; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -force-vector-width=4 -force-vector-interleave=1 -passes=loop-vectorize -S %s | FileCheck %s

target datalayout = "e-m:o-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"

define i32 @test(i64 %N, i32 %x) {
; CHECK-LABEL: @test(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[EXTRA_ITER:%.*]] = and i64 [[N:%.*]], 7
; CHECK-NEXT:    br label [[CHECK:%.*]]
; CHECK:       check:
; CHECK-NEXT:    [[EXTRA_ITER_CHECK:%.*]] = icmp eq i64 [[EXTRA_ITER]], 0
; CHECK-NEXT:    br i1 [[EXTRA_ITER_CHECK]], label [[EXIT:%.*]], label [[LOOP_PREHEADER:%.*]]
; CHECK:       loop.preheader:
; CHECK-NEXT:    br label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[EXTRA_ITER]], 3
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[EXTRA_ITER]], 1
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
; 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> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP2:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i64> poison, i64 [[INDEX]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT1]], <4 x i64> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[VEC_IV:%.*]] = add <4 x i64> [[BROADCAST_SPLAT2]], <i64 0, i64 1, i64 2, i64 3>
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ule <4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    [[TMP1:%.*]] = icmp sgt <4 x i32> [[VEC_PHI]], splat (i32 10)
; CHECK-NEXT:    [[TMP2]] = select <4 x i1> [[TMP1]], <4 x i32> [[VEC_PHI]], <4 x i32> splat (i32 10)
; CHECK-NEXT:    [[TMP3:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP2]], <4 x i32> [[VEC_PHI]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[TMP3]])
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       exit.loopexit:
; CHECK-NEXT:    br label [[EXIT]]
; CHECK:       exit:
; CHECK-NEXT:    [[RESULT:%.*]] = phi i32 [ 0, [[CHECK]] ], [ [[TMP5]], [[LOOP]] ]
; CHECK-NEXT:    ret i32 [[RESULT]]
;
entry:
  %extra.iter = and i64 %N, 7
  br label %check

check:
  %extra.iter.check = icmp eq i64 %extra.iter, 0
  br i1 %extra.iter.check, label %exit, label %loop

loop:
  %next = phi i32 [ %sel, %loop ], [ 0, %check ]
  %iv = phi i64 [ %iv.next, %loop ], [ %extra.iter, %check ]
  %sel.cond = icmp sgt i32 %next, 10
  %sel = select i1 %sel.cond, i32 %next, i32 10
  %iv.next = add nsw i64 %iv, -1
  %ec = icmp eq i64 %iv.next, 0
  br i1 %ec, label %exit, label %loop

exit:
  %result = phi i32 [ %sel, %loop], [ 0, %check ]
  ret i32 %result
}

define i32 @pr66895_tail_fold_reduction_exit_inst_gets_simplified(i32 %n) {
; CHECK-LABEL: @pr66895_tail_fold_reduction_exit_inst_gets_simplified(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 1, i32 1>, [[VECTOR_PH]] ], [ [[VEC_PHI]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i32 [[INDEX_NEXT]], 16
; CHECK-NEXT:    br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> [[VEC_PHI]])
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       exit:
; CHECK-NEXT:    ret i32 [[TMP3]]
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 12, %entry ], [ %iv.next, %loop ]
  %red = phi i32 [ 0, %entry ], [ %red.next, %loop ]
  %iv.next = add i32 %iv, -1
  %red.next = mul i32 %red, 1
  %ec = icmp eq i32 %iv, 0
  br i1 %ec, label %exit, label %loop

exit:
  %red.lcssa = phi i32 [ %red.next, %loop ]
  ret i32 %red.lcssa
}