR-LABEL: test6
; SCALAR:        store i32 %Elt0, i32* %Ptr01, align 4
; SCALAR-NEXT:   %Elt1 = extractelement <8 x i32> %a1, i32 1
; SCALAR-NEXT:   %Ptr12 = extractelement <8 x i32*> %ptr, i32 1
; SCALAR-NEXT:   store i32 %Elt1, i32* %Ptr12, align 4
; SCALAR-NEXT:   %Elt2 = extractelement <8 x i32> %a1, i32 2
; SCALAR-NEXT:   %Ptr23 = extractelement <8 x i32*> %ptr, i32 2
; SCALAR-NEXT:   store i32 %Elt2, i32* %Ptr23, align 4

define <8 x i32> @test6(<8 x i32>%a1, <8 x i32*> %ptr) {
; KNL_64-LABEL: test6:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    kxnorw %k0, %k0, %k2
; KNL_64-NEXT:    vpgatherqd (,%zmm1), %ymm2 {%k2}
; KNL_64-NEXT:    vpscatterqd %ymm0, (,%zmm1) {%k1}
; KNL_64-NEXT:    vmovdqa %ymm2, %ymm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test6:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $ymm1 killed $ymm1 def $zmm1
; KNL_32-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
; KNL_32-NEXT:    movw $255, %ax
; KNL_32-NEXT:    kmovw %eax, %k1
; KNL_32-NEXT:    kmovw %k1, %k2
; KNL_32-NEXT:    vpgatherdd (,%zmm1), %zmm2 {%k2}
; KNL_32-NEXT:    vpscatterdd %zmm0, (,%zmm1) {%k1}
; KNL_32-NEXT:    vmovdqa %ymm2, %ymm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test6:
; SKX:       # %bb.0:
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    kxnorw %k0, %k0, %k2
; SKX-NEXT:    vpgatherqd (,%zmm1), %ymm2 {%k2}
; SKX-NEXT:    vpscatterqd %ymm0, (,%zmm1) {%k1}
; SKX-NEXT:    vmovdqa %ymm2, %ymm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test6:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    kxnorw %k0, %k0, %k2
; SKX_32-NEXT:    vpgatherdd (,%ymm1), %ymm2 {%k2}
; SKX_32-NEXT:    vpscatterdd %ymm0, (,%ymm1) {%k1}
; SKX_32-NEXT:    vmovdqa %ymm2, %ymm0
; SKX_32-NEXT:    retl

  %a = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> %ptr, i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x i32> undef)

  call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret <8 x i32>%a
}

define <8 x i32> @test7(i32* %base, <8 x i32> %ind, i8 %mask) {
;
; KNL_64-LABEL: test7:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
; KNL_64-NEXT:    kmovw %esi, %k0
; KNL_64-NEXT:    kshiftlw $8, %k0, %k0
; KNL_64-NEXT:    kshiftrw $8, %k0, %k1
; KNL_64-NEXT:    kmovw %k1, %k2
; KNL_64-NEXT:    vpgatherdd (%rdi,%zmm0,4), %zmm1 {%k2}
; KNL_64-NEXT:    vmovdqa64 %zmm1, %zmm2
; KNL_64-NEXT:    vpgatherdd (%rdi,%zmm0,4), %zmm2 {%k1}
; KNL_64-NEXT:    vpaddd %ymm2, %ymm1, %ymm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test7:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx
; KNL_32-NEXT:    kmovw %ecx, %k0
; KNL_32-NEXT:    kshiftlw $8, %k0, %k0
; KNL_32-NEXT:    kshiftrw $8, %k0, %k1
; KNL_32-NEXT:    kmovw %k1, %k2
; KNL_32-NEXT:    vpgatherdd (%eax,%zmm0,4), %zmm1 {%k2}
; KNL_32-NEXT:    vmovdqa64 %zmm1, %zmm2
; KNL_32-NEXT:    vpgatherdd (%eax,%zmm0,4), %zmm2 {%k1}
; KNL_32-NEXT:    vpaddd %ymm2, %ymm1, %ymm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test7:
; SKX:       # %bb.0:
; SKX-NEXT:    kmovw %esi, %k1
; SKX-NEXT:    kmovw %k1, %k2
; SKX-NEXT:    vpgatherdd (%rdi,%ymm0,4), %ymm1 {%k2}
; SKX-NEXT:    vmovdqa %ymm1, %ymm2
; SKX-NEXT:    vpgatherdd (%rdi,%ymm0,4), %ymm2 {%k1}
; SKX-NEXT:    vpaddd %ymm2, %ymm1, %ymm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test7:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    kmovb {{[0-9]+}}(%esp), %k1
; SKX_32-NEXT:    kmovw %k1, %k2
; SKX_32-NEXT:    vpgatherdd (%eax,%ymm0,4), %ymm1 {%k2}
; SKX_32-NEXT:    vmovdqa %ymm1, %ymm2
; SKX_32-NEXT:    vpgatherdd (%eax,%ymm0,4), %ymm2 {%k1}
; SKX_32-NEXT:    vpaddd %ymm2, %ymm1, %ymm0
; SKX_32-NEXT:    retl

  %broadcast.splatinsert = insertelement <8 x i32*> undef, i32* %base, i32 0
  %broadcast.splat = shufflevector <8 x i32*> %broadcast.splatinsert, <8 x i32*> undef, <8 x i32> zeroinitializer

  %gep.random = getelementptr i32, <8 x i32*> %broadcast.splat, <8 x i32> %ind
  %imask = bitcast i8 %mask to <8 x i1>
  %gt1 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> %gep.random, i32 4, <8 x i1> %imask, <8 x i32>undef)
  %gt2 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> %gep.random, i32 4, <8 x i1> %imask, <8 x i32>%gt1)
  %res = add <8 x i32> %gt1, %gt2
  ret <8 x i32> %res
}

; No uniform base in this case, index <8 x i64> contains addresses,
; each gather call will be split into two
define <16 x i32> @test8(<16 x i32*> %ptr.random, <16 x i32> %ind, i16 %mask) {
; KNL_64-LABEL: test8:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    kmovw %edi, %k1
; KNL_64-NEXT:    kshiftrw $8, %k1, %k2
; KNL_64-NEXT:    kmovw %k2, %k3
; KNL_64-NEXT:    vpgatherqd (,%zmm1), %ymm2 {%k3}
; KNL_64-NEXT:    kmovw %k1, %k3
; KNL_64-NEXT:    vpgatherqd (,%zmm0), %ymm3 {%k3}
; KNL_64-NEXT:    vinserti64x4 $1, %ymm2, %zmm3, %zmm4
; KNL_64-NEXT:    vpgatherqd (,%zmm1), %ymm2 {%k2}
; KNL_64-NEXT:    vpgatherqd (,%zmm0), %ymm3 {%k1}
; KNL_64-NEXT:    vinserti64x4 $1, %ymm2, %zmm3, %zmm0
; KNL_64-NEXT:    vpaddd %zmm0, %zmm4, %zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test8:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    kmovw {{[0-9]+}}(%esp), %k1
; KNL_32-NEXT:    kmovw %k1, %k2
; KNL_32-NEXT:    vpgatherdd (,%zmm0), %zmm1 {%k2}
; KNL_32-NEXT:    vmovdqa64 %zmm1, %zmm2
; KNL_32-NEXT:    vpgatherdd (,%zmm0), %zmm2 {%k1}
; KNL_32-NEXT:    vpaddd %zmm2, %zmm1, %zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test8:
; SKX:       # %bb.0:
; SKX-NEXT:    kmovw %edi, %k1
; SKX-NEXT:    kshiftrw $8, %k1, %k2
; SKX-NEXT:    kmovw %k2, %k3
; SKX-NEXT:    vpgatherqd (,%zmm1), %ymm2 {%k3}
; SKX-NEXT:    kmovw %k1, %k3
; SKX-NEXT:    vpgatherqd (,%zmm0), %ymm3 {%k3}
; SKX-NEXT:    vinserti64x4 $1, %ymm2, %zmm3, %zmm4
; SKX-NEXT:    vpgatherqd (,%zmm1), %ymm2 {%k2}
; SKX-NEXT:    vpgatherqd (,%zmm0), %ymm3 {%k1}
; SKX-NEXT:    vinserti64x4 $1, %ymm2, %zmm3, %zmm0
; SKX-NEXT:    vpaddd %zmm0, %zmm4, %zmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test8:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    kmovw {{[0-9]+}}(%esp), %k1
; SKX_32-NEXT:    kmovw %k1, %k2
; SKX_32-NEXT:    vpgatherdd (,%zmm0), %zmm1 {%k2}
; SKX_32-NEXT:    vmovdqa64 %zmm1, %zmm2
; SKX_32-NEXT:    vpgatherdd (,%zmm0), %zmm2 {%k1}
; SKX_32-NEXT:    vpaddd %zmm2, %zmm1, %zmm0
; SKX_32-NEXT:    retl

  %imask = bitcast i16 %mask to <16 x i1>
  %gt1 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> %ptr.random, i32 4, <16 x i1> %imask, <16 x i32>undef)
  %gt2 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> %ptr.random, i32 4, <16 x i1> %imask, <16 x i32>%gt1)
  %res = add <16 x i32> %gt1, %gt2
  ret <16 x i32> %res
}

%struct.RT = type { i8, [10 x [20 x i32]], i8 }
%struct.ST = type { i32, double, %struct.RT }

; Masked gather for agregate types
; Test9 and Test10 should give the same result (scalar and vector indices in GEP)


define <8 x i32> @test9(%struct.ST* %base, <8 x i64> %ind1, <8 x i32>%ind5) {
; KNL_64-LABEL: test9:
; KNL_64:       # %bb.0: # %entry
; KNL_64-NEXT:    vpbroadcastq %rdi, %zmm2
; KNL_64-NEXT:    vpbroadcastq {{.*#+}} zmm3 = [824,824,824,824,824,824,824,824]
; KNL_64-NEXT:    vpmuludq %zmm3, %zmm0, %zmm4
; KNL_64-NEXT:    vpsrlq $32, %zmm0, %zmm0
; KNL_64-NEXT:    vpmuludq %zmm3, %zmm0, %zmm0
; KNL_64-NEXT:    vpsllq $32, %zmm0, %zmm0
; KNL_64-NEXT:    vpaddq %zmm2, %zmm0, %zmm0
; KNL_64-NEXT:    vpmovzxdq {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero
; KNL_64-NEXT:    vpmuldq {{.*}}(%rip){1to8}, %zmm1, %zmm1
; KNL_64-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; KNL_64-NEXT:    vpaddq %zmm0, %zmm4, %zmm0
; KNL_64-NEXT:    vpaddq {{.*}}(%rip){1to8}, %zmm0, %zmm1
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test9:
; KNL_32:       # %bb.0: # %entry
; KNL_32-NEXT:    vpbroadcastd {{[0-9]+}}(%esp), %ymm2
; KNL_32-NEXT:    vpbroadcastd {{.*#+}} ymm3 = [80,80,80,80,80,80,80,80]
; KNL_32-NEXT:    vpmulld %ymm3, %ymm1, %ymm1
; KNL_32-NEXT:    vpmovqd %zmm0, %ymm0
; KNL_32-NEXT:    vpbroadcastd {{.*#+}} ymm3 = [820,820,820,820,820,820,820,820]
; KNL_32-NEXT:    vpmulld %ymm3, %ymm0, %ymm0
; KNL_32-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; KNL_32-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [68,68,68,68,68,68,68,68]
; KNL_32-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; KNL_32-NEXT:    vpaddd %ymm0, %ymm2, %ymm1
; KNL_32-NEXT:    movw $255, %ax
; KNL_32-NEXT:    kmovw %eax, %k1
; KNL_32-NEXT:    vpgatherdd (,%zmm1), %zmm0 {%k1}
; KNL_32-NEXT:    # kill: def $ymm0 killed $ymm0 killed $zmm0
; KNL_32-NEXT:    retl
;
; SKX_SMALL-LABEL: test9:
; SKX_SMALL:       # %bb.0: # %entry
; SKX_SMALL-NEXT:    vpbroadcastq %rdi, %zmm2
; SKX_SMALL-NEXT:    vpmullq {{.*}}(%rip){1to8}, %zmm0, %zmm0
; SKX_SMALL-NEXT:    vpmovzxdq {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero
; SKX_SMALL-NEXT:    vpmuldq {{.*}}(%rip){1to8}, %zmm1, %zmm1
; SKX_SMALL-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; SKX_SMALL-NEXT:    vpaddq %zmm0, %zmm2, %zmm0
; SKX_SMALL-NEXT:    vpaddq {{.*}}(%rip){1to8}, %zmm0, %zmm1
; SKX_SMALL-NEXT:    kxnorw %k0, %k0, %k1
; SKX_SMALL-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
; SKX_SMALL-NEXT:    retq
;
; SKX_LARGE-LABEL: test9:
; SKX_LARGE:       # %bb.0: # %entry
; SKX_LARGE-NEXT:    vpbroadcastq %rdi, %zmm2
; SKX_LARGE-NEXT:    vpmovzxdq {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero
; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
; SKX_LARGE-NEXT:    vpmuldq (%rax){1to8}, %zmm1, %zmm1
; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
; SKX_LARGE-NEXT:    vpmullq (%rax){1to8}, %zmm0, %zmm0
; SKX_LARGE-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; SKX_LARGE-NEXT:    vpaddq %zmm0, %zmm2, %zmm0
; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
; SKX_LARGE-NEXT:    vpaddq (%rax){1to8}, %zmm0, %zmm1
; SKX_LARGE-NEXT:    kxnorw %k0, %k0, %k1
; SKX_LARGE-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
; SKX_LARGE-NEXT:    retq
;
; SKX_32-LABEL: test9:
; SKX_32:       # %bb.0: # %entry
; SKX_32-NEXT:    vpmulld {{\.LCPI.*}}{1to8}, %ymm1, %ymm1
; SKX_32-NEXT:    vpmovqd %zmm0, %ymm0
; SKX_32-NEXT:    vpmulld {{\.LCPI.*}}{1to8}, %ymm0, %ymm0
; SKX_32-NEXT:    vpaddd {{[0-9]+}}(%esp){1to8}, %ymm0, %ymm0
; SKX_32-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; SKX_32-NEXT:    vpaddd {{\.LCPI.*}}{1to8}, %ymm0, %ymm1
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vpgatherdd (,%ymm1), %ymm0 {%k1}
; SKX_32-NEXT:    retl
entry:
  %broadcast.splatinsert = insertelement <8 x %struct.ST*> undef, %struct.ST* %base, i32 0
  %broadcast.splat = shufflevector <8 x %struct.ST*> %broadcast.splatinsert, <8 x %struct.ST*> undef, <8 x i32> zeroinitializer

  %arrayidx = getelementptr  %struct.ST, <8 x %struct.ST*> %broadcast.splat, <8 x i64> %ind1, <8 x i32> <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>, <8 x i32><i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>, <8 x i32> %ind5, <8 x i64> <i64 13, i64 13, i64 13, i64 13, i64 13, i64 13, i64 13, i64 13>
  %res = call <8 x i32 >  @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*>%arrayidx, i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x i32> undef)
  ret <8 x i32> %res
}

define <8 x i32> @test10(%struct.ST* %base, <8 x i64> %i1, <8 x i32>%ind5) {
; KNL_64-LABEL: test10:
; KNL_64:       # %bb.0: # %entry
; KNL_64-NEXT:    vpbroadcastq %rdi, %zmm2
; KNL_64-NEXT:    vpbroadcastq {{.*#+}} zmm3 = [824,824,824,824,824,824,824,824]
; KNL_64-NEXT:    vpmuludq %zmm3, %zmm0, %zmm4
; KNL_64-NEXT:    vpsrlq $32, %zmm0, %zmm0
; KNL_64-NEXT:    vpmuludq %zmm3, %zmm0, %zmm0
; KNL_64-NEXT:    vpsllq $32, %zmm0, %zmm0
; KNL_64-NEXT:    vpaddq %zmm2, %zmm0, %zmm0
; KNL_64-NEXT:    vpmovzxdq {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero
; KNL_64-NEXT:    vpmuldq {{.*}}(%rip){1to8}, %zmm1, %zmm1
; KNL_64-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; KNL_64-NEXT:    vpaddq %zmm0, %zmm4, %zmm0
; KNL_64-NEXT:    vpaddq {{.*}}(%rip){1to8}, %zmm0, %zmm1
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test10:
; KNL_32:       # %bb.0: # %entry
; KNL_32-NEXT:    vpbroadcastd {{[0-9]+}}(%esp), %ymm2
; KNL_32-NEXT:    vpbroadcastd {{.*#+}} ymm3 = [80,80,80,80,80,80,80,80]
; KNL_32-NEXT:    vpmulld %ymm3, %ymm1, %ymm1
; KNL_32-NEXT:    vpmovqd %zmm0, %ymm0
; KNL_32-NEXT:    vpbroadcastd {{.*#+}} ymm3 = [820,820,820,820,820,820,820,820]
; KNL_32-NEXT:    vpmulld %ymm3, %ymm0, %ymm0
; KNL_32-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; KNL_32-NEXT:    vpbroadcastd {{.*#+}} ymm1 = [68,68,68,68,68,68,68,68]
; KNL_32-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; KNL_32-NEXT:    vpaddd %ymm0, %ymm2, %ymm1
; KNL_32-NEXT:    movw $255, %ax
; KNL_32-NEXT:    kmovw %eax, %k1
; KNL_32-NEXT:    vpgatherdd (,%zmm1), %zmm0 {%k1}
; KNL_32-NEXT:    # kill: def $ymm0 killed $ymm0 killed $zmm0
; KNL_32-NEXT:    retl
;
; SKX_SMALL-LABEL: test10:
; SKX_SMALL:       # %bb.0: # %entry
; SKX_SMALL-NEXT:    vpbroadcastq %rdi, %zmm2
; SKX_SMALL-NEXT:    vpmullq {{.*}}(%rip){1to8}, %zmm0, %zmm0
; SKX_SMALL-NEXT:    vpmovzxdq {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero
; SKX_SMALL-NEXT:    vpmuldq {{.*}}(%rip){1to8}, %zmm1, %zmm1
; SKX_SMALL-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; SKX_SMALL-NEXT:    vpaddq %zmm0, %zmm2, %zmm0
; SKX_SMALL-NEXT:    vpaddq {{.*}}(%rip){1to8}, %zmm0, %zmm1
; SKX_SMALL-NEXT:    kxnorw %k0, %k0, %k1
; SKX_SMALL-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
; SKX_SMALL-NEXT:    retq
;
; SKX_LARGE-LABEL: test10:
; SKX_LARGE:       # %bb.0: # %entry
; SKX_LARGE-NEXT:    vpbroadcastq %rdi, %zmm2
; SKX_LARGE-NEXT:    vpmovzxdq {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero
; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
; SKX_LARGE-NEXT:    vpmuldq (%rax){1to8}, %zmm1, %zmm1
; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
; SKX_LARGE-NEXT:    vpmullq (%rax){1to8}, %zmm0, %zmm0
; SKX_LARGE-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; SKX_LARGE-NEXT:    vpaddq %zmm0, %zmm2, %zmm0
; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
; SKX_LARGE-NEXT:    vpaddq (%rax){1to8}, %zmm0, %zmm1
; SKX_LARGE-NEXT:    kxnorw %k0, %k0, %k1
; SKX_LARGE-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
; SKX_LARGE-NEXT:    retq
;
; SKX_32-LABEL: test10:
; SKX_32:       # %bb.0: # %entry
; SKX_32-NEXT:    vpmulld {{\.LCPI.*}}{1to8}, %ymm1, %ymm1
; SKX_32-NEXT:    vpmovqd %zmm0, %ymm0
; SKX_32-NEXT:    vpmulld {{\.LCPI.*}}{1to8}, %ymm0, %ymm0
; SKX_32-NEXT:    vpaddd {{[0-9]+}}(%esp){1to8}, %ymm0, %ymm0
; SKX_32-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; SKX_32-NEXT:    vpaddd {{\.LCPI.*}}{1to8}, %ymm0, %ymm1
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vpgatherdd (,%ymm1), %ymm0 {%k1}
; SKX_32-NEXT:    retl
entry:
  %broadcast.splatinsert = insertelement <8 x %struct.ST*> undef, %struct.ST* %base, i32 0
  %broadcast.splat = shufflevector <8 x %struct.ST*> %broadcast.splatinsert, <8 x %struct.ST*> undef, <8 x i32> zeroinitializer

  %arrayidx = getelementptr  %struct.ST, <8 x %struct.ST*> %broadcast.splat, <8 x i64> %i1, i32 2, i32 1, <8 x i32> %ind5, i64 13
  %res = call <8 x i32 >  @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*>%arrayidx, i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x i32> undef)
  ret <8 x i32> %res
}

; Splat index in GEP, requires broadcast
define <16 x float> @test11(float* %base, i32 %ind) {
; KNL_64-LABEL: test11:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpbroadcastd %esi, %zmm1
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm1,4), %zmm0 {%k1}
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test11:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vbroadcastss {{[0-9]+}}(%esp), %zmm1
; KNL_32-NEXT:    kxnorw %k0, %k0, %k1
; KNL_32-NEXT:    vgatherdps (%eax,%zmm1,4), %zmm0 {%k1}
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test11:
; SKX:       # %bb.0:
; SKX-NEXT:    vpbroadcastd %esi, %zmm1
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    vgatherdps (%rdi,%zmm1,4), %zmm0 {%k1}
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test11:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vbroadcastss {{[0-9]+}}(%esp), %zmm1
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vgatherdps (%eax,%zmm1,4), %zmm0 {%k1}
; SKX_32-NEXT:    retl

  %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
  %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer

  %gep.random = getelementptr float, <16 x float*> %broadcast.splat, i32 %ind

  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
  ret <16 x float>%res
}

; We are checking the uniform base here. It is taken directly from input to vgatherdps
define <16 x float> @test12(float* %base, <16 x i32> %ind) {
; KNL_64-LABEL: test12:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; KNL_64-NEXT:    vmovaps %zmm1, %zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test12:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    kxnorw %k0, %k0, %k1
; KNL_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; KNL_32-NEXT:    vmovaps %zmm1, %zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test12:
; SKX:       # %bb.0:
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; SKX-NEXT:    vmovaps %zmm1, %zmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test12:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; SKX_32-NEXT:    vmovaps %zmm1, %zmm0
; SKX_32-NEXT:    retl

  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.random = getelementptr float, float *%base, <16 x i64> %sext_ind

  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
  ret <16 x float>%res
}

; The same as the previous, but the mask is undefined
define <16 x float> @test13(float* %base, <16 x i32> %ind) {
; KNL_64-LABEL: test13:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; KNL_64-NEXT:    vmovaps %zmm1, %zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test13:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    kxnorw %k0, %k0, %k1
; KNL_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; KNL_32-NEXT:    vmovaps %zmm1, %zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test13:
; SKX:       # %bb.0:
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; SKX-NEXT:    vmovaps %zmm1, %zmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test13:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; SKX_32-NEXT:    vmovaps %zmm1, %zmm0
; SKX_32-NEXT:    retl

  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.random = getelementptr float, float *%base, <16 x i64> %sext_ind

  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
  ret <16 x float>%res
}

; The base pointer is not splat, can't find unform base
define <16 x float> @test14(float* %base, i32 %ind, <16 x float*> %vec) {
; KNL_64-LABEL: test14:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpbroadcastq %xmm0, %zmm0
; KNL_64-NEXT:    vmovd %esi, %xmm1
; KNL_64-NEXT:    vpbroadcastd %xmm1, %ymm1
; KNL_64-NEXT:    vpmovsxdq %ymm1, %zmm1
; KNL_64-NEXT:    vpsllq $2, %zmm1, %zmm1
; KNL_64-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    vgatherqps (,%zmm0), %ymm1 {%k1}
; KNL_64-NEXT:    vinsertf64x4 $1, %ymm1, %zmm1, %zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test14:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    vpbroadcastd %xmm0, %zmm0
; KNL_32-NEXT:    vpslld $2, {{[0-9]+}}(%esp){1to16}, %zmm1
; KNL_32-NEXT:    vpaddd %zmm1, %zmm0, %zmm1
; KNL_32-NEXT:    kxnorw %k0, %k0, %k1
; KNL_32-NEXT:    vgatherdps (,%zmm1), %zmm0 {%k1}
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test14:
; SKX:       # %bb.0:
; SKX-NEXT:    vpbroadcastq %xmm0, %zmm0
; SKX-NEXT:    vpbroadcastd %esi, %ymm1
; SKX-NEXT:    vpmovsxdq %ymm1, %zmm1
; SKX-NEXT:    vpsllq $2, %zmm1, %zmm1
; SKX-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    vgatherqps (,%zmm0), %ymm1 {%k1}
; SKX-NEXT:    vinsertf64x4 $1, %ymm1, %zmm1, %zmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test14:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpbroadcastd %xmm0, %zmm0
; SKX_32-NEXT:    vpslld $2, {{[0-9]+}}(%esp){1to16}, %zmm1
; SKX_32-NEXT:    vpaddd %zmm1, %zmm0, %zmm1
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vgatherdps (,%zmm1), %zmm0 {%k1}
; SKX_32-NEXT:    retl

  %broadcast.splatinsert = insertelement <16 x float*> %vec, float* %base, i32 1
  %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer

  %gep.random = getelementptr float, <16 x float*> %broadcast.splat, i32 %ind

  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
  ret <16 x float>%res
}

declare <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*>, i32, <4 x i1>, <4 x float>)
declare <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*>, i32, <4 x i1>, <4 x double>)
declare <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*>, i32, <2 x i1>, <2 x double>)

; Gather smaller than existing instruction
define <4 x float> @test15(float* %base, <4 x i32> %ind, <4 x i1> %mask) {
; KNL_64-LABEL: test15:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
; KNL_64-NEXT:    vpslld $31, %xmm1, %xmm1
; KNL_64-NEXT:    vptestmd %zmm1, %zmm1, %k0
; KNL_64-NEXT:    kshiftlw $12, %k0, %k0
; KNL_64-NEXT:    kshiftrw $12, %k0, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; KNL_64-NEXT:    vmovaps %xmm1, %xmm0
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test15:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
; KNL_32-NEXT:    vpslld $31, %xmm1, %xmm1
; KNL_32-NEXT:    vptestmd %zmm1, %zmm1, %k0
; KNL_32-NEXT:    kshiftlw $12, %k0, %k0
; KNL_32-NEXT:    kshiftrw $12, %k0, %k1
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; KNL_32-NEXT:    vmovaps %xmm1, %xmm0
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test15:
; SKX:       # %bb.0:
; SKX-NEXT:    vpslld $31, %xmm1, %xmm1
; SKX-NEXT:    vpmovd2m %xmm1, %k1
; SKX-NEXT:    vgatherdps (%rdi,%xmm0,4), %xmm1 {%k1}
; SKX-NEXT:    vmovaps %xmm1, %xmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test15:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpslld $31, %xmm1, %xmm1
; SKX_32-NEXT:    vpmovd2m %xmm1, %k1
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vgatherdps (%eax,%xmm0,4), %xmm1 {%k1}
; SKX_32-NEXT:    vmovaps %xmm1, %xmm0
; SKX_32-NEXT:    retl

  %sext_ind = sext <4 x i32> %ind to <4 x i64>
  %gep.random = getelementptr float, float* %base, <4 x i64> %sext_ind
  %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.random, i32 4, <4 x i1> %mask, <4 x float> undef)
  ret <4 x float>%res
}

; Gather smaller than existing instruction
define <4 x double> @test16(double* %base, <4 x i32> %ind, <4 x i1> %mask, <4 x double> %src0) {
; KNL_64-LABEL: test16:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $ymm2 killed $ymm2 def $zmm2
; KNL_64-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
; KNL_64-NEXT:    vpslld $31, %xmm1, %xmm1
; KNL_64-NEXT:    vptestmd %zmm1, %zmm1, %k0
; KNL_64-NEXT:    kshiftlw $12, %k0, %k0
; KNL_64-NEXT:    kshiftrw $12, %k0, %k1
; KNL_64-NEXT:    vgatherdpd (%rdi,%ymm0,8), %zmm2 {%k1}
; KNL_64-NEXT:    vmovapd %ymm2, %ymm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test16:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $ymm2 killed $ymm2 def $zmm2
; KNL_32-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
; KNL_32-NEXT:    vpslld $31, %xmm1, %xmm1
; KNL_32-NEXT:    vptestmd %zmm1, %zmm1, %k0
; KNL_32-NEXT:    kshiftlw $12, %k0, %k0
; KNL_32-NEXT:    kshiftrw $12, %k0, %k1
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vgatherdpd (%eax,%ymm0,8), %zmm2 {%k1}
; KNL_32-NEXT:    vmovapd %ymm2, %ymm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test16:
; SKX:       # %bb.0:
; SKX-NEXT:    vpslld $31, %xmm1, %xmm1
; SKX-NEXT:    vpmovd2m %xmm1, %k1
; SKX-NEXT:    vgatherdpd (%rdi,%xmm0,8), %ymm2 {%k1}
; SKX-NEXT:    vmovapd %ymm2, %ymm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test16:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpslld $31, %xmm1, %xmm1
; SKX_32-NEXT:    vpmovd2m %xmm1, %k1
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vgatherdpd (%eax,%xmm0,8), %ymm2 {%k1}
; SKX_32-NEXT:    vmovapd %ymm2, %ymm0
; SKX_32-NEXT:    retl

  %sext_ind = sext <4 x i32> %ind to <4 x i64>
  %gep.random = getelementptr double, double* %base, <4 x i64> %sext_ind
  %res = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> %gep.random, i32 4, <4 x i1> %mask, <4 x double> %src0)
  ret <4 x double>%res
}

define <2 x double> @test17(double* %base, <2 x i32> %ind, <2 x i1> %mask, <2 x double> %src0) {
; KNL_64-LABEL: test17:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $xmm2 killed $xmm2 def $zmm2
; KNL_64-NEXT:    vpsllq $32, %xmm0, %xmm0
; KNL_64-NEXT:    vpsraq $32, %zmm0, %zmm0
; KNL_64-NEXT:    vpsllq $63, %xmm1, %xmm1
; KNL_64-NEXT:    vptestmq %zmm1, %zmm1, %k0
; KNL_64-NEXT:    kshiftlw $14, %k0, %k0
; KNL_64-NEXT:    kshiftrw $14, %k0, %k1
; KNL_64-NEXT:    vgatherqpd (%rdi,%zmm0,8), %zmm2 {%k1}
; KNL_64-NEXT:    vmovapd %xmm2, %xmm0
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test17:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $xmm2 killed $xmm2 def $zmm2
; KNL_32-NEXT:    vpsllq $32, %xmm0, %xmm0
; KNL_32-NEXT:    vpsraq $32, %zmm0, %zmm0
; KNL_32-NEXT:    vpsllq $63, %xmm1, %xmm1
; KNL_32-NEXT:    vptestmq %zmm1, %zmm1, %k0
; KNL_32-NEXT:    kshiftlw $14, %k0, %k0
; KNL_32-NEXT:    kshiftrw $14, %k0, %k1
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vgatherqpd (%eax,%zmm0,8), %zmm2 {%k1}
; KNL_32-NEXT:    vmovapd %xmm2, %xmm0
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test17:
; SKX:       # %bb.0:
; SKX-NEXT:    vpsllq $32, %xmm0, %xmm0
; SKX-NEXT:    vpsraq $32, %xmm0, %xmm0
; SKX-NEXT:    vpsllq $63, %xmm1, %xmm1
; SKX-NEXT:    vpmovq2m %xmm1, %k1
; SKX-NEXT:    vgatherqpd (%rdi,%xmm0,8), %xmm2 {%k1}
; SKX-NEXT:    vmovapd %xmm2, %xmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test17:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpsllq $32, %xmm0, %xmm0
; SKX_32-NEXT:    vpsraq $32, %xmm0, %xmm0
; SKX_32-NEXT:    vpsllq $63, %xmm1, %xmm1
; SKX_32-NEXT:    vpmovq2m %xmm1, %k1
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vgatherqpd (%eax,%xmm0,8), %xmm2 {%k1}
; SKX_32-NEXT:    vmovapd %xmm2, %xmm0
; SKX_32-NEXT:    retl

  %sext_ind = sext <2 x i32> %ind to <2 x i64>
  %gep.random = getelementptr double, double* %base, <2 x i64> %sext_ind
  %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %gep.random, i32 4, <2 x i1> %mask, <2 x double> %src0)
  ret <2 x double>%res
}

declare void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> , <4 x i32*> , i32 , <4 x i1> )
declare void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> , <4 x double*> , i32 , <4 x i1> )
declare void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> , <2 x i64*> , i32 , <2 x i1> )
declare void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> , <2 x i32*> , i32 , <2 x i1> )
declare void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> , <2 x float*> , i32 , <2 x i1> )

define void @test18(<4 x i32>%a1, <4 x i32*> %ptr, <4 x i1>%mask) {
; KNL_64-LABEL: test18:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $ymm1 killed $ymm1 def $zmm1
; KNL_64-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
; KNL_64-NEXT:    vpslld $31, %xmm2, %xmm2
; KNL_64-NEXT:    vptestmd %zmm2, %zmm2, %k0
; KNL_64-NEXT:    kshiftlw $12, %k0, %k0
; KNL_64-NEXT:    kshiftrw $12, %k0, %k1
; KNL_64-NEXT:    vpscatterqd %ymm0, (,%zmm1) {%k1}
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test18:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $xmm1 killed $xmm1 def $zmm1
; KNL_32-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
; KNL_32-NEXT:    vpslld $31, %xmm2, %xmm2
; KNL_32-NEXT:    vptestmd %zmm2, %zmm2, %k0
; KNL_32-NEXT:    kshiftlw $12, %k0, %k0
; KNL_32-NEXT:    kshiftrw $12, %k0, %k1
; KNL_32-NEXT:    vpscatterdd %zmm0, (,%zmm1) {%k1}
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test18:
; SKX:       # %bb.0:
; SKX-NEXT:    vpslld $31, %xmm2, %xmm2
; SKX-NEXT:    vpmovd2m %xmm2, %k1
; SKX-NEXT:    vpscatterqd %xmm0, (,%ymm1) {%k1}
; SKX-NEXT:    vzeroupper
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test18:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpslld $31, %xmm2, %xmm2
; SKX_32-NEXT:    vpmovd2m %xmm2, %k1
; SKX_32-NEXT:    vpscatterdd %xmm0, (,%xmm1) {%k1}
; SKX_32-NEXT:    retl
  call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
  ret void
}

define void @test19(<4 x double>%a1, double* %ptr, <4 x i1>%mask, <4 x i64> %ind) {
; KNL_64-LABEL: test19:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $ymm2 killed $ymm2 def $zmm2
; KNL_64-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
; KNL_64-NEXT:    vpslld $31, %xmm1, %xmm1
; KNL_64-NEXT:    vptestmd %zmm1, %zmm1, %k0
; KNL_64-NEXT:    kshiftlw $12, %k0, %k0
; KNL_64-NEXT:    kshiftrw $12, %k0, %k1
; KNL_64-NEXT:    vscatterqpd %zmm0, (%rdi,%zmm2,8) {%k1}
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test19:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $ymm2 killed $ymm2 def $zmm2
; KNL_32-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
; KNL_32-NEXT:    vpslld $31, %xmm1, %xmm1
; KNL_32-NEXT:    vptestmd %zmm1, %zmm1, %k0
; KNL_32-NEXT:    kshiftlw $12, %k0, %k0
; KNL_32-NEXT:    kshiftrw $12, %k0, %k1
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vscatterqpd %zmm0, (%eax,%zmm2,8) {%k1}
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test19:
; SKX:       # %bb.0:
; SKX-NEXT:    vpslld $31, %xmm1, %xmm1
; SKX-NEXT:    vpmovd2m %xmm1, %k1
; SKX-NEXT:    vscatterqpd %ymm0, (%rdi,%ymm2,8) {%k1}
; SKX-NEXT:    vzeroupper
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test19:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpslld $31, %xmm1, %xmm1
; SKX_32-NEXT:    vpmovd2m %xmm1, %k1
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vscatterqpd %ymm0, (%eax,%ymm2,8) {%k1}
; SKX_32-NEXT:    vzeroupper
; SKX_32-NEXT:    retl
  %gep = getelementptr double, double* %ptr, <4 x i64> %ind
  call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> %a1, <4 x double*> %gep, i32 8, <4 x i1> %mask)
  ret void
}

; Data type requires widening
define void @test20(<2 x float>%a1, <2 x float*> %ptr, <2 x i1> %mask) {
; KNL_64-LABEL: test20:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $xmm1 killed $xmm1 def $zmm1
; KNL_64-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
; KNL_64-NEXT:    vpsllq $63, %xmm2, %xmm2
; KNL_64-NEXT:    vptestmq %zmm2, %zmm2, %k0
; KNL_64-NEXT:    kshiftlw $14, %k0, %k0
; KNL_64-NEXT:    kshiftrw $14, %k0, %k1
; KNL_64-NEXT:    vscatterqps %ymm0, (,%zmm1) {%k1}
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test20:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
; KNL_32-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,2,3]
; KNL_32-NEXT:    vpsllq $63, %xmm2, %xmm2
; KNL_32-NEXT:    vptestmq %zmm2, %zmm2, %k0
; KNL_32-NEXT:    kshiftlw $14, %k0, %k0
; KNL_32-NEXT:    kshiftrw $14, %k0, %k1
; KNL_32-NEXT:    vscatterdps %zmm0, (,%zmm1) {%k1}
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test20:
; SKX:       # %bb.0:
; SKX-NEXT:    vpsllq $63, %xmm2, %xmm2
; SKX-NEXT:    vpmovq2m %xmm2, %k1
; SKX-NEXT:    vscatterqps %xmm0, (,%xmm1) {%k1}
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test20:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SKX_32-NEXT:    vpsllq $63, %xmm2, %xmm2
; SKX_32-NEXT:    vpmovq2m %xmm2, %k1
; SKX_32-NEXT:    vscatterdps %xmm0, (,%xmm1) {%k1}
; SKX_32-NEXT:    retl
  call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> %a1, <2 x float*> %ptr, i32 4, <2 x i1> %mask)
  ret void
}

; Data type requires promotion
define void @test21(<2 x i32>%a1, <2 x i32*> %ptr, <2 x i1>%mask) {
; KNL_64-LABEL: test21:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $xmm1 killed $xmm1 def $zmm1
; KNL_64-NEXT:    vpsllq $63, %xmm2, %xmm2
; KNL_64-NEXT:    vptestmq %zmm2, %zmm2, %k0
; KNL_64-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; KNL_64-NEXT:    kshiftlw $14, %k0, %k0
; KNL_64-NEXT:    kshiftrw $14, %k0, %k1
; KNL_64-NEXT:    vpscatterqd %ymm0, (,%zmm1) {%k1}
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test21:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    vpsllq $63, %xmm2, %xmm2
; KNL_32-NEXT:    vptestmq %zmm2, %zmm2, %k0
; KNL_32-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; KNL_32-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; KNL_32-NEXT:    kshiftlw $14, %k0, %k0
; KNL_32-NEXT:    kshiftrw $14, %k0, %k1
; KNL_32-NEXT:    vpscatterdd %zmm0, (,%zmm1) {%k1}
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test21:
; SKX:       # %bb.0:
; SKX-NEXT:    vpsllq $63, %xmm2, %xmm2
; SKX-NEXT:    vpmovq2m %xmm2, %k1
; SKX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SKX-NEXT:    vpscatterqd %xmm0, (,%xmm1) {%k1}
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test21:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpsllq $63, %xmm2, %xmm2
; SKX_32-NEXT:    vpmovq2m %xmm2, %k1
; SKX_32-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SKX_32-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SKX_32-NEXT:    vpscatterdd %xmm0, (,%xmm1) {%k1}
; SKX_32-NEXT:    retl
  call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> %a1, <2 x i32*> %ptr, i32 4, <2 x i1> %mask)
  ret void
}

; The result type requires widening
declare <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*>, i32, <2 x i1>, <2 x float>)

define <2 x float> @test22(float* %base, <2 x i32> %ind, <2 x i1> %mask, <2 x float> %src0) {
; KNL_64-LABEL: test22:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $xmm2 killed $xmm2 def $zmm2
; KNL_64-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; KNL_64-NEXT:    vpsllq $63, %xmm1, %xmm1
; KNL_64-NEXT:    vptestmq %zmm1, %zmm1, %k0
; KNL_64-NEXT:    kshiftlw $14, %k0, %k0
; KNL_64-NEXT:    kshiftrw $14, %k0, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm2 {%k1}
; KNL_64-NEXT:    vmovaps %xmm2, %xmm0
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test22:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $xmm2 killed $xmm2 def $zmm2
; KNL_32-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; KNL_32-NEXT:    vpsllq $63, %xmm1, %xmm1
; KNL_32-NEXT:    vptestmq %zmm1, %zmm1, %k0
; KNL_32-NEXT:    kshiftlw $14, %k0, %k0
; KNL_32-NEXT:    kshiftrw $14, %k0, %k1
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm2 {%k1}
; KNL_32-NEXT:    vmovaps %xmm2, %xmm0
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test22:
; SKX:       # %bb.0:
; SKX-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SKX-NEXT:    vpsllq $63, %xmm1, %xmm1
; SKX-NEXT:    vpmovq2m %xmm1, %k1
; SKX-NEXT:    vgatherdps (%rdi,%xmm0,4), %xmm2 {%k1}
; SKX-NEXT:    vmovaps %xmm2, %xmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test22:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SKX_32-NEXT:    vpsllq $63, %xmm1, %xmm1
; SKX_32-NEXT:    vpmovq2m %xmm1, %k1
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vgatherdps (%eax,%xmm0,4), %xmm2 {%k1}
; SKX_32-NEXT:    vmovaps %xmm2, %xmm0
; SKX_32-NEXT:    retl
  %sext_ind = sext <2 x i32> %ind to <2 x i64>
  %gep.random = getelementptr float, float* %base, <2 x i64> %sext_ind
  %res = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> %gep.random, i32 4, <2 x i1> %mask, <2 x float> %src0)
  ret <2 x float>%res
}

define <2 x float> @test22a(float* %base, <2 x i64> %ind, <2 x i1> %mask, <2 x float> %src0) {
; KNL_64-LABEL: test22a:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $xmm2 killed $xmm2 def $ymm2
; KNL_64-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
; KNL_64-NEXT:    vpsllq $63, %xmm1, %xmm1
; KNL_64-NEXT:    vptestmq %zmm1, %zmm1, %k0
; KNL_64-NEXT:    kshiftlw $14, %k0, %k0
; KNL_64-NEXT:    kshiftrw $14, %k0, %k1
; KNL_64-NEXT:    vgatherqps (%rdi,%zmm0,4), %ymm2 {%k1}
; KNL_64-NEXT:    vmovaps %xmm2, %xmm0
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test22a:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $xmm2 killed $xmm2 def $ymm2
; KNL_32-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
; KNL_32-NEXT:    vpsllq $63, %xmm1, %xmm1
; KNL_32-NEXT:    vptestmq %zmm1, %zmm1, %k0
; KNL_32-NEXT:    kshiftlw $14, %k0, %k0
; KNL_32-NEXT:    kshiftrw $14, %k0, %k1
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vgatherqps (%eax,%zmm0,4), %ymm2 {%k1}
; KNL_32-NEXT:    vmovaps %xmm2, %xmm0
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test22a:
; SKX:       # %bb.0:
; SKX-NEXT:    vpsllq $63, %xmm1, %xmm1
; SKX-NEXT:    vpmovq2m %xmm1, %k1
; SKX-NEXT:    vgatherqps (%rdi,%xmm0,4), %xmm2 {%k1}
; SKX-NEXT:    vmovaps %xmm2, %xmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test22a:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpsllq $63, %xmm1, %xmm1
; SKX_32-NEXT:    vpmovq2m %xmm1, %k1
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vgatherqps (%eax,%xmm0,4), %xmm2 {%k1}
; SKX_32-NEXT:    vmovaps %xmm2, %xmm0
; SKX_32-NEXT:    retl
  %gep.random = getelementptr float, float* %base, <2 x i64> %ind
  %res = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> %gep.random, i32 4, <2 x i1> %mask, <2 x float> %src0)
  ret <2 x float>%res
}

declare <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*>, i32, <2 x i1>, <2 x i32>)
declare <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*>, i32, <2 x i1>, <2 x i64>)

define <2 x i32> @test23(i32* %base, <2 x i32> %ind, <2 x i1> %mask, <2 x i32> %src0) {
; KNL_64-LABEL: test23:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpsllq $63, %xmm1, %xmm1
; KNL_64-NEXT:    vptestmq %zmm1, %zmm1, %k0
; KNL_64-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; KNL_64-NEXT:    vpshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; KNL_64-NEXT:    kshiftlw $14, %k0, %k0
; KNL_64-NEXT:    kshiftrw $14, %k0, %k1
; KNL_64-NEXT:    vpgatherdd (%rdi,%zmm0,4), %zmm1 {%k1}
; KNL_64-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test23:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    vpsllq $63, %xmm1, %xmm1
; KNL_32-NEXT:    vptestmq %zmm1, %zmm1, %k0
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; KNL_32-NEXT:    vpshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; KNL_32-NEXT:    kshiftlw $14, %k0, %k0
; KNL_32-NEXT:    kshiftrw $14, %k0, %k1
; KNL_32-NEXT:    vpgatherdd (%eax,%zmm0,4), %zmm1 {%k1}
; KNL_32-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test23:
; SKX:       # %bb.0:
; SKX-NEXT:    vpsllq $63, %xmm1, %xmm1
; SKX-NEXT:    vpmovq2m %xmm1, %k1
; SKX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SKX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SKX-NEXT:    vpgatherdd (%rdi,%xmm0,4), %xmm1 {%k1}
; SKX-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test23:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpsllq $63, %xmm1, %xmm1
; SKX_32-NEXT:    vpmovq2m %xmm1, %k1
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SKX_32-NEXT:    vpshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SKX_32-NEXT:    vpgatherdd (%eax,%xmm0,4), %xmm1 {%k1}
; SKX_32-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; SKX_32-NEXT:    retl
  %sext_ind = sext <2 x i32> %ind to <2 x i64>
  %gep.random = getelementptr i32, i32* %base, <2 x i64> %sext_ind
  %res = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> %gep.random, i32 4, <2 x i1> %mask, <2 x i32> %src0)
  ret <2 x i32>%res
}

define <2 x i32> @test23b(i32* %base, <2 x i64> %ind, <2 x i1> %mask, <2 x i32> %src0) {
; KNL_64-LABEL: test23b:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
; KNL_64-NEXT:    vpsllq $63, %xmm1, %xmm1
; KNL_64-NEXT:    vptestmq %zmm1, %zmm1, %k0
; KNL_64-NEXT:    vpshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; KNL_64-NEXT:    kshiftlw $14, %k0, %k0
; KNL_64-NEXT:    kshiftrw $14, %k0, %k1
; KNL_64-NEXT:    vpgatherqd (%rdi,%zmm0,4), %ymm1 {%k1}
; KNL_64-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test23b:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
; KNL_32-NEXT:    vpsllq $63, %xmm1, %xmm1
; KNL_32-NEXT:    vptestmq %zmm1, %zmm1, %k0
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vpshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; KNL_32-NEXT:    kshiftlw $14, %k0, %k0
; KNL_32-NEXT:    kshiftrw $14, %k0, %k1
; KNL_32-NEXT:    vpgatherqd (%eax,%zmm0,4), %ymm1 {%k1}
; KNL_32-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test23b:
; SKX:       # %bb.0:
; SKX-NEXT:    vpsllq $63, %xmm1, %xmm1
; SKX-NEXT:    vpmovq2m %xmm1, %k1
; SKX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SKX-NEXT:    vpgatherqd (%rdi,%xmm0,4), %xmm1 {%k1}
; SKX-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test23b:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpsllq $63, %xmm1, %xmm1
; SKX_32-NEXT:    vpmovq2m %xmm1, %k1
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vpshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SKX_32-NEXT:    vpgatherqd (%eax,%xmm0,4), %xmm1 {%k1}
; SKX_32-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; SKX_32-NEXT:    retl
  %gep.random = getelementptr i32, i32* %base, <2 x i64> %ind
  %res = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> %gep.random, i32 4, <2 x i1> %mask, <2 x i32> %src0)
  ret <2 x i32>%res
}

define <2 x i32> @test24(i32* %base, <2 x i32> %ind) {
; KNL_64-LABEL: test24:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; KNL_64-NEXT:    movw $3, %ax
; KNL_64-NEXT:    kmovw %eax, %k1
; KNL_64-NEXT:    vpgatherdd (%rdi,%zmm0,4), %zmm1 {%k1}
; KNL_64-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test24:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; KNL_32-NEXT:    movw $3, %cx
; KNL_32-NEXT:    kmovw %ecx, %k1
; KNL_32-NEXT:    vpgatherdd (%eax,%zmm0,4), %zmm1 {%k1}
; KNL_32-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test24:
; SKX:       # %bb.0:
; SKX-NEXT:    movb $3, %al
; SKX-NEXT:    kmovw %eax, %k1
; SKX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SKX-NEXT:    vpgatherdd (%rdi,%xmm0,4), %xmm1 {%k1}
; SKX-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test24:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    movb $3, %cl
; SKX_32-NEXT:    kmovw %ecx, %k1
; SKX_32-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SKX_32-NEXT:    vpgatherdd (%eax,%xmm0,4), %xmm1 {%k1}
; SKX_32-NEXT:    vpmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
; SKX_32-NEXT:    retl
  %sext_ind = sext <2 x i32> %ind to <2 x i64>
  %gep.random = getelementptr i32, i32* %base, <2 x i64> %sext_ind
  %res = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> %gep.random, i32 4, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
  ret <2 x i32>%res
}

define <2 x i64> @test25(i64* %base, <2 x i32> %ind, <2 x i1> %mask, <2 x i64> %src0) {
; KNL_64-LABEL: test25:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $xmm2 killed $xmm2 def $zmm2
; KNL_64-NEXT:    vpsllq $32, %xmm0, %xmm0
; KNL_64-NEXT:    vpsraq $32, %zmm0, %zmm0
; KNL_64-NEXT:    vpsllq $63, %xmm1, %xmm1
; KNL_64-NEXT:    vptestmq %zmm1, %zmm1, %k0
; KNL_64-NEXT:    kshiftlw $14, %k0, %k0
; KNL_64-NEXT:    kshiftrw $14, %k0, %k1
; KNL_64-NEXT:    vpgatherqq (%rdi,%zmm0,8), %zmm2 {%k1}
; KNL_64-NEXT:    vmovdqa %xmm2, %xmm0
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test25:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $xmm2 killed $xmm2 def $zmm2
; KNL_32-NEXT:    vpsllq $32, %xmm0, %xmm0
; KNL_32-NEXT:    vpsraq $32, %zmm0, %zmm0
; KNL_32-NEXT:    vpsllq $63, %xmm1, %xmm1
; KNL_32-NEXT:    vptestmq %zmm1, %zmm1, %k0
; KNL_32-NEXT:    kshiftlw $14, %k0, %k0
; KNL_32-NEXT:    kshiftrw $14, %k0, %k1
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vpgatherqq (%eax,%zmm0,8), %zmm2 {%k1}
; KNL_32-NEXT:    vmovdqa %xmm2, %xmm0
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test25:
; SKX:       # %bb.0:
; SKX-NEXT:    vpsllq $32, %xmm0, %xmm0
; SKX-NEXT:    vpsraq $32, %xmm0, %xmm0
; SKX-NEXT:    vpsllq $63, %xmm1, %xmm1
; SKX-NEXT:    vpmovq2m %xmm1, %k1
; SKX-NEXT:    vpgatherqq (%rdi,%xmm0,8), %xmm2 {%k1}
; SKX-NEXT:    vmovdqa %xmm2, %xmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test25:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpsllq $32, %xmm0, %xmm0
; SKX_32-NEXT:    vpsraq $32, %xmm0, %xmm0
; SKX_32-NEXT:    vpsllq $63, %xmm1, %xmm1
; SKX_32-NEXT:    vpmovq2m %xmm1, %k1
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vpgatherqq (%eax,%xmm0,8), %xmm2 {%k1}
; SKX_32-NEXT:    vmovdqa %xmm2, %xmm0
; SKX_32-NEXT:    retl
  %sext_ind = sext <2 x i32> %ind to <2 x i64>
  %gep.random = getelementptr i64, i64* %base, <2 x i64> %sext_ind
  %res = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> %gep.random, i32 8, <2 x i1> %mask, <2 x i64> %src0)
  ret <2 x i64>%res
}

define <2 x i64> @test26(i64* %base, <2 x i32> %ind, <2 x i64> %src0) {
; KNL_64-LABEL: test26:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $xmm1 killed $xmm1 def $zmm1
; KNL_64-NEXT:    vpsllq $32, %xmm0, %xmm0
; KNL_64-NEXT:    vpsraq $32, %zmm0, %zmm0
; KNL_64-NEXT:    movb $3, %al
; KNL_64-NEXT:    kmovw %eax, %k1
; KNL_64-NEXT:    vpgatherqq (%rdi,%zmm0,8), %zmm1 {%k1}
; KNL_64-NEXT:    vmovdqa %xmm1, %xmm0
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test26:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $xmm1 killed $xmm1 def $zmm1
; KNL_32-NEXT:    vpsllq $32, %xmm0, %xmm0
; KNL_32-NEXT:    vpsraq $32, %zmm0, %zmm0
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    movb $3, %cl
; KNL_32-NEXT:    kmovw %ecx, %k1
; KNL_32-NEXT:    vpgatherqq (%eax,%zmm0,8), %zmm1 {%k1}
; KNL_32-NEXT:    vmovdqa %xmm1, %xmm0
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test26:
; SKX:       # %bb.0:
; SKX-NEXT:    vpsllq $32, %xmm0, %xmm0
; SKX-NEXT:    vpsraq $32, %xmm0, %xmm0
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    vpgatherqq (%rdi,%xmm0,8), %xmm1 {%k1}
; SKX-NEXT:    vmovdqa %xmm1, %xmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test26:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpsllq $32, %xmm0, %xmm0
; SKX_32-NEXT:    vpsraq $32, %xmm0, %xmm0
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vpgatherqq (%eax,%xmm0,8), %xmm1 {%k1}
; SKX_32-NEXT:    vmovdqa %xmm1, %xmm0
; SKX_32-NEXT:    retl
  %sext_ind = sext <2 x i32> %ind to <2 x i64>
  %gep.random = getelementptr i64, i64* %base, <2 x i64> %sext_ind
  %res = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> %gep.random, i32 8, <2 x i1> <i1 true, i1 true>, <2 x i64> %src0)
  ret <2 x i64>%res
}

; Result type requires widening; all-ones mask
define <2 x float> @test27(float* %base, <2 x i32> %ind) {
; KNL_64-LABEL: test27:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,2,2,3]
; KNL_64-NEXT:    movw $3, %ax
; KNL_64-NEXT:    kmovw %eax, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm1,4), %zmm0 {%k1}
; KNL_64-NEXT:    # kill: def $xmm0 killed $xmm0 killed $zmm0
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test27:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,2,2,3]
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    movw $3, %cx
; KNL_32-NEXT:    kmovw %ecx, %k1
; KNL_32-NEXT:    vgatherdps (%eax,%zmm1,4), %zmm0 {%k1}
; KNL_32-NEXT:    # kill: def $xmm0 killed $xmm0 killed $zmm0
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test27:
; SKX:       # %bb.0:
; SKX-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,2,2,3]
; SKX-NEXT:    movb $3, %al
; SKX-NEXT:    kmovw %eax, %k1
; SKX-NEXT:    vgatherdps (%rdi,%xmm1,4), %xmm0 {%k1}
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test27:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,2,2,3]
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    movb $3, %cl
; SKX_32-NEXT:    kmovw %ecx, %k1
; SKX_32-NEXT:    vgatherdps (%eax,%xmm1,4), %xmm0 {%k1}
; SKX_32-NEXT:    retl
  %sext_ind = sext <2 x i32> %ind to <2 x i64>
  %gep.random = getelementptr float, float* %base, <2 x i64> %sext_ind
  %res = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> %gep.random, i32 4, <2 x i1> <i1 true, i1 true>, <2 x float> undef)
  ret <2 x float>%res
}

; Data type requires promotion, mask is all-ones
define void @test28(<2 x i32>%a1, <2 x i32*> %ptr) {
; KNL_64-LABEL: test28:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $xmm1 killed $xmm1 def $zmm1
; KNL_64-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; KNL_64-NEXT:    movb $3, %al
; KNL_64-NEXT:    kmovw %eax, %k1
; KNL_64-NEXT:    vpscatterqd %ymm0, (,%zmm1) {%k1}
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test28:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; KNL_32-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; KNL_32-NEXT:    movw $3, %ax
; KNL_32-NEXT:    kmovw %eax, %k1
; KNL_32-NEXT:    vpscatterdd %zmm0, (,%zmm1) {%k1}
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test28:
; SKX:       # %bb.0:
; SKX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    vpscatterqd %xmm0, (,%xmm1) {%k1}
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test28:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movb $3, %al
; SKX_32-NEXT:    kmovw %eax, %k1
; SKX_32-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SKX_32-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SKX_32-NEXT:    vpscatterdd %xmm0, (,%xmm1) {%k1}
; SKX_32-NEXT:    retl
  call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> %a1, <2 x i32*> %ptr, i32 4, <2 x i1> <i1 true, i1 true>)
  ret void
}

; SCALAR-LABEL: test29
; SCALAR:      extractelement <16 x float*>
; SCALAR-NEXT: load float
; SCALAR-NEXT: insertelement <16 x float>
; SCALAR-NEXT: extractelement <16 x float*>
; SCALAR-NEXT: load float

define <16 x float> @test29(float* %base, <16 x i32> %ind) {
; KNL_64-LABEL: test29:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    movw $44, %ax
; KNL_64-NEXT:    kmovw %eax, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; KNL_64-NEXT:    vmovaps %zmm1, %zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test29:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    movw $44, %cx
; KNL_32-NEXT:    kmovw %ecx, %k1
; KNL_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; KNL_32-NEXT:    vmovaps %zmm1, %zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test29:
; SKX:       # %bb.0:
; SKX-NEXT:    movw $44, %ax
; SKX-NEXT:    kmovw %eax, %k1
; SKX-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; SKX-NEXT:    vmovaps %zmm1, %zmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test29:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    movw $44, %cx
; SKX_32-NEXT:    kmovw %ecx, %k1
; SKX_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; SKX_32-NEXT:    vmovaps %zmm1, %zmm0
; SKX_32-NEXT:    retl

  %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
  %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer

  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind

  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 false, i1 false, i1 true, i1 true, i1 false, i1 true, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false>, <16 x float> undef)
  ret <16 x float>%res
}

; Check non-power-of-2 case. It should be scalarized.
declare <3 x i32> @llvm.masked.gather.v3i32.v3p0i32(<3 x i32*>, i32, <3 x i1>, <3 x i32>)
define <3 x i32> @test30(<3 x i32*> %base, <3 x i32> %ind, <3 x i1> %mask, <3 x i32> %src0) {
; KNL_64-LABEL: test30:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpslld $31, %xmm2, %xmm2
; KNL_64-NEXT:    vptestmd %zmm2, %zmm2, %k0
; KNL_64-NEXT:    kmovw %k0, %eax
; KNL_64-NEXT:    vpmovsxdq %xmm1, %ymm1
; KNL_64-NEXT:    vpsllq $2, %ymm1, %ymm1
; KNL_64-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
; KNL_64-NEXT:    testb $1, %al
; KNL_64-NEXT:    je .LBB31_2
; KNL_64-NEXT:  # %bb.1: # %cond.load
; KNL_64-NEXT:    vmovq %xmm0, %rax
; KNL_64-NEXT:    vpinsrd $0, (%rax), %xmm3, %xmm3
; KNL_64-NEXT:  .LBB31_2: # %else
; KNL_64-NEXT:    kshiftrw $1, %k0, %k1
; KNL_64-NEXT:    kmovw %k1, %eax
; KNL_64-NEXT:    testb $1, %al
; KNL_64-NEXT:    je .LBB31_4
; KNL_64-NEXT:  # %bb.3: # %cond.load1
; KNL_64-NEXT:    vpextrq $1, %xmm0, %rax
; KNL_64-NEXT:    vpinsrd $1, (%rax), %xmm3, %xmm3
; KNL_64-NEXT:  .LBB31_4: # %else2
; KNL_64-NEXT:    kshiftrw $2, %k0, %k0
; KNL_64-NEXT:    kmovw %k0, %eax
; KNL_64-NEXT:    testb $1, %al
; KNL_64-NEXT:    je .LBB31_6
; KNL_64-NEXT:  # %bb.5: # %cond.load4
; KNL_64-NEXT:    vextracti128 $1, %ymm0, %xmm0
; KNL_64-NEXT:    vmovq %xmm0, %rax
; KNL_64-NEXT:    vpinsrd $2, (%rax), %xmm3, %xmm3
; KNL_64-NEXT:  .LBB31_6: # %else5
; KNL_64-NEXT:    vmovdqa %xmm3, %xmm0
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test30:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    subl $12, %esp
; KNL_32-NEXT:    .cfi_def_cfa_offset 16
; KNL_32-NEXT:    vmovdqa %xmm0, %xmm3
; KNL_32-NEXT:    vpslld $31, %xmm2, %xmm0
; KNL_32-NEXT:    vptestmd %zmm0, %zmm0, %k0
; KNL_32-NEXT:    kmovw %k0, %eax
; KNL_32-NEXT:    vmovdqa {{[0-9]+}}(%esp), %xmm0
; KNL_32-NEXT:    vpslld $2, %xmm1, %xmm1
; KNL_32-NEXT:    vpaddd %xmm1, %xmm3, %xmm1
; KNL_32-NEXT:    testb $1, %al
; KNL_32-NEXT:    je .LBB31_2
; KNL_32-NEXT:  # %bb.1: # %cond.load
; KNL_32-NEXT:    vmovd %xmm1, %eax
; KNL_32-NEXT:    vpinsrd $0, (%eax), %xmm0, %xmm0
; KNL_32-NEXT:  .LBB31_2: # %else
; KNL_32-NEXT:    kshiftrw $1, %k0, %k1
; KNL_32-NEXT:    kmovw %k1, %eax
; KNL_32-NEXT:    testb $1, %al
; KNL_32-NEXT:    je .LBB31_4
; KNL_32-NEXT:  # %bb.3: # %cond.load1
; KNL_32-NEXT:    vpextrd $1, %xmm1, %eax
; KNL_32-NEXT:    vpinsrd $1, (%eax), %xmm0, %xmm0
; KNL_32-NEXT:  .LBB31_4: # %else2
; KNL_32-NEXT:    kshiftrw $2, %k0, %k0
; KNL_32-NEXT:    kmovw %k0, %eax
; KNL_32-NEXT:    testb $1, %al
; KNL_32-NEXT:    je .LBB31_6
; KNL_32-NEXT:  # %bb.5: # %cond.load4
; KNL_32-NEXT:    vpextrd $2, %xmm1, %eax
; KNL_32-NEXT:    vpinsrd $2, (%eax), %xmm0, %xmm0
; KNL_32-NEXT:  .LBB31_6: # %else5
; KNL_32-NEXT:    addl $12, %esp
; KNL_32-NEXT:    .cfi_def_cfa_offset 4
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test30:
; SKX:       # %bb.0:
; SKX-NEXT:    vpslld $31, %xmm2, %xmm2
; SKX-NEXT:    vpmovd2m %xmm2, %k0
; SKX-NEXT:    kmovw %k0, %eax
; SKX-NEXT:    vpmovsxdq %xmm1, %ymm1
; SKX-NEXT:    vpsllq $2, %ymm1, %ymm1
; SKX-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
; SKX-NEXT:    testb $1, %al
; SKX-NEXT:    je .LBB31_2
; SKX-NEXT:  # %bb.1: # %cond.load
; SKX-NEXT:    vmovq %xmm0, %rax
; SKX-NEXT:    vpinsrd $0, (%rax), %xmm3, %xmm3
; SKX-NEXT:  .LBB31_2: # %else
; SKX-NEXT:    kshiftrb $1, %k0, %k1
; SKX-NEXT:    kmovw %k1, %eax
; SKX-NEXT:    testb $1, %al
; SKX-NEXT:    je .LBB31_4
; SKX-NEXT:  # %bb.3: # %cond.load1
; SKX-NEXT:    vpextrq $1, %xmm0, %rax
; SKX-NEXT:    vpinsrd $1, (%rax), %xmm3, %xmm3
; SKX-NEXT:  .LBB31_4: # %else2
; SKX-NEXT:    kshiftrb $2, %k0, %k0
; SKX-NEXT:    kmovw %k0, %eax
; SKX-NEXT:    testb $1, %al
; SKX-NEXT:    je .LBB31_6
; SKX-NEXT:  # %bb.5: # %cond.load4
; SKX-NEXT:    vextracti128 $1, %ymm0, %xmm0
; SKX-NEXT:    vmovq %xmm0, %rax
; SKX-NEXT:    vpinsrd $2, (%rax), %xmm3, %xmm3
; SKX-NEXT:  .LBB31_6: # %else5
; SKX-NEXT:    vmovdqa %xmm3, %xmm0
; SKX-NEXT:    vzeroupper
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test30:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    subl $12, %esp
; SKX_32-NEXT:    .cfi_def_cfa_offset 16
; SKX_32-NEXT:    vmovdqa %xmm0, %xmm3
; SKX_32-NEXT:    vpslld $31, %xmm2, %xmm0
; SKX_32-NEXT:    vpmovd2m %xmm0, %k0
; SKX_32-NEXT:    kmovw %k0, %eax
; SKX_32-NEXT:    vmovdqa {{[0-9]+}}(%esp), %xmm0
; SKX_32-NEXT:    vpslld $2, %xmm1, %xmm1
; SKX_32-NEXT:    vpaddd %xmm1, %xmm3, %xmm1
; SKX_32-NEXT:    testb $1, %al
; SKX_32-NEXT:    je .LBB31_2
; SKX_32-NEXT:  # %bb.1: # %cond.load
; SKX_32-NEXT:    vmovd %xmm1, %eax
; SKX_32-NEXT:    vpinsrd $0, (%eax), %xmm0, %xmm0
; SKX_32-NEXT:  .LBB31_2: # %else
; SKX_32-NEXT:    kshiftrb $1, %k0, %k1
; SKX_32-NEXT:    kmovw %k1, %eax
; SKX_32-NEXT:    testb $1, %al
; SKX_32-NEXT:    je .LBB31_4
; SKX_32-NEXT:  # %bb.3: # %cond.load1
; SKX_32-NEXT:    vpextrd $1, %xmm1, %eax
; SKX_32-NEXT:    vpinsrd $1, (%eax), %xmm0, %xmm0
; SKX_32-NEXT:  .LBB31_4: # %else2
; SKX_32-NEXT:    kshiftrb $2, %k0, %k0
; SKX_32-NEXT:    kmovw %k0, %eax
; SKX_32-NEXT:    testb $1, %al
; SKX_32-NEXT:    je .LBB31_6
; SKX_32-NEXT:  # %bb.5: # %cond.load4
; SKX_32-NEXT:    vpextrd $2, %xmm1, %eax
; SKX_32-NEXT:    vpinsrd $2, (%eax), %xmm0, %xmm0
; SKX_32-NEXT:  .LBB31_6: # %else5
; SKX_32-NEXT:    addl $12, %esp
; SKX_32-NEXT:    .cfi_def_cfa_offset 4
; SKX_32-NEXT:    retl

  %sext_ind = sext <3 x i32> %ind to <3 x i64>
  %gep.random = getelementptr i32, <3 x i32*> %base, <3 x i64> %sext_ind
  %res = call <3 x i32> @llvm.masked.gather.v3i32.v3p0i32(<3 x i32*> %gep.random, i32 4, <3 x i1> %mask, <3 x i32> %src0)
  ret <3 x i32>%res
}

declare <16 x float*> @llvm.masked.gather.v16p0f32.v16p0p0f32(<16 x float**>, i32, <16 x i1>, <16 x float*>)
define <16 x float*> @test31(<16 x float**> %ptrs) {
; KNL_64-LABEL: test31:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    kxnorw %k0, %k0, %k2
; KNL_64-NEXT:    vpgatherqq (,%zmm0), %zmm2 {%k2}
; KNL_64-NEXT:    vpgatherqq (,%zmm1), %zmm3 {%k1}
; KNL_64-NEXT:    vmovdqa64 %zmm2, %zmm0
; KNL_64-NEXT:    vmovdqa64 %zmm3, %zmm1
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test31:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    kxnorw %k0, %k0, %k1
; KNL_32-NEXT:    vpgatherdd (,%zmm0), %zmm1 {%k1}
; KNL_32-NEXT:    vmovdqa64 %zmm1, %zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test31:
; SKX:       # %bb.0:
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    kxnorw %k0, %k0, %k2
; SKX-NEXT:    vpgatherqq (,%zmm0), %zmm2 {%k2}
; SKX-NEXT:    vpgatherqq (,%zmm1), %zmm3 {%k1}
; SKX-NEXT:    vmovdqa64 %zmm2, %zmm0
; SKX-NEXT:    vmovdqa64 %zmm3, %zmm1
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test31:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vpgatherdd (,%zmm0), %zmm1 {%k1}
; SKX_32-NEXT:    vmovdqa64 %zmm1, %zmm0
; SKX_32-NEXT:    retl

  %res = call <16 x float*> @llvm.masked.gather.v16p0f32.v16p0p0f32(<16 x float**> %ptrs, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float*> undef)
  ret <16 x float*>%res
}

define <16 x i32> @test_gather_16i32(<16 x i32*> %ptrs, <16 x i1> %mask, <16 x i32> %src0)  {
; KNL_64-LABEL: test_gather_16i32:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; KNL_64-NEXT:    vpslld $31, %zmm2, %zmm2
; KNL_64-NEXT:    vptestmd %zmm2, %zmm2, %k1
; KNL_64-NEXT:    vextracti64x4 $1, %zmm3, %ymm2
; KNL_64-NEXT:    kshiftrw $8, %k1, %k2
; KNL_64-NEXT:    vpgatherqd (,%zmm1), %ymm2 {%k2}
; KNL_64-NEXT:    vpgatherqd (,%zmm0), %ymm3 {%k1}
; KNL_64-NEXT:    vinserti64x4 $1, %ymm2, %zmm3, %zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_gather_16i32:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; KNL_32-NEXT:    vpslld $31, %zmm1, %zmm1
; KNL_32-NEXT:    vptestmd %zmm1, %zmm1, %k1
; KNL_32-NEXT:    vpgatherdd (,%zmm0), %zmm2 {%k1}
; KNL_32-NEXT:    vmovdqa64 %zmm2, %zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_gather_16i32:
; SKX:       # %bb.0:
; SKX-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; SKX-NEXT:    vpslld $31, %zmm2, %zmm2
; SKX-NEXT:    vpmovd2m %zmm2, %k1
; SKX-NEXT:    vextracti64x4 $1, %zmm3, %ymm2
; SKX-NEXT:    kshiftrw $8, %k1, %k2
; SKX-NEXT:    vpgatherqd (,%zmm1), %ymm2 {%k2}
; SKX-NEXT:    vpgatherqd (,%zmm0), %ymm3 {%k1}
; SKX-NEXT:    vinserti64x4 $1, %ymm2, %zmm3, %zmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_gather_16i32:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; SKX_32-NEXT:    vpslld $31, %zmm1, %zmm1
; SKX_32-NEXT:    vpmovd2m %zmm1, %k1
; SKX_32-NEXT:    vpgatherdd (,%zmm0), %zmm2 {%k1}
; SKX_32-NEXT:    vmovdqa64 %zmm2, %zmm0
; SKX_32-NEXT:    retl
  %res = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> %ptrs, i32 4, <16 x i1> %mask, <16 x i32> %src0)
  ret <16 x i32> %res
}
define <16 x i64> @test_gather_16i64(<16 x i64*> %ptrs, <16 x i1> %mask, <16 x i64> %src0)  {
; KNL_64-LABEL: test_gather_16i64:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; KNL_64-NEXT:    vpslld $31, %zmm2, %zmm2
; KNL_64-NEXT:    vptestmd %zmm2, %zmm2, %k1
; KNL_64-NEXT:    kshiftrw $8, %k1, %k2
; KNL_64-NEXT:    vpgatherqq (,%zmm0), %zmm3 {%k1}
; KNL_64-NEXT:    vpgatherqq (,%zmm1), %zmm4 {%k2}
; KNL_64-NEXT:    vmovdqa64 %zmm3, %zmm0
; KNL_64-NEXT:    vmovdqa64 %zmm4, %zmm1
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_gather_16i64:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    pushl %ebp
; KNL_32-NEXT:    .cfi_def_cfa_offset 8
; KNL_32-NEXT:    .cfi_offset %ebp, -8
; KNL_32-NEXT:    movl %esp, %ebp
; KNL_32-NEXT:    .cfi_def_cfa_register %ebp
; KNL_32-NEXT:    andl $-64, %esp
; KNL_32-NEXT:    subl $64, %esp
; KNL_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; KNL_32-NEXT:    vpslld $31, %zmm1, %zmm1
; KNL_32-NEXT:    vptestmd %zmm1, %zmm1, %k1
; KNL_32-NEXT:    vmovdqa64 8(%ebp), %zmm1
; KNL_32-NEXT:    kshiftrw $8, %k1, %k2
; KNL_32-NEXT:    vpgatherdq (,%ymm0), %zmm2 {%k1}
; KNL_32-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
; KNL_32-NEXT:    vpgatherdq (,%ymm0), %zmm1 {%k2}
; KNL_32-NEXT:    vmovdqa64 %zmm2, %zmm0
; KNL_32-NEXT:    movl %ebp, %esp
; KNL_32-NEXT:    popl %ebp
; KNL_32-NEXT:    .cfi_def_cfa %esp, 4
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_gather_16i64:
; SKX:       # %bb.0:
; SKX-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; SKX-NEXT:    vpslld $31, %zmm2, %zmm2
; SKX-NEXT:    vpmovd2m %zmm2, %k1
; SKX-NEXT:    kshiftrw $8, %k1, %k2
; SKX-NEXT:    vpgatherqq (,%zmm0), %zmm3 {%k1}
; SKX-NEXT:    vpgatherqq (,%zmm1), %zmm4 {%k2}
; SKX-NEXT:    vmovdqa64 %zmm3, %zmm0
; SKX-NEXT:    vmovdqa64 %zmm4, %zmm1
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_gather_16i64:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    pushl %ebp
; SKX_32-NEXT:    .cfi_def_cfa_offset 8
; SKX_32-NEXT:    .cfi_offset %ebp, -8
; SKX_32-NEXT:    movl %esp, %ebp
; SKX_32-NEXT:    .cfi_def_cfa_register %ebp
; SKX_32-NEXT:    andl $-64, %esp
; SKX_32-NEXT:    subl $64, %esp
; SKX_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; SKX_32-NEXT:    vpslld $31, %zmm1, %zmm1
; SKX_32-NEXT:    vpmovd2m %zmm1, %k1
; SKX_32-NEXT:    vmovdqa64 8(%ebp), %zmm1
; SKX_32-NEXT:    kshiftrw $8, %k1, %k2
; SKX_32-NEXT:    vpgatherdq (,%ymm0), %zmm2 {%k1}
; SKX_32-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
; SKX_32-NEXT:    vpgatherdq (,%ymm0), %zmm1 {%k2}
; SKX_32-NEXT:    vmovdqa64 %zmm2, %zmm0
; SKX_32-NEXT:    movl %ebp, %esp
; SKX_32-NEXT:    popl %ebp
; SKX_32-NEXT:    .cfi_def_cfa %esp, 4
; SKX_32-NEXT:    retl
  %res = call <16 x i64> @llvm.masked.gather.v16i64.v16p0i64(<16 x i64*> %ptrs, i32 4, <16 x i1> %mask, <16 x i64> %src0)
  ret <16 x i64> %res
}
declare <16 x i64> @llvm.masked.gather.v16i64.v16p0i64(<16 x i64*> %ptrs, i32, <16 x i1> %mask, <16 x i64> %src0)
define <16 x float> @test_gather_16f32(<16 x float*> %ptrs, <16 x i1> %mask, <16 x float> %src0)  {
; KNL_64-LABEL: test_gather_16f32:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; KNL_64-NEXT:    vpslld $31, %zmm2, %zmm2
; KNL_64-NEXT:    vptestmd %zmm2, %zmm2, %k1
; KNL_64-NEXT:    vextractf64x4 $1, %zmm3, %ymm2
; KNL_64-NEXT:    kshiftrw $8, %k1, %k2
; KNL_64-NEXT:    vgatherqps (,%zmm1), %ymm2 {%k2}
; KNL_64-NEXT:    vgatherqps (,%zmm0), %ymm3 {%k1}
; KNL_64-NEXT:    vinsertf64x4 $1, %ymm2, %zmm3, %zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_gather_16f32:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; KNL_32-NEXT:    vpslld $31, %zmm1, %zmm1
; KNL_32-NEXT:    vptestmd %zmm1, %zmm1, %k1
; KNL_32-NEXT:    vgatherdps (,%zmm0), %zmm2 {%k1}
; KNL_32-NEXT:    vmovaps %zmm2, %zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_gather_16f32:
; SKX:       # %bb.0:
; SKX-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; SKX-NEXT:    vpslld $31, %zmm2, %zmm2
; SKX-NEXT:    vpmovd2m %zmm2, %k1
; SKX-NEXT:    vextractf64x4 $1, %zmm3, %ymm2
; SKX-NEXT:    kshiftrw $8, %k1, %k2
; SKX-NEXT:    vgatherqps (,%zmm1), %ymm2 {%k2}
; SKX-NEXT:    vgatherqps (,%zmm0), %ymm3 {%k1}
; SKX-NEXT:    vinsertf64x4 $1, %ymm2, %zmm3, %zmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_gather_16f32:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; SKX_32-NEXT:    vpslld $31, %zmm1, %zmm1
; SKX_32-NEXT:    vpmovd2m %zmm1, %k1
; SKX_32-NEXT:    vgatherdps (,%zmm0), %zmm2 {%k1}
; SKX_32-NEXT:    vmovaps %zmm2, %zmm0
; SKX_32-NEXT:    retl
  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %ptrs, i32 4, <16 x i1> %mask, <16 x float> %src0)
  ret <16 x float> %res
}
define <16 x double> @test_gather_16f64(<16 x double*> %ptrs, <16 x i1> %mask, <16 x double> %src0)  {
; KNL_64-LABEL: test_gather_16f64:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; KNL_64-NEXT:    vpslld $31, %zmm2, %zmm2
; KNL_64-NEXT:    vptestmd %zmm2, %zmm2, %k1
; KNL_64-NEXT:    kshiftrw $8, %k1, %k2
; KNL_64-NEXT:    vgatherqpd (,%zmm0), %zmm3 {%k1}
; KNL_64-NEXT:    vgatherqpd (,%zmm1), %zmm4 {%k2}
; KNL_64-NEXT:    vmovapd %zmm3, %zmm0
; KNL_64-NEXT:    vmovapd %zmm4, %zmm1
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_gather_16f64:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    pushl %ebp
; KNL_32-NEXT:    .cfi_def_cfa_offset 8
; KNL_32-NEXT:    .cfi_offset %ebp, -8
; KNL_32-NEXT:    movl %esp, %ebp
; KNL_32-NEXT:    .cfi_def_cfa_register %ebp
; KNL_32-NEXT:    andl $-64, %esp
; KNL_32-NEXT:    subl $64, %esp
; KNL_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; KNL_32-NEXT:    vpslld $31, %zmm1, %zmm1
; KNL_32-NEXT:    vptestmd %zmm1, %zmm1, %k1
; KNL_32-NEXT:    vmovapd 8(%ebp), %zmm1
; KNL_32-NEXT:    kshiftrw $8, %k1, %k2
; KNL_32-NEXT:    vgatherdpd (,%ymm0), %zmm2 {%k1}
; KNL_32-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
; KNL_32-NEXT:    vgatherdpd (,%ymm0), %zmm1 {%k2}
; KNL_32-NEXT:    vmovapd %zmm2, %zmm0
; KNL_32-NEXT:    movl %ebp, %esp
; KNL_32-NEXT:    popl %ebp
; KNL_32-NEXT:    .cfi_def_cfa %esp, 4
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_gather_16f64:
; SKX:       # %bb.0:
; SKX-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; SKX-NEXT:    vpslld $31, %zmm2, %zmm2
; SKX-NEXT:    vpmovd2m %zmm2, %k1
; SKX-NEXT:    kshiftrw $8, %k1, %k2
; SKX-NEXT:    vgatherqpd (,%zmm0), %zmm3 {%k1}
; SKX-NEXT:    vgatherqpd (,%zmm1), %zmm4 {%k2}
; SKX-NEXT:    vmovapd %zmm3, %zmm0
; SKX-NEXT:    vmovapd %zmm4, %zmm1
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_gather_16f64:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    pushl %ebp
; SKX_32-NEXT:    .cfi_def_cfa_offset 8
; SKX_32-NEXT:    .cfi_offset %ebp, -8
; SKX_32-NEXT:    movl %esp, %ebp
; SKX_32-NEXT:    .cfi_def_cfa_register %ebp
; SKX_32-NEXT:    andl $-64, %esp
; SKX_32-NEXT:    subl $64, %esp
; SKX_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; SKX_32-NEXT:    vpslld $31, %zmm1, %zmm1
; SKX_32-NEXT:    vpmovd2m %zmm1, %k1
; SKX_32-NEXT:    vmovapd 8(%ebp), %zmm1
; SKX_32-NEXT:    kshiftrw $8, %k1, %k2
; SKX_32-NEXT:    vgatherdpd (,%ymm0), %zmm2 {%k1}
; SKX_32-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
; SKX_32-NEXT:    vgatherdpd (,%ymm0), %zmm1 {%k2}
; SKX_32-NEXT:    vmovapd %zmm2, %zmm0
; SKX_32-NEXT:    movl %ebp, %esp
; SKX_32-NEXT:    popl %ebp
; SKX_32-NEXT:    .cfi_def_cfa %esp, 4
; SKX_32-NEXT:    retl
  %res = call <16 x double> @llvm.masked.gather.v16f64.v16p0f64(<16 x double*> %ptrs, i32 4, <16 x i1> %mask, <16 x double> %src0)
  ret <16 x double> %res
}
declare <16 x double> @llvm.masked.gather.v16f64.v16p0f64(<16 x double*> %ptrs, i32, <16 x i1> %mask, <16 x double> %src0)
define void @test_scatter_16i32(<16 x i32*> %ptrs, <16 x i1> %mask, <16 x i32> %src0)  {
; KNL_64-LABEL: test_scatter_16i32:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; KNL_64-NEXT:    vpslld $31, %zmm2, %zmm2
; KNL_64-NEXT:    vptestmd %zmm2, %zmm2, %k1
; KNL_64-NEXT:    kshiftrw $8, %k1, %k2
; KNL_64-NEXT:    vpscatterqd %ymm3, (,%zmm0) {%k1}
; KNL_64-NEXT:    vextracti64x4 $1, %zmm3, %ymm0
; KNL_64-NEXT:    vpscatterqd %ymm0, (,%zmm1) {%k2}
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_scatter_16i32:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; KNL_32-NEXT:    vpslld $31, %zmm1, %zmm1
; KNL_32-NEXT:    vptestmd %zmm1, %zmm1, %k1
; KNL_32-NEXT:    vpscatterdd %zmm2, (,%zmm0) {%k1}
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_scatter_16i32:
; SKX:       # %bb.0:
; SKX-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; SKX-NEXT:    vpslld $31, %zmm2, %zmm2
; SKX-NEXT:    vpmovd2m %zmm2, %k1
; SKX-NEXT:    kshiftrw $8, %k1, %k2
; SKX-NEXT:    vpscatterqd %ymm3, (,%zmm0) {%k1}
; SKX-NEXT:    vextracti64x4 $1, %zmm3, %ymm0
; SKX-NEXT:    vpscatterqd %ymm0, (,%zmm1) {%k2}
; SKX-NEXT:    vzeroupper
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_scatter_16i32:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; SKX_32-NEXT:    vpslld $31, %zmm1, %zmm1
; SKX_32-NEXT:    vpmovd2m %zmm1, %k1
; SKX_32-NEXT:    vpscatterdd %zmm2, (,%zmm0) {%k1}
; SKX_32-NEXT:    vzeroupper
; SKX_32-NEXT:    retl
  call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %src0, <16 x i32*> %ptrs, i32 4, <16 x i1> %mask)
  ret void
}
define void @test_scatter_16i64(<16 x i64*> %ptrs, <16 x i1> %mask, <16 x i64> %src0)  {
; KNL_64-LABEL: test_scatter_16i64:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; KNL_64-NEXT:    vpslld $31, %zmm2, %zmm2
; KNL_64-NEXT:    vptestmd %zmm2, %zmm2, %k1
; KNL_64-NEXT:    kshiftrw $8, %k1, %k2
; KNL_64-NEXT:    vpscatterqq %zmm3, (,%zmm0) {%k1}
; KNL_64-NEXT:    vpscatterqq %zmm4, (,%zmm1) {%k2}
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_scatter_16i64:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    pushl %ebp
; KNL_32-NEXT:    .cfi_def_cfa_offset 8
; KNL_32-NEXT:    .cfi_offset %ebp, -8
; KNL_32-NEXT:    movl %esp, %ebp
; KNL_32-NEXT:    .cfi_def_cfa_register %ebp
; KNL_32-NEXT:    andl $-64, %esp
; KNL_32-NEXT:    subl $64, %esp
; KNL_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; KNL_32-NEXT:    vpslld $31, %zmm1, %zmm1
; KNL_32-NEXT:    vptestmd %zmm1, %zmm1, %k1
; KNL_32-NEXT:    vmovdqa64 8(%ebp), %zmm1
; KNL_32-NEXT:    kshiftrw $8, %k1, %k2
; KNL_32-NEXT:    vpscatterdq %zmm2, (,%ymm0) {%k1}
; KNL_32-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
; KNL_32-NEXT:    vpscatterdq %zmm1, (,%ymm0) {%k2}
; KNL_32-NEXT:    movl %ebp, %esp
; KNL_32-NEXT:    popl %ebp
; KNL_32-NEXT:    .cfi_def_cfa %esp, 4
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_scatter_16i64:
; SKX:       # %bb.0:
; SKX-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; SKX-NEXT:    vpslld $31, %zmm2, %zmm2
; SKX-NEXT:    vpmovd2m %zmm2, %k1
; SKX-NEXT:    kshiftrw $8, %k1, %k2
; SKX-NEXT:    vpscatterqq %zmm3, (,%zmm0) {%k1}
; SKX-NEXT:    vpscatterqq %zmm4, (,%zmm1) {%k2}
; SKX-NEXT:    vzeroupper
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_scatter_16i64:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    pushl %ebp
; SKX_32-NEXT:    .cfi_def_cfa_offset 8
; SKX_32-NEXT:    .cfi_offset %ebp, -8
; SKX_32-NEXT:    movl %esp, %ebp
; SKX_32-NEXT:    .cfi_def_cfa_register %ebp
; SKX_32-NEXT:    andl $-64, %esp
; SKX_32-NEXT:    subl $64, %esp
; SKX_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; SKX_32-NEXT:    vpslld $31, %zmm1, %zmm1
; SKX_32-NEXT:    vpmovd2m %zmm1, %k1
; SKX_32-NEXT:    vmovdqa64 8(%ebp), %zmm1
; SKX_32-NEXT:    kshiftrw $8, %k1, %k2
; SKX_32-NEXT:    vpscatterdq %zmm2, (,%ymm0) {%k1}
; SKX_32-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
; SKX_32-NEXT:    vpscatterdq %zmm1, (,%ymm0) {%k2}
; SKX_32-NEXT:    movl %ebp, %esp
; SKX_32-NEXT:    popl %ebp
; SKX_32-NEXT:    .cfi_def_cfa %esp, 4
; SKX_32-NEXT:    vzeroupper
; SKX_32-NEXT:    retl
  call void @llvm.masked.scatter.v16i64.v16p0i64(<16 x i64> %src0, <16 x i64*> %ptrs, i32 4, <16 x i1> %mask)
  ret void
}
declare void @llvm.masked.scatter.v16i64.v16p0i64(<16 x i64> %src0, <16 x i64*> %ptrs, i32, <16 x i1> %mask)
define void @test_scatter_16f32(<16 x float*> %ptrs, <16 x i1> %mask, <16 x float> %src0)  {
; KNL_64-LABEL: test_scatter_16f32:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; KNL_64-NEXT:    vpslld $31, %zmm2, %zmm2
; KNL_64-NEXT:    vptestmd %zmm2, %zmm2, %k1
; KNL_64-NEXT:    kshiftrw $8, %k1, %k2
; KNL_64-NEXT:    vscatterqps %ymm3, (,%zmm0) {%k1}
; KNL_64-NEXT:    vextractf64x4 $1, %zmm3, %ymm0
; KNL_64-NEXT:    vscatterqps %ymm0, (,%zmm1) {%k2}
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_scatter_16f32:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; KNL_32-NEXT:    vpslld $31, %zmm1, %zmm1
; KNL_32-NEXT:    vptestmd %zmm1, %zmm1, %k1
; KNL_32-NEXT:    vscatterdps %zmm2, (,%zmm0) {%k1}
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_scatter_16f32:
; SKX:       # %bb.0:
; SKX-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; SKX-NEXT:    vpslld $31, %zmm2, %zmm2
; SKX-NEXT:    vpmovd2m %zmm2, %k1
; SKX-NEXT:    kshiftrw $8, %k1, %k2
; SKX-NEXT:    vscatterqps %ymm3, (,%zmm0) {%k1}
; SKX-NEXT:    vextractf64x4 $1, %zmm3, %ymm0
; SKX-NEXT:    vscatterqps %ymm0, (,%zmm1) {%k2}
; SKX-NEXT:    vzeroupper
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_scatter_16f32:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; SKX_32-NEXT:    vpslld $31, %zmm1, %zmm1
; SKX_32-NEXT:    vpmovd2m %zmm1, %k1
; SKX_32-NEXT:    vscatterdps %zmm2, (,%zmm0) {%k1}
; SKX_32-NEXT:    vzeroupper
; SKX_32-NEXT:    retl
  call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %src0, <16 x float*> %ptrs, i32 4, <16 x i1> %mask)
  ret void
}
declare void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> %src0, <16 x float*> %ptrs, i32, <16 x i1> %mask)
define void @test_scatter_16f64(<16 x double*> %ptrs, <16 x i1> %mask, <16 x double> %src0)  {
; KNL_64-LABEL: test_scatter_16f64:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; KNL_64-NEXT:    vpslld $31, %zmm2, %zmm2
; KNL_64-NEXT:    vptestmd %zmm2, %zmm2, %k1
; KNL_64-NEXT:    kshiftrw $8, %k1, %k2
; KNL_64-NEXT:    vscatterqpd %zmm3, (,%zmm0) {%k1}
; KNL_64-NEXT:    vscatterqpd %zmm4, (,%zmm1) {%k2}
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_scatter_16f64:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    pushl %ebp
; KNL_32-NEXT:    .cfi_def_cfa_offset 8
; KNL_32-NEXT:    .cfi_offset %ebp, -8
; KNL_32-NEXT:    movl %esp, %ebp
; KNL_32-NEXT:    .cfi_def_cfa_register %ebp
; KNL_32-NEXT:    andl $-64, %esp
; KNL_32-NEXT:    subl $64, %esp
; KNL_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; KNL_32-NEXT:    vpslld $31, %zmm1, %zmm1
; KNL_32-NEXT:    vptestmd %zmm1, %zmm1, %k1
; KNL_32-NEXT:    vmovapd 8(%ebp), %zmm1
; KNL_32-NEXT:    kshiftrw $8, %k1, %k2
; KNL_32-NEXT:    vscatterdpd %zmm2, (,%ymm0) {%k1}
; KNL_32-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
; KNL_32-NEXT:    vscatterdpd %zmm1, (,%ymm0) {%k2}
; KNL_32-NEXT:    movl %ebp, %esp
; KNL_32-NEXT:    popl %ebp
; KNL_32-NEXT:    .cfi_def_cfa %esp, 4
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_scatter_16f64:
; SKX:       # %bb.0:
; SKX-NEXT:    vpmovzxbd {{.*#+}} zmm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero,xmm2[8],zero,zero,zero,xmm2[9],zero,zero,zero,xmm2[10],zero,zero,zero,xmm2[11],zero,zero,zero,xmm2[12],zero,zero,zero,xmm2[13],zero,zero,zero,xmm2[14],zero,zero,zero,xmm2[15],zero,zero,zero
; SKX-NEXT:    vpslld $31, %zmm2, %zmm2
; SKX-NEXT:    vpmovd2m %zmm2, %k1
; SKX-NEXT:    kshiftrw $8, %k1, %k2
; SKX-NEXT:    vscatterqpd %zmm3, (,%zmm0) {%k1}
; SKX-NEXT:    vscatterqpd %zmm4, (,%zmm1) {%k2}
; SKX-NEXT:    vzeroupper
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_scatter_16f64:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    pushl %ebp
; SKX_32-NEXT:    .cfi_def_cfa_offset 8
; SKX_32-NEXT:    .cfi_offset %ebp, -8
; SKX_32-NEXT:    movl %esp, %ebp
; SKX_32-NEXT:    .cfi_def_cfa_register %ebp
; SKX_32-NEXT:    andl $-64, %esp
; SKX_32-NEXT:    subl $64, %esp
; SKX_32-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
; SKX_32-NEXT:    vpslld $31, %zmm1, %zmm1
; SKX_32-NEXT:    vpmovd2m %zmm1, %k1
; SKX_32-NEXT:    vmovapd 8(%ebp), %zmm1
; SKX_32-NEXT:    kshiftrw $8, %k1, %k2
; SKX_32-NEXT:    vscatterdpd %zmm2, (,%ymm0) {%k1}
; SKX_32-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
; SKX_32-NEXT:    vscatterdpd %zmm1, (,%ymm0) {%k2}
; SKX_32-NEXT:    movl %ebp, %esp
; SKX_32-NEXT:    popl %ebp
; SKX_32-NEXT:    .cfi_def_cfa %esp, 4
; SKX_32-NEXT:    vzeroupper
; SKX_32-NEXT:    retl
  call void @llvm.masked.scatter.v16f64.v16p0f64(<16 x double> %src0, <16 x double*> %ptrs, i32 4, <16 x i1> %mask)
  ret void
}
declare void @llvm.masked.scatter.v16f64.v16p0f64(<16 x double> %src0, <16 x double*> %ptrs, i32, <16 x i1> %mask)

define <4 x i64> @test_pr28312(<4 x i64*> %p1, <4 x i1> %k, <4 x i1> %k2,<4 x i64> %d) {
; KNL_64-LABEL: test_pr28312:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $ymm0 killed $ymm0 def $zmm0
; KNL_64-NEXT:    vpslld $31, %xmm1, %xmm1
; KNL_64-NEXT:    vptestmd %zmm1, %zmm1, %k0
; KNL_64-NEXT:    kshiftlw $12, %k0, %k0
; KNL_64-NEXT:    kshiftrw $12, %k0, %k1
; KNL_64-NEXT:    vpgatherqq (,%zmm0), %zmm1 {%k1}
; KNL_64-NEXT:    vpaddq %ymm1, %ymm1, %ymm0
; KNL_64-NEXT:    vpaddq %ymm0, %ymm1, %ymm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_pr28312:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    pushl %ebp
; KNL_32-NEXT:    .cfi_def_cfa_offset 8
; KNL_32-NEXT:    .cfi_offset %ebp, -8
; KNL_32-NEXT:    movl %esp, %ebp
; KNL_32-NEXT:    .cfi_def_cfa_register %ebp
; KNL_32-NEXT:    andl $-32, %esp
; KNL_32-NEXT:    subl $32, %esp
; KNL_32-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
; KNL_32-NEXT:    vpslld $31, %xmm1, %xmm1
; KNL_32-NEXT:    vptestmd %zmm1, %zmm1, %k0
; KNL_32-NEXT:    kshiftlw $12, %k0, %k0
; KNL_32-NEXT:    kshiftrw $12, %k0, %k1
; KNL_32-NEXT:    vpgatherdq (,%ymm0), %zmm1 {%k1}
; KNL_32-NEXT:    vpaddq %ymm1, %ymm1, %ymm0
; KNL_32-NEXT:    vpaddq %ymm0, %ymm1, %ymm0
; KNL_32-NEXT:    movl %ebp, %esp
; KNL_32-NEXT:    popl %ebp
; KNL_32-NEXT:    .cfi_def_cfa %esp, 4
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_pr28312:
; SKX:       # %bb.0:
; SKX-NEXT:    vpslld $31, %xmm1, %xmm1
; SKX-NEXT:    vpmovd2m %xmm1, %k1
; SKX-NEXT:    vpgatherqq (,%ymm0), %ymm1 {%k1}
; SKX-NEXT:    vpaddq %ymm1, %ymm1, %ymm0
; SKX-NEXT:    vpaddq %ymm0, %ymm1, %ymm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_pr28312:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    pushl %ebp
; SKX_32-NEXT:    .cfi_def_cfa_offset 8
; SKX_32-NEXT:    .cfi_offset %ebp, -8
; SKX_32-NEXT:    movl %esp, %ebp
; SKX_32-NEXT:    .cfi_def_cfa_register %ebp
; SKX_32-NEXT:    andl $-32, %esp
; SKX_32-NEXT:    subl $32, %esp
; SKX_32-NEXT:    vpslld $31, %xmm1, %xmm1
; SKX_32-NEXT:    vpmovd2m %xmm1, %k1
; SKX_32-NEXT:    vpgatherdq (,%xmm0), %ymm1 {%k1}
; SKX_32-NEXT:    vpaddq %ymm1, %ymm1, %ymm0
; SKX_32-NEXT:    vpaddq %ymm0, %ymm1, %ymm0
; SKX_32-NEXT:    movl %ebp, %esp
; SKX_32-NEXT:    popl %ebp
; SKX_32-NEXT:    .cfi_def_cfa %esp, 4
; SKX_32-NEXT:    retl
  %g1 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef)
  %g2 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef)
  %g3 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> %p1, i32 8, <4 x i1> %k, <4 x i64> undef)
  %a = add <4 x i64> %g1, %g2
  %b = add <4 x i64> %a, %g3
  ret <4 x i64> %b
}
declare <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*>, i32, <4 x i1>, <4 x i64>)

define <8 x i32> @test_global_array(<8 x i64> %indxs) {
; KNL_64-LABEL: test_global_array:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    vpgatherqd glob_array(,%zmm0,4), %ymm1 {%k1}
; KNL_64-NEXT:    vmovdqa %ymm1, %ymm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_global_array:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    kxnorw %k0, %k0, %k1
; KNL_32-NEXT:    vpgatherqd glob_array(,%zmm0,4), %ymm1 {%k1}
; KNL_32-NEXT:    vmovdqa %ymm1, %ymm0
; KNL_32-NEXT:    retl
;
; SKX_SMALL-LABEL: test_global_array:
; SKX_SMALL:       # %bb.0:
; SKX_SMALL-NEXT:    kxnorw %k0, %k0, %k1
; SKX_SMALL-NEXT:    vpgatherqd glob_array(,%zmm0,4), %ymm1 {%k1}
; SKX_SMALL-NEXT:    vmovdqa %ymm1, %ymm0
; SKX_SMALL-NEXT:    retq
;
; SKX_LARGE-LABEL: test_global_array:
; SKX_LARGE:       # %bb.0:
; SKX_LARGE-NEXT:    movabsq $glob_array, %rax
; SKX_LARGE-NEXT:    kxnorw %k0, %k0, %k1
; SKX_LARGE-NEXT:    vpgatherqd (%rax,%zmm0,4), %ymm1 {%k1}
; SKX_LARGE-NEXT:    vmovdqa %ymm1, %ymm0
; SKX_LARGE-NEXT:    retq
;
; SKX_32-LABEL: test_global_array:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vpgatherqd glob_array(,%zmm0,4), %ymm1 {%k1}
; SKX_32-NEXT:    vmovdqa %ymm1, %ymm0
; SKX_32-NEXT:    retl
  %p = getelementptr inbounds [16 x i32], [16 x i32]* @glob_array, i64 0, <8 x i64> %indxs
  %g = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> %p, i32 8, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x i32> undef)
  ret <8 x i32> %g
}

define void @v1_scatter(<1 x i32>%a1, <1 x i32*> %ptr, <1 x i1> %mask) {
; KNL_64-LABEL: v1_scatter:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    testb $1, %dl
; KNL_64-NEXT:    je .LBB43_2
; KNL_64-NEXT:  # %bb.1: # %cond.store
; KNL_64-NEXT:    movl %edi, (%rsi)
; KNL_64-NEXT:  .LBB43_2: # %else
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: v1_scatter:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    testb $1, {{[0-9]+}}(%esp)
; KNL_32-NEXT:    je .LBB43_2
; KNL_32-NEXT:  # %bb.1: # %cond.store
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; KNL_32-NEXT:    movl %ecx, (%eax)
; KNL_32-NEXT:  .LBB43_2: # %else
; KNL_32-NEXT:    retl
;
; SKX-LABEL: v1_scatter:
; SKX:       # %bb.0:
; SKX-NEXT:    testb $1, %dl
; SKX-NEXT:    je .LBB43_2
; SKX-NEXT:  # %bb.1: # %cond.store
; SKX-NEXT:    movl %edi, (%rsi)
; SKX-NEXT:  .LBB43_2: # %else
; SKX-NEXT:    retq
;
; SKX_32-LABEL: v1_scatter:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    testb $1, {{[0-9]+}}(%esp)
; SKX_32-NEXT:    je .LBB43_2
; SKX_32-NEXT:  # %bb.1: # %cond.store
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; SKX_32-NEXT:    movl %ecx, (%eax)
; SKX_32-NEXT:  .LBB43_2: # %else
; SKX_32-NEXT:    retl
  call void @llvm.masked.scatter.v1i32.v1p0i32(<1 x i32> %a1, <1 x i32*> %ptr, i32 4, <1 x i1> %mask)
  ret void
}
declare void @llvm.masked.scatter.v1i32.v1p0i32(<1 x i32>, <1 x i32*>, i32, <1 x i1>)

define <1 x i32> @v1_gather(<1 x i32*> %ptr, <1 x i1> %mask, <1 x i32> %src0) {
; KNL_64-LABEL: v1_gather:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    movl (%rdi), %eax
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: v1_gather:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    movl (%eax), %eax
; KNL_32-NEXT:    retl
;
; SKX-LABEL: v1_gather:
; SKX:       # %bb.0:
; SKX-NEXT:    movl (%rdi), %eax
; SKX-NEXT:    retq
;
; SKX_32-LABEL: v1_gather:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    movl (%eax), %eax
; SKX_32-NEXT:    retl
  %res = call <1 x i32> @llvm.masked.gather.v1i32.v1p0i32(<1 x i32*> %ptr, i32 4, <1 x i1> <i1 true>, <1 x i32> %src0)
  ret <1 x i32>%res
}
declare <1 x i32> @llvm.masked.gather.v1i32.v1p0i32(<1 x i32*>, i32, <1 x i1>, <1 x i32>)

; Make sure we don't crash when the index element type is larger than i64 and we need to widen the result
; This experienced a bad interaction when we widened and then tried to split.
define <2 x float> @large_index(float* %base, <2 x i128> %ind, <2 x i1> %mask, <2 x float> %src0) {
; KNL_64-LABEL: large_index:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $xmm1 killed $xmm1 def $ymm1
; KNL_64-NEXT:    vpsllq $63, %xmm0, %xmm0
; KNL_64-NEXT:    vptestmq %zmm0, %zmm0, %k0
; KNL_64-NEXT:    kshiftlw $14, %k0, %k0
; KNL_64-NEXT:    kshiftrw $14, %k0, %k1
; KNL_64-NEXT:    vmovq %rcx, %xmm0
; KNL_64-NEXT:    vmovq %rsi, %xmm2
; KNL_64-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm2[0],xmm0[0]
; KNL_64-NEXT:    vgatherqps (%rdi,%zmm0,4), %ymm1 {%k1}
; KNL_64-NEXT:    vmovaps %xmm1, %xmm0
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: large_index:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $xmm1 killed $xmm1 def $ymm1
; KNL_32-NEXT:    vpsllq $63, %xmm0, %xmm0
; KNL_32-NEXT:    vptestmq %zmm0, %zmm0, %k0
; KNL_32-NEXT:    kshiftlw $14, %k0, %k0
; KNL_32-NEXT:    kshiftrw $14, %k0, %k1
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; KNL_32-NEXT:    vpinsrd $1, {{[0-9]+}}(%esp), %xmm0, %xmm0
; KNL_32-NEXT:    vpinsrd $2, {{[0-9]+}}(%esp), %xmm0, %xmm0
; KNL_32-NEXT:    vpinsrd $3, {{[0-9]+}}(%esp), %xmm0, %xmm0
; KNL_32-NEXT:    vgatherqps (%eax,%zmm0,4), %ymm1 {%k1}
; KNL_32-NEXT:    vmovaps %xmm1, %xmm0
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: large_index:
; SKX:       # %bb.0:
; SKX-NEXT:    vpsllq $63, %xmm0, %xmm0
; SKX-NEXT:    vpmovq2m %xmm0, %k1
; SKX-NEXT:    vmovq %rcx, %xmm0
; SKX-NEXT:    vmovq %rsi, %xmm2
; SKX-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm2[0],xmm0[0]
; SKX-NEXT:    vgatherqps (%rdi,%xmm0,4), %xmm1 {%k1}
; SKX-NEXT:    vmovaps %xmm1, %xmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: large_index:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpsllq $63, %xmm0, %xmm0
; SKX_32-NEXT:    vpmovq2m %xmm0, %k1
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SKX_32-NEXT:    vpinsrd $1, {{[0-9]+}}(%esp), %xmm0, %xmm0
; SKX_32-NEXT:    vpinsrd $2, {{[0-9]+}}(%esp), %xmm0, %xmm0
; SKX_32-NEXT:    vpinsrd $3, {{[0-9]+}}(%esp), %xmm0, %xmm0
; SKX_32-NEXT:    vgatherqps (%eax,%xmm0,4), %xmm1 {%k1}
; SKX_32-NEXT:    vmovaps %xmm1, %xmm0
; SKX_32-NEXT:    retl
  %gep.random = getelementptr float, float* %base, <2 x i128> %ind
  %res = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> %gep.random, i32 4, <2 x i1> %mask, <2 x float> %src0)
  ret <2 x float>%res
}

; Make sure we allow index to be sign extended from a smaller than i32 element size.
define <16 x float> @sext_i8_index(float* %base, <16 x i8> %ind) {
; KNL_64-LABEL: sext_i8_index:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpmovsxbd %xmm0, %zmm1
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm1,4), %zmm0 {%k1}
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: sext_i8_index:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vpmovsxbd %xmm0, %zmm1
; KNL_32-NEXT:    kxnorw %k0, %k0, %k1
; KNL_32-NEXT:    vgatherdps (%eax,%zmm1,4), %zmm0 {%k1}
; KNL_32-NEXT:    retl
;
; SKX-LABEL: sext_i8_index:
; SKX:       # %bb.0:
; SKX-NEXT:    vpmovsxbd %xmm0, %zmm1
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    vgatherdps (%rdi,%zmm1,4), %zmm0 {%k1}
; SKX-NEXT:    retq
;
; SKX_32-LABEL: sext_i8_index:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vpmovsxbd %xmm0, %zmm1
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vgatherdps (%eax,%zmm1,4), %zmm0 {%k1}
; SKX_32-NEXT:    retl

  %sext_ind = sext <16 x i8> %ind to <16 x i64>
  %gep.random = getelementptr float, float *%base, <16 x i64> %sext_ind

  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
  ret <16 x float>%res
}

; Make sure we allow index to be sign extended from a smaller than i32 element size.
define <8 x float> @sext_v8i8_index(float* %base, <8 x i8> %ind) {
; KNL_64-LABEL: sext_v8i8_index:
; KNL_64:       # %bb.0:
; KNL_64-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
; KNL_64-NEXT:    vpslld $24, %ymm0, %ymm0
; KNL_64-NEXT:    vpsrad $24, %ymm0, %ymm1
; KNL_64-NEXT:    movw $255, %ax
; KNL_64-NEXT:    kmovw %eax, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm1,4), %zmm0 {%k1}
; KNL_64-NEXT:    # kill: def $ymm0 killed $ymm0 killed $zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: sext_v8i8_index:
; KNL_32:       # %bb.0:
; KNL_32-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
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vpslld $24, %ymm0, %ymm0
; KNL_32-NEXT:    vpsrad $24, %ymm0, %ymm1
; KNL_32-NEXT:    movw $255, %cx
; KNL_32-NEXT:    kmovw %ecx, %k1
; KNL_32-NEXT:    vgatherdps (%eax,%zmm1,4), %zmm0 {%k1}
; KNL_32-NEXT:    # kill: def $ymm0 killed $ymm0 killed $zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: sext_v8i8_index:
; SKX:       # %bb.0:
; SKX-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
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    vpslld $24, %ymm0, %ymm0
; SKX-NEXT:    vpsrad $24, %ymm0, %ymm1
; SKX-NEXT:    vgatherdps (%rdi,%ymm1,4), %ymm0 {%k1}
; SKX-NEXT:    retq
;
; SKX_32-LABEL: sext_v8i8_index:
; SKX_32:       # %bb.0:
; SKX_32-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
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vpslld $24, %ymm0, %ymm0
; SKX_32-NEXT:    vpsrad $24, %ymm0, %ymm1
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vgatherdps (%eax,%ymm1,4), %ymm0 {%k1}
; SKX_32-NEXT:    retl

  %sext_ind = sext <8 x i8> %ind to <8 x i64>
  %gep.random = getelementptr float, float *%base, <8 x i64> %sext_ind

  %res = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> %gep.random, i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef)
  ret <8 x float>%res
}
declare <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*>, i32, <8 x i1>, <8 x float>)

; Index requires promotion
define void @test_scatter_2i32_index(<2 x double> %a1, double* %base, <2 x i32> %ind, <2 x i1> %mask) {
; KNL_64-LABEL: test_scatter_2i32_index:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
; KNL_64-NEXT:    vpsllq $32, %xmm1, %xmm1
; KNL_64-NEXT:    vpsraq $32, %zmm1, %zmm1
; KNL_64-NEXT:    vpsllq $63, %xmm2, %xmm2
; KNL_64-NEXT:    vptestmq %zmm2, %zmm2, %k0
; KNL_64-NEXT:    kshiftlw $14, %k0, %k0
; KNL_64-NEXT:    kshiftrw $14, %k0, %k1
; KNL_64-NEXT:    vscatterqpd %zmm0, (%rdi,%zmm1,8) {%k1}
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_scatter_2i32_index:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    # kill: def $xmm0 killed $xmm0 def $zmm0
; KNL_32-NEXT:    vpsllq $32, %xmm1, %xmm1
; KNL_32-NEXT:    vpsraq $32, %zmm1, %zmm1
; KNL_32-NEXT:    vpsllq $63, %xmm2, %xmm2
; KNL_32-NEXT:    vptestmq %zmm2, %zmm2, %k0
; KNL_32-NEXT:    kshiftlw $14, %k0, %k0
; KNL_32-NEXT:    kshiftrw $14, %k0, %k1
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vscatterqpd %zmm0, (%eax,%zmm1,8) {%k1}
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_scatter_2i32_index:
; SKX:       # %bb.0:
; SKX-NEXT:    vpsllq $63, %xmm2, %xmm2
; SKX-NEXT:    vpmovq2m %xmm2, %k1
; SKX-NEXT:    vpsllq $32, %xmm1, %xmm1
; SKX-NEXT:    vpsraq $32, %xmm1, %xmm1
; SKX-NEXT:    vscatterqpd %xmm0, (%rdi,%xmm1,8) {%k1}
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_scatter_2i32_index:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    vpsllq $63, %xmm2, %xmm2
; SKX_32-NEXT:    vpmovq2m %xmm2, %k1
; SKX_32-NEXT:    vpsllq $32, %xmm1, %xmm1
; SKX_32-NEXT:    vpsraq $32, %xmm1, %xmm1
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vscatterqpd %xmm0, (%eax,%xmm1,8) {%k1}
; SKX_32-NEXT:    retl
  %gep = getelementptr double, double *%base, <2 x i32> %ind
  call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> %a1, <2 x double*> %gep, i32 4, <2 x i1> %mask)
  ret void
}
declare void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double>, <2 x double*>, i32, <2 x i1>)

define <16 x float> @zext_index(float* %base, <16 x i32> %ind) {
; KNL_64-LABEL: zext_index:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vpandd {{.*}}(%rip){1to16}, %zmm0, %zmm1
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm1,4), %zmm0 {%k1}
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: zext_index:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    vpandd {{\.LCPI.*}}{1to16}, %zmm0, %zmm1
; KNL_32-NEXT:    kxnorw %k0, %k0, %k1
; KNL_32-NEXT:    vgatherdps (%eax,%zmm1,4), %zmm0 {%k1}
; KNL_32-NEXT:    retl
;
; SKX_SMALL-LABEL: zext_index:
; SKX_SMALL:       # %bb.0:
; SKX_SMALL-NEXT:    vandps {{.*}}(%rip){1to16}, %zmm0, %zmm1
; SKX_SMALL-NEXT:    kxnorw %k0, %k0, %k1
; SKX_SMALL-NEXT:    vgatherdps (%rdi,%zmm1,4), %zmm0 {%k1}
; SKX_SMALL-NEXT:    retq
;
; SKX_LARGE-LABEL: zext_index:
; SKX_LARGE:       # %bb.0:
; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
; SKX_LARGE-NEXT:    vandps (%rax){1to16}, %zmm0, %zmm1
; SKX_LARGE-NEXT:    kxnorw %k0, %k0, %k1
; SKX_LARGE-NEXT:    vgatherdps (%rdi,%zmm1,4), %zmm0 {%k1}
; SKX_LARGE-NEXT:    retq
;
; SKX_32-LABEL: zext_index:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    vandps {{\.LCPI.*}}{1to16}, %zmm0, %zmm1
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vgatherdps (%eax,%zmm1,4), %zmm0 {%k1}
; SKX_32-NEXT:    retl
  %ind_masked = and <16 x i32> %ind, <i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15>
  %sext_ind = zext <16 x i32> %ind_masked to <16 x i64>
  %gep.random = getelementptr float, float *%base, <16 x i64> %sext_ind

  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
  ret <16 x float>%res
}

define <16 x double> @test_gather_setcc_split(double* %base, <16 x i32> %ind, <16 x i32> %cmp, <16 x double> %passthru) {
; KNL_64-LABEL: test_gather_setcc_split:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vextractf64x4 $1, %zmm0, %ymm4
; KNL_64-NEXT:    vextracti64x4 $1, %zmm1, %ymm5
; KNL_64-NEXT:    vptestnmd %zmm5, %zmm5, %k1
; KNL_64-NEXT:    vptestnmd %zmm1, %zmm1, %k2
; KNL_64-NEXT:    vgatherdpd (%rdi,%ymm0,8), %zmm2 {%k2}
; KNL_64-NEXT:    vgatherdpd (%rdi,%ymm4,8), %zmm3 {%k1}
; KNL_64-NEXT:    vmovapd %zmm2, %zmm0
; KNL_64-NEXT:    vmovapd %zmm3, %zmm1
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_gather_setcc_split:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    pushl %ebp
; KNL_32-NEXT:    .cfi_def_cfa_offset 8
; KNL_32-NEXT:    .cfi_offset %ebp, -8
; KNL_32-NEXT:    movl %esp, %ebp
; KNL_32-NEXT:    .cfi_def_cfa_register %ebp
; KNL_32-NEXT:    andl $-64, %esp
; KNL_32-NEXT:    subl $64, %esp
; KNL_32-NEXT:    vmovapd 72(%ebp), %zmm3
; KNL_32-NEXT:    movl 8(%ebp), %eax
; KNL_32-NEXT:    vextractf64x4 $1, %zmm0, %ymm4
; KNL_32-NEXT:    vextracti64x4 $1, %zmm1, %ymm5
; KNL_32-NEXT:    vptestnmd %zmm5, %zmm5, %k1
; KNL_32-NEXT:    vptestnmd %zmm1, %zmm1, %k2
; KNL_32-NEXT:    vgatherdpd (%eax,%ymm0,8), %zmm2 {%k2}
; KNL_32-NEXT:    vgatherdpd (%eax,%ymm4,8), %zmm3 {%k1}
; KNL_32-NEXT:    vmovapd %zmm2, %zmm0
; KNL_32-NEXT:    vmovapd %zmm3, %zmm1
; KNL_32-NEXT:    movl %ebp, %esp
; KNL_32-NEXT:    popl %ebp
; KNL_32-NEXT:    .cfi_def_cfa %esp, 4
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_gather_setcc_split:
; SKX:       # %bb.0:
; SKX-NEXT:    vextractf64x4 $1, %zmm0, %ymm4
; SKX-NEXT:    vextracti64x4 $1, %zmm1, %ymm5
; SKX-NEXT:    vptestnmd %ymm5, %ymm5, %k1
; SKX-NEXT:    vptestnmd %ymm1, %ymm1, %k2
; SKX-NEXT:    vgatherdpd (%rdi,%ymm0,8), %zmm2 {%k2}
; SKX-NEXT:    vgatherdpd (%rdi,%ymm4,8), %zmm3 {%k1}
; SKX-NEXT:    vmovapd %zmm2, %zmm0
; SKX-NEXT:    vmovapd %zmm3, %zmm1
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_gather_setcc_split:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    pushl %ebp
; SKX_32-NEXT:    .cfi_def_cfa_offset 8
; SKX_32-NEXT:    .cfi_offset %ebp, -8
; SKX_32-NEXT:    movl %esp, %ebp
; SKX_32-NEXT:    .cfi_def_cfa_register %ebp
; SKX_32-NEXT:    andl $-64, %esp
; SKX_32-NEXT:    subl $64, %esp
; SKX_32-NEXT:    vmovapd 72(%ebp), %zmm3
; SKX_32-NEXT:    movl 8(%ebp), %eax
; SKX_32-NEXT:    vextractf64x4 $1, %zmm0, %ymm4
; SKX_32-NEXT:    vextracti64x4 $1, %zmm1, %ymm5
; SKX_32-NEXT:    vptestnmd %ymm5, %ymm5, %k1
; SKX_32-NEXT:    vptestnmd %ymm1, %ymm1, %k2
; SKX_32-NEXT:    vgatherdpd (%eax,%ymm0,8), %zmm2 {%k2}
; SKX_32-NEXT:    vgatherdpd (%eax,%ymm4,8), %zmm3 {%k1}
; SKX_32-NEXT:    vmovapd %zmm2, %zmm0
; SKX_32-NEXT:    vmovapd %zmm3, %zmm1
; SKX_32-NEXT:    movl %ebp, %esp
; SKX_32-NEXT:    popl %ebp
; SKX_32-NEXT:    .cfi_def_cfa %esp, 4
; SKX_32-NEXT:    retl
  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.random = getelementptr double, double *%base, <16 x i64> %sext_ind

  %mask = icmp eq <16 x i32> %cmp, zeroinitializer
  %res = call <16 x double> @llvm.masked.gather.v16f64.v16p0f64(<16 x double*> %gep.random, i32 4, <16 x i1> %mask, <16 x double> %passthru)
  ret <16 x double>%res
}

define void @test_scatter_setcc_split(double* %base, <16 x i32> %ind, <16 x i32> %cmp, <16 x double> %src0)  {
; KNL_64-LABEL: test_scatter_setcc_split:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vextractf64x4 $1, %zmm0, %ymm4
; KNL_64-NEXT:    vextracti64x4 $1, %zmm1, %ymm5
; KNL_64-NEXT:    vptestnmd %zmm5, %zmm5, %k1
; KNL_64-NEXT:    vptestnmd %zmm1, %zmm1, %k2
; KNL_64-NEXT:    vscatterdpd %zmm2, (%rdi,%ymm0,8) {%k2}
; KNL_64-NEXT:    vscatterdpd %zmm3, (%rdi,%ymm4,8) {%k1}
; KNL_64-NEXT:    vzeroupper
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_scatter_setcc_split:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    pushl %ebp
; KNL_32-NEXT:    .cfi_def_cfa_offset 8
; KNL_32-NEXT:    .cfi_offset %ebp, -8
; KNL_32-NEXT:    movl %esp, %ebp
; KNL_32-NEXT:    .cfi_def_cfa_register %ebp
; KNL_32-NEXT:    andl $-64, %esp
; KNL_32-NEXT:    subl $64, %esp
; KNL_32-NEXT:    vmovapd 72(%ebp), %zmm3
; KNL_32-NEXT:    movl 8(%ebp), %eax
; KNL_32-NEXT:    vextractf64x4 $1, %zmm0, %ymm4
; KNL_32-NEXT:    vextracti64x4 $1, %zmm1, %ymm5
; KNL_32-NEXT:    vptestnmd %zmm5, %zmm5, %k1
; KNL_32-NEXT:    vptestnmd %zmm1, %zmm1, %k2
; KNL_32-NEXT:    vscatterdpd %zmm2, (%eax,%ymm0,8) {%k2}
; KNL_32-NEXT:    vscatterdpd %zmm3, (%eax,%ymm4,8) {%k1}
; KNL_32-NEXT:    movl %ebp, %esp
; KNL_32-NEXT:    popl %ebp
; KNL_32-NEXT:    .cfi_def_cfa %esp, 4
; KNL_32-NEXT:    vzeroupper
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_scatter_setcc_split:
; SKX:       # %bb.0:
; SKX-NEXT:    vextractf64x4 $1, %zmm0, %ymm4
; SKX-NEXT:    vextracti64x4 $1, %zmm1, %ymm5
; SKX-NEXT:    vptestnmd %ymm5, %ymm5, %k1
; SKX-NEXT:    vptestnmd %ymm1, %ymm1, %k2
; SKX-NEXT:    vscatterdpd %zmm2, (%rdi,%ymm0,8) {%k2}
; SKX-NEXT:    vscatterdpd %zmm3, (%rdi,%ymm4,8) {%k1}
; SKX-NEXT:    vzeroupper
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_scatter_setcc_split:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    pushl %ebp
; SKX_32-NEXT:    .cfi_def_cfa_offset 8
; SKX_32-NEXT:    .cfi_offset %ebp, -8
; SKX_32-NEXT:    movl %esp, %ebp
; SKX_32-NEXT:    .cfi_def_cfa_register %ebp
; SKX_32-NEXT:    andl $-64, %esp
; SKX_32-NEXT:    subl $64, %esp
; SKX_32-NEXT:    vmovapd 72(%ebp), %zmm3
; SKX_32-NEXT:    movl 8(%ebp), %eax
; SKX_32-NEXT:    vextractf64x4 $1, %zmm0, %ymm4
; SKX_32-NEXT:    vextracti64x4 $1, %zmm1, %ymm5
; SKX_32-NEXT:    vptestnmd %ymm5, %ymm5, %k1
; SKX_32-NEXT:    vptestnmd %ymm1, %ymm1, %k2
; SKX_32-NEXT:    vscatterdpd %zmm2, (%eax,%ymm0,8) {%k2}
; SKX_32-NEXT:    vscatterdpd %zmm3, (%eax,%ymm4,8) {%k1}
; SKX_32-NEXT:    movl %ebp, %esp
; SKX_32-NEXT:    popl %ebp
; SKX_32-NEXT:    .cfi_def_cfa %esp, 4
; SKX_32-NEXT:    vzeroupper
; SKX_32-NEXT:    retl
  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.random = getelementptr double, double *%base, <16 x i64> %sext_ind

  %mask = icmp eq <16 x i32> %cmp, zeroinitializer
  call void @llvm.masked.scatter.v16f64.v16p0f64(<16 x double> %src0, <16 x double*> %gep.random, i32 4, <16 x i1> %mask)
  ret void
}

; This test case previously triggered an infinite loop when the two gathers became identical after DAG combine removed the sign extend.
define <16 x float> @test_sext_cse(float* %base, <16 x i32> %ind, <16 x i32>* %foo) {
; KNL_64-LABEL: test_sext_cse:
; KNL_64:       # %bb.0:
; KNL_64-NEXT:    vmovaps %zmm0, (%rsi)
; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
; KNL_64-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; KNL_64-NEXT:    vaddps %zmm1, %zmm1, %zmm0
; KNL_64-NEXT:    retq
;
; KNL_32-LABEL: test_sext_cse:
; KNL_32:       # %bb.0:
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; KNL_32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; KNL_32-NEXT:    vmovaps %zmm0, (%ecx)
; KNL_32-NEXT:    kxnorw %k0, %k0, %k1
; KNL_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; KNL_32-NEXT:    vaddps %zmm1, %zmm1, %zmm0
; KNL_32-NEXT:    retl
;
; SKX-LABEL: test_sext_cse:
; SKX:       # %bb.0:
; SKX-NEXT:    vmovaps %zmm0, (%rsi)
; SKX-NEXT:    kxnorw %k0, %k0, %k1
; SKX-NEXT:    vgatherdps (%rdi,%zmm0,4), %zmm1 {%k1}
; SKX-NEXT:    vaddps %zmm1, %zmm1, %zmm0
; SKX-NEXT:    retq
;
; SKX_32-LABEL: test_sext_cse:
; SKX_32:       # %bb.0:
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %eax
; SKX_32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; SKX_32-NEXT:    vmovaps %zmm0, (%ecx)
; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
; SKX_32-NEXT:    vgatherdps (%eax,%zmm0,4), %zmm1 {%k1}
; SKX_32-NEXT:    vaddps %zmm1, %zmm1, %zmm0
; SKX_32-NEXT:    retl
  %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
  %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer

  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind

  store <16 x i32> %ind, <16 x i32>* %foo
  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
  %gep.random2 = getelementptr float, <16 x float*> %broadcast.splat, <16 x i32> %ind
  %res2 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random2, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
  %res3 = fadd <16 x float> %res2, %res
  ret <16 x float>%res3
}