; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -mtriple=thumbv8.1m.main-arm-eabihf -mattr=+mve.fp \
; RUN:   -tail-predication=enabled -loop-vectorize -S < %s | \
; RUN:   FileCheck %s

target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"

define void @trunc_not_allowed_different_vec_elemns(i32* noalias nocapture %A, i32* noalias nocapture readonly %B, i32* noalias nocapture readonly %C, i16* noalias nocapture %D) #0 {
; CHECK-LABEL: @trunc_not_allowed_different_vec_elemns(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 0
; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i32* [[TMP5]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP6]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = add nsw <4 x i32> [[WIDE_LOAD1]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP8]], i32 0
; CHECK-NEXT:    [[TMP10:%.*]] = bitcast i32* [[TMP9]] to <4 x i32>*
; CHECK-NEXT:    store <4 x i32> [[TMP7]], <4 x i32>* [[TMP10]], align 4
; CHECK-NEXT:    [[TMP11:%.*]] = trunc <4 x i32> [[TMP7]] to <4 x i16>
; CHECK-NEXT:    [[TMP12:%.*]] = shl <4 x i16> [[TMP11]], <i16 1, i16 1, i16 1, i16 1>
; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i16, i16* [[D:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i16, i16* [[TMP13]], i32 0
; CHECK-NEXT:    [[TMP15:%.*]] = bitcast i16* [[TMP14]] to <4 x i16>*
; CHECK-NEXT:    store <4 x i16> [[TMP12]], <4 x i16>* [[TMP15]], align 2
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP16:%.*]] = icmp eq i32 [[INDEX_NEXT]], 428
; CHECK-NEXT:    br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 431, 428
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 428, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    ret void
; CHECK:       for.body:
; CHECK-NEXT:    [[I_021:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[ADD9:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 [[I_021]]
; CHECK-NEXT:    [[TMP17:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[C]], i32 [[I_021]]
; CHECK-NEXT:    [[TMP18:%.*]] = load i32, i32* [[ARRAYIDX1]], align 4
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP18]], [[TMP17]]
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 [[I_021]]
; CHECK-NEXT:    store i32 [[ADD]], i32* [[ARRAYIDX2]], align 4
; CHECK-NEXT:    [[ADD_TR:%.*]] = trunc i32 [[ADD]] to i16
; CHECK-NEXT:    [[CONV7:%.*]] = shl i16 [[ADD_TR]], 1
; CHECK-NEXT:    [[ARRAYIDX8:%.*]] = getelementptr inbounds i16, i16* [[D]], i32 [[I_021]]
; CHECK-NEXT:    store i16 [[CONV7]], i16* [[ARRAYIDX8]], align 2
; CHECK-NEXT:    [[ADD9]] = add nuw nsw i32 [[I_021]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[ADD9]], 431
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
;
entry:
  br label %for.body

for.cond.cleanup:
  ret void

for.body:
  %i.021 = phi i32 [ 0, %entry ], [ %add9, %for.body ]
  %arrayidx = getelementptr inbounds i32, i32* %B, i32 %i.021
  %0 = load i32, i32* %arrayidx, align 4
  %arrayidx1 = getelementptr inbounds i32, i32* %C, i32 %i.021
  %1 = load i32, i32* %arrayidx1, align 4
  %add = add nsw i32 %1, %0
  %arrayidx2 = getelementptr inbounds i32, i32* %A, i32 %i.021
  store i32 %add, i32* %arrayidx2, align 4
  %add.tr = trunc i32 %add to i16
  %conv7 = shl i16 %add.tr, 1
  %arrayidx8 = getelementptr inbounds i16, i16* %D, i32 %i.021
  store i16 %conv7, i16* %arrayidx8, align 2
  %add9 = add nuw nsw i32 %i.021, 1
  %exitcond = icmp eq i32 %add9, 431
  br i1 %exitcond, label %for.cond.cleanup, label %for.body
}

define void @unsupported_i64_type(i64* noalias nocapture %A, i64* noalias nocapture readonly %B, i64* noalias nocapture readonly %C) #0 {
; CHECK-LABEL: @unsupported_i64_type(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    ret void
; CHECK:       for.body:
; CHECK-NEXT:    [[I_09:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[ADD3:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i64, i64* [[B:%.*]], i32 [[I_09]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i64, i64* [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i64, i64* [[C:%.*]], i32 [[I_09]]
; CHECK-NEXT:    [[TMP1:%.*]] = load i64, i64* [[ARRAYIDX1]], align 8
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i64 [[TMP1]], [[TMP0]]
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i64, i64* [[A:%.*]], i32 [[I_09]]
; CHECK-NEXT:    store i64 [[ADD]], i64* [[ARRAYIDX2]], align 8
; CHECK-NEXT:    [[ADD3]] = add nuw nsw i32 [[I_09]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[ADD3]], 431
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
;
entry:
  br label %for.body

for.cond.cleanup:
  ret void

for.body:
  %i.09 = phi i32 [ 0, %entry ], [ %add3, %for.body ]
  %arrayidx = getelementptr inbounds i64, i64* %B, i32 %i.09
  %0 = load i64, i64* %arrayidx, align 8
  %arrayidx1 = getelementptr inbounds i64, i64* %C, i32 %i.09
  %1 = load i64, i64* %arrayidx1, align 8
  %add = add nsw i64 %1, %0
  %arrayidx2 = getelementptr inbounds i64, i64* %A, i32 %i.09
  store i64 %add, i64* %arrayidx2, align 8
  %add3 = add nuw nsw i32 %i.09, 1
  %exitcond = icmp eq i32 %add3, 431
  br i1 %exitcond, label %for.cond.cleanup, label %for.body
}

define void @narrowing_load_not_allowed(i8* noalias nocapture %A, i8* noalias nocapture readonly %B, i16* noalias nocapture readonly %C) #0 {
; CHECK-LABEL: @narrowing_load_not_allowed(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i16, i16* [[C:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i16, i16* [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i16* [[TMP2]] to <8 x i16>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <8 x i16>, <8 x i16>* [[TMP3]], align 2
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, i8* [[B:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], i32 0
; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i8* [[TMP5]] to <8 x i8>*
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <8 x i8>, <8 x i8>* [[TMP6]], align 1
; CHECK-NEXT:    [[TMP7:%.*]] = trunc <8 x i16> [[WIDE_LOAD]] to <8 x i8>
; CHECK-NEXT:    [[TMP8:%.*]] = add <8 x i8> [[WIDE_LOAD1]], [[TMP7]]
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, i8* [[A:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[TMP9]], i32 0
; CHECK-NEXT:    [[TMP11:%.*]] = bitcast i8* [[TMP10]] to <8 x i8>*
; CHECK-NEXT:    store <8 x i8> [[TMP8]], <8 x i8>* [[TMP11]], align 1
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 8
; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[INDEX_NEXT]], 424
; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 431, 424
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 424, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    ret void
; CHECK:       for.body:
; CHECK-NEXT:    [[I_012:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[ADD6:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, i16* [[C]], i32 [[I_012]]
; CHECK-NEXT:    [[TMP13:%.*]] = load i16, i16* [[ARRAYIDX]], align 2
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[B]], i32 [[I_012]]
; CHECK-NEXT:    [[TMP14:%.*]] = load i8, i8* [[ARRAYIDX1]], align 1
; CHECK-NEXT:    [[CONV3:%.*]] = trunc i16 [[TMP13]] to i8
; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[TMP14]], [[CONV3]]
; CHECK-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds i8, i8* [[A]], i32 [[I_012]]
; CHECK-NEXT:    store i8 [[ADD]], i8* [[ARRAYIDX5]], align 1
; CHECK-NEXT:    [[ADD6]] = add nuw nsw i32 [[I_012]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[ADD6]], 431
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
;
entry:
  br label %for.body

for.cond.cleanup:                                 ; preds = %for.body
  ret void

for.body:                                         ; preds = %for.body, %entry
  %i.012 = phi i32 [ 0, %entry ], [ %add6, %for.body ]
  %arrayidx = getelementptr inbounds i16, i16* %C, i32 %i.012
  %0 = load i16, i16* %arrayidx, align 2
  %arrayidx1 = getelementptr inbounds i8, i8* %B, i32 %i.012
  %1 = load i8, i8* %arrayidx1, align 1
  %conv3 = trunc i16 %0 to i8
  %add = add i8 %1, %conv3
  %arrayidx5 = getelementptr inbounds i8, i8* %A, i32 %i.012
  store i8 %add, i8* %arrayidx5, align 1
  %add6 = add nuw nsw i32 %i.012, 1
  %exitcond = icmp eq i32 %add6, 431
  br i1 %exitcond, label %for.cond.cleanup, label %for.body
}

; This is a trunc not connected to a store, so we don't allow this.
; TODO: this is conservative, because the trunc is only used in the
; loop control statements, and thus not affecting element sizes, so
; we could allow this case.
;
define void @trunc_not_allowed(i32* noalias nocapture %A, i32* noalias nocapture readonly %B, i32* noalias nocapture readonly %C) #0 {
; CHECK-LABEL: @trunc_not_allowed(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 0
; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i32* [[TMP5]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP6]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = add nsw <4 x i32> [[WIDE_LOAD1]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP8]], i32 0
; CHECK-NEXT:    [[TMP10:%.*]] = bitcast i32* [[TMP9]] to <4 x i32>*
; CHECK-NEXT:    store <4 x i32> [[TMP7]], <4 x i32>* [[TMP10]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP11:%.*]] = icmp eq i32 [[INDEX_NEXT]], 428
; CHECK-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 431, 428
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 428, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    ret void
; CHECK:       for.body:
; CHECK-NEXT:    [[I_09:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[ADD3:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 [[I_09]]
; CHECK-NEXT:    [[TMP12:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[C]], i32 [[I_09]]
; CHECK-NEXT:    [[TMP13:%.*]] = load i32, i32* [[ARRAYIDX1]], align 4
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP13]], [[TMP12]]
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 [[I_09]]
; CHECK-NEXT:    store i32 [[ADD]], i32* [[ARRAYIDX2]], align 4
; CHECK-NEXT:    [[ADD3]] = add nuw nsw i32 [[I_09]], 1
; CHECK-NEXT:    [[ADD_IV:%.*]] = trunc i32 [[ADD3]] to i16
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i16 [[ADD_IV]], 431
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
;
entry:
  br label %for.body

for.cond.cleanup:
  ret void

for.body:
  %i.09 = phi i32 [ 0, %entry ], [ %add3, %for.body ]
  %arrayidx = getelementptr inbounds i32, i32* %B, i32 %i.09
  %0 = load i32, i32* %arrayidx, align 4
  %arrayidx1 = getelementptr inbounds i32, i32* %C, i32 %i.09
  %1 = load i32, i32* %arrayidx1, align 4
  %add = add nsw i32 %1, %0
  %arrayidx2 = getelementptr inbounds i32, i32* %A, i32 %i.09
  store i32 %add, i32* %arrayidx2, align 4
  %add3 = add nuw nsw i32 %i.09, 1

  %add.iv = trunc i32 %add3 to i16

  %exitcond = icmp eq i16 %add.iv, 431
  br i1 %exitcond, label %for.cond.cleanup, label %for.body
}

; Test directions for array indices i and N-1. I.e. check strides 1 and -1, and
; force vectorisation with a loop hint.
;
define void @strides_different_direction(i32* noalias nocapture %A, i32* noalias nocapture readonly %B, i32* noalias nocapture readonly %C, i32 %N) #0 {
; CHECK-LABEL: @strides_different_direction(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = sub nsw i32 [[N:%.*]], [[TMP0]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i32 [[TMP4]]
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP5]], i32 0
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i32 -3
; CHECK-NEXT:    [[TMP8:%.*]] = bitcast i32* [[TMP7]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP8]], align 4
; CHECK-NEXT:    [[REVERSE:%.*]] = shufflevector <4 x i32> [[WIDE_LOAD1]], <4 x i32> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT:    [[TMP9:%.*]] = add nsw <4 x i32> [[REVERSE]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP10]], i32 0
; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>*
; CHECK-NEXT:    store <4 x i32> [[TMP9]], <4 x i32>* [[TMP12]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq i32 [[INDEX_NEXT]], 428
; CHECK-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 431, 428
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 428, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    ret void
; CHECK:       for.body:
; CHECK-NEXT:    [[I_09:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[ADD3:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 [[I_09]]
; CHECK-NEXT:    [[TMP14:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[SUB:%.*]] = sub nsw i32 [[N]], [[I_09]]
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[C]], i32 [[SUB]]
; CHECK-NEXT:    [[TMP15:%.*]] = load i32, i32* [[ARRAYIDX1]], align 4
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP15]], [[TMP14]]
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 [[I_09]]
; CHECK-NEXT:    store i32 [[ADD]], i32* [[ARRAYIDX2]], align 4
; CHECK-NEXT:    [[ADD3]] = add nuw nsw i32 [[I_09]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[ADD3]], 431
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
;
entry:
  br label %for.body

for.cond.cleanup:
  ret void

for.body:
  %i.09 = phi i32 [ 0, %entry ], [ %add3, %for.body ]
  %arrayidx = getelementptr inbounds i32, i32* %B, i32 %i.09
  %0 = load i32, i32* %arrayidx, align 4
  %sub = sub nsw i32 %N, %i.09
  %arrayidx1 = getelementptr inbounds i32, i32* %C, i32 %sub
  %1 = load i32, i32* %arrayidx1, align 4
  %add = add nsw i32 %1, %0
  %arrayidx2 = getelementptr inbounds i32, i32* %A, i32 %i.09
  store i32 %add, i32* %arrayidx2, align 4
  %add3 = add nuw nsw i32 %i.09, 1
  %exitcond = icmp eq i32 %add3, 431
  br i1 %exitcond, label %for.cond.cleanup, label %for.body, !llvm.loop !10
}

define void @too_many_loop_blocks(i32* noalias nocapture %A, i32* noalias nocapture readonly %B, i32* noalias nocapture readonly %C) #0 {
; CHECK-LABEL: @too_many_loop_blocks(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 0
; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i32* [[TMP5]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP6]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = add nsw <4 x i32> [[WIDE_LOAD1]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP8]], i32 0
; CHECK-NEXT:    [[TMP10:%.*]] = bitcast i32* [[TMP9]] to <4 x i32>*
; CHECK-NEXT:    store <4 x i32> [[TMP7]], <4 x i32>* [[TMP10]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP11:%.*]] = icmp eq i32 [[INDEX_NEXT]], 428
; CHECK-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 431, 428
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 428, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    ret void
; CHECK:       for.body:
; CHECK-NEXT:    [[I_09:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[ADD3:%.*]], [[LOOPINCR:%.*]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[B]], i32 [[I_09]]
; CHECK-NEXT:    [[TMP12:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[C]], i32 [[I_09]]
; CHECK-NEXT:    [[TMP13:%.*]] = load i32, i32* [[ARRAYIDX1]], align 4
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP13]], [[TMP12]]
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 [[I_09]]
; CHECK-NEXT:    store i32 [[ADD]], i32* [[ARRAYIDX2]], align 4
; CHECK-NEXT:    br label [[LOOPINCR]]
; CHECK:       loopincr:
; CHECK-NEXT:    [[ADD3]] = add nuw nsw i32 [[I_09]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[ADD3]], 431
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
;
entry:
  br label %for.body

for.cond.cleanup:
  ret void

for.body:
  %i.09 = phi i32 [ 0, %entry ], [ %add3, %loopincr ]
  %arrayidx = getelementptr inbounds i32, i32* %B, i32 %i.09
  %0 = load i32, i32* %arrayidx, align 4
  %arrayidx1 = getelementptr inbounds i32, i32* %C, i32 %i.09
  %1 = load i32, i32* %arrayidx1, align 4
  %add = add nsw i32 %1, %0
  %arrayidx2 = getelementptr inbounds i32, i32* %A, i32 %i.09
  store i32 %add, i32* %arrayidx2, align 4
  br label %loopincr

loopincr:
  %add3 = add nuw nsw i32 %i.09, 1
  %exitcond = icmp eq i32 %add3, 431
  br i1 %exitcond, label %for.cond.cleanup, label %for.body
}

define void @double(double* noalias nocapture %A, double* noalias nocapture readonly %B, double* noalias nocapture readonly %C) #0 {
; CHECK-LABEL: @double(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    ret void
; CHECK:       for.body:
; CHECK-NEXT:    [[I_09:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[ADD3:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds double, double* [[B:%.*]], i32 [[I_09]]
; CHECK-NEXT:    [[TMP0:%.*]] = load double, double* [[ARRAYIDX]], align 8
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds double, double* [[C:%.*]], i32 [[I_09]]
; CHECK-NEXT:    [[TMP1:%.*]] = load double, double* [[ARRAYIDX1]], align 8
; CHECK-NEXT:    [[ADD:%.*]] = fadd fast double [[TMP1]], [[TMP0]]
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds double, double* [[A:%.*]], i32 [[I_09]]
; CHECK-NEXT:    store double [[ADD]], double* [[ARRAYIDX2]], align 8
; CHECK-NEXT:    [[ADD3]] = add nuw nsw i32 [[I_09]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[ADD3]], 431
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
;
entry:
  br label %for.body

for.cond.cleanup:
  ret void

for.body:
  %i.09 = phi i32 [ 0, %entry ], [ %add3, %for.body ]
  %arrayidx = getelementptr inbounds double, double* %B, i32 %i.09
  %0 = load double, double* %arrayidx, align 8
  %arrayidx1 = getelementptr inbounds double, double* %C, i32 %i.09
  %1 = load double, double* %arrayidx1, align 8
  %add = fadd fast double %1, %0
  %arrayidx2 = getelementptr inbounds double, double* %A, i32 %i.09
  store double %add, double* %arrayidx2, align 8
  %add3 = add nuw nsw i32 %i.09, 1
  %exitcond = icmp eq i32 %add3, 431
  br i1 %exitcond, label %for.cond.cleanup, label %for.body
}

define void @fptrunc_not_allowed(float* noalias nocapture %A, float* noalias nocapture readonly %B, float* noalias nocapture readonly %C, half* noalias nocapture %D) #0 {
; CHECK-LABEL: @fptrunc_not_allowed(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds float, float* [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[TMP2]] to <4 x float>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x float>, <4 x float>* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds float, float* [[C:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[TMP4]], i32 0
; CHECK-NEXT:    [[TMP6:%.*]] = bitcast float* [[TMP5]] to <4 x float>*
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x float>, <4 x float>* [[TMP6]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = fadd fast <4 x float> [[WIDE_LOAD1]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds float, float* [[TMP8]], i32 0
; CHECK-NEXT:    [[TMP10:%.*]] = bitcast float* [[TMP9]] to <4 x float>*
; CHECK-NEXT:    store <4 x float> [[TMP7]], <4 x float>* [[TMP10]], align 4
; CHECK-NEXT:    [[TMP11:%.*]] = fptrunc <4 x float> [[TMP7]] to <4 x half>
; CHECK-NEXT:    [[TMP12:%.*]] = fmul fast <4 x half> [[TMP11]], <half 0xH4000, half 0xH4000, half 0xH4000, half 0xH4000>
; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds half, half* [[D:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds half, half* [[TMP13]], i32 0
; CHECK-NEXT:    [[TMP15:%.*]] = bitcast half* [[TMP14]] to <4 x half>*
; CHECK-NEXT:    store <4 x half> [[TMP12]], <4 x half>* [[TMP15]], align 2
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP16:%.*]] = icmp eq i32 [[INDEX_NEXT]], 428
; CHECK-NEXT:    br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 431, 428
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 428, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    ret void
; CHECK:       for.body:
; CHECK-NEXT:    [[I_017:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[ADD6:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, float* [[B]], i32 [[I_017]]
; CHECK-NEXT:    [[TMP17:%.*]] = load float, float* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds float, float* [[C]], i32 [[I_017]]
; CHECK-NEXT:    [[TMP18:%.*]] = load float, float* [[ARRAYIDX1]], align 4
; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP18]], [[TMP17]]
; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A]], i32 [[I_017]]
; CHECK-NEXT:    store float [[ADD]], float* [[ARRAYIDX2]], align 4
; CHECK-NEXT:    [[CONV:%.*]] = fptrunc float [[ADD]] to half
; CHECK-NEXT:    [[FACTOR:%.*]] = fmul fast half [[CONV]], 0xH4000
; CHECK-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds half, half* [[D]], i32 [[I_017]]
; CHECK-NEXT:    store half [[FACTOR]], half* [[ARRAYIDX5]], align 2
; CHECK-NEXT:    [[ADD6]] = add nuw nsw i32 [[I_017]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[ADD6]], 431
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
;
entry:
  br label %for.body

for.cond.cleanup:
  ret void

for.body:
  %i.017 = phi i32 [ 0, %entry ], [ %add6, %for.body ]
  %arrayidx = getelementptr inbounds float, float* %B, i32 %i.017
  %0 = load float, float* %arrayidx, align 4
  %arrayidx1 = getelementptr inbounds float, float* %C, i32 %i.017
  %1 = load float, float* %arrayidx1, align 4
  %add = fadd fast float %1, %0
  %arrayidx2 = getelementptr inbounds float, float* %A, i32 %i.017
  store float %add, float* %arrayidx2, align 4
  %conv = fptrunc float %add to half
  %factor = fmul fast half %conv, 0xH4000
  %arrayidx5 = getelementptr inbounds half, half* %D, i32 %i.017
  store half %factor, half* %arrayidx5, align 2
  %add6 = add nuw nsw i32 %i.017, 1
  %exitcond = icmp eq i32 %add6, 431
  br i1 %exitcond, label %for.cond.cleanup, label %for.body
}

; This is a select which isn't a max or min (it isn't live-out), that we don't
; want to tail-fold. Because this select will result in some mov lanes,
; which aren't supported by the lowoverhead loop pass, causing the tail-predication
; to be reverted which is expensive and what we would like to avoid.
;
define dso_local void @select_not_allowed(i32* noalias nocapture %A, i32* noalias nocapture readonly %B, i32* noalias nocapture readonly %C, i32 %N, i32* noalias nocapture readonly %Cond) {
; CHECK-LABEL: @select_not_allowed(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP10:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP10]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32*> poison, i32* [[C:%.*]], i32 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32*> [[BROADCAST_SPLATINSERT]], <4 x i32*> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32*> poison, i32* [[B:%.*]], i32 0
; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32*> [[BROADCAST_SPLATINSERT1]], <4 x i32*> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[INDEX]], 1
; CHECK-NEXT:    [[TMP2:%.*]] = add i32 [[INDEX]], 2
; CHECK-NEXT:    [[TMP3:%.*]] = add i32 [[INDEX]], 3
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[COND:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i32 0
; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i32* [[TMP5]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP6]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq <4 x i32> [[WIDE_LOAD]], zeroinitializer
; CHECK-NEXT:    [[TMP8:%.*]] = select <4 x i1> [[TMP7]], <4 x i32*> [[BROADCAST_SPLAT]], <4 x i32*> [[BROADCAST_SPLAT2]]
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i32, <4 x i32*> [[TMP8]], <4 x i32> [[VEC_IND]]
; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> [[TMP9]], i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef)
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP10]], i32 0
; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <4 x i32>*
; CHECK-NEXT:    store <4 x i32> [[WIDE_MASKED_GATHER]], <4 x i32>* [[TMP12]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], <i32 4, i32 4, i32 4, i32 4>
; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.cond.cleanup.loopexit:
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    ret void
; CHECK:       for.body:
; CHECK-NEXT:    [[I_011:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[COND]], i32 [[I_011]]
; CHECK-NEXT:    [[TMP14:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[TOBOOL_NOT:%.*]] = icmp eq i32 [[TMP14]], 0
; CHECK-NEXT:    [[C_B:%.*]] = select i1 [[TOBOOL_NOT]], i32* [[C]], i32* [[B]]
; CHECK-NEXT:    [[COND_IN:%.*]] = getelementptr inbounds i32, i32* [[C_B]], i32 [[I_011]]
; CHECK-NEXT:    [[COND:%.*]] = load i32, i32* [[COND_IN]], align 4
; CHECK-NEXT:    [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 [[I_011]]
; CHECK-NEXT:    store i32 [[COND]], i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_011]], 1
; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]]
;
entry:
  %cmp10 = icmp sgt i32 %N, 0
  br i1 %cmp10, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  br label %for.body

for.cond.cleanup.loopexit:                        ; preds = %for.body
  br label %for.cond.cleanup

for.cond.cleanup:                                 ; preds = %for.cond.cleanup.loopexit, %entry
  ret void

for.body:                                         ; preds = %for.body.preheader, %for.body
  %i.011 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
  %arrayidx = getelementptr inbounds i32, i32* %Cond, i32 %i.011
  %0 = load i32, i32* %arrayidx, align 4
  %tobool.not = icmp eq i32 %0, 0
  %C.B = select i1 %tobool.not, i32* %C, i32* %B
  %cond.in = getelementptr inbounds i32, i32* %C.B, i32 %i.011
  %cond = load i32, i32* %cond.in, align 4
  %arrayidx3 = getelementptr inbounds i32, i32* %A, i32 %i.011
  store i32 %cond, i32* %arrayidx3, align 4
  %inc = add nuw nsw i32 %i.011, 1
  %exitcond.not = icmp eq i32 %inc, %N
  br i1 %exitcond.not, label %for.cond.cleanup.loopexit, label %for.body
}

define i32 @i32_smin_reduction(i32* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @i32_smin_reduction(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>, [[VECTOR_PH]] ], [ [[TMP5:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[X:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = icmp slt <4 x i32> [[VEC_PHI]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP5]] = select <4 x i1> [[TMP4]], <4 x i32> [[VEC_PHI]], <4 x i32> [[WIDE_LOAD]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> [[TMP5]])
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ 2147483647, [[FOR_BODY_PREHEADER]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[R_07:%.*]] = phi i32 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[X]], i32 [[I_08]]
; CHECK-NEXT:    [[TMP8:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[C:%.*]] = icmp slt i32 [[R_07]], [[TMP8]]
; CHECK-NEXT:    [[ADD]] = select i1 [[C]], i32 [[R_07]], i32 [[TMP8]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP17:![0-9]+]]
; CHECK:       for.cond.cleanup.loopexit:
; CHECK-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 2147483647, [[ENTRY:%.*]] ], [ [[ADD_LCSSA]], [[FOR_COND_CLEANUP_LOOPEXIT]] ]
; CHECK-NEXT:    ret i32 [[R_0_LCSSA]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i32 [ %add, %for.body ], [ 2147483647, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %0 = load i32, i32* %arrayidx, align 4
  %c = icmp slt i32 %r.07, %0
  %add = select i1 %c, i32 %r.07, i32 %0
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i32 [ 2147483647, %entry ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @i32_smax_reduction(i32* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @i32_smax_reduction(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>, [[VECTOR_PH]] ], [ [[TMP5:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[X:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = icmp sgt <4 x i32> [[VEC_PHI]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP5]] = select <4 x i1> [[TMP4]], <4 x i32> [[VEC_PHI]], <4 x i32> [[WIDE_LOAD]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP18:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[TMP5]])
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ -2147483648, [[FOR_BODY_PREHEADER]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[R_07:%.*]] = phi i32 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[X]], i32 [[I_08]]
; CHECK-NEXT:    [[TMP8:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[C:%.*]] = icmp sgt i32 [[R_07]], [[TMP8]]
; CHECK-NEXT:    [[ADD]] = select i1 [[C]], i32 [[R_07]], i32 [[TMP8]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP19:![0-9]+]]
; CHECK:       for.cond.cleanup.loopexit:
; CHECK-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ -2147483648, [[ENTRY:%.*]] ], [ [[ADD_LCSSA]], [[FOR_COND_CLEANUP_LOOPEXIT]] ]
; CHECK-NEXT:    ret i32 [[R_0_LCSSA]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i32 [ %add, %for.body ], [ -2147483648, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %0 = load i32, i32* %arrayidx, align 4
  %c = icmp sgt i32 %r.07, %0
  %add = select i1 %c, i32 %r.07, i32 %0
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i32 [ -2147483648, %entry ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @i32_umin_reduction(i32* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @i32_umin_reduction(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ <i32 -1, i32 -1, i32 -1, i32 -1>, [[VECTOR_PH]] ], [ [[TMP5:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[X:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = icmp ult <4 x i32> [[VEC_PHI]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP5]] = select <4 x i1> [[TMP4]], <4 x i32> [[VEC_PHI]], <4 x i32> [[WIDE_LOAD]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> [[TMP5]])
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ -1, [[FOR_BODY_PREHEADER]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[R_07:%.*]] = phi i32 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[X]], i32 [[I_08]]
; CHECK-NEXT:    [[TMP8:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[C:%.*]] = icmp ult i32 [[R_07]], [[TMP8]]
; CHECK-NEXT:    [[ADD]] = select i1 [[C]], i32 [[R_07]], i32 [[TMP8]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP21:![0-9]+]]
; CHECK:       for.cond.cleanup.loopexit:
; CHECK-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ -1, [[ENTRY:%.*]] ], [ [[ADD_LCSSA]], [[FOR_COND_CLEANUP_LOOPEXIT]] ]
; CHECK-NEXT:    ret i32 [[R_0_LCSSA]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i32 [ %add, %for.body ], [ 4294967295, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %0 = load i32, i32* %arrayidx, align 4
  %c = icmp ult i32 %r.07, %0
  %add = select i1 %c, i32 %r.07, i32 %0
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i32 [ 4294967295, %entry ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @i32_umax_reduction(i32* nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @i32_umax_reduction(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK:       for.body.preheader:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP5:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[X:%.*]], i32 [[TMP0]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = icmp ugt <4 x i32> [[VEC_PHI]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP5]] = select <4 x i1> [[TMP4]], <4 x i32> [[VEC_PHI]], <4 x i32> [[WIDE_LOAD]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP22:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> [[TMP5]])
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ 0, [[FOR_BODY_PREHEADER]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[R_07:%.*]] = phi i32 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[X]], i32 [[I_08]]
; CHECK-NEXT:    [[TMP8:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[C:%.*]] = icmp ugt i32 [[R_07]], [[TMP8]]
; CHECK-NEXT:    [[ADD]] = select i1 [[C]], i32 [[R_07]], i32 [[TMP8]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP23:![0-9]+]]
; CHECK:       for.cond.cleanup.loopexit:
; CHECK-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[TMP7]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
; CHECK:       for.cond.cleanup:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[ADD_LCSSA]], [[FOR_COND_CLEANUP_LOOPEXIT]] ]
; CHECK-NEXT:    ret i32 [[R_0_LCSSA]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i32 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %x, i32 %i.08
  %0 = load i32, i32* %arrayidx, align 4
  %c = icmp ugt i32 %r.07, %0
  %add = select i1 %c, i32 %r.07, i32 %0
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

!10 = distinct !{!10, !11}
!11 = !{!"llvm.loop.vectorize.width", i32 4}