Skip to content

[VPlan] Use VPInstructionWithType for uniform casts. #140623

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

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[VPlan] Use VPInstructionWithType for uniform casts. #140623

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a65c9c3
[VPlan] Use VPInstructionWithType for uniform casts.
fhahn May 19, 2025
83f27e9
!fixup pass IsSingleScalar to constructor.
fhahn May 29, 2025
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
8 changes: 4 additions & 4 deletions llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -175,8 +175,8 @@ class VPBuilder {
std::initializer_list<VPValue *> Operands,
Type *ResultTy, const VPIRFlags &Flags = {},
DebugLoc DL = {}, const Twine &Name = "") {
return tryInsertInstruction(
new VPInstructionWithType(Opcode, Operands, ResultTy, Flags, DL, Name));
return tryInsertInstruction(new VPInstructionWithType(
Opcode, Operands, ResultTy, Flags, DL, /*IsSingleScalar=*/false, Name));
}

VPInstruction *createOverflowingOp(unsigned Opcode,
Expand Down Expand Up @@ -264,8 +264,8 @@ class VPBuilder {

VPInstruction *createScalarCast(Instruction::CastOps Opcode, VPValue *Op,
Type *ResultTy, DebugLoc DL) {
return tryInsertInstruction(
new VPInstructionWithType(Opcode, Op, ResultTy, {}, DL));
return tryInsertInstruction(new VPInstructionWithType(
Opcode, Op, ResultTy, {}, DL, /*IsSingleScalar=*/true));
}

VPWidenCastRecipe *createWidenCast(Instruction::CastOps Opcode, VPValue *Op,
Expand Down
9 changes: 8 additions & 1 deletion llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8343,7 +8343,7 @@ VPRecipeBuilder::tryToWidenHistogram(const HistogramInfo *HI,
return new VPHistogramRecipe(Opcode, HGramOps, HI->Store->getDebugLoc());
}

VPReplicateRecipe *
VPSingleDefRecipe *
VPRecipeBuilder::handleReplication(Instruction *I, ArrayRef<VPValue *> Operands,
VFRange &Range) {
bool IsUniform = LoopVectorizationPlanner::getDecisionAndClampRange(
Expand Down Expand Up @@ -8401,6 +8401,13 @@ VPRecipeBuilder::handleReplication(Instruction *I, ArrayRef<VPValue *> Operands,
assert((Range.Start.isScalar() || !IsUniform || !IsPredicated ||
(Range.Start.isScalable() && isa<IntrinsicInst>(I))) &&
"Should not predicate a uniform recipe");
if (IsUniform && Instruction::isCast(I->getOpcode())) {
auto *Recipe = new VPInstructionWithType(
I->getOpcode(), Operands, I->getType(), VPIRFlags(*I), I->getDebugLoc(),
/*IsSingleScalar=*/true, I->getName());
Recipe->setUnderlyingValue(I);
return Recipe;
}
auto *Recipe = new VPReplicateRecipe(I, Operands, IsUniform, BlockInMask,
VPIRMetadata(*I, LVer));
return Recipe;
Expand Down
2 changes: 1 addition & 1 deletion llvm/lib/Transforms/Vectorize/VPRecipeBuilder.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -199,7 +199,7 @@ class VPRecipeBuilder {
/// Build a VPReplicationRecipe for \p I using \p Operands. If it is
/// predicated, add the mask as last operand. Range.End may be decreased to
/// ensure same recipe behavior from \p Range.Start to \p Range.End.
VPReplicateRecipe *handleReplication(Instruction *I,
VPSingleDefRecipe *handleReplication(Instruction *I,
ArrayRef<VPValue *> Operands,
VFRange &Range);

Expand Down
17 changes: 9 additions & 8 deletions llvm/lib/Transforms/Vectorize/VPlan.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -876,6 +876,9 @@ class VPInstruction : public VPRecipeWithIRFlags,
public VPUnrollPartAccessor<1> {
friend class VPlanSlp;

/// True if the VPInstruction produces a single scalar value.
bool IsSingleScalar;

public:
/// VPlan opcodes, extending LLVM IR with idiomatics instructions.
enum {
Expand Down Expand Up @@ -966,7 +969,7 @@ class VPInstruction : public VPRecipeWithIRFlags,

VPInstruction(unsigned Opcode, ArrayRef<VPValue *> Operands,
const VPIRFlags &Flags, DebugLoc DL = {},
const Twine &Name = "");
const Twine &Name = "", bool IsSingleScalar = false);

VP_CLASSOF_IMPL(VPDef::VPInstructionSC)

Expand Down Expand Up @@ -1053,8 +1056,9 @@ class VPInstructionWithType : public VPInstruction {
public:
VPInstructionWithType(unsigned Opcode, ArrayRef<VPValue *> Operands,
Type *ResultTy, const VPIRFlags &Flags, DebugLoc DL,
const Twine &Name = "")
: VPInstruction(Opcode, Operands, Flags, DL, Name), ResultTy(ResultTy) {}
bool SingleScalar = false, const Twine &Name = "")
: VPInstruction(Opcode, Operands, Flags, DL, Name, true),
Copy link
Contributor

Choose a reason for hiding this comment

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

Does this mean that all VPInstructionWithTypes are single scalars? Is that true for WideIVSteps/StepVector?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Yep, I think due to them not really being printed at the moment it wasn't really relevant at the moment, but I updated the constructor to take it explicitly.

ResultTy(ResultTy) {}

static inline bool classof(const VPRecipeBase *R) {
// VPInstructionWithType are VPInstructions with specific opcodes requiring
Expand All @@ -1081,7 +1085,7 @@ class VPInstructionWithType : public VPInstruction {
SmallVector<VPValue *, 2> Operands(operands());
auto *New =
new VPInstructionWithType(getOpcode(), Operands, getResultType(), *this,
getDebugLoc(), getName());
getDebugLoc(), isSingleScalar(), getName());
New->setUnderlyingValue(getUnderlyingValue());
return New;
}
Expand All @@ -1090,10 +1094,7 @@ class VPInstructionWithType : public VPInstruction {

/// Return the cost of this VPInstruction.
InstructionCost computeCost(ElementCount VF,
VPCostContext &Ctx) const override {
// TODO: Compute accurate cost after retiring the legacy cost model.
return 0;
}
VPCostContext &Ctx) const override;

Type *getResultType() const { return ResultTy; }

Expand Down
31 changes: 22 additions & 9 deletions llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -408,9 +408,9 @@ template class VPUnrollPartAccessor<3>;

VPInstruction::VPInstruction(unsigned Opcode, ArrayRef<VPValue *> Operands,
const VPIRFlags &Flags, DebugLoc DL,
const Twine &Name)
const Twine &Name, bool IsSingleScalar)
: VPRecipeWithIRFlags(VPDef::VPInstructionSC, Operands, Flags, DL),
Opcode(Opcode), Name(Name.str()) {
IsSingleScalar(IsSingleScalar), Opcode(Opcode), Name(Name.str()) {
assert(flagsValidForOpcode(getOpcode()) &&
"Set flags not supported for the provided opcode");
}
Expand Down Expand Up @@ -847,7 +847,8 @@ bool VPInstruction::isVectorToScalar() const {
}

bool VPInstruction::isSingleScalar() const {
return getOpcode() == VPInstruction::ResumePhi ||
// TODO: Set IsSingleScalar for ResumePhi and PHI.
return IsSingleScalar || getOpcode() == VPInstruction::ResumePhi ||
getOpcode() == Instruction::PHI;
}

Expand Down Expand Up @@ -1055,15 +1056,17 @@ void VPInstruction::print(raw_ostream &O, const Twine &Indent,

void VPInstructionWithType::execute(VPTransformState &State) {
State.setDebugLocFrom(getDebugLoc());
switch (getOpcode()) {
case Instruction::ZExt:
case Instruction::Trunc: {
if (Instruction::isCast(getOpcode())) {
Value *Op = State.get(getOperand(0), VPLane(0));
Value *Cast = State.Builder.CreateCast(Instruction::CastOps(getOpcode()),
Op, ResultTy);
if (auto *I = dyn_cast<Instruction>(Cast))
applyFlags(*I);
State.set(this, Cast, VPLane(0));
break;
return;
}

switch (getOpcode()) {
case VPInstruction::StepVector: {
Value *StepVector =
State.Builder.CreateStepVector(VectorType::get(ResultTy, State.VF));
Expand All @@ -1075,10 +1078,19 @@ void VPInstructionWithType::execute(VPTransformState &State) {
}
}

InstructionCost VPInstructionWithType::computeCost(ElementCount VF,
VPCostContext &Ctx) const {
// TODO: Compute cost for VPInstructions without underlying values once
// the legacy cost model has been retired.
if (!getUnderlyingValue())
return 0;
return Ctx.getLegacyCost(cast<Instruction>(getUnderlyingValue()), VF);
}

#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
void VPInstructionWithType::print(raw_ostream &O, const Twine &Indent,
VPSlotTracker &SlotTracker) const {
O << Indent << "EMIT ";
O << Indent << (isSingleScalar() ? "SINGLE-SCALAR " : "EMIT ");
printAsOperand(O, SlotTracker);
O << " = ";

Expand Down Expand Up @@ -1604,11 +1616,12 @@ bool VPIRFlags::flagsValidForOpcode(unsigned Opcode) const {
return Opcode == Instruction::FAdd || Opcode == Instruction::FMul ||
Opcode == Instruction::FSub || Opcode == Instruction::FNeg ||
Opcode == Instruction::FDiv || Opcode == Instruction::FRem ||
Opcode == Instruction::FPTrunc || Opcode == Instruction::FPExt ||
Opcode == Instruction::FCmp || Opcode == Instruction::Select ||
Opcode == VPInstruction::WideIVStep ||
Opcode == VPInstruction::ComputeReductionResult;
case OperationType::NonNegOp:
return Opcode == Instruction::ZExt;
return Opcode == Instruction::UIToFP || Opcode == Instruction::ZExt;
break;
case OperationType::Cmp:
return Opcode == Instruction::ICmp;
Expand Down
10 changes: 8 additions & 2 deletions llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1048,8 +1048,14 @@ static void simplifyRecipe(VPRecipeBase &R, VPTypeAnalysis &TypeInfo) {
unsigned ExtOpcode = match(R.getOperand(0), m_SExt(m_VPValue()))
? Instruction::SExt
: Instruction::ZExt;
auto *VPC =
new VPWidenCastRecipe(Instruction::CastOps(ExtOpcode), A, TruncTy);
VPSingleDefRecipe *VPC;
if (vputils::isSingleScalar(R.getVPSingleValue()))
VPC = new VPInstructionWithType(Instruction::CastOps(ExtOpcode), {A},
TruncTy, {}, {});
Copy link
Contributor

Choose a reason for hiding this comment

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

Does this need to pass true for isSingleScalar?

else
VPC = new VPWidenCastRecipe(Instruction::CastOps(ExtOpcode), A,
TruncTy);

if (auto *UnderlyingExt = R.getOperand(0)->getUnderlyingValue()) {
// UnderlyingExt has distinct return type, used to retain legacy cost.
VPC->setUnderlyingValue(UnderlyingExt);
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Transforms/LoopVectorize/AArch64/sve2-histcnt-vplan.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ target triple = "aarch64-unknown-linux-gnu"
; CHECK-NEXT: [[STEPS:vp.*]] = SCALAR-STEPS [[IV]], ir<1>, [[VF]]
; CHECK-NEXT: CLONE [[GEP_IDX:.*]] = getelementptr inbounds ir<%indices>, [[STEPS]]
; CHECK-NEXT: CLONE [[IDX:.*]] = load [[GEP_IDX]]
; CHECK-NEXT: CLONE [[EXT_IDX:.*]] = zext [[IDX]]
; CHECK-NEXT: SINGLE-SCALAR [[EXT_IDX:.*]] = zext [[IDX]]
; CHECK-NEXT: CLONE [[GEP_BUCKET:.*]] = getelementptr inbounds ir<%buckets>, [[EXT_IDX]]
; CHECK-NEXT: CLONE [[HISTVAL:.*]] = load [[GEP_BUCKET]]
; CHECK-NEXT: CLONE [[UPDATE:.*]] = add nsw [[HISTVAL]], ir<1>
Expand Down
8 changes: 4 additions & 4 deletions llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: vp<[[DEV_IV:%.+]]> = DERIVED-IV ir<%n> + vp<[[CAN_IV]]> * ir<-1>
; CHECK-NEXT: vp<[[STEPS:%.+]]> = SCALAR-STEPS vp<[[DEV_IV]]>, ir<-1>
; CHECK-NEXT: CLONE ir<%i.0> = add nsw vp<[[STEPS]]>, ir<-1>
; CHECK-NEXT: CLONE ir<%idxprom> = zext ir<%i.0>
; CHECK-NEXT: SINGLE-SCALAR ir<%idxprom> = zext ir<%i.0>
; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%B>, ir<%idxprom>
; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-end-pointer inbounds ir<%arrayidx>, vp<[[VF]]>
; CHECK-NEXT: WIDEN ir<%1> = load vp<[[VEC_PTR]]>
Expand Down Expand Up @@ -199,7 +199,7 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: EMIT-SCALAR vp<[[CAN_IV:%.+]]> = phi [ ir<0>, ir-bb<vector.ph> ], [ vp<[[CAN_IV_NEXT:%.+]]>, vector.body ]
; CHECK-NEXT: vp<[[DEV_IV:%.+]]> = DERIVED-IV ir<%n> + vp<[[CAN_IV]]> * ir<-1>
; CHECK-NEXT: CLONE ir<%i.0> = add nsw vp<[[DEV_IV]]>, ir<-1>
; CHECK-NEXT: CLONE ir<%idxprom> = zext ir<%i.0>
; CHECK-NEXT: SINGLE-SCALAR ir<%idxprom> = zext ir<%i.0>
; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%B>, ir<%idxprom>
; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-end-pointer inbounds ir<%arrayidx>, ir<[[VF]]>
; CHECK-NEXT: WIDEN ir<[[L:%.+]]> = load vp<[[VEC_PTR]]>
Expand Down Expand Up @@ -323,7 +323,7 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: vp<[[DEV_IV:%.+]]> = DERIVED-IV ir<%n> + vp<[[CAN_IV]]> * ir<-1>
; CHECK-NEXT: vp<[[STEPS:%.+]]> = SCALAR-STEPS vp<[[DEV_IV]]>, ir<-1>
; CHECK-NEXT: CLONE ir<%i.0> = add nsw vp<[[STEPS]]>, ir<-1>
; CHECK-NEXT: CLONE ir<%idxprom> = zext ir<%i.0>
; CHECK-NEXT: SINGLE-SCALAR ir<%idxprom> = zext ir<%i.0>
; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%B>, ir<%idxprom>
; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-end-pointer inbounds ir<%arrayidx>, vp<[[VF]]>
; CHECK-NEXT: WIDEN ir<%1> = load vp<[[VEC_PTR]]>
Expand Down Expand Up @@ -447,7 +447,7 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; CHECK-NEXT: EMIT-SCALAR vp<[[CAN_IV:%.+]]> = phi [ ir<0>, ir-bb<vector.ph> ], [ vp<[[CAN_IV_NEXT:%.+]]>, vector.body ]
; CHECK-NEXT: vp<[[DEV_IV:%.+]]> = DERIVED-IV ir<%n> + vp<[[CAN_IV]]> * ir<-1>
; CHECK-NEXT: CLONE ir<%i.0> = add nsw vp<[[DEV_IV]]>, ir<-1>
; CHECK-NEXT: CLONE ir<%idxprom> = zext ir<%i.0>
; CHECK-NEXT: SINGLE-SCALAR ir<%idxprom> = zext ir<%i.0>
; CHECK-NEXT: CLONE ir<%arrayidx> = getelementptr inbounds ir<%B>, ir<%idxprom>
; CHECK-NEXT: vp<[[VEC_PTR:%.+]]> = vector-end-pointer inbounds ir<%arrayidx>, ir<[[VF]]>
; CHECK-NEXT: WIDEN ir<[[L:%.+]]> = load vp<[[VEC_PTR]]>
Expand Down
18 changes: 9 additions & 9 deletions llvm/test/Transforms/LoopVectorize/RISCV/vplan-vp-call-intrinsics.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ define void @vp_smax(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]>
; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, ir<[[SMAX]]>, vp<[[EVL]]>
; IF-EVL-NEXT: EMIT vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: SINGLE-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
; IF-EVL-NEXT: EMIT branch-on-count vp<[[IV_NEXT_EXIT]]>, vp<[[VTC]]>
Expand Down Expand Up @@ -92,7 +92,7 @@ define void @vp_smin(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]>
; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, ir<[[SMIN]]>, vp<[[EVL]]>
; IF-EVL-NEXT: EMIT vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: SINGLE-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
; IF-EVL-NEXT: EMIT branch-on-count vp<[[IV_NEXT_EXIT]]>, vp<[[VTC]]>
Expand Down Expand Up @@ -149,7 +149,7 @@ define void @vp_umax(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]>
; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, ir<[[UMAX]]>, vp<[[EVL]]>
; IF-EVL-NEXT: EMIT vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: SINGLE-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
; IF-EVL-NEXT: EMIT branch-on-count vp<[[IV_NEXT_EXIT]]>, vp<[[VTC]]>
Expand Down Expand Up @@ -206,7 +206,7 @@ define void @vp_umin(ptr %a, ptr %b, ptr %c, i64 %N) {
; IF-EVL-NEXT: CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR3:%[0-9]+]]> = vector-pointer ir<[[GEP3]]>
; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR3]]>, ir<[[UMIN]]>, vp<[[EVL]]>
; IF-EVL-NEXT: EMIT vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: SINGLE-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
; IF-EVL-NEXT: EMIT branch-on-count vp<[[IV_NEXT_EXIT]]>, vp<[[VTC]]>
Expand Down Expand Up @@ -260,7 +260,7 @@ define void @vp_ctlz(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[CTLZ]]>, vp<[[EVL]]>
; IF-EVL-NEXT: EMIT vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: SINGLE-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
; IF-EVL-NEXT: EMIT branch-on-count vp<[[IV_NEXT_EXIT]]>, vp<[[VTC]]>
Expand Down Expand Up @@ -312,7 +312,7 @@ define void @vp_cttz(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[CTTZ]]>, vp<[[EVL]]>
; IF-EVL-NEXT: EMIT vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: SINGLE-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
; IF-EVL-NEXT: EMIT branch-on-count vp<[[IV_NEXT_EXIT]]>, vp<[[VTC]]>
Expand Down Expand Up @@ -366,7 +366,7 @@ define void @vp_lrint(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[TRUNC]]>, vp<[[EVL]]>
; IF-EVL-NEXT: EMIT vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: SINGLE-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
; IF-EVL-NEXT: EMIT branch-on-count vp<[[IV_NEXT_EXIT]]>, vp<[[VTC]]>
Expand Down Expand Up @@ -422,7 +422,7 @@ define void @vp_llrint(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[TRUNC]]>, vp<[[EVL]]>
; IF-EVL-NEXT: EMIT vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: SINGLE-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
; IF-EVL-NEXT: EMIT branch-on-count vp<[[IV_NEXT_EXIT]]>, vp<[[VTC]]>
Expand Down Expand Up @@ -476,7 +476,7 @@ define void @vp_abs(ptr %a, ptr %b, i64 %N) {
; IF-EVL-NEXT: CLONE ir<[[GEP2:%.+]]> = getelementptr inbounds ir<%a>, vp<[[ST]]>
; IF-EVL-NEXT: vp<[[PTR2:%[0-9]+]]> = vector-pointer ir<[[GEP2]]>
; IF-EVL-NEXT: WIDEN vp.store vp<[[PTR2]]>, ir<[[ABS]]>, vp<[[EVL]]>
; IF-EVL-NEXT: EMIT vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: SINGLE-SCALAR vp<[[CAST:%[0-9]+]]> = zext vp<[[EVL]]> to i64
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT]]> = add vp<[[CAST]]>, vp<[[EVL_PHI]]>
; IF-EVL-NEXT: EMIT vp<[[IV_NEXT_EXIT:%.+]]> = add vp<[[IV]]>, vp<[[VFUF]]>
; IF-EVL-NEXT: EMIT branch-on-count vp<[[IV_NEXT_EXIT]]>, vp<[[VTC]]>
Expand Down
Loading
Loading