llvm-project/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h

180 lines
5.5 KiB
C
Raw Normal View History

//===- AArch64TargetTransformInfo.h - AArch64 specific TTI ------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
/// \file
/// This file a TargetTransformInfo::Concept conforming object specific to the
/// AArch64 target machine. It uses the target's detailed information to
/// provide more precise answers to certain TTI queries, while letting the
/// target independent and default TTI implementations handle the rest.
///
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_TARGET_AARCH64_AARCH64TARGETTRANSFORMINFO_H
#define LLVM_LIB_TARGET_AARCH64_AARCH64TARGETTRANSFORMINFO_H
#include "AArch64.h"
#include "AArch64Subtarget.h"
#include "AArch64TargetMachine.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/BasicTTIImpl.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/Intrinsics.h"
#include <cstdint>
namespace llvm {
class APInt;
class Instruction;
class IntrinsicInst;
class Loop;
class SCEV;
class ScalarEvolution;
class Type;
class Value;
class VectorType;
class AArch64TTIImpl : public BasicTTIImplBase<AArch64TTIImpl> {
using BaseT = BasicTTIImplBase<AArch64TTIImpl>;
using TTI = TargetTransformInfo;
friend BaseT;
const AArch64Subtarget *ST;
const AArch64TargetLowering *TLI;
const AArch64Subtarget *getST() const { return ST; }
const AArch64TargetLowering *getTLI() const { return TLI; }
enum MemIntrinsicType {
VECTOR_LDST_TWO_ELEMENTS,
VECTOR_LDST_THREE_ELEMENTS,
VECTOR_LDST_FOUR_ELEMENTS
};
bool isWideningInstruction(Type *Ty, unsigned Opcode,
ArrayRef<const Value *> Args);
public:
explicit AArch64TTIImpl(const AArch64TargetMachine *TM, const Function &F)
: BaseT(TM, F.getParent()->getDataLayout()), ST(TM->getSubtargetImpl(F)),
TLI(ST->getTargetLowering()) {}
bool areInlineCompatible(const Function *Caller,
const Function *Callee) const;
/// \name Scalar TTI Implementations
/// @{
using BaseT::getIntImmCost;
int getIntImmCost(int64_t Val);
int getIntImmCost(const APInt &Imm, Type *Ty);
int getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm, Type *Ty);
int getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
Type *Ty);
TTI::PopcntSupportKind getPopcntSupport(unsigned TyWidth);
/// @}
/// \name Vector TTI Implementations
/// @{
bool enableInterleavedAccessVectorization() { return true; }
unsigned getNumberOfRegisters(bool Vector) {
if (Vector) {
if (ST->hasNEON())
return 32;
return 0;
}
return 31;
}
unsigned getRegisterBitWidth(bool Vector) const {
if (Vector) {
if (ST->hasNEON())
return 128;
return 0;
}
return 64;
}
[SLP] Enable 64-bit wide vectorization on AArch64 ARM Neon has native support for half-sized vector registers (64 bits). This is beneficial for example for 2D and 3D graphics. This patch adds the option to lower MinVecRegSize from 128 via a TTI in the SLP Vectorizer. *** Performance Analysis This change was motivated by some internal benchmarks but it is also beneficial on SPEC and the LLVM testsuite. The results are with -O3 and PGO. A negative percentage is an improvement. The testsuite was run with a sample size of 4. ** SPEC * CFP2006/482.sphinx3 -3.34% A pretty hot loop is SLP vectorized resulting in nice instruction reduction. This used to be a +22% regression before rL299482. * CFP2000/177.mesa -3.34% * CINT2000/256.bzip2 +6.97% My current plan is to extend the fix in rL299482 to i16 which brings the regression down to +2.5%. There are also other problems with the codegen in this loop so there is further room for improvement. ** LLVM testsuite * SingleSource/Benchmarks/Misc/ReedSolomon -10.75% There are multiple small SLP vectorizations outside the hot code. It's a bit surprising that it adds up to 10%. Some of this may be code-layout noise. * MultiSource/Benchmarks/VersaBench/beamformer/beamformer -8.40% The opt-viewer screenshot can be seen at F3218284. We start at a colder store but the tree leads us into the hottest loop. * MultiSource/Applications/lambda-0.1.3/lambda -2.68% * MultiSource/Benchmarks/Bullet/bullet -2.18% This is using 3D vectors. * SingleSource/Benchmarks/Shootout-C++/Shootout-C++-lists +6.67% Noise, binary is unchanged. * MultiSource/Benchmarks/Ptrdist/anagram/anagram +4.90% There is an additional SLP in the cold code. The test runs for ~1sec and prints out over 2000 lines. This is most likely noise. * MultiSource/Applications/aha/aha +1.63% * MultiSource/Applications/JM/lencod/lencod +1.41% * SingleSource/Benchmarks/Misc/richards_benchmark +1.15% Differential Revision: https://reviews.llvm.org/D31965 llvm-svn: 303116
2017-05-16 05:15:01 +08:00
unsigned getMinVectorRegisterBitWidth() {
return ST->getMinVectorRegisterBitWidth();
}
unsigned getMaxInterleaveFactor(unsigned VF);
int getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
const Instruction *I = nullptr);
int getExtractWithExtendCost(unsigned Opcode, Type *Dst, VectorType *VecTy,
unsigned Index);
int getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);
int getArithmeticInstrCost(
unsigned Opcode, Type *Ty,
TTI::OperandValueKind Opd1Info = TTI::OK_AnyValue,
TTI::OperandValueKind Opd2Info = TTI::OK_AnyValue,
TTI::OperandValueProperties Opd1PropInfo = TTI::OP_None,
TTI::OperandValueProperties Opd2PropInfo = TTI::OP_None,
ArrayRef<const Value *> Args = ArrayRef<const Value *>());
int getAddressComputationCost(Type *Ty, ScalarEvolution *SE, const SCEV *Ptr);
int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
const Instruction *I = nullptr);
int getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
unsigned AddressSpace, const Instruction *I = nullptr);
int getCostOfKeepingLiveOverCall(ArrayRef<Type *> Tys);
void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
TTI::UnrollingPreferences &UP);
Value *getOrCreateResultFromMemIntrinsic(IntrinsicInst *Inst,
Type *ExpectedType);
bool getTgtMemIntrinsic(IntrinsicInst *Inst, MemIntrinsicInfo &Info);
int getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy, unsigned Factor,
ArrayRef<unsigned> Indices, unsigned Alignment,
unsigned AddressSpace);
bool
shouldConsiderAddressTypePromotion(const Instruction &I,
bool &AllowPromotionWithoutCommonHeader);
unsigned getCacheLineSize();
unsigned getPrefetchDistance();
unsigned getMinPrefetchStride();
unsigned getMaxPrefetchIterationsAhead();
bool shouldExpandReduction(const IntrinsicInst *II) const {
return false;
}
bool useReductionIntrinsic(unsigned Opcode, Type *Ty,
TTI::ReductionFlags Flags) const;
int getArithmeticReductionCost(unsigned Opcode, Type *Ty,
bool IsPairwiseForm);
int getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index, Type *SubTp);
/// @}
};
} // end namespace llvm
#endif // LLVM_LIB_TARGET_AARCH64_AARCH64TARGETTRANSFORMINFO_H