Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[VPlan] Delete the redundant overflow check for DataAndControlFlowWithoutRuntimeCheck #79825

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[VPlan] Delete the redundant overflow check for DataAndControlFlowWithoutRuntimeCheck #79825

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 12 additions & 21 deletions llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1107,21 +1107,6 @@ static VPActiveLaneMaskPHIRecipe *addVPLaneMaskPhiAndUpdateExitBranch(
// Create the ActiveLaneMask instruction using the correct start values.
VPValue *TC = Plan.getTripCount();

VPValue *TripCount, *IncrementValue;
if (!DataAndControlFlowWithoutRuntimeCheck) {
// When the loop is guarded by a runtime overflow check for the loop
// induction variable increment by VF, we can increment the value before
// the get.active.lane mask and use the unmodified tripcount.
IncrementValue = CanonicalIVIncrement;
TripCount = TC;
} else {
// When avoiding a runtime check, the active.lane.mask inside the loop
// uses a modified trip count and the induction variable increment is
// done after the active.lane.mask intrinsic is called.
IncrementValue = CanonicalIVPHI;
TripCount = Builder.createNaryOp(VPInstruction::CalculateTripCountMinusVF,
{TC}, DL);
}
auto *EntryIncrement = Builder.createOverflowingOp(
VPInstruction::CanonicalIVIncrementForPart, {StartV}, {false, false}, DL,
"index.part.next");
Expand All @@ -1140,12 +1125,18 @@ static VPActiveLaneMaskPHIRecipe *addVPLaneMaskPhiAndUpdateExitBranch(
// original terminator.
VPRecipeBase *OriginalTerminator = EB->getTerminator();
Builder.setInsertPoint(OriginalTerminator);
auto *InLoopIncrement =
Builder.createOverflowingOp(VPInstruction::CanonicalIVIncrementForPart,
{IncrementValue}, {false, false}, DL);
auto *ALM = Builder.createNaryOp(VPInstruction::ActiveLaneMask,
{InLoopIncrement, TripCount}, DL,
"active.lane.mask.next");

auto *InLoopIncrement = CanonicalIVIncrement;
// When the loop is guarded by a runtime overflow check for the loop induction
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I might be missing something, but if DataAndControlFlowWithoutRuntimeCheck there is no runtime check to make sure iv + UFxVF doesn't overflow.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

hi @fhahn
Do you mean use -mllvm -force-tail-folding-style=data-and-control-without-rt-check to enable DataAndControlFlowWithoutRuntimeCheck ? I don't find any change with the option, see https://gcc.godbolt.org/z/M878YbK8d

// variable increment by VF, we can increment the value before the
// get.active.lane mask and use the unmodified tripcount.
if (!DataAndControlFlowWithoutRuntimeCheck)
InLoopIncrement =
Builder.createOverflowingOp(VPInstruction::CanonicalIVIncrementForPart,
{InLoopIncrement}, {false, false}, DL);
auto *ALM =
Builder.createNaryOp(VPInstruction::ActiveLaneMask, {InLoopIncrement, TC},
DL, "active.lane.mask.next");
LaneMaskPhi->addOperand(ALM);

// Replace the original terminator with BranchOnCond. We have to invert the
Expand Down
6 changes: 2 additions & 4 deletions llvm/test/Transforms/LoopVectorize/AArch64/scalable-reductions-tf.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,17 +4,15 @@
define void @invariant_store_red_exit_is_phi(ptr %dst, ptr readonly %src, i64 %n) {
; CHECK-LABEL: @invariant_store_red_exit_is_phi(
; CHECK: vector.ph:
; CHECK: %[[N_MINUS_VF:.*]] = sub i64 %n, %[[VSCALE_X_4:.*]]
; CHECK: %[[CMP:.*]] = icmp ugt i64 %n, %[[VSCALE_X_4]]
; CHECK: %[[N2:.*]] = select i1 %[[CMP]], i64 %[[N_MINUS_VF]], i64 0
; CHECK: %[[ACTIVE_LANE_MASK_ENTRY:.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 %n)
; CHECK: vector.body:
; CHECK: %[[ACTIVE_LANE_MASK:.*]] = phi <vscale x 4 x i1> [ %[[ACTIVE_LANE_MASK_ENTRY]], %vector.ph ], [ %[[ACTIVE_LANE_MASK_NEXT:.*]], %vector.body ]
; CHECK: %[[VEC_PHI:.*]] = phi <vscale x 4 x i32> [ zeroinitializer, %vector.ph ], [ %[[PREDPHI:.*]], %vector.body ]
; CHECK: %[[LOAD:.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0
; CHECK-NEXT: %[[ADD:.*]] = add <vscale x 4 x i32> %[[VEC_PHI]], %[[LOAD]]
; CHECK-NEXT: %[[SELECT:.*]] = select <vscale x 4 x i1> %[[ACTIVE_LANE_MASK]], <vscale x 4 x i32> %[[ADD]], <vscale x 4 x i32> %[[VEC_PHI]]
; CHECK: %[[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 %{{.*}}, i64 %[[N2]])
; CHECK-NEXT: %[[INDEX_NEXT:.*]] = add i64 %index, %{{.*}}
; CHECK: %[[ACTIVE_LANE_MASK_NEXT:.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 %[[INDEX_NEXT]], i64 %n)
; CHECK: middle.block:
; CHECK-NEXT: %[[SUM:.*]] = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %[[SELECT]])
; CHECK-NEXT: store i32 %[[SUM]], ptr %dst, align 4
Expand Down
1,778 changes: 840 additions & 938 deletions llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
View file
Open in desktop

Large diffs are not rendered by default.

245 changes: 118 additions & 127 deletions llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-masked-accesses.ll
View file
Open in desktop

Large diffs are not rendered by default.

57 changes: 25 additions & 32 deletions llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-forced.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,33 +9,31 @@
target triple = "aarch64-unknown-linux-gnu"

; VPLANS-LABEL: Checking a loop in 'simple_memset'
; VPLANS: VPlan 'Initial VPlan for VF={vscale x 1,vscale x 2,vscale x 4},UF>=1' {
; VPLANS-NEXT: Live-in vp<[[VFxUF:%.+]]> = VF * UF
; VPLANS-NEXT: vp<[[TC:%[0-9]+]]> = original trip-count
; VPLANS: VPlan 'Initial VPlan for VF={vscale x 1,vscale x 2,vscale x 4},UF>=1' {
; VPLANS-NEXT: Live-in vp<%0> = VF * UF
; VPLANS-NEXT: vp<%3> = original trip-count
; VPLANS-EMPTY:
; VPLANS-NEXT: ph:
; VPLANS-NEXT: EMIT vp<[[TC]]> = EXPAND SCEV (1 umax %n)
; VPLANS-NEXT: EMIT vp<%3> = EXPAND SCEV (1 umax %n)
; VPLANS-NEXT: No successors
; VPLANS-EMPTY:
; VPLANS-NEXT: vector.ph:
; VPLANS-NEXT: EMIT vp<[[NEWTC:%[0-9]+]]> = TC > VF ? TC - VF : 0 vp<[[TC]]>
; VPLANS-NEXT: EMIT vp<[[VF:%[0-9]+]]> = VF * Part + ir<0>
; VPLANS-NEXT: EMIT vp<[[LANEMASK_ENTRY:%[0-9]+]]> = active lane mask vp<[[VF]]>, vp<[[TC]]>
; VPLANS-NEXT: EMIT vp<%4> = VF * Part + ir<0>
; VPLANS-NEXT: EMIT vp<%5> = active lane mask vp<%4>, vp<%3>
; VPLANS-NEXT: Successor(s): vector loop
; VPLANS-EMPTY:
; VPLANS-NEXT: <x1> vector loop: {
; VPLANS-NEXT: vector.body:
; VPLANS-NEXT: EMIT vp<[[INDV:%[0-9]+]]> = CANONICAL-INDUCTION
; VPLANS-NEXT: ACTIVE-LANE-MASK-PHI vp<[[LANEMASK_PHI:%[0-9]+]]> = phi vp<[[LANEMASK_ENTRY]]>, vp<[[LANEMASK_LOOP:%[0-9]+]]>
; VPLANS-NEXT: vp<[[STEP:%[0-9]+]]> = SCALAR-STEPS vp<[[INDV]]>, ir<1>
; VPLANS-NEXT: CLONE ir<%gep> = getelementptr ir<%ptr>, vp<[[STEP]]>
; VPLANS-NEXT: vp<[[VEC_PTR:%[0-9]+]]> = vector-pointer ir<%gep>
; VPLANS-NEXT: WIDEN store vp<[[VEC_PTR]]>, ir<%val>, vp<[[LANEMASK_PHI]]>
; VPLANS-NEXT: EMIT vp<[[INDV_UPDATE:%[0-9]+]]> = add vp<[[INDV]]>, vp<[[VFxUF]]>
; VPLANS-NEXT: EMIT vp<[[INC:%[0-9]+]]> = VF * Part + vp<[[INDV]]>
; VPLANS-NEXT: EMIT vp<[[LANEMASK_LOOP]]> = active lane mask vp<[[INC]]>, vp<[[NEWTC]]>
; VPLANS-NEXT: EMIT vp<[[NOT:%[0-9]+]]> = not vp<[[LANEMASK_LOOP]]>
; VPLANS-NEXT: EMIT branch-on-cond vp<[[NOT]]>
; VPLANS-NEXT: EMIT vp<%6> = CANONICAL-INDUCTION ir<0>, vp<%11>
; VPLANS-NEXT: ACTIVE-LANE-MASK-PHI vp<%7> = phi vp<%5>, vp<%12>
; VPLANS-NEXT: vp<%8> = SCALAR-STEPS vp<%6>, ir<1>
; VPLANS-NEXT: CLONE ir<%gep> = getelementptr ir<%ptr>, vp<%8>
; VPLANS-NEXT: vp<%10> = vector-pointer ir<%gep>
; VPLANS-NEXT: WIDEN store vp<%10>, ir<%val>, vp<%7>
; VPLANS-NEXT: EMIT vp<%11> = add vp<%6>, vp<%0>
; VPLANS-NEXT: EMIT vp<%12> = active lane mask vp<%11>, vp<%3>
; VPLANS-NEXT: EMIT vp<%13> = not vp<%12>
; VPLANS-NEXT: EMIT branch-on-cond vp<%13>
; VPLANS-NEXT: No successors
; VPLANS-NEXT: }

Expand All @@ -53,29 +51,24 @@ define void @simple_memset(i32 %val, ptr %ptr, i64 %n) #0 {
; CHECK-NEXT: [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP4]]
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP14:%.*]] = mul i64 [[TMP13]], 4
; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 4
; CHECK-NEXT: [[TMP7:%.*]] = sub i64 [[UMAX]], [[TMP6]]
; CHECK-NEXT: [[TMP8:%.*]] = icmp ugt i64 [[UMAX]], [[TMP6]]
; CHECK-NEXT: [[TMP9:%.*]] = select i1 [[TMP8]], i64 [[TMP7]], i64 0
; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[VAL:%.*]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP10:%.*]] = add i64 [[INDEX1]], 0
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[TMP10]]
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr i32, ptr [[TMP11]], i32 0
; CHECK-NEXT: call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP14]]
; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX1]], i64 [[TMP9]])
; CHECK-NEXT: [[TMP15:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP16:%.*]] = extractelement <vscale x 4 x i1> [[TMP15]], i32 0
; CHECK-NEXT: br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK-NEXT: [[TMP7:%.*]] = add i64 [[INDEX1]], 0
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr i32, ptr [[TMP8]], i32 0
; CHECK-NEXT: call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[BROADCAST_SPLAT]], ptr [[TMP9]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP6]]
; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT2]], i64 [[UMAX]])
; CHECK-NEXT: [[TMP10:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP11:%.*]] = extractelement <vscale x 4 x i1> [[TMP10]], i32 0
; CHECK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[WHILE_END_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
Expand Down
37 changes: 17 additions & 20 deletions llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding-overflow-checks.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,19 +15,19 @@ define void @cannot_overflow_i32_induction_var(ptr noalias %dst, ptr readonly %s
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[N]] to i64
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP4:%.*]] = shl nuw nsw i64 [[TMP3]], 2
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[WIDE_TRIP_COUNT]])
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds i32, ptr [[SRC:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr [[TMP0]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
; CHECK-NEXT: [[TMP1:%.*]] = add nsw <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 42, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[DST:%.*]], i64 [[INDEX]]
; CHECK-NEXT: call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP1]], ptr [[TMP2]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP4]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[SRC:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr [[TMP2]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
; CHECK-NEXT: [[TMP3:%.*]] = add nsw <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 42, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i32, ptr [[DST:%.*]], i64 [[INDEX]]
; CHECK-NEXT: call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP3]], ptr [[TMP4]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP1]]
; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT]], i64 [[WIDE_TRIP_COUNT]])
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], i64 0
; CHECK-NEXT: br i1 [[TMP5]], label [[VECTOR_BODY]], label [[MIDDLE_BLOCK:%.*]], !llvm.loop [[LOOP0:![0-9]+]]
Expand Down Expand Up @@ -76,25 +76,22 @@ define void @can_overflow_i64_induction_var(ptr noalias %dst, ptr readonly %src,
; CHECK: for.body.preheader:
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP7:%.*]] = shl nuw nsw i64 [[TMP6]], 2
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[TMP0]], 2
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.usub.sat.i64(i64 [[N]], i64 [[TMP1]])
; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[N]])
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, ptr [[SRC:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr [[TMP3]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
; CHECK-NEXT: [[TMP4:%.*]] = add nsw <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 42, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i32, ptr [[DST:%.*]], i64 [[INDEX]]
; CHECK-NEXT: call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP4]], ptr [[TMP5]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP7]]
; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP2]])
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], i64 0
; CHECK-NEXT: br i1 [[TMP8]], label [[VECTOR_BODY]], label [[MIDDLE_BLOCK:%.*]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[SRC:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr [[TMP2]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
; CHECK-NEXT: [[TMP3:%.*]] = add nsw <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 42, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i32, ptr [[DST:%.*]], i64 [[INDEX]]
; CHECK-NEXT: call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP3]], ptr [[TMP4]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP1]]
; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT]], i64 [[N]])
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], i64 0
; CHECK-NEXT: br i1 [[TMP5]], label [[VECTOR_BODY]], label [[MIDDLE_BLOCK:%.*]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
Expand Down
Loading
Loading