; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-vectorize < %s -S -o - | FileCheck %s

target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv8.1m.main-arm-none-eabi"

; This test could produce gather/scatter or predicated scalar load/stores. It
; should never choose scalar load/store, and the cost of gather/scatter may be
; high enough to make vectorization unwarranted.

define i32 @nested(float* nocapture %pG, float* nocapture readonly %pA, i32 %n, i32 %ii) #0 {
; CHECK-LABEL: @nested(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP66:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP66]], label [[FOR_BODY4_LR_PH_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body4.lr.ph.preheader:
; CHECK-NEXT:    br label [[FOR_BODY4_LR_PH:%.*]]
; CHECK:       for.body4.lr.ph:
; CHECK-NEXT:    [[I_067:%.*]] = phi i32 [ [[INC29:%.*]], [[FOR_COND_CLEANUP3:%.*]] ], [ 0, [[FOR_BODY4_LR_PH_PREHEADER]] ]
; CHECK-NEXT:    [[CMP962_NOT:%.*]] = icmp eq i32 [[I_067]], 0
; CHECK-NEXT:    [[MUL15:%.*]] = mul nsw i32 [[I_067]], [[N]]
; CHECK-NEXT:    br i1 [[CMP962_NOT]], label [[FOR_BODY4_PREHEADER:%.*]], label [[FOR_BODY4_US_PREHEADER:%.*]]
; CHECK:       for.body4.us.preheader:
; CHECK-NEXT:    br label [[FOR_BODY4_US:%.*]]
; CHECK:       for.body4.preheader:
; CHECK-NEXT:    br label [[FOR_BODY4:%.*]]
; CHECK:       for.body4.us:
; CHECK-NEXT:    [[J_065_US:%.*]] = phi i32 [ [[INC26_US:%.*]], [[FOR_COND8_FOR_COND_CLEANUP10_CRIT_EDGE_US:%.*]] ], [ [[I_067]], [[FOR_BODY4_US_PREHEADER]] ]
; CHECK-NEXT:    [[MUL_US:%.*]] = mul nsw i32 [[J_065_US]], [[N]]
; CHECK-NEXT:    [[ADD_US:%.*]] = add nsw i32 [[MUL_US]], [[I_067]]
; CHECK-NEXT:    [[ARRAYIDX_US:%.*]] = getelementptr inbounds float, float* [[PA:%.*]], i32 [[ADD_US]]
; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[ARRAYIDX_US]], align 4
; CHECK-NEXT:    [[ARRAYIDX7_US:%.*]] = getelementptr inbounds float, float* [[PG:%.*]], i32 [[ADD_US]]
; CHECK-NEXT:    store float [[TMP0]], float* [[ARRAYIDX7_US]], align 4
; CHECK-NEXT:    br label [[FOR_BODY11_US:%.*]]
; CHECK:       for.body11.us:
; CHECK-NEXT:    [[TMP1:%.*]] = phi float [ [[TMP0]], [[FOR_BODY4_US]] ], [ [[SUB_US:%.*]], [[FOR_BODY11_US]] ]
; CHECK-NEXT:    [[K_063_US:%.*]] = phi i32 [ 0, [[FOR_BODY4_US]] ], [ [[INC_US:%.*]], [[FOR_BODY11_US]] ]
; CHECK-NEXT:    [[ADD16_US:%.*]] = add nsw i32 [[K_063_US]], [[MUL15]]
; CHECK-NEXT:    [[ARRAYIDX17_US:%.*]] = getelementptr inbounds float, float* [[PG]], i32 [[ADD16_US]]
; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[ARRAYIDX17_US]], align 4
; CHECK-NEXT:    [[ADD19_US:%.*]] = add nsw i32 [[K_063_US]], [[MUL_US]]
; CHECK-NEXT:    [[ARRAYIDX20_US:%.*]] = getelementptr inbounds float, float* [[PG]], i32 [[ADD19_US]]
; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[ARRAYIDX20_US]], align 4
; CHECK-NEXT:    [[MUL21_US:%.*]] = fmul fast float [[TMP3]], [[TMP2]]
; CHECK-NEXT:    [[SUB_US]] = fsub fast float [[TMP1]], [[MUL21_US]]
; CHECK-NEXT:    store float [[SUB_US]], float* [[ARRAYIDX7_US]], align 4
; CHECK-NEXT:    [[INC_US]] = add nuw nsw i32 [[K_063_US]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i32 [[INC_US]], [[I_067]]
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND8_FOR_COND_CLEANUP10_CRIT_EDGE_US]], label [[FOR_BODY11_US]]
; CHECK:       for.cond8.for.cond.cleanup10_crit_edge.us:
; CHECK-NEXT:    [[INC26_US]] = add nuw nsw i32 [[J_065_US]], 1
; CHECK-NEXT:    [[EXITCOND71_NOT:%.*]] = icmp eq i32 [[INC26_US]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND71_NOT]], label [[FOR_COND_CLEANUP3_LOOPEXIT1:%.*]], label [[FOR_BODY4_US]]
; CHECK:       for.cond.cleanup.loopexit:
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    ret i32 0
; CHECK:       for.cond.cleanup3.loopexit:
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP3]]
; CHECK:       for.cond.cleanup3.loopexit1:
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP3]]
; CHECK:       for.cond.cleanup3:
; CHECK-NEXT:    [[INC29]] = add nuw nsw i32 [[I_067]], 1
; CHECK-NEXT:    [[EXITCOND73_NOT:%.*]] = icmp eq i32 [[INC29]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND73_NOT]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[FOR_BODY4_LR_PH]]
; CHECK:       for.body4:
; CHECK-NEXT:    [[J_065:%.*]] = phi i32 [ [[INC26:%.*]], [[FOR_BODY4]] ], [ 0, [[FOR_BODY4_PREHEADER]] ]
; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i32 [[J_065]], [[N]]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[PA]], i32 [[MUL]]
; CHECK-NEXT:    [[TMP4:%.*]] = load float, float* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ARRAYIDX7:%.*]] = getelementptr inbounds float, float* [[PG]], i32 [[MUL]]
; CHECK-NEXT:    store float [[TMP4]], float* [[ARRAYIDX7]], align 4
; CHECK-NEXT:    [[INC26]] = add nuw nsw i32 [[J_065]], 1
; CHECK-NEXT:    [[EXITCOND72_NOT:%.*]] = icmp eq i32 [[INC26]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND72_NOT]], label [[FOR_COND_CLEANUP3_LOOPEXIT:%.*]], label [[FOR_BODY4]]
;
entry:
  %cmp66 = icmp sgt i32 %n, 0
  br i1 %cmp66, label %for.body4.lr.ph, label %for.cond.cleanup

for.body4.lr.ph:                                  ; preds = %entry, %for.cond.cleanup3
  %i.067 = phi i32 [ %inc29, %for.cond.cleanup3 ], [ 0, %entry ]
  %cmp962.not = icmp eq i32 %i.067, 0
  %mul15 = mul nsw i32 %i.067, %n
  br i1 %cmp962.not, label %for.body4, label %for.body4.us

for.body4.us:                                     ; preds = %for.body4.lr.ph, %for.cond8.for.cond.cleanup10_crit_edge.us
  %j.065.us = phi i32 [ %inc26.us, %for.cond8.for.cond.cleanup10_crit_edge.us ], [ %i.067, %for.body4.lr.ph ]
  %mul.us = mul nsw i32 %j.065.us, %n
  %add.us = add nsw i32 %mul.us, %i.067
  %arrayidx.us = getelementptr inbounds float, float* %pA, i32 %add.us
  %0 = load float, float* %arrayidx.us, align 4
  %arrayidx7.us = getelementptr inbounds float, float* %pG, i32 %add.us
  store float %0, float* %arrayidx7.us, align 4
  br label %for.body11.us

for.body11.us:                                    ; preds = %for.body4.us, %for.body11.us
  %1 = phi float [ %0, %for.body4.us ], [ %sub.us, %for.body11.us ]
  %k.063.us = phi i32 [ 0, %for.body4.us ], [ %inc.us, %for.body11.us ]
  %add16.us = add nsw i32 %k.063.us, %mul15
  %arrayidx17.us = getelementptr inbounds float, float* %pG, i32 %add16.us
  %2 = load float, float* %arrayidx17.us, align 4
  %add19.us = add nsw i32 %k.063.us, %mul.us
  %arrayidx20.us = getelementptr inbounds float, float* %pG, i32 %add19.us
  %3 = load float, float* %arrayidx20.us, align 4
  %mul21.us = fmul fast float %3, %2
  %sub.us = fsub fast float %1, %mul21.us
  store float %sub.us, float* %arrayidx7.us, align 4
  %inc.us = add nuw nsw i32 %k.063.us, 1
  %exitcond.not = icmp eq i32 %inc.us, %i.067
  br i1 %exitcond.not, label %for.cond8.for.cond.cleanup10_crit_edge.us, label %for.body11.us

for.cond8.for.cond.cleanup10_crit_edge.us:        ; preds = %for.body11.us
  %inc26.us = add nuw nsw i32 %j.065.us, 1
  %exitcond71.not = icmp eq i32 %inc26.us, %n
  br i1 %exitcond71.not, label %for.cond.cleanup3, label %for.body4.us

for.cond.cleanup:                                 ; preds = %for.cond.cleanup3, %entry
  ret i32 0

for.cond.cleanup3:                                ; preds = %for.cond8.for.cond.cleanup10_crit_edge.us, %for.body4
  %inc29 = add nuw nsw i32 %i.067, 1
  %exitcond73.not = icmp eq i32 %inc29, %n
  br i1 %exitcond73.not, label %for.cond.cleanup, label %for.body4.lr.ph

for.body4:                                        ; preds = %for.body4.lr.ph, %for.body4
  %j.065 = phi i32 [ %inc26, %for.body4 ], [ 0, %for.body4.lr.ph ]
  %mul = mul nsw i32 %j.065, %n
  %arrayidx = getelementptr inbounds float, float* %pA, i32 %mul
  %4 = load float, float* %arrayidx, align 4
  %arrayidx7 = getelementptr inbounds float, float* %pG, i32 %mul
  store float %4, float* %arrayidx7, align 4
  %inc26 = add nuw nsw i32 %j.065, 1
  %exitcond72.not = icmp eq i32 %inc26, %n
  br i1 %exitcond72.not, label %for.cond.cleanup3, label %for.body4
}

attributes #0 = { "target-features"="+mve" }