forked from OSchip/llvm-project
304 lines
10 KiB
C++
304 lines
10 KiB
C++
//===-- AArch64Subtarget.cpp - AArch64 Subtarget Information ----*- 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file implements the AArch64 specific subclass of TargetSubtarget.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "AArch64Subtarget.h"
|
|
|
|
#include "AArch64.h"
|
|
#include "AArch64CallLowering.h"
|
|
#include "AArch64InstrInfo.h"
|
|
#include "AArch64LegalizerInfo.h"
|
|
#include "AArch64PBQPRegAlloc.h"
|
|
#include "AArch64RegisterBankInfo.h"
|
|
#include "AArch64TargetMachine.h"
|
|
#include "MCTargetDesc/AArch64AddressingModes.h"
|
|
#include "llvm/CodeGen/GlobalISel/InstructionSelect.h"
|
|
#include "llvm/CodeGen/MachineScheduler.h"
|
|
#include "llvm/IR/GlobalValue.h"
|
|
#include "llvm/Support/TargetParser.h"
|
|
|
|
using namespace llvm;
|
|
|
|
#define DEBUG_TYPE "aarch64-subtarget"
|
|
|
|
#define GET_SUBTARGETINFO_CTOR
|
|
#define GET_SUBTARGETINFO_TARGET_DESC
|
|
#include "AArch64GenSubtargetInfo.inc"
|
|
|
|
static cl::opt<bool>
|
|
EnableEarlyIfConvert("aarch64-early-ifcvt", cl::desc("Enable the early if "
|
|
"converter pass"), cl::init(true), cl::Hidden);
|
|
|
|
// If OS supports TBI, use this flag to enable it.
|
|
static cl::opt<bool>
|
|
UseAddressTopByteIgnored("aarch64-use-tbi", cl::desc("Assume that top byte of "
|
|
"an address is ignored"), cl::init(false), cl::Hidden);
|
|
|
|
static cl::opt<bool>
|
|
UseNonLazyBind("aarch64-enable-nonlazybind",
|
|
cl::desc("Call nonlazybind functions via direct GOT load"),
|
|
cl::init(false), cl::Hidden);
|
|
|
|
AArch64Subtarget &
|
|
AArch64Subtarget::initializeSubtargetDependencies(StringRef FS,
|
|
StringRef CPUString) {
|
|
// Determine default and user-specified characteristics
|
|
|
|
if (CPUString.empty())
|
|
CPUString = "generic";
|
|
|
|
ParseSubtargetFeatures(CPUString, FS);
|
|
initializeProperties();
|
|
|
|
return *this;
|
|
}
|
|
|
|
void AArch64Subtarget::initializeProperties() {
|
|
// Initialize CPU specific properties. We should add a tablegen feature for
|
|
// this in the future so we can specify it together with the subtarget
|
|
// features.
|
|
switch (ARMProcFamily) {
|
|
case Others:
|
|
break;
|
|
case CortexA35:
|
|
break;
|
|
case CortexA53:
|
|
PrefFunctionAlignment = 3;
|
|
break;
|
|
case CortexA55:
|
|
break;
|
|
case CortexA57:
|
|
MaxInterleaveFactor = 4;
|
|
PrefFunctionAlignment = 4;
|
|
break;
|
|
case CortexA65:
|
|
break;
|
|
case CortexA72:
|
|
case CortexA73:
|
|
case CortexA75:
|
|
case CortexA76:
|
|
PrefFunctionAlignment = 4;
|
|
break;
|
|
case Cyclone:
|
|
CacheLineSize = 64;
|
|
PrefetchDistance = 280;
|
|
MinPrefetchStride = 2048;
|
|
MaxPrefetchIterationsAhead = 3;
|
|
break;
|
|
case ExynosM1:
|
|
MaxInterleaveFactor = 4;
|
|
MaxJumpTableSize = 8;
|
|
PrefFunctionAlignment = 4;
|
|
PrefLoopAlignment = 3;
|
|
break;
|
|
case ExynosM3:
|
|
MaxInterleaveFactor = 4;
|
|
MaxJumpTableSize = 20;
|
|
PrefFunctionAlignment = 5;
|
|
PrefLoopAlignment = 4;
|
|
break;
|
|
case Falkor:
|
|
MaxInterleaveFactor = 4;
|
|
// FIXME: remove this to enable 64-bit SLP if performance looks good.
|
|
MinVectorRegisterBitWidth = 128;
|
|
CacheLineSize = 128;
|
|
PrefetchDistance = 820;
|
|
MinPrefetchStride = 2048;
|
|
MaxPrefetchIterationsAhead = 8;
|
|
break;
|
|
case Kryo:
|
|
MaxInterleaveFactor = 4;
|
|
VectorInsertExtractBaseCost = 2;
|
|
CacheLineSize = 128;
|
|
PrefetchDistance = 740;
|
|
MinPrefetchStride = 1024;
|
|
MaxPrefetchIterationsAhead = 11;
|
|
// FIXME: remove this to enable 64-bit SLP if performance looks good.
|
|
MinVectorRegisterBitWidth = 128;
|
|
break;
|
|
case NeoverseE1:
|
|
break;
|
|
case NeoverseN1:
|
|
PrefFunctionAlignment = 4;
|
|
break;
|
|
case Saphira:
|
|
MaxInterleaveFactor = 4;
|
|
// FIXME: remove this to enable 64-bit SLP if performance looks good.
|
|
MinVectorRegisterBitWidth = 128;
|
|
break;
|
|
case ThunderX2T99:
|
|
CacheLineSize = 64;
|
|
PrefFunctionAlignment = 3;
|
|
PrefLoopAlignment = 2;
|
|
MaxInterleaveFactor = 4;
|
|
PrefetchDistance = 128;
|
|
MinPrefetchStride = 1024;
|
|
MaxPrefetchIterationsAhead = 4;
|
|
// FIXME: remove this to enable 64-bit SLP if performance looks good.
|
|
MinVectorRegisterBitWidth = 128;
|
|
break;
|
|
case ThunderX:
|
|
case ThunderXT88:
|
|
case ThunderXT81:
|
|
case ThunderXT83:
|
|
CacheLineSize = 128;
|
|
PrefFunctionAlignment = 3;
|
|
PrefLoopAlignment = 2;
|
|
// FIXME: remove this to enable 64-bit SLP if performance looks good.
|
|
MinVectorRegisterBitWidth = 128;
|
|
break;
|
|
case TSV110:
|
|
CacheLineSize = 64;
|
|
PrefFunctionAlignment = 4;
|
|
PrefLoopAlignment = 2;
|
|
break;
|
|
}
|
|
}
|
|
|
|
AArch64Subtarget::AArch64Subtarget(const Triple &TT, const std::string &CPU,
|
|
const std::string &FS,
|
|
const TargetMachine &TM, bool LittleEndian)
|
|
: AArch64GenSubtargetInfo(TT, CPU, FS),
|
|
ReserveXRegister(AArch64::GPR64commonRegClass.getNumRegs()),
|
|
CustomCallSavedXRegs(AArch64::GPR64commonRegClass.getNumRegs()),
|
|
IsLittle(LittleEndian),
|
|
TargetTriple(TT), FrameLowering(),
|
|
InstrInfo(initializeSubtargetDependencies(FS, CPU)), TSInfo(),
|
|
TLInfo(TM, *this) {
|
|
if (AArch64::isX18ReservedByDefault(TT))
|
|
ReserveXRegister.set(18);
|
|
|
|
CallLoweringInfo.reset(new AArch64CallLowering(*getTargetLowering()));
|
|
Legalizer.reset(new AArch64LegalizerInfo(*this));
|
|
|
|
auto *RBI = new AArch64RegisterBankInfo(*getRegisterInfo());
|
|
|
|
// FIXME: At this point, we can't rely on Subtarget having RBI.
|
|
// It's awkward to mix passing RBI and the Subtarget; should we pass
|
|
// TII/TRI as well?
|
|
InstSelector.reset(createAArch64InstructionSelector(
|
|
*static_cast<const AArch64TargetMachine *>(&TM), *this, *RBI));
|
|
|
|
RegBankInfo.reset(RBI);
|
|
}
|
|
|
|
const CallLowering *AArch64Subtarget::getCallLowering() const {
|
|
return CallLoweringInfo.get();
|
|
}
|
|
|
|
const InstructionSelector *AArch64Subtarget::getInstructionSelector() const {
|
|
return InstSelector.get();
|
|
}
|
|
|
|
const LegalizerInfo *AArch64Subtarget::getLegalizerInfo() const {
|
|
return Legalizer.get();
|
|
}
|
|
|
|
const RegisterBankInfo *AArch64Subtarget::getRegBankInfo() const {
|
|
return RegBankInfo.get();
|
|
}
|
|
|
|
/// Find the target operand flags that describe how a global value should be
|
|
/// referenced for the current subtarget.
|
|
unsigned
|
|
AArch64Subtarget::ClassifyGlobalReference(const GlobalValue *GV,
|
|
const TargetMachine &TM) const {
|
|
// MachO large model always goes via a GOT, simply to get a single 8-byte
|
|
// absolute relocation on all global addresses.
|
|
if (TM.getCodeModel() == CodeModel::Large && isTargetMachO())
|
|
return AArch64II::MO_GOT;
|
|
|
|
if (!TM.shouldAssumeDSOLocal(*GV->getParent(), GV)) {
|
|
if (GV->hasDLLImportStorageClass())
|
|
return AArch64II::MO_GOT | AArch64II::MO_DLLIMPORT;
|
|
if (getTargetTriple().isOSWindows())
|
|
return AArch64II::MO_GOT | AArch64II::MO_COFFSTUB;
|
|
return AArch64II::MO_GOT;
|
|
}
|
|
|
|
// The small code model's direct accesses use ADRP, which cannot
|
|
// necessarily produce the value 0 (if the code is above 4GB).
|
|
// Same for the tiny code model, where we have a pc relative LDR.
|
|
if ((useSmallAddressing() || TM.getCodeModel() == CodeModel::Tiny) &&
|
|
GV->hasExternalWeakLinkage())
|
|
return AArch64II::MO_GOT;
|
|
|
|
// References to tagged globals are marked with MO_NC | MO_TAGGED to indicate
|
|
// that their nominal addresses are tagged and outside of the code model. In
|
|
// AArch64ExpandPseudo::expandMI we emit an additional instruction to set the
|
|
// tag if necessary based on MO_TAGGED.
|
|
if (AllowTaggedGlobals && !isa<FunctionType>(GV->getValueType()))
|
|
return AArch64II::MO_NC | AArch64II::MO_TAGGED;
|
|
|
|
return AArch64II::MO_NO_FLAG;
|
|
}
|
|
|
|
unsigned AArch64Subtarget::classifyGlobalFunctionReference(
|
|
const GlobalValue *GV, const TargetMachine &TM) const {
|
|
// MachO large model always goes via a GOT, because we don't have the
|
|
// relocations available to do anything else..
|
|
if (TM.getCodeModel() == CodeModel::Large && isTargetMachO() &&
|
|
!GV->hasInternalLinkage())
|
|
return AArch64II::MO_GOT;
|
|
|
|
// NonLazyBind goes via GOT unless we know it's available locally.
|
|
auto *F = dyn_cast<Function>(GV);
|
|
if (UseNonLazyBind && F && F->hasFnAttribute(Attribute::NonLazyBind) &&
|
|
!TM.shouldAssumeDSOLocal(*GV->getParent(), GV))
|
|
return AArch64II::MO_GOT;
|
|
|
|
return AArch64II::MO_NO_FLAG;
|
|
}
|
|
|
|
void AArch64Subtarget::overrideSchedPolicy(MachineSchedPolicy &Policy,
|
|
unsigned NumRegionInstrs) const {
|
|
// LNT run (at least on Cyclone) showed reasonably significant gains for
|
|
// bi-directional scheduling. 253.perlbmk.
|
|
Policy.OnlyTopDown = false;
|
|
Policy.OnlyBottomUp = false;
|
|
// Enabling or Disabling the latency heuristic is a close call: It seems to
|
|
// help nearly no benchmark on out-of-order architectures, on the other hand
|
|
// it regresses register pressure on a few benchmarking.
|
|
Policy.DisableLatencyHeuristic = DisableLatencySchedHeuristic;
|
|
}
|
|
|
|
bool AArch64Subtarget::enableEarlyIfConversion() const {
|
|
return EnableEarlyIfConvert;
|
|
}
|
|
|
|
bool AArch64Subtarget::supportsAddressTopByteIgnored() const {
|
|
if (!UseAddressTopByteIgnored)
|
|
return false;
|
|
|
|
if (TargetTriple.isiOS()) {
|
|
unsigned Major, Minor, Micro;
|
|
TargetTriple.getiOSVersion(Major, Minor, Micro);
|
|
return Major >= 8;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
std::unique_ptr<PBQPRAConstraint>
|
|
AArch64Subtarget::getCustomPBQPConstraints() const {
|
|
return balanceFPOps() ? llvm::make_unique<A57ChainingConstraint>() : nullptr;
|
|
}
|
|
|
|
void AArch64Subtarget::mirFileLoaded(MachineFunction &MF) const {
|
|
// We usually compute max call frame size after ISel. Do the computation now
|
|
// if the .mir file didn't specify it. Note that this will probably give you
|
|
// bogus values after PEI has eliminated the callframe setup/destroy pseudo
|
|
// instructions, specify explicitly if you need it to be correct.
|
|
MachineFrameInfo &MFI = MF.getFrameInfo();
|
|
if (!MFI.isMaxCallFrameSizeComputed())
|
|
MFI.computeMaxCallFrameSize(MF);
|
|
}
|