; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=sse4.2 | FileCheck %s

define <8 x i8> @foo(<16 x i8> %a) {
; CHECK-LABEL: foo:
; CHECK:       # %bb.0: # %cond.store
; CHECK-NEXT:    pextrb $0, %xmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    pextrb $2, %xmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    pextrb $4, %xmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    pextrb $6, %xmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    pextrb $8, %xmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    pextrb $10, %xmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    pextrb $12, %xmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    pextrb $14, %xmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    pmovzxbw {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; CHECK-NEXT:    retq
  %v = alloca i8, i32 8, align 16
  call void @llvm.masked.compressstore.v16i8(<16 x i8> %a, i8* %v, <16 x i1> <i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false>)
  %ptr = bitcast i8* %v to <8 x i8>*
  %out = load <8 x i8>, <8 x i8>* %ptr
  ret <8 x i8> %out
}
declare void @llvm.masked.compressstore.v16i8(<16 x i8>, i8*, <16 x i1>) #0