CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
193 lines
7.9 KiB
C++
193 lines
7.9 KiB
C++
//==- HexagonTargetTransformInfo.cpp - Hexagon specific TTI pass -*- 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 implements a TargetTransformInfo analysis pass specific to the
|
|
/// Hexagon 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_HEXAGON_HEXAGONTARGETTRANSFORMINFO_H
|
|
#define LLVM_LIB_TARGET_HEXAGON_HEXAGONTARGETTRANSFORMINFO_H
|
|
|
|
#include "Hexagon.h"
|
|
#include "HexagonSubtarget.h"
|
|
#include "HexagonTargetMachine.h"
|
|
#include "llvm/ADT/ArrayRef.h"
|
|
#include "llvm/Analysis/TargetTransformInfo.h"
|
|
#include "llvm/CodeGen/BasicTTIImpl.h"
|
|
#include "llvm/IR/Function.h"
|
|
|
|
namespace llvm {
|
|
|
|
class Loop;
|
|
class ScalarEvolution;
|
|
class User;
|
|
class Value;
|
|
|
|
class HexagonTTIImpl final : public BasicTTIImplBase<HexagonTTIImpl> {
|
|
using BaseT = BasicTTIImplBase<HexagonTTIImpl>;
|
|
using TTI = TargetTransformInfo;
|
|
|
|
friend BaseT;
|
|
|
|
const HexagonSubtarget &ST;
|
|
const HexagonTargetLowering &TLI;
|
|
|
|
const HexagonSubtarget *getST() const { return &ST; }
|
|
const HexagonTargetLowering *getTLI() const { return &TLI; }
|
|
|
|
bool useHVX() const;
|
|
bool isHVXVectorType(Type *Ty) const;
|
|
|
|
// Returns the number of vector elements of Ty, if Ty is a vector type,
|
|
// or 1 if Ty is a scalar type. It is incorrect to call this function
|
|
// with any other type.
|
|
unsigned getTypeNumElements(Type *Ty) const;
|
|
|
|
public:
|
|
explicit HexagonTTIImpl(const HexagonTargetMachine *TM, const Function &F)
|
|
: BaseT(TM, F.getDataLayout()),
|
|
ST(*TM->getSubtargetImpl(F)), TLI(*ST.getTargetLowering()) {}
|
|
|
|
/// \name Scalar TTI Implementations
|
|
/// @{
|
|
|
|
TTI::PopcntSupportKind
|
|
getPopcntSupport(unsigned IntTyWidthInBit) const override;
|
|
|
|
// The Hexagon target can unroll loops with run-time trip counts.
|
|
void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
|
|
TTI::UnrollingPreferences &UP,
|
|
OptimizationRemarkEmitter *ORE) const override;
|
|
|
|
void getPeelingPreferences(Loop *L, ScalarEvolution &SE,
|
|
TTI::PeelingPreferences &PP) const override;
|
|
|
|
/// Bias LSR towards creating post-increment opportunities.
|
|
TTI::AddressingModeKind
|
|
getPreferredAddressingMode(const Loop *L, ScalarEvolution *SE) const override;
|
|
|
|
// L1 cache prefetch.
|
|
unsigned getPrefetchDistance() const override;
|
|
unsigned getCacheLineSize() const override;
|
|
|
|
/// @}
|
|
|
|
/// \name Vector TTI Implementations
|
|
/// @{
|
|
|
|
unsigned getNumberOfRegisters(unsigned ClassID) const override;
|
|
unsigned getMaxInterleaveFactor(ElementCount VF) const override;
|
|
TypeSize
|
|
getRegisterBitWidth(TargetTransformInfo::RegisterKind K) const override;
|
|
unsigned getMinVectorRegisterBitWidth() const override;
|
|
ElementCount getMinimumVF(unsigned ElemWidth, bool IsScalable) const override;
|
|
|
|
bool shouldMaximizeVectorBandwidth(
|
|
TargetTransformInfo::RegisterKind K) const override {
|
|
return true;
|
|
}
|
|
bool supportsEfficientVectorElementLoadStore() const override {
|
|
return false;
|
|
}
|
|
bool hasBranchDivergence(const Function *F = nullptr) const override {
|
|
return false;
|
|
}
|
|
bool enableAggressiveInterleaving(bool LoopHasReductions) const override {
|
|
return false;
|
|
}
|
|
bool prefersVectorizedAddressing() const override { return false; }
|
|
bool enableInterleavedAccessVectorization() const override { return true; }
|
|
|
|
InstructionCost getCallInstrCost(Function *F, Type *RetTy,
|
|
ArrayRef<Type *> Tys,
|
|
TTI::TargetCostKind CostKind) const override;
|
|
InstructionCost
|
|
getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
|
|
TTI::TargetCostKind CostKind) const override;
|
|
InstructionCost
|
|
getAddressComputationCost(Type *PtrTy, ScalarEvolution *SE, const SCEV *S,
|
|
TTI::TargetCostKind CostKind) const override;
|
|
InstructionCost getMemoryOpCost(
|
|
unsigned Opcode, Type *Src, Align Alignment, unsigned AddressSpace,
|
|
TTI::TargetCostKind CostKind,
|
|
TTI::OperandValueInfo OpInfo = {TTI::OK_AnyValue, TTI::OP_None},
|
|
const Instruction *I = nullptr) const override;
|
|
InstructionCost
|
|
getShuffleCost(TTI::ShuffleKind Kind, VectorType *DstTy, VectorType *SrcTy,
|
|
ArrayRef<int> Mask, TTI::TargetCostKind CostKind, int Index,
|
|
VectorType *SubTp, ArrayRef<const Value *> Args = {},
|
|
const Instruction *CxtI = nullptr) const override;
|
|
InstructionCost getInterleavedMemoryOpCost(
|
|
unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices,
|
|
Align Alignment, unsigned AddressSpace, TTI::TargetCostKind CostKind,
|
|
bool UseMaskForCond = false, bool UseMaskForGaps = false) const override;
|
|
InstructionCost getCmpSelInstrCost(
|
|
unsigned Opcode, Type *ValTy, Type *CondTy, CmpInst::Predicate VecPred,
|
|
TTI::TargetCostKind CostKind,
|
|
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
|
|
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
|
|
const Instruction *I = nullptr) const override;
|
|
InstructionCost getArithmeticInstrCost(
|
|
unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
|
|
TTI::OperandValueInfo Op1Info = {TTI::OK_AnyValue, TTI::OP_None},
|
|
TTI::OperandValueInfo Op2Info = {TTI::OK_AnyValue, TTI::OP_None},
|
|
ArrayRef<const Value *> Args = {},
|
|
const Instruction *CxtI = nullptr) const override;
|
|
InstructionCost
|
|
getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
|
|
TTI::CastContextHint CCH, TTI::TargetCostKind CostKind,
|
|
const Instruction *I = nullptr) const override;
|
|
using BaseT::getVectorInstrCost;
|
|
InstructionCost
|
|
getVectorInstrCost(unsigned Opcode, Type *Val, TTI::TargetCostKind CostKind,
|
|
unsigned Index, const Value *Op0, const Value *Op1,
|
|
TTI::VectorInstrContext VIC =
|
|
TTI::VectorInstrContext::None) const override;
|
|
|
|
InstructionCost
|
|
getCFInstrCost(unsigned Opcode, TTI::TargetCostKind CostKind,
|
|
const Instruction *I = nullptr) const override {
|
|
return 1;
|
|
}
|
|
bool shouldExpandReduction(const IntrinsicInst *II) const override;
|
|
bool isLegalMaskedStore(Type *DataType, Align Alignment,
|
|
unsigned AddressSpace,
|
|
TTI::MaskKind MaskKind) const override;
|
|
bool isLegalMaskedLoad(Type *DataType, Align Alignment, unsigned AddressSpace,
|
|
TTI::MaskKind MaskKind) const override;
|
|
bool isLegalMaskedGather(Type *Ty, Align Alignment) const override;
|
|
bool isLegalMaskedScatter(Type *Ty, Align Alignment) const override;
|
|
bool forceScalarizeMaskedGather(VectorType *VTy,
|
|
Align Alignment) const override;
|
|
bool forceScalarizeMaskedScatter(VectorType *VTy,
|
|
Align Alignment) const override;
|
|
|
|
InstructionCost getPartialReductionCost(
|
|
unsigned Opcode, Type *InputTypeA, Type *InputTypeB, Type *AccumType,
|
|
ElementCount VF, TTI::PartialReductionExtendKind OpAExtend,
|
|
TTI::PartialReductionExtendKind OpBExtend, std::optional<unsigned> BinOp,
|
|
TTI::TargetCostKind CostKind,
|
|
std::optional<FastMathFlags> FMF) const override {
|
|
return InstructionCost::getInvalid();
|
|
}
|
|
|
|
/// @}
|
|
|
|
InstructionCost
|
|
getInstructionCost(const User *U, ArrayRef<const Value *> Operands,
|
|
TTI::TargetCostKind CostKind) const override;
|
|
|
|
// Hexagon specific decision to generate a lookup table.
|
|
bool shouldBuildLookupTables() const override;
|
|
};
|
|
|
|
} // end namespace llvm
|
|
#endif // LLVM_LIB_TARGET_HEXAGON_HEXAGONTARGETTRANSFORMINFO_H
|