Compiler projects using llvm
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -mtriple=x86_64-unknown -slp-vectorizer -S | FileCheck %s

; Reproducer for an issue discussed here:
; https://reviews.llvm.org/D108703#2974289

define void @test([4 x float]* nocapture %o, [2 x float]* nocapture nonnull readonly dereferenceable(8) %a, [2 x float]* nocapture nonnull readonly dereferenceable(8) %b, i32 signext %component) {
; CHECK-LABEL: @test(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = bitcast [2 x float]* [[A:%.*]] to <2 x float>*
; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x float>, <2 x float>* [[TMP0]], align 1
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast [2 x float]* [[B:%.*]] to <2 x float>*
; CHECK-NEXT:    [[TMP3:%.*]] = load <2 x float>, <2 x float>* [[TMP2]], align 1
; CHECK-NEXT:    [[TMP4:%.*]] = trunc i32 [[COMPONENT:%.*]] to i8
; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP1]], <2 x float> [[TMP3]], <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 2, i32 3, i32 undef, i32 undef>
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x float> [[TMP5]], i8 [[TMP4]]
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x float> undef, float [[TMP6]], i64 0
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x float> [[TMP3]], i32 1
; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <4 x float> [[TMP7]], float [[TMP8]], i64 1
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x float> [[TMP1]], i32 1
; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <4 x float> [[TMP9]], float [[TMP10]], i64 2
; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <4 x float> [[TMP11]], float [[TMP6]], i64 3
; CHECK-NEXT:    [[TMP13:%.*]] = bitcast [4 x float]* [[O:%.*]] to <4 x float>*
; CHECK-NEXT:    store <4 x float> [[TMP12]], <4 x float>* [[TMP13]], align 1
; CHECK-NEXT:    ret void
;
entry:
  %0 = bitcast [2 x float]* %a to <2 x float>*
  %1 = load <2 x float>, <2 x float>* %0, align 1
  %2 = bitcast [2 x float]* %b to <2 x float>*
  %3 = load <2 x float>, <2 x float>* %2, align 1
  %4 = trunc i32 %component to i8
  %5 = shufflevector <2 x float> %1, <2 x float> %3, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 2, i32 3, i32 undef, i32 undef>
  %6 = extractelement <8 x float> %5, i8 %4
  %7 = insertelement <4 x float> undef, float %6, i64 0
  %8 = extractelement <2 x float> %3, i32 1
  %9 = insertelement <4 x float> %7, float %8, i64 1
  %10 = extractelement <2 x float> %1, i32 1
  %11 = insertelement <4 x float> %9, float %10, i64 2
  %12 = insertelement <4 x float> %11, float %6, i64 3
  %13 = bitcast [4 x float]* %o to <4 x float>*
  store <4 x float> %12, <4 x float>* %13, align 1
  ret void
}