llvm-project/llvm/lib/CodeGen/MachineFunction.cpp

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

1215 lines
42 KiB
C++
Raw Normal View History

//===- MachineFunction.cpp ------------------------------------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
2002-10-28 09:16:38 +08:00
// Collect native machine code information for a function. This allows
// target-specific information about the generated code to be stored with each
// function.
//
//===----------------------------------------------------------------------===//
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/ADT/BitVector.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/DenseSet.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/Twine.h"
#include "llvm/Analysis/ConstantFolding.h"
#include "llvm/Analysis/EHPersonalities.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachineConstantPool.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineInstr.h"
#include "llvm/CodeGen/MachineJumpTableInfo.h"
#include "llvm/CodeGen/MachineMemOperand.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/PseudoSourceValue.h"
#include "llvm/CodeGen/TargetFrameLowering.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
#include "llvm/CodeGen/TargetLowering.h"
#include "llvm/CodeGen/TargetRegisterInfo.h"
#include "llvm/CodeGen/TargetSubtargetInfo.h"
#include "llvm/CodeGen/WasmEHFuncInfo.h"
#include "llvm/CodeGen/WinEHFuncInfo.h"
#include "llvm/Config/llvm-config.h"
#include "llvm/IR/Attributes.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Constant.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DebugInfoMetadata.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/ModuleSlotTracker.h"
#include "llvm/IR/Value.h"
#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCSymbol.h"
#include "llvm/MC/SectionKind.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/DOTGraphTraits.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
2006-10-04 04:19:23 +08:00
#include "llvm/Support/GraphWriter.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetMachine.h"
#include <algorithm>
#include <cassert>
#include <cstddef>
#include <cstdint>
#include <iterator>
#include <string>
#include <type_traits>
#include <utility>
#include <vector>
using namespace llvm;
[Modules] Make Support/Debug.h modular. This requires it to not change behavior based on other files defining DEBUG_TYPE, which means it cannot define DEBUG_TYPE at all. This is actually better IMO as it forces folks to define relevant DEBUG_TYPEs for their files. However, it requires all files that currently use DEBUG(...) to define a DEBUG_TYPE if they don't already. I've updated all such files in LLVM and will do the same for other upstream projects. This still leaves one important change in how LLVM uses the DEBUG_TYPE macro going forward: we need to only define the macro *after* header files have been #include-ed. Previously, this wasn't possible because Debug.h required the macro to be pre-defined. This commit removes that. By defining DEBUG_TYPE after the includes two things are fixed: - Header files that need to provide a DEBUG_TYPE for some inline code can do so by defining the macro before their inline code and undef-ing it afterward so the macro does not escape. - We no longer have rampant ODR violations due to including headers with different DEBUG_TYPE definitions. This may be mostly an academic violation today, but with modules these types of violations are easy to check for and potentially very relevant. Where necessary to suppor headers with DEBUG_TYPE, I have moved the definitions below the includes in this commit. I plan to move the rest of the DEBUG_TYPE macros in LLVM in subsequent commits; this one is big enough. The comments in Debug.h, which were hilariously out of date already, have been updated to reflect the recommended practice going forward. llvm-svn: 206822
2014-04-22 06:55:11 +08:00
#define DEBUG_TYPE "codegen"
static cl::opt<unsigned> AlignAllFunctions(
"align-all-functions",
cl::desc("Force the alignment of all functions in log2 format (e.g. 4 "
"means align on 16B boundaries)."),
cl::init(0), cl::Hidden);
static const char *getPropertyName(MachineFunctionProperties::Property Prop) {
using P = MachineFunctionProperties::Property;
switch(Prop) {
case P::FailedISel: return "FailedISel";
case P::IsSSA: return "IsSSA";
case P::Legalized: return "Legalized";
case P::NoPHIs: return "NoPHIs";
case P::NoVRegs: return "NoVRegs";
case P::RegBankSelected: return "RegBankSelected";
case P::Selected: return "Selected";
case P::TracksLiveness: return "TracksLiveness";
case P::TiedOpsRewritten: return "TiedOpsRewritten";
}
llvm_unreachable("Invalid machine function property");
}
// Pin the vtable to this file.
void MachineFunction::Delegate::anchor() {}
void MachineFunctionProperties::print(raw_ostream &OS) const {
const char *Separator = "";
for (BitVector::size_type I = 0; I < Properties.size(); ++I) {
if (!Properties[I])
continue;
OS << Separator << getPropertyName(static_cast<Property>(I));
Separator = ", ";
}
}
//===----------------------------------------------------------------------===//
// MachineFunction implementation
//===----------------------------------------------------------------------===//
// Out-of-line virtual method.
MachineFunctionInfo::~MachineFunctionInfo() = default;
void ilist_alloc_traits<MachineBasicBlock>::deleteNode(MachineBasicBlock *MBB) {
MBB->getParent()->DeleteMachineBasicBlock(MBB);
}
static inline unsigned getFnStackAlignment(const TargetSubtargetInfo *STI,
const Function &F) {
if (F.hasFnAttribute(Attribute::StackAlignment))
return F.getFnStackAlignment();
return STI->getFrameLowering()->getStackAlign().value();
}
MachineFunction::MachineFunction(Function &F, const LLVMTargetMachine &Target,
const TargetSubtargetInfo &STI,
unsigned FunctionNum, MachineModuleInfo &mmi)
: F(F), Target(Target), STI(&STI), Ctx(mmi.getContext()), MMI(mmi) {
FunctionNumber = FunctionNum;
init();
}
void MachineFunction::handleInsertion(MachineInstr &MI) {
if (TheDelegate)
TheDelegate->MF_HandleInsertion(MI);
}
void MachineFunction::handleRemoval(MachineInstr &MI) {
if (TheDelegate)
TheDelegate->MF_HandleRemoval(MI);
}
void MachineFunction::init() {
// Assume the function starts in SSA form with correct liveness.
Properties.set(MachineFunctionProperties::Property::IsSSA);
Properties.set(MachineFunctionProperties::Property::TracksLiveness);
if (STI->getRegisterInfo())
RegInfo = new (Allocator) MachineRegisterInfo(this);
else
RegInfo = nullptr;
MFInfo = nullptr;
// We can realign the stack if the target supports it and the user hasn't
// explicitly asked us not to.
bool CanRealignSP = STI->getFrameLowering()->isStackRealignable() &&
!F.hasFnAttribute("no-realign-stack");
FrameInfo = new (Allocator) MachineFrameInfo(
getFnStackAlignment(STI, F), /*StackRealignable=*/CanRealignSP,
/*ForcedRealign=*/CanRealignSP &&
F.hasFnAttribute(Attribute::StackAlignment));
if (F.hasFnAttribute(Attribute::StackAlignment))
FrameInfo->ensureMaxAlignment(*F.getFnStackAlign());
ConstantPool = new (Allocator) MachineConstantPool(getDataLayout());
Alignment = STI->getTargetLowering()->getMinFunctionAlignment();
// FIXME: Shouldn't use pref alignment if explicit alignment is set on F.
// FIXME: Use Function::hasOptSize().
if (!F.hasFnAttribute(Attribute::OptimizeForSize))
Alignment = std::max(Alignment,
STI->getTargetLowering()->getPrefFunctionAlignment());
if (AlignAllFunctions)
Alignment = Align(1ULL << AlignAllFunctions);
JumpTableInfo = nullptr;
if (isFuncletEHPersonality(classifyEHPersonality(
F.hasPersonalityFn() ? F.getPersonalityFn() : nullptr))) {
WinEHInfo = new (Allocator) WinEHFuncInfo();
}
if (isScopedEHPersonality(classifyEHPersonality(
F.hasPersonalityFn() ? F.getPersonalityFn() : nullptr))) {
WasmEHInfo = new (Allocator) WasmEHFuncInfo();
}
assert(Target.isCompatibleDataLayout(getDataLayout()) &&
"Can't create a MachineFunction using a Module with a "
"Target-incompatible DataLayout attached\n");
PSVManager =
std::make_unique<PseudoSourceValueManager>(*(getSubtarget().
getInstrInfo()));
}
MachineFunction::~MachineFunction() {
clear();
}
void MachineFunction::clear() {
Properties.reset();
// Don't call destructors on MachineInstr and MachineOperand. All of their
// memory comes from the BumpPtrAllocator which is about to be purged.
//
// Do call MachineBasicBlock destructors, it contains std::vectors.
for (iterator I = begin(), E = end(); I != E; I = BasicBlocks.erase(I))
I->Insts.clearAndLeakNodesUnsafely();
MBBNumbering.clear();
InstructionRecycler.clear(Allocator);
OperandRecycler.clear(Allocator);
BasicBlockRecycler.clear(Allocator);
CodeViewAnnotations.clear();
VariableDbgInfos.clear();
if (RegInfo) {
RegInfo->~MachineRegisterInfo();
Allocator.Deallocate(RegInfo);
}
if (MFInfo) {
MFInfo->~MachineFunctionInfo();
Allocator.Deallocate(MFInfo);
}
2012-06-20 07:37:57 +08:00
FrameInfo->~MachineFrameInfo();
Allocator.Deallocate(FrameInfo);
ConstantPool->~MachineConstantPool();
Allocator.Deallocate(ConstantPool);
if (JumpTableInfo) {
JumpTableInfo->~MachineJumpTableInfo();
Allocator.Deallocate(JumpTableInfo);
}
if (WinEHInfo) {
WinEHInfo->~WinEHFuncInfo();
Allocator.Deallocate(WinEHInfo);
}
if (WasmEHInfo) {
WasmEHInfo->~WasmEHFuncInfo();
Allocator.Deallocate(WasmEHInfo);
}
}
const DataLayout &MachineFunction::getDataLayout() const {
return F.getParent()->getDataLayout();
}
/// Get the JumpTableInfo for this function.
/// If it does not already exist, allocate one.
MachineJumpTableInfo *MachineFunction::
getOrCreateJumpTableInfo(unsigned EntryKind) {
if (JumpTableInfo) return JumpTableInfo;
2012-06-20 07:37:57 +08:00
JumpTableInfo = new (Allocator)
MachineJumpTableInfo((MachineJumpTableInfo::JTEntryKind)EntryKind);
return JumpTableInfo;
}
DenormalMode MachineFunction::getDenormalMode(const fltSemantics &FPType) const {
Consolidate internal denormal flushing controls Currently there are 4 different mechanisms for controlling denormal flushing behavior, and about as many equivalent frontend controls. - AMDGPU uses the fp32-denormals and fp64-f16-denormals subtarget features - NVPTX uses the nvptx-f32ftz attribute - ARM directly uses the denormal-fp-math attribute - Other targets indirectly use denormal-fp-math in one DAGCombine - cl-denorms-are-zero has a corresponding denorms-are-zero attribute AMDGPU wants a distinct control for f32 flushing from f16/f64, and as far as I can tell the same is true for NVPTX (based on the attribute name). Work on consolidating these into the denormal-fp-math attribute, and a new type specific denormal-fp-math-f32 variant. Only ARM seems to support the two different flush modes, so this is overkill for the other use cases. Ideally we would error on the unsupported positive-zero mode on other targets from somewhere. Move the logic for selecting the flush mode into the compiler driver, instead of handling it in cc1. denormal-fp-math/denormal-fp-math-f32 are now both cc1 flags, but denormal-fp-math-f32 is not yet exposed as a user flag. -cl-denorms-are-zero, -fcuda-flush-denormals-to-zero and -fno-cuda-flush-denormals-to-zero will be mapped to -fp-denormal-math-f32=ieee or preserve-sign rather than the old attributes. Stop emitting the denorms-are-zero attribute for the OpenCL flag. It has no in-tree users. The meaning would also be target dependent, such as the AMDGPU choice to treat this as only meaning allow flushing of f32 and not f16 or f64. The naming is also potentially confusing, since DAZ in other contexts refers to instructions implicitly treating input denormals as zero, not necessarily flushing output denormals to zero. This also does not attempt to change the behavior for the current attribute. The LangRef now states that the default is ieee behavior, but this is inaccurate for the current implementation. The clang handling is slightly hacky to avoid touching the existing denormal-fp-math uses. Fixing this will be left for a future patch. AMDGPU is still using the subtarget feature to control the denormal mode, but the new attribute are now emitted. A future change will switch this and remove the subtarget features.
2019-11-02 08:57:29 +08:00
if (&FPType == &APFloat::IEEEsingle()) {
Attribute Attr = F.getFnAttribute("denormal-fp-math-f32");
StringRef Val = Attr.getValueAsString();
if (!Val.empty())
return parseDenormalFPAttribute(Val);
// If the f32 variant of the attribute isn't specified, try to use the
// generic one.
}
// TODO: Should probably avoid the connection to the IR and store directly
// in the MachineFunction.
Attribute Attr = F.getFnAttribute("denormal-fp-math");
return parseDenormalFPAttribute(Attr.getValueAsString());
}
/// Should we be emitting segmented stack stuff for the function
bool MachineFunction::shouldSplitStack() const {
return getFunction().hasFnAttribute("split-stack");
}
LLVM_NODISCARD unsigned
MachineFunction::addFrameInst(const MCCFIInstruction &Inst) {
FrameInstructions.push_back(Inst);
return FrameInstructions.size() - 1;
}
/// This discards all of the MachineBasicBlock numbers and recomputes them.
/// This guarantees that the MBB numbers are sequential, dense, and match the
/// ordering of the blocks within the function. If a specific MachineBasicBlock
/// is specified, only that block and those after it are renumbered.
void MachineFunction::RenumberBlocks(MachineBasicBlock *MBB) {
if (empty()) { MBBNumbering.clear(); return; }
MachineFunction::iterator MBBI, E = end();
if (MBB == nullptr)
MBBI = begin();
else
MBBI = MBB->getIterator();
2012-06-20 07:37:57 +08:00
// Figure out the block number this should have.
unsigned BlockNo = 0;
2006-10-04 04:19:23 +08:00
if (MBBI != begin())
BlockNo = std::prev(MBBI)->getNumber() + 1;
2012-06-20 07:37:57 +08:00
for (; MBBI != E; ++MBBI, ++BlockNo) {
if (MBBI->getNumber() != (int)BlockNo) {
// Remove use of the old number.
if (MBBI->getNumber() != -1) {
assert(MBBNumbering[MBBI->getNumber()] == &*MBBI &&
"MBB number mismatch!");
MBBNumbering[MBBI->getNumber()] = nullptr;
}
2012-06-20 07:37:57 +08:00
// If BlockNo is already taken, set that block's number to -1.
if (MBBNumbering[BlockNo])
MBBNumbering[BlockNo]->setNumber(-1);
MBBNumbering[BlockNo] = &*MBBI;
MBBI->setNumber(BlockNo);
}
2012-06-20 07:37:57 +08:00
}
// Okay, all the blocks are renumbered. If we have compactified the block
// numbering, shrink MBBNumbering now.
assert(BlockNo <= MBBNumbering.size() && "Mismatch!");
MBBNumbering.resize(BlockNo);
}
/// This method iterates over the basic blocks and assigns their IsBeginSection
/// and IsEndSection fields. This must be called after MBB layout is finalized
/// and the SectionID's are assigned to MBBs.
void MachineFunction::assignBeginEndSections() {
front().setIsBeginSection();
auto CurrentSectionID = front().getSectionID();
for (auto MBBI = std::next(begin()), E = end(); MBBI != E; ++MBBI) {
if (MBBI->getSectionID() == CurrentSectionID)
continue;
MBBI->setIsBeginSection();
std::prev(MBBI)->setIsEndSection();
CurrentSectionID = MBBI->getSectionID();
}
back().setIsEndSection();
}
/// Allocate a new MachineInstr. Use this instead of `new MachineInstr'.
MachineInstr *MachineFunction::CreateMachineInstr(const MCInstrDesc &MCID,
const DebugLoc &DL,
bool NoImp) {
return new (InstructionRecycler.Allocate<MachineInstr>(Allocator))
MachineInstr(*this, MCID, DL, NoImp);
}
/// Create a new MachineInstr which is a copy of the 'Orig' instruction,
/// identical in all ways except the instruction has no parent, prev, or next.
MachineInstr *
MachineFunction::CloneMachineInstr(const MachineInstr *Orig) {
return new (InstructionRecycler.Allocate<MachineInstr>(Allocator))
MachineInstr(*this, *Orig);
}
MachineInstr &MachineFunction::CloneMachineInstrBundle(MachineBasicBlock &MBB,
MachineBasicBlock::iterator InsertBefore, const MachineInstr &Orig) {
MachineInstr *FirstClone = nullptr;
MachineBasicBlock::const_instr_iterator I = Orig.getIterator();
while (true) {
MachineInstr *Cloned = CloneMachineInstr(&*I);
MBB.insert(InsertBefore, Cloned);
if (FirstClone == nullptr) {
FirstClone = Cloned;
} else {
Cloned->bundleWithPred();
}
if (!I->isBundledWithSucc())
break;
++I;
}
// Copy over call site info to the cloned instruction if needed. If Orig is in
// a bundle, copyCallSiteInfo takes care of finding the call instruction in
// the bundle.
if (Orig.shouldUpdateCallSiteInfo())
copyCallSiteInfo(&Orig, FirstClone);
return *FirstClone;
}
/// Delete the given MachineInstr.
///
/// This function also serves as the MachineInstr destructor - the real
/// ~MachineInstr() destructor must be empty.
void
MachineFunction::DeleteMachineInstr(MachineInstr *MI) {
// Verify that a call site info is at valid state. This assertion should
// be triggered during the implementation of support for the
// call site info of a new architecture. If the assertion is triggered,
// back trace will tell where to insert a call to updateCallSiteInfo().
assert((!MI->isCandidateForCallSiteEntry() ||
CallSitesInfo.find(MI) == CallSitesInfo.end()) &&
"Call site info was not updated!");
// Strip it for parts. The operand array and the MI object itself are
// independently recyclable.
if (MI->Operands)
deallocateOperandArray(MI->CapOperands, MI->Operands);
// Don't call ~MachineInstr() which must be trivial anyway because
// ~MachineFunction drops whole lists of MachineInstrs wihout calling their
// destructors.
InstructionRecycler.Deallocate(Allocator, MI);
}
/// Allocate a new MachineBasicBlock. Use this instead of
/// `new MachineBasicBlock'.
MachineBasicBlock *
MachineFunction::CreateMachineBasicBlock(const BasicBlock *bb) {
return new (BasicBlockRecycler.Allocate<MachineBasicBlock>(Allocator))
MachineBasicBlock(*this, bb);
}
/// Delete the given MachineBasicBlock.
void
MachineFunction::DeleteMachineBasicBlock(MachineBasicBlock *MBB) {
assert(MBB->getParent() == this && "MBB parent mismatch!");
MBB->~MachineBasicBlock();
BasicBlockRecycler.Deallocate(Allocator, MBB);
}
MachineMemOperand *MachineFunction::getMachineMemOperand(
MachinePointerInfo PtrInfo, MachineMemOperand::Flags f, uint64_t s,
Align base_alignment, const AAMDNodes &AAInfo, const MDNode *Ranges,
SyncScope::ID SSID, AtomicOrdering Ordering,
AtomicOrdering FailureOrdering) {
return new (Allocator)
MachineMemOperand(PtrInfo, f, s, base_alignment, AAInfo, Ranges,
SSID, Ordering, FailureOrdering);
}
MachineMemOperand *MachineFunction::getMachineMemOperand(
const MachineMemOperand *MMO, MachinePointerInfo &PtrInfo, uint64_t Size) {
return new (Allocator) MachineMemOperand(
PtrInfo, MMO->getFlags(), Size, MMO->getBaseAlign(), AAMDNodes(), nullptr,
MMO->getSyncScopeID(), MMO->getOrdering(), MMO->getFailureOrdering());
}
MachineMemOperand *
MachineFunction::getMachineMemOperand(const MachineMemOperand *MMO,
int64_t Offset, uint64_t Size) {
const MachinePointerInfo &PtrInfo = MMO->getPointerInfo();
// If there is no pointer value, the offset isn't tracked so we need to adjust
// the base alignment.
Align Alignment = PtrInfo.V.isNull()
? commonAlignment(MMO->getBaseAlign(), Offset)
: MMO->getBaseAlign();
// Do not preserve ranges, since we don't necessarily know what the high bits
// are anymore.
return new (Allocator)
MachineMemOperand(PtrInfo.getWithOffset(Offset), MMO->getFlags(), Size,
Alignment, MMO->getAAInfo(), nullptr, MMO->getSyncScopeID(),
MMO->getOrdering(), MMO->getFailureOrdering());
}
MachineMemOperand *
MachineFunction::getMachineMemOperand(const MachineMemOperand *MMO,
const AAMDNodes &AAInfo) {
MachinePointerInfo MPI = MMO->getValue() ?
MachinePointerInfo(MMO->getValue(), MMO->getOffset()) :
MachinePointerInfo(MMO->getPseudoValue(), MMO->getOffset());
return new (Allocator) MachineMemOperand(
MPI, MMO->getFlags(), MMO->getSize(), MMO->getBaseAlign(), AAInfo,
MMO->getRanges(), MMO->getSyncScopeID(), MMO->getOrdering(),
MMO->getFailureOrdering());
}
MachineMemOperand *
MachineFunction::getMachineMemOperand(const MachineMemOperand *MMO,
MachineMemOperand::Flags Flags) {
return new (Allocator) MachineMemOperand(
MMO->getPointerInfo(), Flags, MMO->getSize(), MMO->getBaseAlign(),
MMO->getAAInfo(), MMO->getRanges(), MMO->getSyncScopeID(),
MMO->getOrdering(), MMO->getFailureOrdering());
}
MachineInstr::ExtraInfo *MachineFunction::createMIExtraInfo(
ArrayRef<MachineMemOperand *> MMOs, MCSymbol *PreInstrSymbol,
MCSymbol *PostInstrSymbol, MDNode *HeapAllocMarker) {
[MI] Change the array of `MachineMemOperand` pointers to be a generically extensible collection of extra info attached to a `MachineInstr`. The primary change here is cleaning up the APIs used for setting and manipulating the `MachineMemOperand` pointer arrays so chat we can change how they are allocated. Then we introduce an extra info object that using the trailing object pattern to attach some number of MMOs but also other extra info. The design of this is specifically so that this extra info has a fixed necessary cost (the header tracking what extra info is included) and everything else can be tail allocated. This pattern works especially well with a `BumpPtrAllocator` which we use here. I've also added the basic scaffolding for putting interesting pointers into this, namely pre- and post-instruction symbols. These aren't used anywhere yet, they're just there to ensure I've actually gotten the data structure types correct. I'll flesh out support for these in a subsequent patch (MIR dumping, parsing, the works). Finally, I've included an optimization where we store any single pointer inline in the `MachineInstr` to avoid the allocation overhead. This is expected to be the overwhelmingly most common case and so should avoid any memory usage growth due to slightly less clever / dense allocation when dealing with >1 MMO. This did require several ergonomic improvements to the `PointerSumType` to reasonably support the various usage models. This also has a side effect of freeing up 8 bits within the `MachineInstr` which could be repurposed for something else. The suggested direction here came largely from Hal Finkel. I hope it was worth it. ;] It does hopefully clear a path for subsequent extensions w/o nearly as much leg work. Lots of thanks to Reid and Justin for careful reviews and ideas about how to do all of this. Differential Revision: https://reviews.llvm.org/D50701 llvm-svn: 339940
2018-08-17 05:30:05 +08:00
return MachineInstr::ExtraInfo::create(Allocator, MMOs, PreInstrSymbol,
PostInstrSymbol, HeapAllocMarker);
}
const char *MachineFunction::createExternalSymbolName(StringRef Name) {
char *Dest = Allocator.Allocate<char>(Name.size() + 1);
2018-11-17 09:44:25 +08:00
llvm::copy(Name, Dest);
Dest[Name.size()] = 0;
return Dest;
}
uint32_t *MachineFunction::allocateRegMask() {
unsigned NumRegs = getSubtarget().getRegisterInfo()->getNumRegs();
unsigned Size = MachineOperand::getRegMaskSize(NumRegs);
uint32_t *Mask = Allocator.Allocate<uint32_t>(Size);
memset(Mask, 0, Size * sizeof(Mask[0]));
return Mask;
}
ArrayRef<int> MachineFunction::allocateShuffleMask(ArrayRef<int> Mask) {
int* AllocMask = Allocator.Allocate<int>(Mask.size());
copy(Mask, AllocMask);
return {AllocMask, Mask.size()};
}
#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
LLVM_DUMP_METHOD void MachineFunction::dump() const {
print(dbgs());
}
#endif
StringRef MachineFunction::getName() const {
return getFunction().getName();
}
void MachineFunction::print(raw_ostream &OS, const SlotIndexes *Indexes) const {
OS << "# Machine code for function " << getName() << ": ";
getProperties().print(OS);
OS << '\n';
// Print Frame Information
FrameInfo->print(*this, OS);
2012-06-20 07:37:57 +08:00
// Print JumpTable Information
if (JumpTableInfo)
JumpTableInfo->print(OS);
// Print Constant Pool
ConstantPool->print(OS);
2012-06-20 07:37:57 +08:00
const TargetRegisterInfo *TRI = getSubtarget().getRegisterInfo();
2012-06-20 07:37:57 +08:00
if (RegInfo && !RegInfo->livein_empty()) {
OS << "Function Live Ins: ";
for (MachineRegisterInfo::livein_iterator
I = RegInfo->livein_begin(), E = RegInfo->livein_end(); I != E; ++I) {
OS << printReg(I->first, TRI);
if (I->second)
OS << " in " << printReg(I->second, TRI);
if (std::next(I) != E)
OS << ", ";
}
OS << '\n';
}
2012-06-20 07:37:57 +08:00
ModuleSlotTracker MST(getFunction().getParent());
MST.incorporateFunction(getFunction());
for (const auto &BB : *this) {
OS << '\n';
// If we print the whole function, print it at its most verbose level.
BB.print(OS, MST, Indexes, /*IsStandalone=*/true);
}
OS << "\n# End machine code for function " << getName() << ".\n\n";
}
/// True if this function needs frame moves for debug or exceptions.
bool MachineFunction::needsFrameMoves() const {
return getMMI().hasDebugInfo() ||
getTarget().Options.ForceDwarfFrameSection ||
F.needsUnwindTableEntry();
}
namespace llvm {
template<>
struct DOTGraphTraits<const MachineFunction*> : public DefaultDOTGraphTraits {
DOTGraphTraits(bool isSimple = false) : DefaultDOTGraphTraits(isSimple) {}
static std::string getGraphName(const MachineFunction *F) {
return ("CFG for '" + F->getName() + "' function").str();
}
std::string getNodeLabel(const MachineBasicBlock *Node,
const MachineFunction *Graph) {
std::string OutStr;
{
raw_string_ostream OSS(OutStr);
if (isSimple()) {
OSS << printMBBReference(*Node);
if (const BasicBlock *BB = Node->getBasicBlock())
OSS << ": " << BB->getName();
} else
Node->print(OSS);
}
if (OutStr[0] == '\n') OutStr.erase(OutStr.begin());
// Process string output to make it nicer...
for (unsigned i = 0; i != OutStr.length(); ++i)
if (OutStr[i] == '\n') { // Left justify
OutStr[i] = '\\';
OutStr.insert(OutStr.begin()+i+1, 'l');
}
return OutStr;
}
};
} // end namespace llvm
void MachineFunction::viewCFG() const
{
#ifndef NDEBUG
ViewGraph(this, "mf" + getName());
#else
errs() << "MachineFunction::viewCFG is only available in debug builds on "
<< "systems with Graphviz or gv!\n";
#endif // NDEBUG
}
void MachineFunction::viewCFGOnly() const
{
#ifndef NDEBUG
ViewGraph(this, "mf" + getName(), true);
#else
errs() << "MachineFunction::viewCFGOnly is only available in debug builds on "
<< "systems with Graphviz or gv!\n";
#endif // NDEBUG
}
/// Add the specified physical register as a live-in value and
/// create a corresponding virtual register for it.
2020-05-20 01:01:19 +08:00
Register MachineFunction::addLiveIn(MCRegister PReg,
const TargetRegisterClass *RC) {
MachineRegisterInfo &MRI = getRegInfo();
2020-05-20 01:01:19 +08:00
Register VReg = MRI.getLiveInVirtReg(PReg);
if (VReg) {
const TargetRegisterClass *VRegRC = MRI.getRegClass(VReg);
(void)VRegRC;
// A physical register can be added several times.
// Between two calls, the register class of the related virtual register
// may have been constrained to match some operation constraints.
// In that case, check that the current register class includes the
// physical register and is a sub class of the specified RC.
assert((VRegRC == RC || (VRegRC->contains(PReg) &&
RC->hasSubClassEq(VRegRC))) &&
"Register class mismatch!");
return VReg;
}
VReg = MRI.createVirtualRegister(RC);
MRI.addLiveIn(PReg, VReg);
return VReg;
}
/// Return the MCSymbol for the specified non-empty jump table.
/// If isLinkerPrivate is specified, an 'l' label is returned, otherwise a
/// normal 'L' label is returned.
2014-06-25 20:40:56 +08:00
MCSymbol *MachineFunction::getJTISymbol(unsigned JTI, MCContext &Ctx,
bool isLinkerPrivate) const {
const DataLayout &DL = getDataLayout();
assert(JumpTableInfo && "No jump tables");
assert(JTI < JumpTableInfo->getJumpTables().size() && "Invalid JTI!");
2012-06-20 07:37:57 +08:00
StringRef Prefix = isLinkerPrivate ? DL.getLinkerPrivateGlobalPrefix()
: DL.getPrivateGlobalPrefix();
SmallString<60> Name;
raw_svector_ostream(Name)
<< Prefix << "JTI" << getFunctionNumber() << '_' << JTI;
return Ctx.getOrCreateSymbol(Name);
}
/// Return a function-local symbol to represent the PIC base.
MCSymbol *MachineFunction::getPICBaseSymbol() const {
const DataLayout &DL = getDataLayout();
return Ctx.getOrCreateSymbol(Twine(DL.getPrivateGlobalPrefix()) +
Twine(getFunctionNumber()) + "$pb");
}
/// \name Exception Handling
/// \{
LandingPadInfo &
MachineFunction::getOrCreateLandingPadInfo(MachineBasicBlock *LandingPad) {
unsigned N = LandingPads.size();
for (unsigned i = 0; i < N; ++i) {
LandingPadInfo &LP = LandingPads[i];
if (LP.LandingPadBlock == LandingPad)
return LP;
}
LandingPads.push_back(LandingPadInfo(LandingPad));
return LandingPads[N];
}
void MachineFunction::addInvoke(MachineBasicBlock *LandingPad,
MCSymbol *BeginLabel, MCSymbol *EndLabel) {
LandingPadInfo &LP = getOrCreateLandingPadInfo(LandingPad);
LP.BeginLabels.push_back(BeginLabel);
LP.EndLabels.push_back(EndLabel);
}
MCSymbol *MachineFunction::addLandingPad(MachineBasicBlock *LandingPad) {
MCSymbol *LandingPadLabel = Ctx.createTempSymbol();
LandingPadInfo &LP = getOrCreateLandingPadInfo(LandingPad);
LP.LandingPadLabel = LandingPadLabel;
const Instruction *FirstI = LandingPad->getBasicBlock()->getFirstNonPHI();
if (const auto *LPI = dyn_cast<LandingPadInst>(FirstI)) {
if (const auto *PF =
dyn_cast<Function>(F.getPersonalityFn()->stripPointerCasts()))
getMMI().addPersonality(PF);
if (LPI->isCleanup())
addCleanup(LandingPad);
// FIXME: New EH - Add the clauses in reverse order. This isn't 100%
// correct, but we need to do it this way because of how the DWARF EH
// emitter processes the clauses.
for (unsigned I = LPI->getNumClauses(); I != 0; --I) {
Value *Val = LPI->getClause(I - 1);
if (LPI->isCatch(I - 1)) {
addCatchTypeInfo(LandingPad,
dyn_cast<GlobalValue>(Val->stripPointerCasts()));
} else {
// Add filters in a list.
auto *CVal = cast<Constant>(Val);
SmallVector<const GlobalValue *, 4> FilterList;
for (User::op_iterator II = CVal->op_begin(), IE = CVal->op_end();
II != IE; ++II)
FilterList.push_back(cast<GlobalValue>((*II)->stripPointerCasts()));
addFilterTypeInfo(LandingPad, FilterList);
}
}
} else if (const auto *CPI = dyn_cast<CatchPadInst>(FirstI)) {
for (unsigned I = CPI->getNumArgOperands(); I != 0; --I) {
Value *TypeInfo = CPI->getArgOperand(I - 1)->stripPointerCasts();
addCatchTypeInfo(LandingPad, dyn_cast<GlobalValue>(TypeInfo));
}
} else {
assert(isa<CleanupPadInst>(FirstI) && "Invalid landingpad!");
}
return LandingPadLabel;
}
void MachineFunction::addCatchTypeInfo(MachineBasicBlock *LandingPad,
ArrayRef<const GlobalValue *> TyInfo) {
LandingPadInfo &LP = getOrCreateLandingPadInfo(LandingPad);
for (unsigned N = TyInfo.size(); N; --N)
LP.TypeIds.push_back(getTypeIDFor(TyInfo[N - 1]));
}
void MachineFunction::addFilterTypeInfo(MachineBasicBlock *LandingPad,
ArrayRef<const GlobalValue *> TyInfo) {
LandingPadInfo &LP = getOrCreateLandingPadInfo(LandingPad);
std::vector<unsigned> IdsInFilter(TyInfo.size());
for (unsigned I = 0, E = TyInfo.size(); I != E; ++I)
IdsInFilter[I] = getTypeIDFor(TyInfo[I]);
LP.TypeIds.push_back(getFilterIDFor(IdsInFilter));
}
void MachineFunction::tidyLandingPads(DenseMap<MCSymbol *, uintptr_t> *LPMap,
bool TidyIfNoBeginLabels) {
for (unsigned i = 0; i != LandingPads.size(); ) {
LandingPadInfo &LandingPad = LandingPads[i];
if (LandingPad.LandingPadLabel &&
!LandingPad.LandingPadLabel->isDefined() &&
(!LPMap || (*LPMap)[LandingPad.LandingPadLabel] == 0))
LandingPad.LandingPadLabel = nullptr;
// Special case: we *should* emit LPs with null LP MBB. This indicates
// "nounwind" case.
if (!LandingPad.LandingPadLabel && LandingPad.LandingPadBlock) {
LandingPads.erase(LandingPads.begin() + i);
continue;
}
if (TidyIfNoBeginLabels) {
for (unsigned j = 0, e = LandingPads[i].BeginLabels.size(); j != e; ++j) {
MCSymbol *BeginLabel = LandingPad.BeginLabels[j];
MCSymbol *EndLabel = LandingPad.EndLabels[j];
if ((BeginLabel->isDefined() || (LPMap && (*LPMap)[BeginLabel] != 0)) &&
(EndLabel->isDefined() || (LPMap && (*LPMap)[EndLabel] != 0)))
continue;
LandingPad.BeginLabels.erase(LandingPad.BeginLabels.begin() + j);
LandingPad.EndLabels.erase(LandingPad.EndLabels.begin() + j);
--j;
--e;
}
// Remove landing pads with no try-ranges.
if (LandingPads[i].BeginLabels.empty()) {
LandingPads.erase(LandingPads.begin() + i);
continue;
}
}
// If there is no landing pad, ensure that the list of typeids is empty.
// If the only typeid is a cleanup, this is the same as having no typeids.
if (!LandingPad.LandingPadBlock ||
(LandingPad.TypeIds.size() == 1 && !LandingPad.TypeIds[0]))
LandingPad.TypeIds.clear();
++i;
}
}
void MachineFunction::addCleanup(MachineBasicBlock *LandingPad) {
LandingPadInfo &LP = getOrCreateLandingPadInfo(LandingPad);
LP.TypeIds.push_back(0);
}
void MachineFunction::addSEHCatchHandler(MachineBasicBlock *LandingPad,
const Function *Filter,
const BlockAddress *RecoverBA) {
LandingPadInfo &LP = getOrCreateLandingPadInfo(LandingPad);
SEHHandler Handler;
Handler.FilterOrFinally = Filter;
Handler.RecoverBA = RecoverBA;
LP.SEHHandlers.push_back(Handler);
}
void MachineFunction::addSEHCleanupHandler(MachineBasicBlock *LandingPad,
const Function *Cleanup) {
LandingPadInfo &LP = getOrCreateLandingPadInfo(LandingPad);
SEHHandler Handler;
Handler.FilterOrFinally = Cleanup;
Handler.RecoverBA = nullptr;
LP.SEHHandlers.push_back(Handler);
}
void MachineFunction::setCallSiteLandingPad(MCSymbol *Sym,
ArrayRef<unsigned> Sites) {
LPadToCallSiteMap[Sym].append(Sites.begin(), Sites.end());
}
unsigned MachineFunction::getTypeIDFor(const GlobalValue *TI) {
for (unsigned i = 0, N = TypeInfos.size(); i != N; ++i)
if (TypeInfos[i] == TI) return i + 1;
TypeInfos.push_back(TI);
return TypeInfos.size();
}
int MachineFunction::getFilterIDFor(std::vector<unsigned> &TyIds) {
// If the new filter coincides with the tail of an existing filter, then
// re-use the existing filter. Folding filters more than this requires
// re-ordering filters and/or their elements - probably not worth it.
for (std::vector<unsigned>::iterator I = FilterEnds.begin(),
E = FilterEnds.end(); I != E; ++I) {
unsigned i = *I, j = TyIds.size();
while (i && j)
if (FilterIds[--i] != TyIds[--j])
goto try_next;
if (!j)
// The new filter coincides with range [i, end) of the existing filter.
return -(1 + i);
try_next:;
}
// Add the new filter.
int FilterID = -(1 + FilterIds.size());
FilterIds.reserve(FilterIds.size() + TyIds.size() + 1);
FilterIds.insert(FilterIds.end(), TyIds.begin(), TyIds.end());
FilterEnds.push_back(FilterIds.size());
FilterIds.push_back(0); // terminator
return FilterID;
}
MachineFunction::CallSiteInfoMap::iterator
MachineFunction::getCallSiteInfo(const MachineInstr *MI) {
assert(MI->isCandidateForCallSiteEntry() &&
"Call site info refers only to call (MI) candidates");
if (!Target.Options.EmitCallSiteInfo)
return CallSitesInfo.end();
return CallSitesInfo.find(MI);
}
/// Return the call machine instruction or find a call within bundle.
static const MachineInstr *getCallInstr(const MachineInstr *MI) {
if (!MI->isBundle())
return MI;
for (auto &BMI : make_range(getBundleStart(MI->getIterator()),
getBundleEnd(MI->getIterator())))
if (BMI.isCandidateForCallSiteEntry())
return &BMI;
llvm_unreachable("Unexpected bundle without a call site candidate");
}
void MachineFunction::eraseCallSiteInfo(const MachineInstr *MI) {
assert(MI->shouldUpdateCallSiteInfo() &&
"Call site info refers only to call (MI) candidates or "
"candidates inside bundles");
const MachineInstr *CallMI = getCallInstr(MI);
CallSiteInfoMap::iterator CSIt = getCallSiteInfo(CallMI);
if (CSIt == CallSitesInfo.end())
return;
CallSitesInfo.erase(CSIt);
}
void MachineFunction::copyCallSiteInfo(const MachineInstr *Old,
const MachineInstr *New) {
assert(Old->shouldUpdateCallSiteInfo() &&
"Call site info refers only to call (MI) candidates or "
"candidates inside bundles");
if (!New->isCandidateForCallSiteEntry())
return eraseCallSiteInfo(Old);
const MachineInstr *OldCallMI = getCallInstr(Old);
CallSiteInfoMap::iterator CSIt = getCallSiteInfo(OldCallMI);
if (CSIt == CallSitesInfo.end())
return;
CallSiteInfo CSInfo = CSIt->second;
CallSitesInfo[New] = CSInfo;
}
void MachineFunction::moveCallSiteInfo(const MachineInstr *Old,
const MachineInstr *New) {
assert(Old->shouldUpdateCallSiteInfo() &&
"Call site info refers only to call (MI) candidates or "
"candidates inside bundles");
if (!New->isCandidateForCallSiteEntry())
return eraseCallSiteInfo(Old);
const MachineInstr *OldCallMI = getCallInstr(Old);
CallSiteInfoMap::iterator CSIt = getCallSiteInfo(OldCallMI);
if (CSIt == CallSitesInfo.end())
return;
CallSiteInfo CSInfo = std::move(CSIt->second);
CallSitesInfo.erase(CSIt);
CallSitesInfo[New] = CSInfo;
}
/// \}
//===----------------------------------------------------------------------===//
// MachineJumpTableInfo implementation
//===----------------------------------------------------------------------===//
/// Return the size of each entry in the jump table.
unsigned MachineJumpTableInfo::getEntrySize(const DataLayout &TD) const {
// The size of a jump table entry is 4 bytes unless the entry is just the
// address of a block, in which case it is the pointer size.
switch (getEntryKind()) {
case MachineJumpTableInfo::EK_BlockAddress:
Revert the majority of the next patch in the address space series: r165941: Resubmit the changes to llvm core to update the functions to support different pointer sizes on a per address space basis. Despite this commit log, this change primarily changed stuff outside of VMCore, and those changes do not carry any tests for correctness (or even plausibility), and we have consistently found questionable or flat out incorrect cases in these changes. Most of them are probably correct, but we need to devise a system that makes it more clear when we have handled the address space concerns correctly, and ideally each pass that gets updated would receive an accompanying test case that exercises that pass specificaly w.r.t. alternate address spaces. However, from this commit, I have retained the new C API entry points. Those were an orthogonal change that probably should have been split apart, but they seem entirely good. In several places the changes were very obvious cleanups with no actual multiple address space code added; these I have not reverted when I spotted them. In a few other places there were merge conflicts due to a cleaner solution being implemented later, often not using address spaces at all. In those cases, I've preserved the new code which isn't address space dependent. This is part of my ongoing effort to clean out the partial address space code which carries high risk and low test coverage, and not likely to be finished before the 3.2 release looms closer. Duncan and I would both like to see the above issues addressed before we return to these changes. llvm-svn: 167222
2012-11-01 17:14:31 +08:00
return TD.getPointerSize();
case MachineJumpTableInfo::EK_GPRel64BlockAddress:
return 8;
case MachineJumpTableInfo::EK_GPRel32BlockAddress:
case MachineJumpTableInfo::EK_LabelDifference32:
case MachineJumpTableInfo::EK_Custom32:
return 4;
case MachineJumpTableInfo::EK_Inline:
return 0;
}
llvm_unreachable("Unknown jump table encoding!");
}
/// Return the alignment of each entry in the jump table.
unsigned MachineJumpTableInfo::getEntryAlignment(const DataLayout &TD) const {
// The alignment of a jump table entry is the alignment of int32 unless the
// entry is just the address of a block, in which case it is the pointer
// alignment.
switch (getEntryKind()) {
case MachineJumpTableInfo::EK_BlockAddress:
return TD.getPointerABIAlignment(0).value();
case MachineJumpTableInfo::EK_GPRel64BlockAddress:
return TD.getABIIntegerTypeAlignment(64).value();
case MachineJumpTableInfo::EK_GPRel32BlockAddress:
case MachineJumpTableInfo::EK_LabelDifference32:
case MachineJumpTableInfo::EK_Custom32:
return TD.getABIIntegerTypeAlignment(32).value();
case MachineJumpTableInfo::EK_Inline:
return 1;
}
llvm_unreachable("Unknown jump table encoding!");
}
/// Create a new jump table entry in the jump table info.
unsigned MachineJumpTableInfo::createJumpTableIndex(
const std::vector<MachineBasicBlock*> &DestBBs) {
2006-10-29 02:11:20 +08:00
assert(!DestBBs.empty() && "Cannot create an empty jump table!");
JumpTables.push_back(MachineJumpTableEntry(DestBBs));
return JumpTables.size()-1;
}
/// If Old is the target of any jump tables, update the jump tables to branch
/// to New instead.
bool MachineJumpTableInfo::ReplaceMBBInJumpTables(MachineBasicBlock *Old,
MachineBasicBlock *New) {
assert(Old != New && "Not making a change?");
bool MadeChange = false;
for (size_t i = 0, e = JumpTables.size(); i != e; ++i)
ReplaceMBBInJumpTable(i, Old, New);
return MadeChange;
}
/// If Old is a target of the jump tables, update the jump table to branch to
/// New instead.
bool MachineJumpTableInfo::ReplaceMBBInJumpTable(unsigned Idx,
MachineBasicBlock *Old,
MachineBasicBlock *New) {
assert(Old != New && "Not making a change?");
bool MadeChange = false;
MachineJumpTableEntry &JTE = JumpTables[Idx];
for (size_t j = 0, e = JTE.MBBs.size(); j != e; ++j)
if (JTE.MBBs[j] == Old) {
JTE.MBBs[j] = New;
MadeChange = true;
}
return MadeChange;
}
void MachineJumpTableInfo::print(raw_ostream &OS) const {
if (JumpTables.empty()) return;
OS << "Jump Tables:\n";
for (unsigned i = 0, e = JumpTables.size(); i != e; ++i) {
OS << printJumpTableEntryReference(i) << ':';
for (unsigned j = 0, f = JumpTables[i].MBBs.size(); j != f; ++j)
OS << ' ' << printMBBReference(*JumpTables[i].MBBs[j]);
if (i != e)
OS << '\n';
}
OS << '\n';
}
#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
LLVM_DUMP_METHOD void MachineJumpTableInfo::dump() const { print(dbgs()); }
#endif
Printable llvm::printJumpTableEntryReference(unsigned Idx) {
return Printable([Idx](raw_ostream &OS) { OS << "%jump-table." << Idx; });
}
//===----------------------------------------------------------------------===//
// MachineConstantPool implementation
//===----------------------------------------------------------------------===//
void MachineConstantPoolValue::anchor() {}
Type *MachineConstantPoolEntry::getType() const {
if (isMachineConstantPoolEntry())
return Val.MachineCPVal->getType();
return Val.ConstVal->getType();
}
bool MachineConstantPoolEntry::needsRelocation() const {
if (isMachineConstantPoolEntry())
return true;
return Val.ConstVal->needsRelocation();
}
SectionKind
MachineConstantPoolEntry::getSectionKind(const DataLayout *DL) const {
if (needsRelocation())
return SectionKind::getReadOnlyWithRel();
switch (DL->getTypeAllocSize(getType())) {
case 4:
return SectionKind::getMergeableConst4();
case 8:
return SectionKind::getMergeableConst8();
case 16:
return SectionKind::getMergeableConst16();
case 32:
return SectionKind::getMergeableConst32();
default:
return SectionKind::getReadOnly();
}
}
MachineConstantPool::~MachineConstantPool() {
// A constant may be a member of both Constants and MachineCPVsSharingEntries,
// so keep track of which we've deleted to avoid double deletions.
DenseSet<MachineConstantPoolValue*> Deleted;
for (unsigned i = 0, e = Constants.size(); i != e; ++i)
if (Constants[i].isMachineConstantPoolEntry()) {
Deleted.insert(Constants[i].Val.MachineCPVal);
delete Constants[i].Val.MachineCPVal;
}
for (DenseSet<MachineConstantPoolValue*>::iterator I =
MachineCPVsSharingEntries.begin(), E = MachineCPVsSharingEntries.end();
I != E; ++I) {
if (Deleted.count(*I) == 0)
delete *I;
}
}
/// Test whether the given two constants can be allocated the same constant pool
/// entry.
static bool CanShareConstantPoolEntry(const Constant *A, const Constant *B,
const DataLayout &DL) {
// Handle the trivial case quickly.
if (A == B) return true;
// If they have the same type but weren't the same constant, quickly
// reject them.
if (A->getType() == B->getType()) return false;
// We can't handle structs or arrays.
if (isa<StructType>(A->getType()) || isa<ArrayType>(A->getType()) ||
isa<StructType>(B->getType()) || isa<ArrayType>(B->getType()))
return false;
2014-06-25 20:40:56 +08:00
// For now, only support constants with the same size.
uint64_t StoreSize = DL.getTypeStoreSize(A->getType());
if (StoreSize != DL.getTypeStoreSize(B->getType()) || StoreSize > 128)
return false;
Type *IntTy = IntegerType::get(A->getContext(), StoreSize*8);
// Try constant folding a bitcast of both instructions to an integer. If we
// get two identical ConstantInt's, then we are good to share them. We use
// the constant folding APIs to do this so that we get the benefit of
// DataLayout.
if (isa<PointerType>(A->getType()))
A = ConstantFoldCastOperand(Instruction::PtrToInt,
const_cast<Constant *>(A), IntTy, DL);
else if (A->getType() != IntTy)
A = ConstantFoldCastOperand(Instruction::BitCast, const_cast<Constant *>(A),
IntTy, DL);
if (isa<PointerType>(B->getType()))
B = ConstantFoldCastOperand(Instruction::PtrToInt,
const_cast<Constant *>(B), IntTy, DL);
else if (B->getType() != IntTy)
B = ConstantFoldCastOperand(Instruction::BitCast, const_cast<Constant *>(B),
IntTy, DL);
2012-06-20 07:37:57 +08:00
return A == B;
}
/// Create a new entry in the constant pool or return an existing one.
/// User must specify the log2 of the minimum required alignment for the object.
2014-06-25 20:40:56 +08:00
unsigned MachineConstantPool::getConstantPoolIndex(const Constant *C,
Align Alignment) {
if (Alignment > PoolAlignment) PoolAlignment = Alignment;
// Check to see if we already have this constant.
//
// FIXME, this could be made much more efficient for large constant pools.
for (unsigned i = 0, e = Constants.size(); i != e; ++i)
if (!Constants[i].isMachineConstantPoolEntry() &&
CanShareConstantPoolEntry(Constants[i].Val.ConstVal, C, DL)) {
if (Constants[i].getAlign() < Alignment)
Constants[i].Alignment = Alignment;
return i;
}
2012-06-20 07:37:57 +08:00
Fix some significant problems with constant pools that resulted in unnecessary paddings between constant pool entries, larger than necessary alignments (e.g. 8 byte alignment for .literal4 sections), and potentially other issues. 1. ConstantPoolSDNode alignment field is log2 value of the alignment requirement. This is not consistent with other SDNode variants. 2. MachineConstantPool alignment field is also a log2 value. 3. However, some places are creating ConstantPoolSDNode with alignment value rather than log2 values. This creates entries with artificially large alignments, e.g. 256 for SSE vector values. 4. Constant pool entry offsets are computed when they are created. However, asm printer group them by sections. That means the offsets are no longer valid. However, asm printer uses them to determine size of padding between entries. 5. Asm printer uses expensive data structure multimap to track constant pool entries by sections. 6. Asm printer iterate over SmallPtrSet when it's emitting constant pool entries. This is non-deterministic. Solutions: 1. ConstantPoolSDNode alignment field is changed to keep non-log2 value. 2. MachineConstantPool alignment field is also changed to keep non-log2 value. 3. Functions that create ConstantPool nodes are passing in non-log2 alignments. 4. MachineConstantPoolEntry no longer keeps an offset field. It's replaced with an alignment field. Offsets are not computed when constant pool entries are created. They are computed on the fly in asm printer and JIT. 5. Asm printer uses cheaper data structure to group constant pool entries. 6. Asm printer compute entry offsets after grouping is done. 7. Change JIT code to compute entry offsets on the fly. llvm-svn: 66875
2009-03-13 15:51:59 +08:00
Constants.push_back(MachineConstantPoolEntry(C, Alignment));
return Constants.size()-1;
}
unsigned MachineConstantPool::getConstantPoolIndex(MachineConstantPoolValue *V,
Align Alignment) {
if (Alignment > PoolAlignment) PoolAlignment = Alignment;
2012-06-20 07:37:57 +08:00
// Check to see if we already have this constant.
//
// FIXME, this could be made much more efficient for large constant pools.
int Idx = V->getExistingMachineCPValue(this, Alignment);
if (Idx != -1) {
MachineCPVsSharingEntries.insert(V);
return (unsigned)Idx;
}
Fix some significant problems with constant pools that resulted in unnecessary paddings between constant pool entries, larger than necessary alignments (e.g. 8 byte alignment for .literal4 sections), and potentially other issues. 1. ConstantPoolSDNode alignment field is log2 value of the alignment requirement. This is not consistent with other SDNode variants. 2. MachineConstantPool alignment field is also a log2 value. 3. However, some places are creating ConstantPoolSDNode with alignment value rather than log2 values. This creates entries with artificially large alignments, e.g. 256 for SSE vector values. 4. Constant pool entry offsets are computed when they are created. However, asm printer group them by sections. That means the offsets are no longer valid. However, asm printer uses them to determine size of padding between entries. 5. Asm printer uses expensive data structure multimap to track constant pool entries by sections. 6. Asm printer iterate over SmallPtrSet when it's emitting constant pool entries. This is non-deterministic. Solutions: 1. ConstantPoolSDNode alignment field is changed to keep non-log2 value. 2. MachineConstantPool alignment field is also changed to keep non-log2 value. 3. Functions that create ConstantPool nodes are passing in non-log2 alignments. 4. MachineConstantPoolEntry no longer keeps an offset field. It's replaced with an alignment field. Offsets are not computed when constant pool entries are created. They are computed on the fly in asm printer and JIT. 5. Asm printer uses cheaper data structure to group constant pool entries. 6. Asm printer compute entry offsets after grouping is done. 7. Change JIT code to compute entry offsets on the fly. llvm-svn: 66875
2009-03-13 15:51:59 +08:00
Constants.push_back(MachineConstantPoolEntry(V, Alignment));
return Constants.size()-1;
}
void MachineConstantPool::print(raw_ostream &OS) const {
if (Constants.empty()) return;
OS << "Constant Pool:\n";
for (unsigned i = 0, e = Constants.size(); i != e; ++i) {
OS << " cp#" << i << ": ";
if (Constants[i].isMachineConstantPoolEntry())
Constants[i].Val.MachineCPVal->print(OS);
else
Constants[i].Val.ConstVal->printAsOperand(OS, /*PrintType=*/false);
OS << ", align=" << Constants[i].getAlign().value();
OS << "\n";
}
}
#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
LLVM_DUMP_METHOD void MachineConstantPool::dump() const { print(dbgs()); }
#endif