; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -passes=loop-vectorize -force-tail-folding-style=none < %s | FileCheck %s --check-prefix=NONE
; RUN: opt -S -passes=loop-vectorize -force-tail-folding-style=data < %s | FileCheck %s --check-prefix=DATA
; RUN: opt -S -passes=loop-vectorize -force-tail-folding-style=data-without-lane-mask < %s | FileCheck %s --check-prefix=DATA_NO_LANEMASK
; RUN: opt -S -passes=loop-vectorize -force-tail-folding-style=data-and-control < %s | FileCheck %s --check-prefix=DATA_AND_CONTROL
; RUN: opt -S -passes=loop-vectorize -force-tail-folding-style=data-and-control-without-rt-check < %s | FileCheck %s --check-prefix=DATA_AND_CONTROL_NO_RT_CHECK

target triple = "aarch64-unknown-linux-gnu"

; Test the different tail folding styles.

define void @simple_memset_tailfold(i32 %val, ptr %ptr, i64 %n) "target-features" = "+sve" {
; NONE-LABEL: @simple_memset_tailfold(
; NONE-NEXT:  entry:
; NONE-NEXT:    [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
; NONE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; NONE-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 2
; NONE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[UMAX]], [[TMP1]]
; NONE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; NONE:       vector.ph:
; NONE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; NONE-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 4
; NONE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[UMAX]], [[TMP3]]
; NONE-NEXT:    [[N_VEC:%.*]] = sub i64 [[UMAX]], [[N_MOD_VF]]
; NONE-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[VAL:%.*]], i64 0
; NONE-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; NONE-NEXT:    br label [[VECTOR_BODY:%.*]]
; NONE:       vector.body:
; NONE-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[VECTOR_BODY]] ]
; NONE-NEXT:    [[TMP5:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[INDEX1]]
; NONE-NEXT:    store <vscale x 4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP5]], align 4
; NONE-NEXT:    [[INDEX_NEXT2]] = add nuw i64 [[INDEX1]], [[TMP3]]
; NONE-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT2]], [[N_VEC]]
; NONE-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; NONE:       middle.block:
; NONE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[UMAX]], [[N_VEC]]
; NONE-NEXT:    br i1 [[CMP_N]], label [[WHILE_END_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; NONE:       scalar.ph:
; NONE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; NONE-NEXT:    br label [[WHILE_BODY:%.*]]
; NONE:       while.body:
; NONE-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; NONE-NEXT:    [[GEP:%.*]] = getelementptr i32, ptr [[PTR]], i64 [[INDEX]]
; NONE-NEXT:    store i32 [[VAL]], ptr [[GEP]], align 4
; NONE-NEXT:    [[INDEX_NEXT]] = add nsw i64 [[INDEX]], 1
; NONE-NEXT:    [[CMP10:%.*]] = icmp ult i64 [[INDEX_NEXT]], [[N]]
; NONE-NEXT:    br i1 [[CMP10]], label [[WHILE_BODY]], label [[WHILE_END_LOOPEXIT]], !llvm.loop [[LOOP3:![0-9]+]]
; NONE:       while.end.loopexit:
; NONE-NEXT:    ret void
;
; DATA-LABEL: @simple_memset_tailfold(
; DATA-NEXT:  entry:
; DATA-NEXT:    [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
; DATA-NEXT:    br label [[VECTOR_PH:%.*]]
; DATA:       vector.ph:
; DATA-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; DATA-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 4
; DATA-NEXT:    [[TMP8:%.*]] = sub i64 [[TMP5]], 1
; DATA-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP8]]
; DATA-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
; DATA-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; DATA-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[VAL:%.*]], i64 0
; DATA-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; DATA-NEXT:    br label [[VECTOR_BODY:%.*]]
; DATA:       vector.body:
; DATA-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[VECTOR_BODY]] ]
; DATA-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[UMAX]])
; DATA-NEXT:    [[TMP10:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[INDEX1]]
; DATA-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP10]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; DATA-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP5]]
; DATA-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT2]], [[N_VEC]]
; DATA-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; DATA:       middle.block:
; DATA-NEXT:    br label [[WHILE_END_LOOPEXIT:%.*]]
; DATA:       scalar.ph:
; DATA-NEXT:    br label [[WHILE_BODY:%.*]]
; DATA:       while.body:
; DATA-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[WHILE_BODY]] ], [ 0, [[SCALAR_PH:%.*]] ]
; DATA-NEXT:    [[GEP:%.*]] = getelementptr i32, ptr [[PTR]], i64 [[INDEX]]
; DATA-NEXT:    store i32 [[VAL]], ptr [[GEP]], align 4
; DATA-NEXT:    [[INDEX_NEXT]] = add nsw i64 [[INDEX]], 1
; DATA-NEXT:    [[CMP10:%.*]] = icmp ult i64 [[INDEX_NEXT]], [[N]]
; DATA-NEXT:    br i1 [[CMP10]], label [[WHILE_BODY]], label [[WHILE_END_LOOPEXIT]], !llvm.loop [[LOOP3:![0-9]+]]
; DATA:       while.end.loopexit:
; DATA-NEXT:    ret void
;
; DATA_NO_LANEMASK-LABEL: @simple_memset_tailfold(
; DATA_NO_LANEMASK-NEXT:  entry:
; DATA_NO_LANEMASK-NEXT:    [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
; DATA_NO_LANEMASK-NEXT:    br label [[VECTOR_PH:%.*]]
; DATA_NO_LANEMASK:       vector.ph:
; DATA_NO_LANEMASK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; DATA_NO_LANEMASK-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 4
; DATA_NO_LANEMASK-NEXT:    [[TMP8:%.*]] = sub i64 [[TMP5]], 1
; DATA_NO_LANEMASK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP8]]
; DATA_NO_LANEMASK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
; DATA_NO_LANEMASK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; DATA_NO_LANEMASK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[UMAX]], 1
; DATA_NO_LANEMASK-NEXT:    [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i64 0
; DATA_NO_LANEMASK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT5]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; DATA_NO_LANEMASK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[VAL:%.*]], i64 0
; DATA_NO_LANEMASK-NEXT:    [[BROADCAST_SPLAT5:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT1]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; DATA_NO_LANEMASK-NEXT:    br label [[VECTOR_BODY:%.*]]
; DATA_NO_LANEMASK:       vector.body:
; DATA_NO_LANEMASK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT6:%.*]], [[VECTOR_BODY]] ]
; DATA_NO_LANEMASK-NEXT:    [[BROADCAST_SPLATINSERT2:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX1]], i64 0
; DATA_NO_LANEMASK-NEXT:    [[BROADCAST_SPLAT3:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT2]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; DATA_NO_LANEMASK-NEXT:    [[TMP10:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
; DATA_NO_LANEMASK-NEXT:    [[TMP11:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP10]]
; DATA_NO_LANEMASK-NEXT:    [[VEC_IV:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT3]], [[TMP11]]
; DATA_NO_LANEMASK-NEXT:    [[TMP12:%.*]] = icmp ule <vscale x 4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT]]
; DATA_NO_LANEMASK-NEXT:    [[TMP13:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[INDEX1]]
; DATA_NO_LANEMASK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[BROADCAST_SPLAT5]], ptr [[TMP13]], i32 4, <vscale x 4 x i1> [[TMP12]])
; DATA_NO_LANEMASK-NEXT:    [[INDEX_NEXT6]] = add i64 [[INDEX1]], [[TMP5]]
; DATA_NO_LANEMASK-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT6]], [[N_VEC]]
; DATA_NO_LANEMASK-NEXT:    br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; DATA_NO_LANEMASK:       middle.block:
; DATA_NO_LANEMASK-NEXT:    br label [[WHILE_END_LOOPEXIT:%.*]]
; DATA_NO_LANEMASK:       scalar.ph:
; DATA_NO_LANEMASK-NEXT:    br label [[WHILE_BODY:%.*]]
; DATA_NO_LANEMASK:       while.body:
; DATA_NO_LANEMASK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[WHILE_BODY]] ], [ 0, [[SCALAR_PH:%.*]] ]
; DATA_NO_LANEMASK-NEXT:    [[GEP:%.*]] = getelementptr i32, ptr [[PTR]], i64 [[INDEX]]
; DATA_NO_LANEMASK-NEXT:    store i32 [[VAL]], ptr [[GEP]], align 4
; DATA_NO_LANEMASK-NEXT:    [[INDEX_NEXT]] = add nsw i64 [[INDEX]], 1
; DATA_NO_LANEMASK-NEXT:    [[CMP10:%.*]] = icmp ult i64 [[INDEX_NEXT]], [[N]]
; DATA_NO_LANEMASK-NEXT:    br i1 [[CMP10]], label [[WHILE_BODY]], label [[WHILE_END_LOOPEXIT]], !llvm.loop [[LOOP3:![0-9]+]]
; DATA_NO_LANEMASK:       while.end.loopexit:
; DATA_NO_LANEMASK-NEXT:    ret void
;
; DATA_AND_CONTROL-LABEL: @simple_memset_tailfold(
; DATA_AND_CONTROL-NEXT:  entry:
; DATA_AND_CONTROL-NEXT:    [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
; DATA_AND_CONTROL-NEXT:    br label [[VECTOR_PH:%.*]]
; DATA_AND_CONTROL:       vector.ph:
; DATA_AND_CONTROL-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; DATA_AND_CONTROL-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 4
; DATA_AND_CONTROL-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
; DATA_AND_CONTROL-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[VAL:%.*]], i64 0
; DATA_AND_CONTROL-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; DATA_AND_CONTROL-NEXT:    br label [[VECTOR_BODY:%.*]]
; DATA_AND_CONTROL:       vector.body:
; DATA_AND_CONTROL-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[VECTOR_BODY]] ]
; DATA_AND_CONTROL-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
; DATA_AND_CONTROL-NEXT:    [[TMP10:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[INDEX1]]
; DATA_AND_CONTROL-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP10]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; DATA_AND_CONTROL-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP5]]
; DATA_AND_CONTROL-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT2]], i64 [[UMAX]])
; DATA_AND_CONTROL-NEXT:    [[TMP6:%.*]] = extractelement <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], i32 0
; DATA_AND_CONTROL-NEXT:    [[TMP7:%.*]] = xor i1 [[TMP6]], true
; DATA_AND_CONTROL-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; DATA_AND_CONTROL:       middle.block:
; DATA_AND_CONTROL-NEXT:    br label [[WHILE_END_LOOPEXIT:%.*]]
; DATA_AND_CONTROL:       scalar.ph:
; DATA_AND_CONTROL-NEXT:    br label [[WHILE_BODY:%.*]]
; DATA_AND_CONTROL:       while.body:
; DATA_AND_CONTROL-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[WHILE_BODY]] ], [ 0, [[SCALAR_PH:%.*]] ]
; DATA_AND_CONTROL-NEXT:    [[GEP:%.*]] = getelementptr i32, ptr [[PTR]], i64 [[INDEX]]
; DATA_AND_CONTROL-NEXT:    store i32 [[VAL]], ptr [[GEP]], align 4
; DATA_AND_CONTROL-NEXT:    [[INDEX_NEXT]] = add nsw i64 [[INDEX]], 1
; DATA_AND_CONTROL-NEXT:    [[CMP10:%.*]] = icmp ult i64 [[INDEX_NEXT]], [[N]]
; DATA_AND_CONTROL-NEXT:    br i1 [[CMP10]], label [[WHILE_BODY]], label [[WHILE_END_LOOPEXIT]], !llvm.loop [[LOOP3:![0-9]+]]
; DATA_AND_CONTROL:       while.end.loopexit:
; DATA_AND_CONTROL-NEXT:    ret void
;
; DATA_AND_CONTROL_NO_RT_CHECK-LABEL: @simple_memset_tailfold(
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:  entry:
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    br label [[VECTOR_PH:%.*]]
; DATA_AND_CONTROL_NO_RT_CHECK:       vector.ph:
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 4
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP6:%.*]] = shl nuw i64 [[TMP5]], 2
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP7:%.*]] = sub i64 [[UMAX]], [[TMP6]]
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP8:%.*]] = icmp ugt i64 [[UMAX]], [[TMP6]]
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[TMP8]], i64 [[TMP7]], i64 0
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[VAL:%.*]], i64 0
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; DATA_AND_CONTROL_NO_RT_CHECK:       vector.body:
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[VECTOR_BODY]] ]
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[INDEX1]]
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP11]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP1]]
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP15:%.*]] = extractelement <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], i32 0
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[TMP12:%.*]] = xor i1 [[TMP15]], true
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; DATA_AND_CONTROL_NO_RT_CHECK:       middle.block:
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    br label [[WHILE_END_LOOPEXIT:%.*]]
; DATA_AND_CONTROL_NO_RT_CHECK:       scalar.ph:
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    br label [[WHILE_BODY:%.*]]
; DATA_AND_CONTROL_NO_RT_CHECK:       while.body:
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[WHILE_BODY]] ], [ 0, [[SCALAR_PH:%.*]] ]
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[GEP:%.*]] = getelementptr i32, ptr [[PTR]], i64 [[INDEX]]
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    store i32 [[VAL]], ptr [[GEP]], align 4
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[INDEX_NEXT]] = add nsw i64 [[INDEX]], 1
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    [[CMP10:%.*]] = icmp ult i64 [[INDEX_NEXT]], [[N]]
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    br i1 [[CMP10]], label [[WHILE_BODY]], label [[WHILE_END_LOOPEXIT]], !llvm.loop [[LOOP3:![0-9]+]]
; DATA_AND_CONTROL_NO_RT_CHECK:       while.end.loopexit:
; DATA_AND_CONTROL_NO_RT_CHECK-NEXT:    ret void
;
entry:
  br label %while.body

while.body:                                       ; preds = %while.body, %entry
  %index = phi i64 [ %index.next, %while.body ], [ 0, %entry ]
  %gep = getelementptr i32, ptr %ptr, i64 %index
  store i32 %val, ptr %gep
  %index.next = add nsw i64 %index, 1
  %cmp10 = icmp ult i64 %index.next, %n
  br i1 %cmp10, label %while.body, label %while.end.loopexit, !llvm.loop !0

while.end.loopexit:                               ; preds = %while.body
  ret void
}

!0 = distinct !{!0, !1, !2, !3, !4}
!1 = !{!"llvm.loop.vectorize.predicate.enable", i1 true}
!2 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
!3 = !{!"llvm.loop.interleave.count", i32 1}
!4 = !{!"llvm.loop.vectorize.width", i32 4}