1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 11:42:57 +01:00
llvm-mirror/lib/Target/ARM/ARMTargetTransformInfo.h
Bernard Ogden 1a1a8110d3 [ARM/AArch64] Support FP16 +fp16fml instructions
Add +fp16fml feature for new FP16 instructions, which are a
mandatory part of FP16 from v8.4-A and an optional part of FP16
from v8.2-A. It doesn't seem to be possible to model this in
LLVM, but the relationship between the options is handled by
the related clang patch.

In keeping with what I think is the usual practice, the fp16fml
extension is accepted regardless of base architecture version.

Builds on/replaces Sjoerd Meijer's patch to add these instructions at
https://reviews.llvm.org/D49839.

Differential Revision: https://reviews.llvm.org/D50228

llvm-svn: 340013
2018-08-17 11:29:49 +00:00

192 lines
6.8 KiB
C++

//===- ARMTargetTransformInfo.h - ARM 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
/// ARM 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_ARM_ARMTARGETTRANSFORMINFO_H
#define LLVM_LIB_TARGET_ARM_ARMTARGETTRANSFORMINFO_H
#include "ARM.h"
#include "ARMSubtarget.h"
#include "ARMTargetMachine.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/BasicTTIImpl.h"
#include "llvm/IR/Constant.h"
#include "llvm/IR/Function.h"
#include "llvm/MC/SubtargetFeature.h"
namespace llvm {
class APInt;
class ARMTargetLowering;
class Instruction;
class Loop;
class SCEV;
class ScalarEvolution;
class Type;
class Value;
class ARMTTIImpl : public BasicTTIImplBase<ARMTTIImpl> {
using BaseT = BasicTTIImplBase<ARMTTIImpl>;
using TTI = TargetTransformInfo;
friend BaseT;
const ARMSubtarget *ST;
const ARMTargetLowering *TLI;
// Currently the following features are excluded from InlineFeatureWhitelist.
// ModeThumb, FeatureNoARM, ModeSoftFloat, FeatureVFPOnlySP, FeatureD16
// Depending on whether they are set or unset, different
// instructions/registers are available. For example, inlining a callee with
// -thumb-mode in a caller with +thumb-mode, may cause the assembler to
// fail if the callee uses ARM only instructions, e.g. in inline asm.
const FeatureBitset InlineFeatureWhitelist = {
ARM::FeatureVFP2, ARM::FeatureVFP3, ARM::FeatureNEON, ARM::FeatureThumb2,
ARM::FeatureFP16, ARM::FeatureVFP4, ARM::FeatureFPARMv8,
ARM::FeatureFullFP16, ARM::FeatureFP16FML, ARM::FeatureHWDivThumb,
ARM::FeatureHWDivARM, ARM::FeatureDB, ARM::FeatureV7Clrex,
ARM::FeatureAcquireRelease, ARM::FeatureSlowFPBrcc,
ARM::FeaturePerfMon, ARM::FeatureTrustZone, ARM::Feature8MSecExt,
ARM::FeatureCrypto, ARM::FeatureCRC, ARM::FeatureRAS,
ARM::FeatureFPAO, ARM::FeatureFuseAES, ARM::FeatureZCZeroing,
ARM::FeatureProfUnpredicate, ARM::FeatureSlowVGETLNi32,
ARM::FeatureSlowVDUP32, ARM::FeaturePreferVMOVSR,
ARM::FeaturePrefISHSTBarrier, ARM::FeatureMuxedUnits,
ARM::FeatureSlowOddRegister, ARM::FeatureSlowLoadDSubreg,
ARM::FeatureDontWidenVMOVS, ARM::FeatureExpandMLx,
ARM::FeatureHasVMLxHazards, ARM::FeatureNEONForFPMovs,
ARM::FeatureNEONForFP, ARM::FeatureCheckVLDnAlign,
ARM::FeatureHasSlowFPVMLx, ARM::FeatureVMLxForwarding,
ARM::FeaturePref32BitThumb, ARM::FeatureAvoidPartialCPSR,
ARM::FeatureCheapPredicableCPSR, ARM::FeatureAvoidMOVsShOp,
ARM::FeatureHasRetAddrStack, ARM::FeatureHasNoBranchPredictor,
ARM::FeatureDSP, ARM::FeatureMP, ARM::FeatureVirtualization,
ARM::FeatureMClass, ARM::FeatureRClass, ARM::FeatureAClass,
ARM::FeatureNaClTrap, ARM::FeatureStrictAlign, ARM::FeatureLongCalls,
ARM::FeatureExecuteOnly, ARM::FeatureReserveR9, ARM::FeatureNoMovt,
ARM::FeatureNoNegativeImmediates
};
const ARMSubtarget *getST() const { return ST; }
const ARMTargetLowering *getTLI() const { return TLI; }
public:
explicit ARMTTIImpl(const ARMBaseTargetMachine *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;
bool enableInterleavedAccessVectorization() { return true; }
/// Floating-point computation using ARMv8 AArch32 Advanced
/// SIMD instructions remains unchanged from ARMv7. Only AArch64 SIMD
/// is IEEE-754 compliant, but it's not covered in this target.
bool isFPVectorizationPotentiallyUnsafe() {
return !ST->isTargetDarwin();
}
/// \name Scalar TTI Implementations
/// @{
int getIntImmCodeSizeCost(unsigned Opcode, unsigned Idx, const APInt &Imm,
Type *Ty);
using BaseT::getIntImmCost;
int getIntImmCost(const APInt &Imm, Type *Ty);
int getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm, Type *Ty);
/// @}
/// \name Vector TTI Implementations
/// @{
unsigned getNumberOfRegisters(bool Vector) {
if (Vector) {
if (ST->hasNEON())
return 16;
return 0;
}
if (ST->isThumb1Only())
return 8;
return 13;
}
unsigned getRegisterBitWidth(bool Vector) const {
if (Vector) {
if (ST->hasNEON())
return 128;
return 0;
}
return 32;
}
unsigned getMaxInterleaveFactor(unsigned VF) {
return ST->getMaxInterleaveFactor();
}
int getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index, Type *SubTp);
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);
int getAddressComputationCost(Type *Val, ScalarEvolution *SE,
const SCEV *Ptr);
int getArithmeticInstrCost(
unsigned Opcode, Type *Ty,
TTI::OperandValueKind Op1Info = TTI::OK_AnyValue,
TTI::OperandValueKind Op2Info = TTI::OK_AnyValue,
TTI::OperandValueProperties Opd1PropInfo = TTI::OP_None,
TTI::OperandValueProperties Opd2PropInfo = TTI::OP_None,
ArrayRef<const Value *> Args = ArrayRef<const Value *>());
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);
void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
TTI::UnrollingPreferences &UP);
bool shouldBuildLookupTablesForConstant(Constant *C) const {
// In the ROPI and RWPI relocation models we can't have pointers to global
// variables or functions in constant data, so don't convert switches to
// lookup tables if any of the values would need relocation.
if (ST->isROPI() || ST->isRWPI())
return !C->needsRelocation();
return true;
}
/// @}
};
} // end namespace llvm
#endif // LLVM_LIB_TARGET_ARM_ARMTARGETTRANSFORMINFO_H