; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s  -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -prefer-inloop-reductions -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -dce -instcombine -S | FileCheck %s

target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"

define i32 @reduction_sum_single(i32* noalias nocapture %A) {
; CHECK-LABEL: @reduction_sum_single(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE6:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP26:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP3]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP5:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP6]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
; CHECK:       pred.load.if1:
; CHECK-NEXT:    [[TMP7:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP7]]
; CHECK-NEXT:    [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <4 x i32> [[TMP5]], i32 [[TMP9]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
; CHECK:       pred.load.continue2:
; CHECK-NEXT:    [[TMP11:%.*]] = phi <4 x i32> [ [[TMP5]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP10]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP12]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP13:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP13]]
; CHECK-NEXT:    [[TMP15:%.*]] = load i32, i32* [[TMP14]], align 4
; CHECK-NEXT:    [[TMP16:%.*]] = insertelement <4 x i32> [[TMP11]], i32 [[TMP15]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP17:%.*]] = phi <4 x i32> [ [[TMP11]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP16]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP18]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP19:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP20:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP19]]
; CHECK-NEXT:    [[TMP21:%.*]] = load i32, i32* [[TMP20]], align 4
; CHECK-NEXT:    [[TMP22:%.*]] = insertelement <4 x i32> [[TMP17]], i32 [[TMP21]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP23:%.*]] = phi <4 x i32> [ [[TMP17]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP22]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP24:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP23]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP25:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP24]])
; CHECK-NEXT:    [[TMP26]] = add i32 [[TMP25]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[TMP27:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP27]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[DOT_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[DOTLR_PH:%.*]]
; CHECK:       .lr.ph:
; CHECK-NEXT:    br i1 undef, label [[DOT_CRIT_EDGE]], label [[DOTLR_PH]], !llvm.loop [[LOOP2:![0-9]+]]
; CHECK:       ._crit_edge:
; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i32 [ undef, [[DOTLR_PH]] ], [ [[TMP26]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[SUM_0_LCSSA]]
;
entry:
  br label %.lr.ph

.lr.ph:                                           ; preds = %entry, %.lr.ph
  %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %entry ]
  %sum.02 = phi i32 [ %l7, %.lr.ph ], [ 0, %entry ]
  %l2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
  %l3 = load i32, i32* %l2, align 4
  %l7 = add i32 %sum.02, %l3
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %._crit_edge, label %.lr.ph

._crit_edge:                                      ; preds = %.lr.ph
  %sum.0.lcssa = phi i32 [ %l7, %.lr.ph ]
  ret i32 %sum.0.lcssa
}

define i32 @reduction_sum(i32* noalias nocapture %A, i32* noalias nocapture %B) {
; CHECK-LABEL: @reduction_sum(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE8:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE8]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP48:%.*]], [[PRED_LOAD_CONTINUE8]] ]
; CHECK-NEXT:    [[VEC_IND1:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT2:%.*]], [[PRED_LOAD_CONTINUE8]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP3]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, i32* [[TMP5]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> poison, i32 [[TMP6]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP8:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP9:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP7]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP10]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP11:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <4 x i32> [[TMP8]], i32 [[TMP13]], i32 1
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <4 x i32> [[TMP9]], i32 [[TMP16]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP18:%.*]] = phi <4 x i32> [ [[TMP8]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP14]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP19:%.*]] = phi <4 x i32> [ [[TMP9]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP17]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP20]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6:%.*]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP21:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4
; CHECK-NEXT:    [[TMP24:%.*]] = insertelement <4 x i32> [[TMP18]], i32 [[TMP23]], i32 2
; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
; CHECK-NEXT:    [[TMP27:%.*]] = insertelement <4 x i32> [[TMP19]], i32 [[TMP26]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP28:%.*]] = phi <4 x i32> [ [[TMP18]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP24]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP29:%.*]] = phi <4 x i32> [ [[TMP19]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP27]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP30]], label [[PRED_LOAD_IF7:%.*]], label [[PRED_LOAD_CONTINUE8]]
; CHECK:       pred.load.if7:
; CHECK-NEXT:    [[TMP31:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP33:%.*]] = load i32, i32* [[TMP32]], align 4
; CHECK-NEXT:    [[TMP34:%.*]] = insertelement <4 x i32> [[TMP28]], i32 [[TMP33]], i32 3
; CHECK-NEXT:    [[TMP35:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP36:%.*]] = load i32, i32* [[TMP35]], align 4
; CHECK-NEXT:    [[TMP37:%.*]] = insertelement <4 x i32> [[TMP29]], i32 [[TMP36]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE8]]
; CHECK:       pred.load.continue8:
; CHECK-NEXT:    [[TMP38:%.*]] = phi <4 x i32> [ [[TMP28]], [[PRED_LOAD_CONTINUE6]] ], [ [[TMP34]], [[PRED_LOAD_IF7]] ]
; CHECK-NEXT:    [[TMP39:%.*]] = phi <4 x i32> [ [[TMP29]], [[PRED_LOAD_CONTINUE6]] ], [ [[TMP37]], [[PRED_LOAD_IF7]] ]
; CHECK-NEXT:    [[TMP40:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[VEC_IND1]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP41:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP40]])
; CHECK-NEXT:    [[TMP42:%.*]] = add i32 [[TMP41]], [[VEC_PHI]]
; CHECK-NEXT:    [[TMP43:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP38]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP44:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP43]])
; CHECK-NEXT:    [[TMP45:%.*]] = add i32 [[TMP44]], [[TMP42]]
; CHECK-NEXT:    [[TMP46:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP39]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP47:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP46]])
; CHECK-NEXT:    [[TMP48]] = add i32 [[TMP47]], [[TMP45]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[VEC_IND_NEXT2]] = add <4 x i32> [[VEC_IND1]], <i32 4, i32 4, i32 4, i32 4>
; CHECK-NEXT:    [[TMP49:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP49]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[DOT_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[DOTLR_PH:%.*]]
; CHECK:       .lr.ph:
; CHECK-NEXT:    br i1 undef, label [[DOT_CRIT_EDGE]], label [[DOTLR_PH]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       ._crit_edge:
; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i32 [ undef, [[DOTLR_PH]] ], [ [[TMP48]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[SUM_0_LCSSA]]
;
entry:
  br label %.lr.ph

.lr.ph:                                           ; preds = %entry, %.lr.ph
  %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %entry ]
  %sum.02 = phi i32 [ %l9, %.lr.ph ], [ 0, %entry ]
  %l2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
  %l3 = load i32, i32* %l2, align 4
  %l4 = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
  %l5 = load i32, i32* %l4, align 4
  %l6 = trunc i64 %indvars.iv to i32
  %l7 = add i32 %sum.02, %l6
  %l8 = add i32 %l7, %l3
  %l9 = add i32 %l8, %l5
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %._crit_edge, label %.lr.ph

._crit_edge:                                      ; preds = %.lr.ph
  %sum.0.lcssa = phi i32 [ %l9, %.lr.ph ]
  ret i32 %sum.0.lcssa
}

define i32 @reduction_sum_const(i32* noalias nocapture %A) {
; CHECK-LABEL: @reduction_sum_const(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE6:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP29:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP3]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP5:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP6]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
; CHECK:       pred.load.if1:
; CHECK-NEXT:    [[TMP7:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP7]]
; CHECK-NEXT:    [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <4 x i32> [[TMP5]], i32 [[TMP9]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
; CHECK:       pred.load.continue2:
; CHECK-NEXT:    [[TMP11:%.*]] = phi <4 x i32> [ [[TMP5]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP10]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP12]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP13:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP13]]
; CHECK-NEXT:    [[TMP15:%.*]] = load i32, i32* [[TMP14]], align 4
; CHECK-NEXT:    [[TMP16:%.*]] = insertelement <4 x i32> [[TMP11]], i32 [[TMP15]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP17:%.*]] = phi <4 x i32> [ [[TMP11]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP16]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP18]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP19:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP20:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP19]]
; CHECK-NEXT:    [[TMP21:%.*]] = load i32, i32* [[TMP20]], align 4
; CHECK-NEXT:    [[TMP22:%.*]] = insertelement <4 x i32> [[TMP17]], i32 [[TMP21]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP23:%.*]] = phi <4 x i32> [ [[TMP17]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP22]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP24:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP23]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP25:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP24]])
; CHECK-NEXT:    [[TMP26:%.*]] = add i32 [[TMP25]], [[VEC_PHI]]
; CHECK-NEXT:    [[TMP27:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> <i32 3, i32 3, i32 3, i32 3>, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP28:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP27]])
; CHECK-NEXT:    [[TMP29]] = add i32 [[TMP28]], [[TMP26]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[TMP30:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP30]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[DOT_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[DOTLR_PH:%.*]]
; CHECK:       .lr.ph:
; CHECK-NEXT:    br i1 undef, label [[DOT_CRIT_EDGE]], label [[DOTLR_PH]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK:       ._crit_edge:
; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i32 [ undef, [[DOTLR_PH]] ], [ [[TMP29]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[SUM_0_LCSSA]]
;
entry:
  br label %.lr.ph

.lr.ph:                                           ; preds = %entry, %.lr.ph
  %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %entry ]
  %sum.02 = phi i32 [ %l9, %.lr.ph ], [ 0, %entry ]
  %l2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
  %l3 = load i32, i32* %l2, align 4
  %l7 = add i32 %sum.02, %l3
  %l9 = add i32 %l7, 3
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %._crit_edge, label %.lr.ph

._crit_edge:                                      ; preds = %.lr.ph
  %sum.0.lcssa = phi i32 [ %l9, %.lr.ph ]
  ret i32 %sum.0.lcssa
}

define i32 @reduction_prod(i32* noalias nocapture %A, i32* noalias nocapture %B) {
; CHECK-LABEL: @reduction_prod(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE8:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE8]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 1, [[VECTOR_PH]] ], [ [[TMP48:%.*]], [[PRED_LOAD_CONTINUE8]] ]
; CHECK-NEXT:    [[VEC_IND1:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT2:%.*]], [[PRED_LOAD_CONTINUE8]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP3]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, i32* [[TMP5]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> poison, i32 [[TMP6]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP8:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP9:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP7]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP10]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP11:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <4 x i32> [[TMP8]], i32 [[TMP13]], i32 1
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <4 x i32> [[TMP9]], i32 [[TMP16]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP18:%.*]] = phi <4 x i32> [ [[TMP8]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP14]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP19:%.*]] = phi <4 x i32> [ [[TMP9]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP17]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP20]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6:%.*]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP21:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4
; CHECK-NEXT:    [[TMP24:%.*]] = insertelement <4 x i32> [[TMP18]], i32 [[TMP23]], i32 2
; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
; CHECK-NEXT:    [[TMP27:%.*]] = insertelement <4 x i32> [[TMP19]], i32 [[TMP26]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP28:%.*]] = phi <4 x i32> [ [[TMP18]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP24]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP29:%.*]] = phi <4 x i32> [ [[TMP19]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP27]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP30]], label [[PRED_LOAD_IF7:%.*]], label [[PRED_LOAD_CONTINUE8]]
; CHECK:       pred.load.if7:
; CHECK-NEXT:    [[TMP31:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP33:%.*]] = load i32, i32* [[TMP32]], align 4
; CHECK-NEXT:    [[TMP34:%.*]] = insertelement <4 x i32> [[TMP28]], i32 [[TMP33]], i32 3
; CHECK-NEXT:    [[TMP35:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP36:%.*]] = load i32, i32* [[TMP35]], align 4
; CHECK-NEXT:    [[TMP37:%.*]] = insertelement <4 x i32> [[TMP29]], i32 [[TMP36]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE8]]
; CHECK:       pred.load.continue8:
; CHECK-NEXT:    [[TMP38:%.*]] = phi <4 x i32> [ [[TMP28]], [[PRED_LOAD_CONTINUE6]] ], [ [[TMP34]], [[PRED_LOAD_IF7]] ]
; CHECK-NEXT:    [[TMP39:%.*]] = phi <4 x i32> [ [[TMP29]], [[PRED_LOAD_CONTINUE6]] ], [ [[TMP37]], [[PRED_LOAD_IF7]] ]
; CHECK-NEXT:    [[TMP40:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[VEC_IND1]], <4 x i32> <i32 1, i32 1, i32 1, i32 1>
; CHECK-NEXT:    [[TMP41:%.*]] = call i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> [[TMP40]])
; CHECK-NEXT:    [[TMP42:%.*]] = mul i32 [[TMP41]], [[VEC_PHI]]
; CHECK-NEXT:    [[TMP43:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP38]], <4 x i32> <i32 1, i32 1, i32 1, i32 1>
; CHECK-NEXT:    [[TMP44:%.*]] = call i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> [[TMP43]])
; CHECK-NEXT:    [[TMP45:%.*]] = mul i32 [[TMP44]], [[TMP42]]
; CHECK-NEXT:    [[TMP46:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP39]], <4 x i32> <i32 1, i32 1, i32 1, i32 1>
; CHECK-NEXT:    [[TMP47:%.*]] = call i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> [[TMP46]])
; CHECK-NEXT:    [[TMP48]] = mul i32 [[TMP47]], [[TMP45]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[VEC_IND_NEXT2]] = add <4 x i32> [[VEC_IND1]], <i32 4, i32 4, i32 4, i32 4>
; CHECK-NEXT:    [[TMP49:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP49]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[DOT_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[DOTLR_PH:%.*]]
; CHECK:       .lr.ph:
; CHECK-NEXT:    br i1 undef, label [[DOT_CRIT_EDGE]], label [[DOTLR_PH]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK:       ._crit_edge:
; CHECK-NEXT:    [[PROD_0_LCSSA:%.*]] = phi i32 [ undef, [[DOTLR_PH]] ], [ [[TMP48]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[PROD_0_LCSSA]]
;
entry:
  br label %.lr.ph

.lr.ph:                                           ; preds = %entry, %.lr.ph
  %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %entry ]
  %prod.02 = phi i32 [ %l9, %.lr.ph ], [ 1, %entry ]
  %l2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
  %l3 = load i32, i32* %l2, align 4
  %l4 = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
  %l5 = load i32, i32* %l4, align 4
  %l6 = trunc i64 %indvars.iv to i32
  %l7 = mul i32 %prod.02, %l6
  %l8 = mul i32 %l7, %l3
  %l9 = mul i32 %l8, %l5
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %._crit_edge, label %.lr.ph

._crit_edge:                                      ; preds = %.lr.ph
  %prod.0.lcssa = phi i32 [ %l9, %.lr.ph ]
  ret i32 %prod.0.lcssa
}

define i32 @reduction_mix(i32* noalias nocapture %A, i32* noalias nocapture %B) {
; CHECK-LABEL: @reduction_mix(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE8:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE8]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP46:%.*]], [[PRED_LOAD_CONTINUE8]] ]
; CHECK-NEXT:    [[VEC_IND1:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT2:%.*]], [[PRED_LOAD_CONTINUE8]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP3]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, i32* [[TMP5]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> poison, i32 [[TMP6]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP8:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP9:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP7]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP10]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP11:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <4 x i32> [[TMP8]], i32 [[TMP13]], i32 1
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <4 x i32> [[TMP9]], i32 [[TMP16]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP18:%.*]] = phi <4 x i32> [ [[TMP8]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP14]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP19:%.*]] = phi <4 x i32> [ [[TMP9]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP17]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP20]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6:%.*]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP21:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4
; CHECK-NEXT:    [[TMP24:%.*]] = insertelement <4 x i32> [[TMP18]], i32 [[TMP23]], i32 2
; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
; CHECK-NEXT:    [[TMP27:%.*]] = insertelement <4 x i32> [[TMP19]], i32 [[TMP26]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP28:%.*]] = phi <4 x i32> [ [[TMP18]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP24]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP29:%.*]] = phi <4 x i32> [ [[TMP19]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP27]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP30]], label [[PRED_LOAD_IF7:%.*]], label [[PRED_LOAD_CONTINUE8]]
; CHECK:       pred.load.if7:
; CHECK-NEXT:    [[TMP31:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP33:%.*]] = load i32, i32* [[TMP32]], align 4
; CHECK-NEXT:    [[TMP34:%.*]] = insertelement <4 x i32> [[TMP28]], i32 [[TMP33]], i32 3
; CHECK-NEXT:    [[TMP35:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP36:%.*]] = load i32, i32* [[TMP35]], align 4
; CHECK-NEXT:    [[TMP37:%.*]] = insertelement <4 x i32> [[TMP29]], i32 [[TMP36]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE8]]
; CHECK:       pred.load.continue8:
; CHECK-NEXT:    [[TMP38:%.*]] = phi <4 x i32> [ [[TMP28]], [[PRED_LOAD_CONTINUE6]] ], [ [[TMP34]], [[PRED_LOAD_IF7]] ]
; CHECK-NEXT:    [[TMP39:%.*]] = phi <4 x i32> [ [[TMP29]], [[PRED_LOAD_CONTINUE6]] ], [ [[TMP37]], [[PRED_LOAD_IF7]] ]
; CHECK-NEXT:    [[TMP40:%.*]] = mul nsw <4 x i32> [[TMP39]], [[TMP38]]
; CHECK-NEXT:    [[TMP41:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[VEC_IND1]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP42:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP41]])
; CHECK-NEXT:    [[TMP43:%.*]] = add i32 [[TMP42]], [[VEC_PHI]]
; CHECK-NEXT:    [[TMP44:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP40]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP45:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP44]])
; CHECK-NEXT:    [[TMP46]] = add i32 [[TMP45]], [[TMP43]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[VEC_IND_NEXT2]] = add <4 x i32> [[VEC_IND1]], <i32 4, i32 4, i32 4, i32 4>
; CHECK-NEXT:    [[TMP47:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP47]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[DOT_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[DOTLR_PH:%.*]]
; CHECK:       .lr.ph:
; CHECK-NEXT:    br i1 undef, label [[DOT_CRIT_EDGE]], label [[DOTLR_PH]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK:       ._crit_edge:
; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i32 [ undef, [[DOTLR_PH]] ], [ [[TMP46]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[SUM_0_LCSSA]]
;
entry:
  br label %.lr.ph

.lr.ph:                                           ; preds = %entry, %.lr.ph
  %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %entry ]
  %sum.02 = phi i32 [ %l9, %.lr.ph ], [ 0, %entry ]
  %l2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
  %l3 = load i32, i32* %l2, align 4
  %l4 = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
  %l5 = load i32, i32* %l4, align 4
  %l6 = mul nsw i32 %l5, %l3
  %l7 = trunc i64 %indvars.iv to i32
  %l8 = add i32 %sum.02, %l7
  %l9 = add i32 %l8, %l6
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %._crit_edge, label %.lr.ph

._crit_edge:                                      ; preds = %.lr.ph
  %sum.0.lcssa = phi i32 [ %l9, %.lr.ph ]
  ret i32 %sum.0.lcssa
}

define i32 @reduction_mul(i32* noalias nocapture %A, i32* noalias nocapture %B) {
; CHECK-LABEL: @reduction_mul(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE6:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 19, [[VECTOR_PH]] ], [ [[TMP45:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP3]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, i32* [[TMP5]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> poison, i32 [[TMP6]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP8:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP9:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP7]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP10]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
; CHECK:       pred.load.if1:
; CHECK-NEXT:    [[TMP11:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <4 x i32> [[TMP8]], i32 [[TMP13]], i32 1
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <4 x i32> [[TMP9]], i32 [[TMP16]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
; CHECK:       pred.load.continue2:
; CHECK-NEXT:    [[TMP18:%.*]] = phi <4 x i32> [ [[TMP8]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP14]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP19:%.*]] = phi <4 x i32> [ [[TMP9]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP17]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP20]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP21:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4
; CHECK-NEXT:    [[TMP24:%.*]] = insertelement <4 x i32> [[TMP18]], i32 [[TMP23]], i32 2
; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
; CHECK-NEXT:    [[TMP27:%.*]] = insertelement <4 x i32> [[TMP19]], i32 [[TMP26]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP28:%.*]] = phi <4 x i32> [ [[TMP18]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP24]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP29:%.*]] = phi <4 x i32> [ [[TMP19]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP27]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP30]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP31:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP33:%.*]] = load i32, i32* [[TMP32]], align 4
; CHECK-NEXT:    [[TMP34:%.*]] = insertelement <4 x i32> [[TMP28]], i32 [[TMP33]], i32 3
; CHECK-NEXT:    [[TMP35:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP36:%.*]] = load i32, i32* [[TMP35]], align 4
; CHECK-NEXT:    [[TMP37:%.*]] = insertelement <4 x i32> [[TMP29]], i32 [[TMP36]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP38:%.*]] = phi <4 x i32> [ [[TMP28]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP34]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP39:%.*]] = phi <4 x i32> [ [[TMP29]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP37]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP40:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP38]], <4 x i32> <i32 1, i32 1, i32 1, i32 1>
; CHECK-NEXT:    [[TMP41:%.*]] = call i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> [[TMP40]])
; CHECK-NEXT:    [[TMP42:%.*]] = mul i32 [[TMP41]], [[VEC_PHI]]
; CHECK-NEXT:    [[TMP43:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP39]], <4 x i32> <i32 1, i32 1, i32 1, i32 1>
; CHECK-NEXT:    [[TMP44:%.*]] = call i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> [[TMP43]])
; CHECK-NEXT:    [[TMP45]] = mul i32 [[TMP44]], [[TMP42]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[TMP46:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP46]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[DOT_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[DOTLR_PH:%.*]]
; CHECK:       .lr.ph:
; CHECK-NEXT:    br i1 undef, label [[DOT_CRIT_EDGE]], label [[DOTLR_PH]], !llvm.loop [[LOOP13:![0-9]+]]
; CHECK:       ._crit_edge:
; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i32 [ undef, [[DOTLR_PH]] ], [ [[TMP45]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[SUM_0_LCSSA]]
;
entry:
  br label %.lr.ph

.lr.ph:                                           ; preds = %entry, %.lr.ph
  %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %entry ]
  %sum.02 = phi i32 [ %l7, %.lr.ph ], [ 19, %entry ]
  %l2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
  %l3 = load i32, i32* %l2, align 4
  %l4 = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
  %l5 = load i32, i32* %l4, align 4
  %l6 = mul i32 %sum.02, %l3
  %l7 = mul i32 %l6, %l5
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %._crit_edge, label %.lr.ph

._crit_edge:                                      ; preds = %.lr.ph
  %sum.0.lcssa = phi i32 [ %l7, %.lr.ph ]
  ret i32 %sum.0.lcssa
}

define i32 @reduction_and(i32* nocapture %A, i32* nocapture %B) {
; CHECK-LABEL: @reduction_and(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE6:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ -1, [[VECTOR_PH]] ], [ [[TMP45:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP3]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, i32* [[TMP5]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> poison, i32 [[TMP6]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP8:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP9:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP7]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP10]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
; CHECK:       pred.load.if1:
; CHECK-NEXT:    [[TMP11:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <4 x i32> [[TMP8]], i32 [[TMP13]], i32 1
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <4 x i32> [[TMP9]], i32 [[TMP16]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
; CHECK:       pred.load.continue2:
; CHECK-NEXT:    [[TMP18:%.*]] = phi <4 x i32> [ [[TMP8]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP14]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP19:%.*]] = phi <4 x i32> [ [[TMP9]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP17]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP20]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP21:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4
; CHECK-NEXT:    [[TMP24:%.*]] = insertelement <4 x i32> [[TMP18]], i32 [[TMP23]], i32 2
; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
; CHECK-NEXT:    [[TMP27:%.*]] = insertelement <4 x i32> [[TMP19]], i32 [[TMP26]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP28:%.*]] = phi <4 x i32> [ [[TMP18]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP24]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP29:%.*]] = phi <4 x i32> [ [[TMP19]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP27]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP30]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP31:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP33:%.*]] = load i32, i32* [[TMP32]], align 4
; CHECK-NEXT:    [[TMP34:%.*]] = insertelement <4 x i32> [[TMP28]], i32 [[TMP33]], i32 3
; CHECK-NEXT:    [[TMP35:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP36:%.*]] = load i32, i32* [[TMP35]], align 4
; CHECK-NEXT:    [[TMP37:%.*]] = insertelement <4 x i32> [[TMP29]], i32 [[TMP36]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP38:%.*]] = phi <4 x i32> [ [[TMP28]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP34]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP39:%.*]] = phi <4 x i32> [ [[TMP29]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP37]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP40:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP38]], <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
; CHECK-NEXT:    [[TMP41:%.*]] = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> [[TMP40]])
; CHECK-NEXT:    [[TMP42:%.*]] = and i32 [[TMP41]], [[VEC_PHI]]
; CHECK-NEXT:    [[TMP43:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP39]], <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
; CHECK-NEXT:    [[TMP44:%.*]] = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> [[TMP43]])
; CHECK-NEXT:    [[TMP45]] = and i32 [[TMP44]], [[TMP42]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[TMP46:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP46]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    br i1 undef, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi i32 [ undef, [[FOR_BODY]] ], [ [[TMP45]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[RESULT_0_LCSSA]]
;
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
  %result.08 = phi i32 [ %and, %for.body ], [ -1, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
  %l0 = load i32, i32* %arrayidx, align 4
  %arrayidx2 = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
  %l1 = load i32, i32* %arrayidx2, align 4
  %add = and i32 %result.08, %l0
  %and = and i32 %add, %l1
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  %result.0.lcssa = phi i32 [ %and, %for.body ]
  ret i32 %result.0.lcssa
}

define i32 @reduction_or(i32* nocapture %A, i32* nocapture %B) {
; CHECK-LABEL: @reduction_or(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE6:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP43:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP3]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, i32* [[TMP5]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> poison, i32 [[TMP6]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP8:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP9:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP7]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP10]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
; CHECK:       pred.load.if1:
; CHECK-NEXT:    [[TMP11:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <4 x i32> [[TMP8]], i32 [[TMP13]], i32 1
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <4 x i32> [[TMP9]], i32 [[TMP16]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
; CHECK:       pred.load.continue2:
; CHECK-NEXT:    [[TMP18:%.*]] = phi <4 x i32> [ [[TMP8]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP14]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP19:%.*]] = phi <4 x i32> [ [[TMP9]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP17]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP20]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP21:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4
; CHECK-NEXT:    [[TMP24:%.*]] = insertelement <4 x i32> [[TMP18]], i32 [[TMP23]], i32 2
; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
; CHECK-NEXT:    [[TMP27:%.*]] = insertelement <4 x i32> [[TMP19]], i32 [[TMP26]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP28:%.*]] = phi <4 x i32> [ [[TMP18]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP24]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP29:%.*]] = phi <4 x i32> [ [[TMP19]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP27]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP30]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP31:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP33:%.*]] = load i32, i32* [[TMP32]], align 4
; CHECK-NEXT:    [[TMP34:%.*]] = insertelement <4 x i32> [[TMP28]], i32 [[TMP33]], i32 3
; CHECK-NEXT:    [[TMP35:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP36:%.*]] = load i32, i32* [[TMP35]], align 4
; CHECK-NEXT:    [[TMP37:%.*]] = insertelement <4 x i32> [[TMP29]], i32 [[TMP36]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP38:%.*]] = phi <4 x i32> [ [[TMP28]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP34]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP39:%.*]] = phi <4 x i32> [ [[TMP29]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP37]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP40:%.*]] = add nsw <4 x i32> [[TMP39]], [[TMP38]]
; CHECK-NEXT:    [[TMP41:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP40]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP42:%.*]] = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> [[TMP41]])
; CHECK-NEXT:    [[TMP43]] = or i32 [[TMP42]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[TMP44:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP44]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    br i1 undef, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP17:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi i32 [ undef, [[FOR_BODY]] ], [ [[TMP43]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[RESULT_0_LCSSA]]
;
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
  %result.08 = phi i32 [ %or, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
  %l0 = load i32, i32* %arrayidx, align 4
  %arrayidx2 = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
  %l1 = load i32, i32* %arrayidx2, align 4
  %add = add nsw i32 %l1, %l0
  %or = or i32 %add, %result.08
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  %result.0.lcssa = phi i32 [ %or, %for.body ]
  ret i32 %result.0.lcssa
}

define i32 @reduction_xor(i32* nocapture %A, i32* nocapture %B) {
; CHECK-LABEL: @reduction_xor(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE6:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP43:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP3]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, i32* [[TMP5]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> poison, i32 [[TMP6]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP8:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP9:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP7]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP10]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
; CHECK:       pred.load.if1:
; CHECK-NEXT:    [[TMP11:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = load i32, i32* [[TMP12]], align 4
; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <4 x i32> [[TMP8]], i32 [[TMP13]], i32 1
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4
; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <4 x i32> [[TMP9]], i32 [[TMP16]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
; CHECK:       pred.load.continue2:
; CHECK-NEXT:    [[TMP18:%.*]] = phi <4 x i32> [ [[TMP8]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP14]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP19:%.*]] = phi <4 x i32> [ [[TMP9]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP17]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP20]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP21:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4
; CHECK-NEXT:    [[TMP24:%.*]] = insertelement <4 x i32> [[TMP18]], i32 [[TMP23]], i32 2
; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP26:%.*]] = load i32, i32* [[TMP25]], align 4
; CHECK-NEXT:    [[TMP27:%.*]] = insertelement <4 x i32> [[TMP19]], i32 [[TMP26]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP28:%.*]] = phi <4 x i32> [ [[TMP18]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP24]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP29:%.*]] = phi <4 x i32> [ [[TMP19]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP27]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP30]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP31:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP33:%.*]] = load i32, i32* [[TMP32]], align 4
; CHECK-NEXT:    [[TMP34:%.*]] = insertelement <4 x i32> [[TMP28]], i32 [[TMP33]], i32 3
; CHECK-NEXT:    [[TMP35:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP36:%.*]] = load i32, i32* [[TMP35]], align 4
; CHECK-NEXT:    [[TMP37:%.*]] = insertelement <4 x i32> [[TMP29]], i32 [[TMP36]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP38:%.*]] = phi <4 x i32> [ [[TMP28]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP34]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP39:%.*]] = phi <4 x i32> [ [[TMP29]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP37]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP40:%.*]] = add nsw <4 x i32> [[TMP39]], [[TMP38]]
; CHECK-NEXT:    [[TMP41:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP40]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP42:%.*]] = call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> [[TMP41]])
; CHECK-NEXT:    [[TMP43]] = xor i32 [[TMP42]], [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[TMP44:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP44]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP18:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    br i1 undef, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP19:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi i32 [ undef, [[FOR_BODY]] ], [ [[TMP43]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[RESULT_0_LCSSA]]
;
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
  %result.08 = phi i32 [ %xor, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
  %l0 = load i32, i32* %arrayidx, align 4
  %arrayidx2 = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
  %l1 = load i32, i32* %arrayidx2, align 4
  %add = add nsw i32 %l1, %l0
  %xor = xor i32 %add, %result.08
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  %result.0.lcssa = phi i32 [ %xor, %for.body ]
  ret i32 %result.0.lcssa
}

define float @reduction_fadd(float* nocapture %A, float* nocapture %B) {
; CHECK-LABEL: @reduction_fadd(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE6:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi float [ 0.000000e+00, [[VECTOR_PH]] ], [ [[TMP43:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x float> poison, float [[TMP3]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP6:%.*]] = load float, float* [[TMP5]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x float> poison, float [[TMP6]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP8:%.*]] = phi <4 x float> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP9:%.*]] = phi <4 x float> [ poison, [[VECTOR_BODY]] ], [ [[TMP7]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP10]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
; CHECK:       pred.load.if1:
; CHECK-NEXT:    [[TMP11:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = load float, float* [[TMP12]], align 4
; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <4 x float> [[TMP8]], float [[TMP13]], i32 1
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP16:%.*]] = load float, float* [[TMP15]], align 4
; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <4 x float> [[TMP9]], float [[TMP16]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
; CHECK:       pred.load.continue2:
; CHECK-NEXT:    [[TMP18:%.*]] = phi <4 x float> [ [[TMP8]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP14]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP19:%.*]] = phi <4 x float> [ [[TMP9]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP17]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP20]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP21:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP23:%.*]] = load float, float* [[TMP22]], align 4
; CHECK-NEXT:    [[TMP24:%.*]] = insertelement <4 x float> [[TMP18]], float [[TMP23]], i32 2
; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP26:%.*]] = load float, float* [[TMP25]], align 4
; CHECK-NEXT:    [[TMP27:%.*]] = insertelement <4 x float> [[TMP19]], float [[TMP26]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP28:%.*]] = phi <4 x float> [ [[TMP18]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP24]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP29:%.*]] = phi <4 x float> [ [[TMP19]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP27]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP30]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP31:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP33:%.*]] = load float, float* [[TMP32]], align 4
; CHECK-NEXT:    [[TMP34:%.*]] = insertelement <4 x float> [[TMP28]], float [[TMP33]], i32 3
; CHECK-NEXT:    [[TMP35:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP36:%.*]] = load float, float* [[TMP35]], align 4
; CHECK-NEXT:    [[TMP37:%.*]] = insertelement <4 x float> [[TMP29]], float [[TMP36]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP38:%.*]] = phi <4 x float> [ [[TMP28]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP34]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP39:%.*]] = phi <4 x float> [ [[TMP29]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP37]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP40:%.*]] = select fast <4 x i1> [[TMP0]], <4 x float> [[TMP38]], <4 x float> zeroinitializer
; CHECK-NEXT:    [[TMP41:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float [[VEC_PHI]], <4 x float> [[TMP40]])
; CHECK-NEXT:    [[TMP42:%.*]] = select fast <4 x i1> [[TMP0]], <4 x float> [[TMP39]], <4 x float> zeroinitializer
; CHECK-NEXT:    [[TMP43]] = call fast float @llvm.vector.reduce.fadd.v4f32(float [[TMP41]], <4 x float> [[TMP42]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[TMP44:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP44]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    br i1 undef, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP21:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi float [ undef, [[FOR_BODY]] ], [ [[TMP43]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret float [[RESULT_0_LCSSA]]
;
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
  %result.08 = phi float [ %fadd, %for.body ], [ 0.0, %entry ]
  %arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
  %l0 = load float, float* %arrayidx, align 4
  %arrayidx2 = getelementptr inbounds float, float* %B, i64 %indvars.iv
  %l1 = load float, float* %arrayidx2, align 4
  %add = fadd fast float %result.08, %l0
  %fadd = fadd fast float %add, %l1
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  %result.0.lcssa = phi float [ %fadd, %for.body ]
  ret float %result.0.lcssa
}

define float @reduction_fmul(float* nocapture %A, float* nocapture %B) {
; CHECK-LABEL: @reduction_fmul(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE6:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi float [ 0.000000e+00, [[VECTOR_PH]] ], [ [[TMP45:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x float> poison, float [[TMP3]], i32 0
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP6:%.*]] = load float, float* [[TMP5]], align 4
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x float> poison, float [[TMP6]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP8:%.*]] = phi <4 x float> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP9:%.*]] = phi <4 x float> [ poison, [[VECTOR_BODY]] ], [ [[TMP7]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP10]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
; CHECK:       pred.load.if1:
; CHECK-NEXT:    [[TMP11:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = load float, float* [[TMP12]], align 4
; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <4 x float> [[TMP8]], float [[TMP13]], i32 1
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP11]]
; CHECK-NEXT:    [[TMP16:%.*]] = load float, float* [[TMP15]], align 4
; CHECK-NEXT:    [[TMP17:%.*]] = insertelement <4 x float> [[TMP9]], float [[TMP16]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
; CHECK:       pred.load.continue2:
; CHECK-NEXT:    [[TMP18:%.*]] = phi <4 x float> [ [[TMP8]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP14]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP19:%.*]] = phi <4 x float> [ [[TMP9]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP17]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP20]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP21:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP23:%.*]] = load float, float* [[TMP22]], align 4
; CHECK-NEXT:    [[TMP24:%.*]] = insertelement <4 x float> [[TMP18]], float [[TMP23]], i32 2
; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP21]]
; CHECK-NEXT:    [[TMP26:%.*]] = load float, float* [[TMP25]], align 4
; CHECK-NEXT:    [[TMP27:%.*]] = insertelement <4 x float> [[TMP19]], float [[TMP26]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP28:%.*]] = phi <4 x float> [ [[TMP18]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP24]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP29:%.*]] = phi <4 x float> [ [[TMP19]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP27]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP30]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP31:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP33:%.*]] = load float, float* [[TMP32]], align 4
; CHECK-NEXT:    [[TMP34:%.*]] = insertelement <4 x float> [[TMP28]], float [[TMP33]], i32 3
; CHECK-NEXT:    [[TMP35:%.*]] = getelementptr inbounds float, float* [[B]], i64 [[TMP31]]
; CHECK-NEXT:    [[TMP36:%.*]] = load float, float* [[TMP35]], align 4
; CHECK-NEXT:    [[TMP37:%.*]] = insertelement <4 x float> [[TMP29]], float [[TMP36]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP38:%.*]] = phi <4 x float> [ [[TMP28]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP34]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP39:%.*]] = phi <4 x float> [ [[TMP29]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP37]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP40:%.*]] = select fast <4 x i1> [[TMP0]], <4 x float> [[TMP38]], <4 x float> <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT:    [[TMP41:%.*]] = call fast float @llvm.vector.reduce.fmul.v4f32(float 1.000000e+00, <4 x float> [[TMP40]])
; CHECK-NEXT:    [[TMP42:%.*]] = fmul fast float [[TMP41]], [[VEC_PHI]]
; CHECK-NEXT:    [[TMP43:%.*]] = select fast <4 x i1> [[TMP0]], <4 x float> [[TMP39]], <4 x float> <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT:    [[TMP44:%.*]] = call fast float @llvm.vector.reduce.fmul.v4f32(float 1.000000e+00, <4 x float> [[TMP43]])
; CHECK-NEXT:    [[TMP45]] = fmul fast float [[TMP44]], [[TMP42]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[TMP46:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP46]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP22:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    br i1 undef, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP23:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi float [ undef, [[FOR_BODY]] ], [ [[TMP45]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret float [[RESULT_0_LCSSA]]
;
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
  %result.08 = phi float [ %fmul, %for.body ], [ 0.0, %entry ]
  %arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
  %l0 = load float, float* %arrayidx, align 4
  %arrayidx2 = getelementptr inbounds float, float* %B, i64 %indvars.iv
  %l1 = load float, float* %arrayidx2, align 4
  %add = fmul fast float %result.08, %l0
  %fmul = fmul fast float %add, %l1
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  %result.0.lcssa = phi float [ %fmul, %for.body ]
  ret float %result.0.lcssa
}

define i32 @reduction_min(i32* nocapture %A, i32* nocapture %B) {
; CHECK-LABEL: @reduction_min(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE6:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 1000, [[VECTOR_PH]] ], [ [[RDX_MINMAX_SELECT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP3]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP5:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP6]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
; CHECK:       pred.load.if1:
; CHECK-NEXT:    [[TMP7:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP7]]
; CHECK-NEXT:    [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <4 x i32> [[TMP5]], i32 [[TMP9]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
; CHECK:       pred.load.continue2:
; CHECK-NEXT:    [[TMP11:%.*]] = phi <4 x i32> [ [[TMP5]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP10]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP12]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP13:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP13]]
; CHECK-NEXT:    [[TMP15:%.*]] = load i32, i32* [[TMP14]], align 4
; CHECK-NEXT:    [[TMP16:%.*]] = insertelement <4 x i32> [[TMP11]], i32 [[TMP15]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP17:%.*]] = phi <4 x i32> [ [[TMP11]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP16]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP18]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP19:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP20:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP19]]
; CHECK-NEXT:    [[TMP21:%.*]] = load i32, i32* [[TMP20]], align 4
; CHECK-NEXT:    [[TMP22:%.*]] = insertelement <4 x i32> [[TMP17]], i32 [[TMP21]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP23:%.*]] = phi <4 x i32> [ [[TMP17]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP22]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP24:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP23]], <4 x i32> <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
; CHECK-NEXT:    [[TMP25:%.*]] = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> [[TMP24]])
; CHECK-NEXT:    [[RDX_MINMAX_CMP:%.*]] = icmp slt i32 [[TMP25]], [[VEC_PHI]]
; CHECK-NEXT:    [[RDX_MINMAX_SELECT]] = select i1 [[RDX_MINMAX_CMP]], i32 [[TMP25]], i32 [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[TMP26:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP26]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP24:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    br i1 undef, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP25:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi i32 [ undef, [[FOR_BODY]] ], [ [[RDX_MINMAX_SELECT]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[RESULT_0_LCSSA]]
;
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
  %result.08 = phi i32 [ %v0, %for.body ], [ 1000, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
  %l0 = load i32, i32* %arrayidx, align 4
  %c0 = icmp slt i32 %result.08, %l0
  %v0 = select i1 %c0, i32 %result.08, i32 %l0
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  %result.0.lcssa = phi i32 [ %v0, %for.body ]
  ret i32 %result.0.lcssa
}

define i32 @reduction_max(i32* nocapture %A, i32* nocapture %B) {
; CHECK-LABEL: @reduction_max(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_LOAD_CONTINUE6:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 1000, [[VECTOR_PH]] ], [ [[RDX_MINMAX_SELECT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i64> [[VEC_IND]], <i64 257, i64 257, i64 257, i64 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[TMP3]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP5:%.*]] = phi <4 x i32> [ poison, [[VECTOR_BODY]] ], [ [[TMP4]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP6]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
; CHECK:       pred.load.if1:
; CHECK-NEXT:    [[TMP7:%.*]] = or i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP7]]
; CHECK-NEXT:    [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <4 x i32> [[TMP5]], i32 [[TMP9]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
; CHECK:       pred.load.continue2:
; CHECK-NEXT:    [[TMP11:%.*]] = phi <4 x i32> [ [[TMP5]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP10]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP12]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP13:%.*]] = or i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP13]]
; CHECK-NEXT:    [[TMP15:%.*]] = load i32, i32* [[TMP14]], align 4
; CHECK-NEXT:    [[TMP16:%.*]] = insertelement <4 x i32> [[TMP11]], i32 [[TMP15]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP17:%.*]] = phi <4 x i32> [ [[TMP11]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP16]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP18]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP19:%.*]] = or i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP20:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP19]]
; CHECK-NEXT:    [[TMP21:%.*]] = load i32, i32* [[TMP20]], align 4
; CHECK-NEXT:    [[TMP22:%.*]] = insertelement <4 x i32> [[TMP17]], i32 [[TMP21]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP23:%.*]] = phi <4 x i32> [ [[TMP17]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP22]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP24:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP23]], <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP25:%.*]] = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> [[TMP24]])
; CHECK-NEXT:    [[RDX_MINMAX_CMP:%.*]] = icmp ugt i32 [[TMP25]], [[VEC_PHI]]
; CHECK-NEXT:    [[RDX_MINMAX_SELECT]] = select i1 [[RDX_MINMAX_CMP]], i32 [[TMP25]], i32 [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; CHECK-NEXT:    [[TMP26:%.*]] = icmp eq i64 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP26]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP26:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    br i1 undef, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP27:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi i32 [ undef, [[FOR_BODY]] ], [ [[RDX_MINMAX_SELECT]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i32 [[RESULT_0_LCSSA]]
;
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
  %result.08 = phi i32 [ %v0, %for.body ], [ 1000, %entry ]
  %arrayidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
  %l0 = load i32, i32* %arrayidx, align 4
  %c0 = icmp ugt i32 %result.08, %l0
  %v0 = select i1 %c0, i32 %result.08, i32 %l0
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp eq i32 %lftr.wideiv, 257
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  %result.0.lcssa = phi i32 [ %v0, %for.body ]
  ret i32 %result.0.lcssa
}

; Conditional reductions with multi-input phis.
define float @reduction_conditional(float* %A, float* %B, float* %C, float %S) {
; CHECK-LABEL: @reduction_conditional(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x float> <float poison, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00>, float [[S:%.*]], i32 0
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x float> [ [[TMP0]], [[VECTOR_PH]] ], [ [[PREDPHI3:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds float, float* [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP2:%.*]] = bitcast float* [[TMP1]] to <4 x float>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x float>, <4 x float>* [[TMP2]], align 4
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds float, float* [[B:%.*]], i64 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast float* [[TMP3]] to <4 x float>*
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x float>, <4 x float>* [[TMP4]], align 4
; CHECK-NEXT:    [[TMP5:%.*]] = fcmp ogt <4 x float> [[WIDE_LOAD]], [[WIDE_LOAD1]]
; CHECK-NEXT:    [[TMP6:%.*]] = fcmp ule <4 x float> [[WIDE_LOAD1]], <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT:    [[TMP7:%.*]] = fcmp ogt <4 x float> [[WIDE_LOAD]], <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00>
; CHECK-NEXT:    [[TMP8:%.*]] = and <4 x i1> [[TMP5]], [[TMP6]]
; CHECK-NEXT:    [[TMP9:%.*]] = and <4 x i1> [[TMP8]], [[TMP7]]
; CHECK-NEXT:    [[TMP10:%.*]] = xor <4 x i1> [[TMP7]], <i1 true, i1 true, i1 true, i1 true>
; CHECK-NEXT:    [[TMP11:%.*]] = and <4 x i1> [[TMP8]], [[TMP10]]
; CHECK-NEXT:    [[TMP12:%.*]] = xor <4 x i1> [[TMP5]], <i1 true, i1 true, i1 true, i1 true>
; CHECK-NEXT:    [[PREDPHI_V:%.*]] = select <4 x i1> [[TMP9]], <4 x float> [[WIDE_LOAD1]], <4 x float> [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP13:%.*]] = select <4 x i1> [[TMP12]], <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i1> [[TMP11]]
; CHECK-NEXT:    [[PREDPHI2:%.*]] = select <4 x i1> [[TMP13]], <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, <4 x float> [[PREDPHI_V]]
; CHECK-NEXT:    [[PREDPHI3]] = fadd fast <4 x float> [[VEC_PHI]], [[PREDPHI2]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], 128
; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP28:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP15:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float -0.000000e+00, <4 x float> [[PREDPHI3]])
; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    br i1 undef, label [[IF_THEN:%.*]], label [[FOR_INC:%.*]]
; CHECK:       if.then:
; CHECK-NEXT:    br i1 undef, label [[IF_THEN8:%.*]], label [[IF_ELSE:%.*]]
; CHECK:       if.then8:
; CHECK-NEXT:    br label [[FOR_INC]]
; CHECK:       if.else:
; CHECK-NEXT:    br i1 undef, label [[IF_THEN16:%.*]], label [[FOR_INC]]
; CHECK:       if.then16:
; CHECK-NEXT:    br label [[FOR_INC]]
; CHECK:       for.inc:
; CHECK-NEXT:    br i1 undef, label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP29:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[SUM_1_LCSSA:%.*]] = phi float [ undef, [[FOR_INC]] ], [ [[TMP15]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret float [[SUM_1_LCSSA]]
;
entry:
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.inc ]
  %sum.033 = phi float [ %S, %entry ], [ %sum.1, %for.inc ]
  %arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
  %l0 = load float, float* %arrayidx, align 4
  %arrayidx2 = getelementptr inbounds float, float* %B, i64 %indvars.iv
  %l1 = load float, float* %arrayidx2, align 4
  %cmp3 = fcmp ogt float %l0, %l1
  br i1 %cmp3, label %if.then, label %for.inc

if.then:
  %cmp6 = fcmp ogt float %l1, 1.000000e+00
  br i1 %cmp6, label %if.then8, label %if.else

if.then8:
  %add = fadd fast float %sum.033, %l0
  br label %for.inc

if.else:
  %cmp14 = fcmp ogt float %l0, 2.000000e+00
  br i1 %cmp14, label %if.then16, label %for.inc

if.then16:
  %add19 = fadd fast float %sum.033, %l1
  br label %for.inc

for.inc:
  %sum.1 = phi float [ %add, %if.then8 ], [ %add19, %if.then16 ], [ %sum.033, %if.else ], [ %sum.033, %for.body ]
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp ne i32 %lftr.wideiv, 128
  br i1 %exitcond, label %for.body, label %for.end

for.end:
  %sum.1.lcssa = phi float [ %sum.1, %for.inc ]
  ret float %sum.1.lcssa
}

define i8 @reduction_add_trunc(i8* noalias nocapture %A) {
; CHECK-LABEL: @reduction_add_trunc(
; 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:%.*]], [[PRED_LOAD_CONTINUE6:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ <i32 255, i32 0, i32 0, i32 0>, [[VECTOR_PH]] ], [ [[TMP30:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i32> [[VEC_IND]], <i32 257, i32 257, i32 257, i32 257>
; CHECK-NEXT:    [[TMP1:%.*]] = and <4 x i32> [[VEC_PHI]], <i32 255, i32 255, i32 255, i32 255>
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP2]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP3:%.*]] = sext i32 [[INDEX]] to i64
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, i8* [[A:%.*]], i64 [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = load i8, i8* [[TMP4]], align 4
; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <4 x i8> poison, i8 [[TMP5]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP7:%.*]] = phi <4 x i8> [ poison, [[VECTOR_BODY]] ], [ [[TMP6]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP8]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
; CHECK:       pred.load.if1:
; CHECK-NEXT:    [[TMP9:%.*]] = or i32 [[INDEX]], 1
; CHECK-NEXT:    [[TMP10:%.*]] = sext i32 [[TMP9]] to i64
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[TMP10]]
; CHECK-NEXT:    [[TMP12:%.*]] = load i8, i8* [[TMP11]], align 4
; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <4 x i8> [[TMP7]], i8 [[TMP12]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
; CHECK:       pred.load.continue2:
; CHECK-NEXT:    [[TMP14:%.*]] = phi <4 x i8> [ [[TMP7]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP13]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP15]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP16:%.*]] = or i32 [[INDEX]], 2
; CHECK-NEXT:    [[TMP17:%.*]] = sext i32 [[TMP16]] to i64
; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[TMP17]]
; CHECK-NEXT:    [[TMP19:%.*]] = load i8, i8* [[TMP18]], align 4
; CHECK-NEXT:    [[TMP20:%.*]] = insertelement <4 x i8> [[TMP14]], i8 [[TMP19]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP21:%.*]] = phi <4 x i8> [ [[TMP14]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP20]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP22:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP22]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP23:%.*]] = or i32 [[INDEX]], 3
; CHECK-NEXT:    [[TMP24:%.*]] = sext i32 [[TMP23]] to i64
; CHECK-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[TMP24]]
; CHECK-NEXT:    [[TMP26:%.*]] = load i8, i8* [[TMP25]], align 4
; CHECK-NEXT:    [[TMP27:%.*]] = insertelement <4 x i8> [[TMP21]], i8 [[TMP26]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP28:%.*]] = phi <4 x i8> [ [[TMP21]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP27]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP29:%.*]] = zext <4 x i8> [[TMP28]] to <4 x i32>
; CHECK-NEXT:    [[TMP30]] = add nuw nsw <4 x i32> [[TMP1]], [[TMP29]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], <i32 4, i32 4, i32 4, i32 4>
; CHECK-NEXT:    [[TMP31:%.*]] = icmp eq i32 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP31]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP30:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP32:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP30]], <4 x i32> [[VEC_PHI]]
; CHECK-NEXT:    [[TMP33:%.*]] = trunc <4 x i32> [[TMP32]] to <4 x i8>
; CHECK-NEXT:    [[TMP34:%.*]] = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> [[TMP33]])
; CHECK-NEXT:    br i1 true, label [[DOT_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[DOTLR_PH:%.*]]
; CHECK:       .lr.ph:
; CHECK-NEXT:    br i1 undef, label [[DOT_CRIT_EDGE]], label [[DOTLR_PH]], !llvm.loop [[LOOP31:![0-9]+]]
; CHECK:       ._crit_edge:
; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i8 [ undef, [[DOTLR_PH]] ], [ [[TMP34]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i8 [[SUM_0_LCSSA]]
;
entry:
  br label %.lr.ph

.lr.ph:                                           ; preds = %entry, %.lr.ph
  %indvars.iv = phi i32 [ %indvars.iv.next, %.lr.ph ], [ 0, %entry ]
  %sum.02p = phi i32 [ %l9, %.lr.ph ], [ 255, %entry ]
  %sum.02 = and i32 %sum.02p, 255
  %l2 = getelementptr inbounds i8, i8* %A, i32 %indvars.iv
  %l3 = load i8, i8* %l2, align 4
  %l3e = zext i8 %l3 to i32
  %l9 = add i32 %sum.02, %l3e
  %indvars.iv.next = add i32 %indvars.iv, 1
  %exitcond = icmp eq i32 %indvars.iv.next, 257
  br i1 %exitcond, label %._crit_edge, label %.lr.ph

._crit_edge:                                      ; preds = %.lr.ph
  %sum.0.lcssa = phi i32 [ %l9, %.lr.ph ]
  %ret = trunc i32 %sum.0.lcssa to i8
  ret i8 %ret
}


define i8 @reduction_and_trunc(i8* noalias nocapture %A) {
; CHECK-LABEL: @reduction_and_trunc(
; 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:%.*]], [[PRED_LOAD_CONTINUE6:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ <i32 255, i32 -1, i32 -1, i32 -1>, [[VECTOR_PH]] ], [ [[TMP29:%.*]], [[PRED_LOAD_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ult <4 x i32> [[VEC_IND]], <i32 257, i32 257, i32 257, i32 257>
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
; CHECK-NEXT:    br i1 [[TMP1]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
; CHECK:       pred.load.if:
; CHECK-NEXT:    [[TMP2:%.*]] = sext i32 [[INDEX]] to i64
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8, i8* [[A:%.*]], i64 [[TMP2]]
; CHECK-NEXT:    [[TMP4:%.*]] = load i8, i8* [[TMP3]], align 4
; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <4 x i8> poison, i8 [[TMP4]], i32 0
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
; CHECK:       pred.load.continue:
; CHECK-NEXT:    [[TMP6:%.*]] = phi <4 x i8> [ poison, [[VECTOR_BODY]] ], [ [[TMP5]], [[PRED_LOAD_IF]] ]
; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
; CHECK-NEXT:    br i1 [[TMP7]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
; CHECK:       pred.load.if1:
; CHECK-NEXT:    [[TMP8:%.*]] = or i32 [[INDEX]], 1
; CHECK-NEXT:    [[TMP9:%.*]] = sext i32 [[TMP8]] to i64
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[TMP9]]
; CHECK-NEXT:    [[TMP11:%.*]] = load i8, i8* [[TMP10]], align 4
; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <4 x i8> [[TMP6]], i8 [[TMP11]], i32 1
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
; CHECK:       pred.load.continue2:
; CHECK-NEXT:    [[TMP13:%.*]] = phi <4 x i8> [ [[TMP6]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP12]], [[PRED_LOAD_IF1]] ]
; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
; CHECK-NEXT:    br i1 [[TMP14]], label [[PRED_LOAD_IF3:%.*]], label [[PRED_LOAD_CONTINUE4:%.*]]
; CHECK:       pred.load.if3:
; CHECK-NEXT:    [[TMP15:%.*]] = or i32 [[INDEX]], 2
; CHECK-NEXT:    [[TMP16:%.*]] = sext i32 [[TMP15]] to i64
; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[TMP16]]
; CHECK-NEXT:    [[TMP18:%.*]] = load i8, i8* [[TMP17]], align 4
; CHECK-NEXT:    [[TMP19:%.*]] = insertelement <4 x i8> [[TMP13]], i8 [[TMP18]], i32 2
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE4]]
; CHECK:       pred.load.continue4:
; CHECK-NEXT:    [[TMP20:%.*]] = phi <4 x i8> [ [[TMP13]], [[PRED_LOAD_CONTINUE2]] ], [ [[TMP19]], [[PRED_LOAD_IF3]] ]
; CHECK-NEXT:    [[TMP21:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
; CHECK-NEXT:    br i1 [[TMP21]], label [[PRED_LOAD_IF5:%.*]], label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.if5:
; CHECK-NEXT:    [[TMP22:%.*]] = or i32 [[INDEX]], 3
; CHECK-NEXT:    [[TMP23:%.*]] = sext i32 [[TMP22]] to i64
; CHECK-NEXT:    [[TMP24:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[TMP23]]
; CHECK-NEXT:    [[TMP25:%.*]] = load i8, i8* [[TMP24]], align 4
; CHECK-NEXT:    [[TMP26:%.*]] = insertelement <4 x i8> [[TMP20]], i8 [[TMP25]], i32 3
; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE6]]
; CHECK:       pred.load.continue6:
; CHECK-NEXT:    [[TMP27:%.*]] = phi <4 x i8> [ [[TMP20]], [[PRED_LOAD_CONTINUE4]] ], [ [[TMP26]], [[PRED_LOAD_IF5]] ]
; CHECK-NEXT:    [[TMP28:%.*]] = zext <4 x i8> [[TMP27]] to <4 x i32>
; CHECK-NEXT:    [[TMP29]] = and <4 x i32> [[VEC_PHI]], [[TMP28]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], <i32 4, i32 4, i32 4, i32 4>
; CHECK-NEXT:    [[TMP30:%.*]] = icmp eq i32 [[INDEX_NEXT]], 260
; CHECK-NEXT:    br i1 [[TMP30]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP32:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP31:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP29]], <4 x i32> [[VEC_PHI]]
; CHECK-NEXT:    [[TMP32:%.*]] = trunc <4 x i32> [[TMP31]] to <4 x i8>
; CHECK-NEXT:    [[TMP33:%.*]] = call i8 @llvm.vector.reduce.and.v4i8(<4 x i8> [[TMP32]])
; CHECK-NEXT:    br i1 true, label [[DOT_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[DOTLR_PH:%.*]]
; CHECK:       .lr.ph:
; CHECK-NEXT:    br i1 undef, label [[DOT_CRIT_EDGE]], label [[DOTLR_PH]], !llvm.loop [[LOOP33:![0-9]+]]
; CHECK:       ._crit_edge:
; CHECK-NEXT:    [[SUM_0_LCSSA:%.*]] = phi i8 [ undef, [[DOTLR_PH]] ], [ [[TMP33]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i8 [[SUM_0_LCSSA]]
;
entry:
  br label %.lr.ph

.lr.ph:                                           ; preds = %entry, %.lr.ph
  %indvars.iv = phi i32 [ %indvars.iv.next, %.lr.ph ], [ 0, %entry ]
  %sum.02p = phi i32 [ %l9, %.lr.ph ], [ 255, %entry ]
  %sum.02 = and i32 %sum.02p, 255
  %l2 = getelementptr inbounds i8, i8* %A, i32 %indvars.iv
  %l3 = load i8, i8* %l2, align 4
  %l3e = zext i8 %l3 to i32
  %l9 = and i32 %sum.02, %l3e
  %indvars.iv.next = add i32 %indvars.iv, 1
  %exitcond = icmp eq i32 %indvars.iv.next, 257
  br i1 %exitcond, label %._crit_edge, label %.lr.ph

._crit_edge:                                      ; preds = %.lr.ph
  %sum.0.lcssa = phi i32 [ %l9, %.lr.ph ]
  %ret = trunc i32 %sum.0.lcssa to i8
  ret i8 %ret
}