9802268ad3
In loop-vectorize, interleave count and vector factor depend on target register number. Currently, it does not estimate different register pressure for different register class separately(especially for scalar type, float type should not be on the same position with int type), so it's not accurate. Specifically, it causes too many times interleaving/unrolling, result in too many register spills in loop body and hurting performance. So we need classify the register classes in IR level, and importantly these are abstract register classes, and are not the target register class of backend provided in td file. It's used to establish the mapping between the types of IR values and the number of simultaneous live ranges to which we'd like to limit for some set of those types. For example, POWER target, register num is special when VSX is enabled. When VSX is enabled, the number of int scalar register is 32(GPR), float is 64(VSR), but for int and float vector register both are 64(VSR). So there should be 2 kinds of register class when vsx is enabled, and 3 kinds of register class when VSX is NOT enabled. It runs on POWER target, it makes big(+~30%) performance improvement in one specific bmk(503.bwaves_r) of spec2017 and no other obvious degressions. Differential revision: https://reviews.llvm.org/D67148 llvm-svn: 374634
113 lines
4.5 KiB
C++
113 lines
4.5 KiB
C++
//===-- SystemZTargetTransformInfo.h - SystemZ-specific TTI ---------------===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_LIB_TARGET_SYSTEMZ_SYSTEMZTARGETTRANSFORMINFO_H
|
|
#define LLVM_LIB_TARGET_SYSTEMZ_SYSTEMZTARGETTRANSFORMINFO_H
|
|
|
|
#include "SystemZTargetMachine.h"
|
|
#include "llvm/Analysis/TargetTransformInfo.h"
|
|
#include "llvm/CodeGen/BasicTTIImpl.h"
|
|
|
|
namespace llvm {
|
|
|
|
class SystemZTTIImpl : public BasicTTIImplBase<SystemZTTIImpl> {
|
|
typedef BasicTTIImplBase<SystemZTTIImpl> BaseT;
|
|
typedef TargetTransformInfo TTI;
|
|
friend BaseT;
|
|
|
|
const SystemZSubtarget *ST;
|
|
const SystemZTargetLowering *TLI;
|
|
|
|
const SystemZSubtarget *getST() const { return ST; }
|
|
const SystemZTargetLowering *getTLI() const { return TLI; }
|
|
|
|
unsigned const LIBCALL_COST = 30;
|
|
|
|
public:
|
|
explicit SystemZTTIImpl(const SystemZTargetMachine *TM, const Function &F)
|
|
: BaseT(TM, F.getParent()->getDataLayout()), ST(TM->getSubtargetImpl(F)),
|
|
TLI(ST->getTargetLowering()) {}
|
|
|
|
/// \name Scalar TTI Implementations
|
|
/// @{
|
|
|
|
unsigned getInliningThresholdMultiplier() { return 3; }
|
|
|
|
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);
|
|
|
|
void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
|
|
TTI::UnrollingPreferences &UP);
|
|
|
|
bool isLSRCostLess(TargetTransformInfo::LSRCost &C1,
|
|
TargetTransformInfo::LSRCost &C2);
|
|
/// @}
|
|
|
|
/// \name Vector TTI Implementations
|
|
/// @{
|
|
|
|
unsigned getNumberOfRegisters(unsigned ClassID) const;
|
|
unsigned getRegisterBitWidth(bool Vector) const;
|
|
|
|
unsigned getCacheLineSize() const override { return 256; }
|
|
unsigned getPrefetchDistance() const override { return 2000; }
|
|
unsigned getMinPrefetchStride() const override { return 2048; }
|
|
|
|
bool hasDivRemOp(Type *DataType, bool IsSigned);
|
|
bool prefersVectorizedAddressing() { return false; }
|
|
bool LSRWithInstrQueries() { return true; }
|
|
bool supportsEfficientVectorElementLoadStore() { return true; }
|
|
bool enableInterleavedAccessVectorization() { return true; }
|
|
|
|
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 getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index, Type *SubTp);
|
|
unsigned getVectorTruncCost(Type *SrcTy, Type *DstTy);
|
|
unsigned getVectorBitmaskConversionCost(Type *SrcTy, Type *DstTy);
|
|
unsigned getBoolVecToIntConversionCost(unsigned Opcode, Type *Dst,
|
|
const Instruction *I);
|
|
int getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
|
|
const Instruction *I = nullptr);
|
|
int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
|
|
const Instruction *I = nullptr);
|
|
int getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index);
|
|
bool isFoldableLoad(const LoadInst *Ld, const Instruction *&FoldedValue);
|
|
int getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
|
|
unsigned AddressSpace, const Instruction *I = nullptr);
|
|
|
|
int getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy,
|
|
unsigned Factor,
|
|
ArrayRef<unsigned> Indices,
|
|
unsigned Alignment,
|
|
unsigned AddressSpace,
|
|
bool UseMaskForCond = false,
|
|
bool UseMaskForGaps = false);
|
|
|
|
int getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy,
|
|
ArrayRef<Value *> Args, FastMathFlags FMF,
|
|
unsigned VF = 1);
|
|
int getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy,
|
|
ArrayRef<Type *> Tys, FastMathFlags FMF,
|
|
unsigned ScalarizationCostPassed = UINT_MAX);
|
|
/// @}
|
|
};
|
|
|
|
} // end namespace llvm
|
|
|
|
#endif
|