1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 11:02:59 +02:00
llvm-mirror/lib/Target/AArch64/AArch64TargetTransformInfo.h
Matthew Simpson 0ecc1283b2 [TTI, AArch64] Add transpose shuffle kind
This patch adds a new shuffle kind useful for transposing a 2xn matrix. These
transpose shuffle masks read corresponding even- or odd-numbered vector
elements from two n-dimensional source vectors and write each result into
consecutive elements of an n-dimensional destination vector. The transpose
shuffle kind is meant to model the TRN1 and TRN2 AArch64 instructions. As such,
this patch also considers transpose shuffles in the AArch64 implementation of
getShuffleCost.

Differential Revision: https://reviews.llvm.org/D45982

llvm-svn: 330941
2018-04-26 13:48:33 +00:00

180 lines
5.5 KiB
C++

//===- 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;
}
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