; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
; RUN: opt < %s -passes=loop-vectorize,dce,instcombine -force-vector-interleave=1 -force-vector-width=4 -prefer-inloop-reductions -S | FileCheck %s

define i32 @reduction_smin(ptr nocapture %A, ptr nocapture %B) {
; CHECK-LABEL: define i32 @reduction_smin
; CHECK-SAME: (ptr nocapture [[A:%.*]], ptr nocapture [[B:%.*]]) {
; 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:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 1000, [[VECTOR_PH]] ], [ [[RDX_MINMAX:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> [[WIDE_LOAD]])
; CHECK-NEXT:    [[RDX_MINMAX]] = call i32 @llvm.smin.i32(i32 [[TMP1]], i32 [[VEC_PHI]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
; CHECK-NEXT:    br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![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 poison, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi i32 [ poison, [[FOR_BODY]] ], [ [[RDX_MINMAX]], [[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, ptr %A, i64 %indvars.iv
  %l0 = load i32, ptr %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, 256
  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_smin_select_ops_flipped(ptr nocapture %A, ptr nocapture %B) {
; CHECK-LABEL: define i32 @reduction_smin_select_ops_flipped
; CHECK-SAME: (ptr nocapture [[A:%.*]], ptr nocapture [[B:%.*]]) {
; 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:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 1000, [[VECTOR_PH]] ], [ [[RDX_MINMAX:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[WIDE_LOAD]])
; CHECK-NEXT:    [[RDX_MINMAX]] = call i32 @llvm.smax.i32(i32 [[TMP1]], i32 [[VEC_PHI]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
; CHECK-NEXT:    br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![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 poison, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi i32 [ poison, [[FOR_BODY]] ], [ [[RDX_MINMAX]], [[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, ptr %A, i64 %indvars.iv
  %l0 = load i32, ptr %arrayidx, align 4
  %c0 = icmp slt i32 %result.08, %l0
  %v0 = select i1 %c0, i32 %l0, i32 %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, 256
  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_smin_intrinsic(ptr nocapture %A, ptr nocapture %B) {
; CHECK-LABEL: define i32 @reduction_smin_intrinsic
; CHECK-SAME: (ptr nocapture [[A:%.*]], ptr nocapture [[B:%.*]]) {
; 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:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ <i32 1000, i32 1000, i32 1000, i32 1000>, [[VECTOR_PH]] ], [ [[TMP1:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[TMP1]] = call <4 x i32> @llvm.smin.v4i32(<4 x i32> [[VEC_PHI]], <4 x i32> [[WIDE_LOAD]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
; CHECK-NEXT:    br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> [[TMP1]])
; 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 poison, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi i32 [ poison, [[FOR_BODY]] ], [ [[TMP3]], [[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, ptr %A, i64 %indvars.iv
  %l0 = load i32, ptr %arrayidx, align 4
  %v0 = call i32 @llvm.smin.i32(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, 256
  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
}

declare i32 @llvm.smin.i32(i32, i32)

define i32 @reduction_umax(ptr nocapture %A, ptr nocapture %B) {
; CHECK-LABEL: define i32 @reduction_umax
; CHECK-SAME: (ptr nocapture [[A:%.*]], ptr nocapture [[B:%.*]]) {
; 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:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 1000, [[VECTOR_PH]] ], [ [[RDX_MINMAX:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> [[WIDE_LOAD]])
; CHECK-NEXT:    [[RDX_MINMAX]] = call i32 @llvm.umax.i32(i32 [[TMP1]], i32 [[VEC_PHI]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
; CHECK-NEXT:    br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![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 poison, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi i32 [ poison, [[FOR_BODY]] ], [ [[RDX_MINMAX]], [[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, ptr %A, i64 %indvars.iv
  %l0 = load i32, ptr %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, 256
  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_umax_select_ops_flipped(ptr nocapture %A, ptr nocapture %B) {
; CHECK-LABEL: define i32 @reduction_umax_select_ops_flipped
; CHECK-SAME: (ptr nocapture [[A:%.*]], ptr nocapture [[B:%.*]]) {
; 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:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 1000, [[VECTOR_PH]] ], [ [[RDX_MINMAX:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> [[WIDE_LOAD]])
; CHECK-NEXT:    [[RDX_MINMAX]] = call i32 @llvm.umin.i32(i32 [[TMP1]], i32 [[VEC_PHI]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
; CHECK-NEXT:    br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![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 poison, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi i32 [ poison, [[FOR_BODY]] ], [ [[RDX_MINMAX]], [[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, ptr %A, i64 %indvars.iv
  %l0 = load i32, ptr %arrayidx, align 4
  %c0 = icmp ugt i32 %result.08, %l0
  %v0 = select i1 %c0, i32 %l0, i32 %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, 256
  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_umax_intrinsic(ptr nocapture %A, ptr nocapture %B) {
; CHECK-LABEL: define i32 @reduction_umax_intrinsic
; CHECK-SAME: (ptr nocapture [[A:%.*]], ptr nocapture [[B:%.*]]) {
; 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:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ <i32 1000, i32 1000, i32 1000, i32 1000>, [[VECTOR_PH]] ], [ [[TMP1:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDEX]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[TMP1]] = call <4 x i32> @llvm.umax.v4i32(<4 x i32> [[VEC_PHI]], <4 x i32> [[WIDE_LOAD]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], 256
; CHECK-NEXT:    br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> [[TMP1]])
; 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 poison, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    [[RESULT_0_LCSSA:%.*]] = phi i32 [ poison, [[FOR_BODY]] ], [ [[TMP3]], [[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, ptr %A, i64 %indvars.iv
  %l0 = load i32, ptr %arrayidx, align 4
  %v0 = call i32 @llvm.umax.i32(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, 256
  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
}

declare i32 @llvm.umax.i32(i32, i32)