
This is a major change on how we represent nested name qualifications in the AST. * The nested name specifier itself and how it's stored is changed. The prefixes for types are handled within the type hierarchy, which makes canonicalization for them super cheap, no memory allocation required. Also translating a type into nested name specifier form becomes a no-op. An identifier is stored as a DependentNameType. The nested name specifier gains a lightweight handle class, to be used instead of passing around pointers, which is similar to what is implemented for TemplateName. There is still one free bit available, and this handle can be used within a PointerUnion and PointerIntPair, which should keep bit-packing aficionados happy. * The ElaboratedType node is removed, all type nodes in which it could previously apply to can now store the elaborated keyword and name qualifier, tail allocating when present. * TagTypes can now point to the exact declaration found when producing these, as opposed to the previous situation of there only existing one TagType per entity. This increases the amount of type sugar retained, and can have several applications, for example in tracking module ownership, and other tools which care about source file origins, such as IWYU. These TagTypes are lazily allocated, in order to limit the increase in AST size. This patch offers a great performance benefit. It greatly improves compilation time for [stdexec](https://github.com/NVIDIA/stdexec). For one datapoint, for `test_on2.cpp` in that project, which is the slowest compiling test, this patch improves `-c` compilation time by about 7.2%, with the `-fsyntax-only` improvement being at ~12%. This has great results on compile-time-tracker as well:  This patch also further enables other optimziations in the future, and will reduce the performance impact of template specialization resugaring when that lands. It has some other miscelaneous drive-by fixes. About the review: Yes the patch is huge, sorry about that. Part of the reason is that I started by the nested name specifier part, before the ElaboratedType part, but that had a huge performance downside, as ElaboratedType is a big performance hog. I didn't have the steam to go back and change the patch after the fact. There is also a lot of internal API changes, and it made sense to remove ElaboratedType in one go, versus removing it from one type at a time, as that would present much more churn to the users. Also, the nested name specifier having a different API avoids missing changes related to how prefixes work now, which could make existing code compile but not work. How to review: The important changes are all in `clang/include/clang/AST` and `clang/lib/AST`, with also important changes in `clang/lib/Sema/TreeTransform.h`. The rest and bulk of the changes are mostly consequences of the changes in API. PS: TagType::getDecl is renamed to `getOriginalDecl` in this patch, just for easier to rebasing. I plan to rename it back after this lands. Fixes #136624 Fixes https://github.com/llvm/llvm-project/issues/43179 Fixes https://github.com/llvm/llvm-project/issues/68670 Fixes https://github.com/llvm/llvm-project/issues/92757
163 lines
5.5 KiB
C++
163 lines
5.5 KiB
C++
//===- ARC.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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "ABIInfoImpl.h"
|
|
#include "TargetInfo.h"
|
|
|
|
using namespace clang;
|
|
using namespace clang::CodeGen;
|
|
|
|
// ARC ABI implementation.
|
|
namespace {
|
|
|
|
class ARCABIInfo : public DefaultABIInfo {
|
|
struct CCState {
|
|
unsigned FreeRegs;
|
|
};
|
|
|
|
public:
|
|
using DefaultABIInfo::DefaultABIInfo;
|
|
|
|
private:
|
|
RValue EmitVAArg(CodeGenFunction &CGF, Address VAListAddr, QualType Ty,
|
|
AggValueSlot Slot) const override;
|
|
|
|
void updateState(const ABIArgInfo &Info, QualType Ty, CCState &State) const {
|
|
if (!State.FreeRegs)
|
|
return;
|
|
if (Info.isIndirect() && Info.getInReg())
|
|
State.FreeRegs--;
|
|
else if (Info.isDirect() && Info.getInReg()) {
|
|
unsigned sz = (getContext().getTypeSize(Ty) + 31) / 32;
|
|
if (sz < State.FreeRegs)
|
|
State.FreeRegs -= sz;
|
|
else
|
|
State.FreeRegs = 0;
|
|
}
|
|
}
|
|
|
|
void computeInfo(CGFunctionInfo &FI) const override {
|
|
CCState State;
|
|
// ARC uses 8 registers to pass arguments.
|
|
State.FreeRegs = 8;
|
|
|
|
if (!getCXXABI().classifyReturnType(FI))
|
|
FI.getReturnInfo() = classifyReturnType(FI.getReturnType());
|
|
updateState(FI.getReturnInfo(), FI.getReturnType(), State);
|
|
for (auto &I : FI.arguments()) {
|
|
I.info = classifyArgumentType(I.type, State.FreeRegs);
|
|
updateState(I.info, I.type, State);
|
|
}
|
|
}
|
|
|
|
ABIArgInfo getIndirectByRef(QualType Ty, bool HasFreeRegs) const;
|
|
ABIArgInfo getIndirectByValue(QualType Ty) const;
|
|
ABIArgInfo classifyArgumentType(QualType Ty, uint8_t FreeRegs) const;
|
|
ABIArgInfo classifyReturnType(QualType RetTy) const;
|
|
};
|
|
|
|
class ARCTargetCodeGenInfo : public TargetCodeGenInfo {
|
|
public:
|
|
ARCTargetCodeGenInfo(CodeGenTypes &CGT)
|
|
: TargetCodeGenInfo(std::make_unique<ARCABIInfo>(CGT)) {}
|
|
};
|
|
|
|
|
|
ABIArgInfo ARCABIInfo::getIndirectByRef(QualType Ty, bool HasFreeRegs) const {
|
|
return HasFreeRegs ? getNaturalAlignIndirectInReg(Ty)
|
|
: getNaturalAlignIndirect(
|
|
Ty, getDataLayout().getAllocaAddrSpace(), false);
|
|
}
|
|
|
|
ABIArgInfo ARCABIInfo::getIndirectByValue(QualType Ty) const {
|
|
// Compute the byval alignment.
|
|
const unsigned MinABIStackAlignInBytes = 4;
|
|
unsigned TypeAlign = getContext().getTypeAlign(Ty) / 8;
|
|
return ABIArgInfo::getIndirect(
|
|
CharUnits::fromQuantity(4),
|
|
/*AddrSpace=*/getDataLayout().getAllocaAddrSpace(),
|
|
/*ByVal=*/true, TypeAlign > MinABIStackAlignInBytes);
|
|
}
|
|
|
|
RValue ARCABIInfo::EmitVAArg(CodeGenFunction &CGF, Address VAListAddr,
|
|
QualType Ty, AggValueSlot Slot) const {
|
|
return emitVoidPtrVAArg(CGF, VAListAddr, Ty, /*indirect*/ false,
|
|
getContext().getTypeInfoInChars(Ty),
|
|
CharUnits::fromQuantity(4), true, Slot);
|
|
}
|
|
|
|
ABIArgInfo ARCABIInfo::classifyArgumentType(QualType Ty,
|
|
uint8_t FreeRegs) const {
|
|
// Handle the generic C++ ABI.
|
|
const RecordType *RT = Ty->getAs<RecordType>();
|
|
if (RT) {
|
|
CGCXXABI::RecordArgABI RAA = getRecordArgABI(RT, getCXXABI());
|
|
if (RAA == CGCXXABI::RAA_Indirect)
|
|
return getIndirectByRef(Ty, FreeRegs > 0);
|
|
|
|
if (RAA == CGCXXABI::RAA_DirectInMemory)
|
|
return getIndirectByValue(Ty);
|
|
}
|
|
|
|
// Treat an enum type as its underlying type.
|
|
if (const EnumType *EnumTy = Ty->getAs<EnumType>())
|
|
Ty = EnumTy->getOriginalDecl()->getDefinitionOrSelf()->getIntegerType();
|
|
|
|
auto SizeInRegs = llvm::alignTo(getContext().getTypeSize(Ty), 32) / 32;
|
|
|
|
if (isAggregateTypeForABI(Ty)) {
|
|
// Structures with flexible arrays are always indirect.
|
|
if (RT &&
|
|
RT->getOriginalDecl()->getDefinitionOrSelf()->hasFlexibleArrayMember())
|
|
return getIndirectByValue(Ty);
|
|
|
|
// Ignore empty structs/unions.
|
|
if (isEmptyRecord(getContext(), Ty, true))
|
|
return ABIArgInfo::getIgnore();
|
|
|
|
llvm::LLVMContext &LLVMContext = getVMContext();
|
|
|
|
llvm::IntegerType *Int32 = llvm::Type::getInt32Ty(LLVMContext);
|
|
SmallVector<llvm::Type *, 3> Elements(SizeInRegs, Int32);
|
|
llvm::Type *Result = llvm::StructType::get(LLVMContext, Elements);
|
|
|
|
return FreeRegs >= SizeInRegs ?
|
|
ABIArgInfo::getDirectInReg(Result) :
|
|
ABIArgInfo::getDirect(Result, 0, nullptr, false);
|
|
}
|
|
|
|
if (const auto *EIT = Ty->getAs<BitIntType>())
|
|
if (EIT->getNumBits() > 64)
|
|
return getIndirectByValue(Ty);
|
|
|
|
return isPromotableIntegerTypeForABI(Ty)
|
|
? (FreeRegs >= SizeInRegs ? ABIArgInfo::getExtendInReg(Ty)
|
|
: ABIArgInfo::getExtend(Ty))
|
|
: (FreeRegs >= SizeInRegs ? ABIArgInfo::getDirectInReg()
|
|
: ABIArgInfo::getDirect());
|
|
}
|
|
|
|
ABIArgInfo ARCABIInfo::classifyReturnType(QualType RetTy) const {
|
|
if (RetTy->isAnyComplexType())
|
|
return ABIArgInfo::getDirectInReg();
|
|
|
|
// Arguments of size > 4 registers are indirect.
|
|
auto RetSize = llvm::alignTo(getContext().getTypeSize(RetTy), 32) / 32;
|
|
if (RetSize > 4)
|
|
return getIndirectByRef(RetTy, /*HasFreeRegs*/ true);
|
|
|
|
return DefaultABIInfo::classifyReturnType(RetTy);
|
|
}
|
|
|
|
} // End anonymous namespace.
|
|
|
|
std::unique_ptr<TargetCodeGenInfo>
|
|
CodeGen::createARCTargetCodeGenInfo(CodeGenModule &CGM) {
|
|
return std::make_unique<ARCTargetCodeGenInfo>(CGM.getTypes());
|
|
}
|