#ifndef LLVM_ANALYSIS_TARGETTRANSFORMINFO_H
#define LLVM_ANALYSIS_TARGETTRANSFORMINFO_H
+#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/Operator.h"
#include "llvm/IR/PassManager.h"
#include "llvm/Pass.h"
/// \returns The expected cost of compare and select instructions. If there
/// is an existing instruction that holds Opcode, it may be passed in the
- /// 'I' parameter.
- int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy = nullptr,
- TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput,
- const Instruction *I = nullptr) const;
+ /// 'I' parameter. The \p VecPred parameter can be used to indicate the select
+ /// is using a compare with the specified predicate as condition. When vector
+ /// types are passed, \p VecPred must be used for all lanes.
+ int getCmpSelInstrCost(
+ unsigned Opcode, Type *ValTy, Type *CondTy = nullptr,
+ CmpInst::Predicate VecPred = CmpInst::BAD_ICMP_PREDICATE,
+ TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput,
+ const Instruction *I = nullptr) const;
/// \return The expected cost of vector Insert and Extract.
/// Use -1 to indicate that there is no information on the index value.
virtual int getCFInstrCost(unsigned Opcode,
TTI::TargetCostKind CostKind) = 0;
virtual int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I) = 0;
virtual int getVectorInstrCost(unsigned Opcode, Type *Val,
return Impl.getCFInstrCost(Opcode, CostKind);
}
int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I) override {
- return Impl.getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind, I);
+ return Impl.getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind, I);
}
int getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index) override {
return Impl.getVectorInstrCost(Opcode, Val, Index);
}
unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I) const {
return 1;
case Instruction::Select: {
Type *CondTy = U->getOperand(0)->getType();
return TargetTTI->getCmpSelInstrCost(Opcode, U->getType(), CondTy,
+ CmpInst::BAD_ICMP_PREDICATE,
CostKind, I);
}
case Instruction::ICmp:
case Instruction::FCmp: {
Type *ValTy = U->getOperand(0)->getType();
+ // TODO: Also handle ICmp/FCmp constant expressions.
return TargetTTI->getCmpSelInstrCost(Opcode, ValTy, U->getType(),
+ I ? cast<CmpInst>(I)->getPredicate()
+ : CmpInst::BAD_ICMP_PREDICATE,
CostKind, I);
}
case Instruction::InsertElement: {
}
unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I = nullptr) {
const TargetLoweringBase *TLI = getTLI();
// TODO: Handle other cost kinds.
if (CostKind != TTI::TCK_RecipThroughput)
- return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind, I);
+ return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind,
+ I);
// Selects on vectors are actually vector selects.
if (ISD == ISD::SELECT) {
if (CondTy)
CondTy = CondTy->getScalarType();
unsigned Cost = thisT()->getCmpSelInstrCost(
- Opcode, ValVTy->getScalarType(), CondTy, CostKind, I);
+ Opcode, ValVTy->getScalarType(), CondTy, VecPred, CostKind, I);
// Return the cost of multiple scalar invocation plus the cost of
// inserting and extracting the values.
// For non-rotates (X != Y) we must add shift-by-zero handling costs.
if (X != Y) {
Type *CondTy = RetTy->getWithNewBitWidth(1);
- Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy, CondTy,
- CostKind);
- Cost += thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy,
- CondTy, CostKind);
+ Cost +=
+ thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy, CondTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
+ Cost +=
+ thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy, CondTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
}
return Cost;
}
Type *CondTy = RetTy->getWithNewBitWidth(1);
unsigned Cost = 0;
// TODO: Ideally getCmpSelInstrCost would accept an icmp condition code.
- Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy, CondTy,
- CostKind);
- Cost += thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy, CondTy,
- CostKind);
+ Cost +=
+ thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy, CondTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
+ Cost +=
+ thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy, CondTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
// TODO: Should we add an OperandValueProperties::OP_Zero property?
if (IID == Intrinsic::abs)
Cost += thisT()->getArithmeticInstrCost(
IntrinsicCostAttributes Attrs(OverflowOp, OpTy, {RetTy, RetTy}, FMF,
ScalarizationCostPassed);
Cost += thisT()->getIntrinsicInstrCost(Attrs, CostKind);
- Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy, CondTy,
- CostKind);
- Cost += 2 * thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy,
- CondTy, CostKind);
+ Cost +=
+ thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy, CondTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
+ Cost += 2 * thisT()->getCmpSelInstrCost(
+ BinaryOperator::Select, RetTy, CondTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
return Cost;
}
case Intrinsic::uadd_sat:
IntrinsicCostAttributes Attrs(OverflowOp, OpTy, {RetTy, RetTy}, FMF,
ScalarizationCostPassed);
Cost += thisT()->getIntrinsicInstrCost(Attrs, CostKind);
- Cost += thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy, CondTy,
- CostKind);
+ Cost +=
+ thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy, CondTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
return Cost;
}
case Intrinsic::smul_fix:
// Overflow -> (LHSSign != RHSSign) && (LHSSign != SumSign)
unsigned Cost = 0;
Cost += thisT()->getArithmeticInstrCost(Opcode, SumTy, CostKind);
- Cost += 3 * thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, SumTy,
- OverflowTy, CostKind);
- Cost += 2 * thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, OverflowTy,
- OverflowTy, CostKind);
+ Cost += 3 * thisT()->getCmpSelInstrCost(
+ BinaryOperator::ICmp, SumTy, OverflowTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
+ Cost += 2 * thisT()->getCmpSelInstrCost(
+ BinaryOperator::ICmp, OverflowTy, OverflowTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
Cost += thisT()->getArithmeticInstrCost(BinaryOperator::And, OverflowTy,
CostKind);
return Cost;
unsigned Cost = 0;
Cost += thisT()->getArithmeticInstrCost(Opcode, SumTy, CostKind);
- Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, SumTy,
- OverflowTy, CostKind);
+ Cost +=
+ thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, SumTy, OverflowTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
return Cost;
}
case Intrinsic::smul_with_overflow:
CostKind, TTI::OK_AnyValue,
TTI::OK_UniformConstantValue);
- Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, MulTy,
- OverflowTy, CostKind);
+ Cost +=
+ thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, MulTy, OverflowTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
return Cost;
}
case Intrinsic::ctpop:
(IsPairwise + 1) * thisT()->getShuffleCost(TTI::SK_ExtractSubvector,
Ty, NumVecElts, SubTy);
MinMaxCost +=
- thisT()->getCmpSelInstrCost(CmpOpcode, SubTy, CondTy, CostKind) +
+ thisT()->getCmpSelInstrCost(CmpOpcode, SubTy, CondTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind) +
thisT()->getCmpSelInstrCost(Instruction::Select, SubTy, CondTy,
- CostKind);
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
Ty = SubTy;
++LongVectorCount;
}
thisT()->getShuffleCost(TTI::SK_PermuteSingleSrc, Ty, 0, Ty);
MinMaxCost +=
NumReduxLevels *
- (thisT()->getCmpSelInstrCost(CmpOpcode, Ty, CondTy, CostKind) +
+ (thisT()->getCmpSelInstrCost(CmpOpcode, Ty, CondTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind) +
thisT()->getCmpSelInstrCost(Instruction::Select, Ty, CondTy,
- CostKind));
+ CmpInst::BAD_ICMP_PREDICATE, CostKind));
// The last min/max should be in vector registers and we counted it above.
// So just need a single extractelement.
return ShuffleCost + MinMaxCost +
int TargetTransformInfo::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I) const {
assert((I == nullptr || I->getOpcode() == Opcode) &&
"Opcode should reflect passed instruction.");
- int Cost = TTIImpl->getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind, I);
+ int Cost =
+ TTIImpl->getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind, I);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
//
//===----------------------------------------------------------------------===//
-#include "AArch64ExpandImm.h"
#include "AArch64TargetTransformInfo.h"
+#include "AArch64ExpandImm.h"
#include "MCTargetDesc/AArch64AddressingModes.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/TargetLowering.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/IntrinsicsAArch64.h"
+#include "llvm/IR/PatternMatch.h"
#include "llvm/Support/Debug.h"
#include <algorithm>
using namespace llvm;
+using namespace llvm::PatternMatch;
#define DEBUG_TYPE "aarch64tti"
}
int AArch64TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
- Type *CondTy,
+ Type *CondTy, CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I) {
// TODO: Handle other cost kinds.
if (CostKind != TTI::TCK_RecipThroughput)
- return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind, I);
+ return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind,
+ I);
int ISD = TLI->InstructionOpcodeToISD(Opcode);
// We don't lower some vector selects well that are wider than the register
if (ValTy->isVectorTy() && ISD == ISD::SELECT) {
// We would need this many instructions to hide the scalarization happening.
const int AmortizationCost = 20;
+
+ // If VecPred is not set, check if we can get a predicate from the context
+ // instruction, if its type matches the requested ValTy.
+ if (VecPred == CmpInst::BAD_ICMP_PREDICATE && I && I->getType() == ValTy) {
+ CmpInst::Predicate CurrentPred;
+ if (match(I, m_Select(m_Cmp(CurrentPred, m_Value(), m_Value()), m_Value(),
+ m_Value())))
+ VecPred = CurrentPred;
+ }
+ // Check if we have a compare/select chain that can be lowered using CMxx &
+ // BFI pair.
+ if (CmpInst::isIntPredicate(VecPred)) {
+ static const auto ValidMinMaxTys = {MVT::v8i8, MVT::v16i8, MVT::v4i16,
+ MVT::v8i16, MVT::v2i32, MVT::v4i32,
+ MVT::v2i64};
+ auto LT = TLI->getTypeLegalizationCost(DL, ValTy);
+ if (any_of(ValidMinMaxTys, [<](MVT M) { return M == LT.second; }))
+ return LT.first;
+ }
+
static const TypeConversionCostTblEntry
VectorSelectTbl[] = {
{ ISD::SELECT, MVT::v16i1, MVT::v16i16, 16 },
return Entry->Cost;
}
}
- return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind, I);
+ return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind, I);
}
AArch64TTIImpl::TTI::MemCmpExpansionOptions
int getAddressComputationCost(Type *Ty, ScalarEvolution *SE, const SCEV *Ptr);
int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I = nullptr);
}
int ARMTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I) {
int ISD = TLI->InstructionOpcodeToISD(Opcode);
}
if (CostKind != TTI::TCK_RecipThroughput)
- return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind, I);
+ return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind,
+ I);
// On NEON a vector select gets lowered to vbsl.
if (ST->hasNEON() && ValTy->isVectorTy() && ISD == ISD::SELECT) {
int BaseCost = ST->hasMVEIntegerOps() && ValTy->isVectorTy()
? ST->getMVEVectorCostFactor()
: 1;
- return BaseCost * BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind,
- I);
+ return BaseCost *
+ BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind, I);
}
int ARMTTIImpl::getAddressComputationCost(Type *Ty, ScalarEvolution *SE,
const Instruction *I = nullptr);
int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I = nullptr);
}
unsigned HexagonTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
- Type *CondTy, TTI::TargetCostKind CostKind, const Instruction *I) {
+ Type *CondTy,
+ CmpInst::Predicate VecPred,
+ TTI::TargetCostKind CostKind,
+ const Instruction *I) {
if (ValTy->isVectorTy() && CostKind == TTI::TCK_RecipThroughput) {
std::pair<int, MVT> LT = TLI.getTypeLegalizationCost(DL, ValTy);
if (Opcode == Instruction::FCmp)
return LT.first + FloatFactor * getTypeNumElements(ValTy);
}
- return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind, I);
+ return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind, I);
}
unsigned HexagonTTIImpl::getArithmeticInstrCost(
TTI::TargetCostKind CostKind = TTI::TCK_SizeAndLatency,
bool UseMaskForCond = false, bool UseMaskForGaps = false);
unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I = nullptr);
unsigned getArithmeticInstrCost(
}
int PPCTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I) {
- int Cost = BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind, I);
+ int Cost =
+ BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind, I);
// TODO: Handle other cost kinds.
if (CostKind != TTI::TCK_RecipThroughput)
return Cost;
const Instruction *I = nullptr);
int getCFInstrCost(unsigned Opcode, TTI::TargetCostKind CostKind);
int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I = nullptr);
int getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);
}
int SystemZTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
- Type *CondTy,
+ Type *CondTy, CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I) {
if (CostKind != TTI::TCK_RecipThroughput)
- return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind);
+ return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind);
if (!ValTy->isVectorTy()) {
switch (Opcode) {
}
}
- return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind);
+ return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind);
}
int SystemZTTIImpl::
TTI::CastContextHint CCH, TTI::TargetCostKind CostKind,
const Instruction *I = nullptr);
int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I = nullptr);
int getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);
}
int X86TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I) {
// TODO: Handle other cost kinds.
if (CostKind != TTI::TCK_RecipThroughput)
- return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind, I);
+ return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind,
+ I);
// Legalize the type.
std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, ValTy);
if (const auto *Entry = CostTableLookup(SSE1CostTbl, ISD, MTy))
return LT.first * (ExtraCost + Entry->Cost);
- return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, CostKind, I);
+ return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind, I);
}
unsigned X86TTIImpl::getAtomicMemIntrinsicMaxElementSize() const { return 16; }
getScalarizationOverhead(MaskTy, DemandedElts, false, true);
int ScalarCompareCost = getCmpSelInstrCost(
Instruction::ICmp, Type::getInt8Ty(SrcVTy->getContext()), nullptr,
- CostKind);
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
int BranchCost = getCFInstrCost(Instruction::Br, CostKind);
int MaskCmpCost = NumElem * (BranchCost + ScalarCompareCost);
int ValueSplitCost =
TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
// Otherwise fall back to cmp+select.
- return getCmpSelInstrCost(CmpOpcode, Ty, CondTy, CostKind) +
- getCmpSelInstrCost(Instruction::Select, Ty, CondTy, CostKind);
+ return getCmpSelInstrCost(CmpOpcode, Ty, CondTy, CmpInst::BAD_ICMP_PREDICATE,
+ CostKind) +
+ getCmpSelInstrCost(Instruction::Select, Ty, CondTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
}
int X86TTIImpl::getMinMaxReductionCost(VectorType *ValTy, VectorType *CondTy,
FixedVectorType::get(Type::getInt1Ty(SrcVTy->getContext()), VF);
MaskUnpackCost =
getScalarizationOverhead(MaskTy, DemandedElts, false, true);
- int ScalarCompareCost =
- getCmpSelInstrCost(Instruction::ICmp, Type::getInt1Ty(SrcVTy->getContext()),
- nullptr, CostKind);
+ int ScalarCompareCost = getCmpSelInstrCost(
+ Instruction::ICmp, Type::getInt1Ty(SrcVTy->getContext()), nullptr,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
int BranchCost = getCFInstrCost(Instruction::Br, CostKind);
MaskUnpackCost += VF * (BranchCost + ScalarCompareCost);
}
TTI::CastContextHint CCH, TTI::TargetCostKind CostKind,
const Instruction *I = nullptr);
int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
+ CmpInst::Predicate VecPred,
TTI::TargetCostKind CostKind,
const Instruction *I = nullptr);
int getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);
unsigned MinIdx, unsigned MaxIdx) {
Operations.emplace_back(Opcode, MinIdx, MaxIdx);
Type *OpType = S->getOperand(0)->getType();
- return NumRequired *
- TTI.getCmpSelInstrCost(Opcode, OpType,
- CmpInst::makeCmpResultType(OpType), CostKind);
+ return NumRequired * TTI.getCmpSelInstrCost(
+ Opcode, OpType, CmpInst::makeCmpResultType(OpType),
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
};
switch (S->getSCEVType()) {
BudgetRemaining -=
TTI.getCmpSelInstrCost(Instruction::Select, PN.getType(), nullptr,
- CostKind);
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
// Don't convert to selects if we could remove undefined behavior instead.
if (passingValueIsAlwaysUndefined(OrigV, &PN) ||
TTI.getCmpSelInstrCost(
Instruction::Select, ToVectorTy(Phi->getType(), VF),
ToVectorTy(Type::getInt1Ty(Phi->getContext()), VF),
- CostKind);
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
return TTI.getCFInstrCost(Instruction::PHI, CostKind);
}
CondTy = VectorType::get(CondTy, VF);
}
return TTI.getCmpSelInstrCost(I->getOpcode(), VectorTy, CondTy,
- CostKind, I);
+ CmpInst::BAD_ICMP_PREDICATE, CostKind, I);
}
case Instruction::ICmp:
case Instruction::FCmp: {
if (canTruncateToMinimalBitwidth(Op0AsInstruction, VF))
ValTy = IntegerType::get(ValTy->getContext(), MinBWs[Op0AsInstruction]);
VectorTy = ToVectorTy(ValTy, VF);
- return TTI.getCmpSelInstrCost(I->getOpcode(), VectorTy, nullptr, CostKind,
- I);
+ return TTI.getCmpSelInstrCost(I->getOpcode(), VectorTy, nullptr,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind, I);
}
case Instruction::Store:
case Instruction::Load: {
case Instruction::ICmp:
case Instruction::Select: {
// Calculate the cost of this instruction.
- int ScalarEltCost = TTI->getCmpSelInstrCost(E->getOpcode(), ScalarTy,
- Builder.getInt1Ty(),
- CostKind, VL0);
+ int ScalarEltCost =
+ TTI->getCmpSelInstrCost(E->getOpcode(), ScalarTy, Builder.getInt1Ty(),
+ CmpInst::BAD_ICMP_PREDICATE, CostKind, VL0);
if (NeedToShuffleReuses) {
ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
}
auto *MaskTy = FixedVectorType::get(Builder.getInt1Ty(), VL.size());
int ScalarCost = VecTy->getNumElements() * ScalarEltCost;
- int VecCost = TTI->getCmpSelInstrCost(E->getOpcode(), VecTy, MaskTy,
- CostKind, VL0);
+ int VecCost =
+ TTI->getCmpSelInstrCost(E->getOpcode(), VecTy, MaskTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind, VL0);
// Check if it is possible and profitable to use min/max for selects in
// VL.
//
// If the selects are the only uses of the compares, they will be dead
// and we can adjust the cost by removing their cost.
if (IntrinsicAndUse.second)
- IntrinsicCost -= TTI->getCmpSelInstrCost(Instruction::ICmp, VecTy,
- MaskTy, CostKind);
+ IntrinsicCost -=
+ TTI->getCmpSelInstrCost(Instruction::ICmp, VecTy, MaskTy,
+ CmpInst::BAD_ICMP_PREDICATE, CostKind);
VecCost = std::min(VecCost, IntrinsicCost);
}
return ReuseShuffleCost + VecCost - ScalarCost;
; COST-LABEL: v8i8_select_eq
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = icmp eq <8 x i8> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x i8> %a, <8 x i8> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x i8> %a, <8 x i8> %c
; CODE-LABEL: v8i8_select_eq
; CODE: bb.0
; COST-LABEL: v16i8_select_sgt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = icmp sgt <16 x i8> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %s.1 = select <16 x i1> %cmp.1, <16 x i8> %a, <16 x i8> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <16 x i1> %cmp.1, <16 x i8> %a, <16 x i8> %c
; CODE-LABEL: v16i8_select_sgt
; CODE: bb.0
; COST-LABEL: v4i16_select_ne
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = icmp ne <4 x i16> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x i16> %a, <4 x i16> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x i16> %a, <4 x i16> %c
; CODE-LABEL: v4i16_select_ne
; CODE: bb.0
; COST-LABEL: v8i16_select_ugt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = icmp ugt <8 x i16> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x i16> %a, <8 x i16> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x i16> %a, <8 x i16> %c
; CODE-LABEL: v8i16_select_ugt
; CODE: bb.0
; COST-LABEL: v2i32_select_ule
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = icmp ule <2 x i32> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x i32> %a, <2 x i32> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x i32> %a, <2 x i32> %c
; CODE-LABEL: v2i32_select_ule
; CODE: bb.0
; COST-LABEL: v4i32_select_ult
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = icmp ult <4 x i32> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x i32> %a, <4 x i32> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x i32> %a, <4 x i32> %c
; CODE-LABEL: v4i32_select_ult
; CODE: bb.0
; COST-LABEL: v2i64_select_sle
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = icmp sle <2 x i64> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x i64> %a, <2 x i64> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x i64> %a, <2 x i64> %c
; CODE-LABEL: v2i64_select_sle
; CODE: bb.0
; COST-LABEL: v3i64_select_sle
; COST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %cmp.1 = icmp sle <3 x i64> %a, %b
-; COST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %s.1 = select <3 x i1> %cmp.1, <3 x i64> %a, <3 x i64> %c
+; COST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %s.1 = select <3 x i1> %cmp.1, <3 x i64> %a, <3 x i64> %c
; CODE-LABEL: v3i64_select_sle
; CODE: bb.0
--- /dev/null
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -simplifycfg -S %s | FileCheck %s
+
+@glob = internal constant [5 x i8*] zeroinitializer, align 16
+
+; Make sure simplifycfg does not crash when dealing with icmp constant
+; expressions.
+define i1 @test(i1 %c) {
+; CHECK-LABEL: @test(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[SPEC_SELECT:%.*]] = select i1 [[C:%.*]], i1 false, i1 icmp ult (i8** getelementptr inbounds ([5 x i8*], [5 x i8*]* @glob, i64 0, i64 0), i8** inttoptr (i64 -40 to i8**))
+; CHECK-NEXT: ret i1 [[SPEC_SELECT]]
+;
+entry:
+ br i1 %c, label %if.then, label %exit
+
+if.then:
+ br label %exit
+
+exit:
+ %p = phi i1 [ false, %if.then ], [ icmp ult (i8** getelementptr inbounds ([5 x i8*], [5 x i8*]* @glob, i64 0, i64 0), i8** inttoptr (i64 -40 to i8**)), %entry ]
+ ret i1 %p
+}