1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-01 13:11:39 +01:00
llvm-mirror/lib/Target/AArch64/AArch64TargetTransformInfo.h
David Green 5da8fa266d [ARM] Teach the Arm cost model that a Shift can be folded into other instructions
This attempts to teach the cost model in Arm that code such as:
  %s = shl i32 %a, 3
  %a = and i32 %s, %b
Can under Arm or Thumb2 become:
  and r0, r1, r2, lsl #3

So the cost of the shift can essentially be free. To do this without
trying to artificially adjust the cost of the "and" instruction, it
needs to get the users of the shl and check if they are a type of
instruction that the shift can be folded into. And so it needs to have
access to the actual instruction in getArithmeticInstrCost, which if
available is added as an extra parameter much like getCastInstrCost.

We otherwise limit it to shifts with a single user, which should
hopefully handle most of the cases. The list of instruction that the
shift can be folded into include ADC, ADD, AND, BIC, CMP, EOR, MVN, ORR,
ORN, RSB, SBC and SUB. This translates to Add, Sub, And, Or, Xor and
ICmp.

Differential Revision: https://reviews.llvm.org/D70966
2019-12-09 10:24:33 +00:00

205 lines
6.5 KiB
C++

//===- AArch64TargetTransformInfo.h - AArch64 specific TTI ------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
/// \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(unsigned ClassID) const {
bool Vector = (ClassID == 1);
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;
}
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 *>(),
const Instruction *CxtI = nullptr);
int getAddressComputationCost(Type *Ty, ScalarEvolution *SE, const SCEV *Ptr);
int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
const Instruction *I = nullptr);
TTI::MemCmpExpansionOptions enableMemCmpExpansion(bool OptSize,
bool IsZeroCmp) const;
int getMemoryOpCost(unsigned Opcode, Type *Src, MaybeAlign 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);
bool isLegalMaskedLoadStore(Type *DataType, MaybeAlign Alignment) {
if (!isa<VectorType>(DataType) || !ST->hasSVE())
return false;
Type *Ty = DataType->getVectorElementType();
if (Ty->isHalfTy() || Ty->isFloatTy() || Ty->isDoubleTy())
return true;
if (Ty->isIntegerTy(8) || Ty->isIntegerTy(16) ||
Ty->isIntegerTy(32) || Ty->isIntegerTy(64))
return true;
return false;
}
bool isLegalMaskedLoad(Type *DataType, MaybeAlign Alignment) {
return isLegalMaskedLoadStore(DataType, Alignment);
}
bool isLegalMaskedStore(Type *DataType, MaybeAlign Alignment) {
return isLegalMaskedLoadStore(DataType, Alignment);
}
int getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy, unsigned Factor,
ArrayRef<unsigned> Indices, unsigned Alignment,
unsigned AddressSpace,
bool UseMaskForCond = false,
bool UseMaskForGaps = false);
bool
shouldConsiderAddressTypePromotion(const Instruction &I,
bool &AllowPromotionWithoutCommonHeader);
bool shouldExpandReduction(const IntrinsicInst *II) const {
return false;
}
unsigned getGISelRematGlobalCost() const {
return 2;
}
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