; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -slp-vectorizer %s -slp-threshold=-10 | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-gnu"

%structA = type { [2 x float] }

define void @test1(%structA* nocapture readonly %J, i32 %xmin, i32 %ymin) {
; CHECK-LABEL: @test1(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x i32> undef, i32 [[XMIN:%.*]], i32 0
; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x i32> [[TMP0]], i32 [[YMIN:%.*]], i32 1
; CHECK-NEXT:    br label [[FOR_BODY3_LR_PH:%.*]]
; CHECK:       for.body3.lr.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = sitofp <2 x i32> [[TMP1]] to <2 x float>
; CHECK-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds [[STRUCTA:%.*]], %structA* [[J:%.*]], i64 0, i32 0, i64 0
; CHECK-NEXT:    [[ARRAYIDX9:%.*]] = getelementptr inbounds [[STRUCTA]], %structA* [[J]], i64 0, i32 0, i64 1
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[ARRAYIDX4]] to <2 x float>*
; CHECK-NEXT:    [[TMP4:%.*]] = load <2 x float>, <2 x float>* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP5:%.*]] = fsub fast <2 x float> [[TMP2]], [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = fmul fast <2 x float> [[TMP5]], [[TMP5]]
; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <2 x float> [[TMP6]], i32 0
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x float> [[TMP6]], i32 1
; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP7]], [[TMP8]]
; CHECK-NEXT:    [[CMP:%.*]] = fcmp oeq float [[ADD]], 0.000000e+00
; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY3_LR_PH]], label [[FOR_END27:%.*]]
; CHECK:       for.end27:
; CHECK-NEXT:    ret void
;

entry:
  br label %for.body3.lr.ph

for.body3.lr.ph:
  %conv5 = sitofp i32 %ymin to float
  %conv = sitofp i32 %xmin to float
  %arrayidx4 = getelementptr inbounds %structA, %structA* %J, i64 0, i32 0, i64 0
  %0 = load float, float* %arrayidx4, align 4
  %sub = fsub fast float %conv, %0
  %arrayidx9 = getelementptr inbounds %structA, %structA* %J, i64 0, i32 0, i64 1
  %1 = load float, float* %arrayidx9, align 4
  %sub10 = fsub fast float %conv5, %1
  %mul11 = fmul fast float %sub, %sub
  %mul12 = fmul fast float %sub10, %sub10
  %add = fadd fast float %mul11, %mul12
  %cmp = fcmp oeq float %add, 0.000000e+00
  br i1 %cmp, label %for.body3.lr.ph, label %for.end27

for.end27:
  ret void
}

define void @test2(%structA* nocapture readonly %J, i32 %xmin, i32 %ymin) {
; CHECK-LABEL: @test2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x i32> undef, i32 [[XMIN:%.*]], i32 0
; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x i32> [[TMP0]], i32 [[YMIN:%.*]], i32 1
; CHECK-NEXT:    br label [[FOR_BODY3_LR_PH:%.*]]
; CHECK:       for.body3.lr.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = sitofp <2 x i32> [[TMP1]] to <2 x float>
; CHECK-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds [[STRUCTA:%.*]], %structA* [[J:%.*]], i64 0, i32 0, i64 0
; CHECK-NEXT:    [[ARRAYIDX9:%.*]] = getelementptr inbounds [[STRUCTA]], %structA* [[J]], i64 0, i32 0, i64 1
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[ARRAYIDX4]] to <2 x float>*
; CHECK-NEXT:    [[TMP4:%.*]] = load <2 x float>, <2 x float>* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP5:%.*]] = fsub fast <2 x float> [[TMP2]], [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = fmul fast <2 x float> [[TMP5]], [[TMP5]]
; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <2 x float> [[TMP6]], i32 0
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x float> [[TMP6]], i32 1
; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP8]], [[TMP7]]
; CHECK-NEXT:    [[CMP:%.*]] = fcmp oeq float [[ADD]], 0.000000e+00
; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY3_LR_PH]], label [[FOR_END27:%.*]]
; CHECK:       for.end27:
; CHECK-NEXT:    ret void
;

entry:
  br label %for.body3.lr.ph

for.body3.lr.ph:
  %conv5 = sitofp i32 %ymin to float
  %conv = sitofp i32 %xmin to float
  %arrayidx4 = getelementptr inbounds %structA, %structA* %J, i64 0, i32 0, i64 0
  %0 = load float, float* %arrayidx4, align 4
  %sub = fsub fast float %conv, %0
  %arrayidx9 = getelementptr inbounds %structA, %structA* %J, i64 0, i32 0, i64 1
  %1 = load float, float* %arrayidx9, align 4
  %sub10 = fsub fast float %conv5, %1
  %mul11 = fmul fast float %sub, %sub
  %mul12 = fmul fast float %sub10, %sub10
  %add = fadd fast float %mul12, %mul11         ;;;<---- Operands commuted!!
  %cmp = fcmp oeq float %add, 0.000000e+00
  br i1 %cmp, label %for.body3.lr.ph, label %for.end27

for.end27:
  ret void
}