; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
; RUN: opt -S -scalable-vectorization=on -force-target-supports-scalable-vectors=true -passes=loop-vectorize -force-vector-width=2 -force-vector-interleave=1 < %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"

; Make sure we can vectorize loops which contain lifetime markers.

define void @test(ptr %d) {
; CHECK-LABEL: define void @test
; CHECK-SAME: (ptr [[D:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[ARR:%.*]] = alloca [1024 x i32], align 16
; CHECK-NEXT:    call void @llvm.lifetime.start.p0(ptr [[ARR]])
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 1
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 128, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 128, [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 128, [[N_MOD_VF]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    call void @llvm.lifetime.end.p0(ptr [[ARR]])
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, ptr [[D]], i64 [[INDEX]]
; CHECK-NEXT:    store <vscale x 2 x i32> splat (i32 100), ptr [[TMP4]], align 8
; CHECK-NEXT:    call void @llvm.lifetime.start.p0(ptr [[ARR]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP5]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 128, [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    call void @llvm.lifetime.end.p0(ptr [[ARR]])
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[D]], i64 [[INDVARS_IV]]
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    store i32 100, ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    call void @llvm.lifetime.start.p0(ptr [[ARR]])
; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1
; CHECK-NEXT:    [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[LFTR_WIDEIV]], 128
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    call void @llvm.lifetime.end.p0(ptr [[ARR]])
; CHECK-NEXT:    ret void
;

entry:
  %arr = alloca [1024 x i32], align 16
  call void @llvm.lifetime.start.p0(ptr %arr) #1
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  call void @llvm.lifetime.end.p0(ptr %arr) #1
  %arrayidx = getelementptr inbounds i32, ptr %d, i64 %indvars.iv
  %0 = load i32, ptr %arrayidx, align 8
  store i32 100, ptr %arrayidx, align 8
  call void @llvm.lifetime.start.p0(ptr %arr) #1
  %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, !llvm.loop !0

for.end:
  call void @llvm.lifetime.end.p0(ptr %arr) #1
  ret void
}

define void @testloopvariant(ptr %d) {
; CHECK-LABEL: define void @testloopvariant
; CHECK-SAME: (ptr [[D:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[ARR:%.*]] = alloca [1024 x i32], align 16
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 1
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 128, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 2
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 128, [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 128, [[N_MOD_VF]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    call void @llvm.lifetime.end.p0(ptr [[ARR]])
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, ptr [[D]], i64 [[INDEX]]
; CHECK-NEXT:    store <vscale x 2 x i32> splat (i32 100), ptr [[TMP4]], align 8
; CHECK-NEXT:    call void @llvm.lifetime.start.p0(ptr [[ARR]])
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP5]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 128, [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       for.body:
; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr [1024 x i32], ptr [[ARR]], i32 0, i64 [[INDVARS_IV]]
; CHECK-NEXT:    call void @llvm.lifetime.end.p0(ptr [[ARR]])
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[D]], i64 [[INDVARS_IV]]
; CHECK-NEXT:    [[TMP7:%.*]] = load i32, ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    store i32 100, ptr [[ARRAYIDX]], align 8
; CHECK-NEXT:    call void @llvm.lifetime.start.p0(ptr [[ARR]])
; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1
; CHECK-NEXT:    [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[LFTR_WIDEIV]], 128
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       for.end:
; CHECK-NEXT:    ret void
;
entry:
  %arr = alloca [1024 x i32], align 16
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %0 = getelementptr [1024 x i32], ptr %arr, i32 0, i64 %indvars.iv
  call void @llvm.lifetime.end.p0(ptr %arr) #1
  %arrayidx = getelementptr inbounds i32, ptr %d, i64 %indvars.iv
  %1 = load i32, ptr %arrayidx, align 8
  store i32 100, ptr %arrayidx, align 8
  call void @llvm.lifetime.start.p0(ptr %arr) #1
  %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, !llvm.loop !0

for.end:
  ret void
}

declare void @llvm.lifetime.start.p0(ptr nocapture) #1

declare void @llvm.lifetime.end.p0(ptr nocapture) #1

!0 = distinct !{!0, !1}
!1 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}