Google Git
Sign in
llvm / llvm-project / 1e8286467036d8ef1a972de723f805a4981b2692 / . / clang / lib / CodeGen / CGBuiltin.cpp
blob: 849423c8b9baeb10112926c94b5348253c322057 [file] [log] [blame]
//===---- CGBuiltin.cpp - Emit LLVM Code for builtins ---------------------===//
//
// 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 contains code to emit Builtin calls as LLVM code.
//
//===----------------------------------------------------------------------===//
#include "CGCUDARuntime.h"
#include "CGCXXABI.h"
#include "CGObjCRuntime.h"
#include "CGOpenCLRuntime.h"
#include "CGRecordLayout.h"
#include "CodeGenFunction.h"
#include "CodeGenModule.h"
#include "ConstantEmitter.h"
#include "PatternInit.h"
#include "TargetInfo.h"
#include "clang/AST/ASTContext.h"
#include "clang/AST/Attr.h"
#include "clang/AST/Decl.h"
#include "clang/AST/OSLog.h"
#include "clang/Basic/TargetBuiltins.h"
#include "clang/Basic/TargetInfo.h"
#include "clang/CodeGen/CGFunctionInfo.h"
#include "llvm/ADT/APFloat.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/InlineAsm.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/IntrinsicsAArch64.h"
#include "llvm/IR/IntrinsicsAMDGPU.h"
#include "llvm/IR/IntrinsicsARM.h"
#include "llvm/IR/IntrinsicsBPF.h"
#include "llvm/IR/IntrinsicsHexagon.h"
#include "llvm/IR/IntrinsicsNVPTX.h"
#include "llvm/IR/IntrinsicsPowerPC.h"
#include "llvm/IR/IntrinsicsR600.h"
#include "llvm/IR/IntrinsicsRISCV.h"
#include "llvm/IR/IntrinsicsS390.h"
#include "llvm/IR/IntrinsicsWebAssembly.h"
#include "llvm/IR/IntrinsicsX86.h"
#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/MatrixBuilder.h"
#include "llvm/Support/ConvertUTF.h"
#include "llvm/Support/ScopedPrinter.h"
#include "llvm/Support/X86TargetParser.h"
#include <sstream>
using namespace clang;
using namespace CodeGen;
using namespace llvm;
static
int64_t clamp(int64_t Value, int64_t Low, int64_t High) {
return std::min(High, std::max(Low, Value));
}
static void initializeAlloca(CodeGenFunction &CGF, AllocaInst *AI, Value *Size,
Align AlignmentInBytes) {
ConstantInt *Byte;
switch (CGF.getLangOpts().getTrivialAutoVarInit()) {
case LangOptions::TrivialAutoVarInitKind::Uninitialized:
// Nothing to initialize.
return;
case LangOptions::TrivialAutoVarInitKind::Zero:
Byte = CGF.Builder.getInt8(0x00);
break;
case LangOptions::TrivialAutoVarInitKind::Pattern: {
llvm::Type *Int8 = llvm::IntegerType::getInt8Ty(CGF.CGM.getLLVMContext());
Byte = llvm::dyn_cast<llvm::ConstantInt>(
initializationPatternFor(CGF.CGM, Int8));
break;
}
}
if (CGF.CGM.stopAutoInit())
return;
auto *I = CGF.Builder.CreateMemSet(AI, Byte, Size, AlignmentInBytes);
I->addAnnotationMetadata("auto-init");
}
/// getBuiltinLibFunction - Given a builtin id for a function like
/// "__builtin_fabsf", return a Function* for "fabsf".
llvm::Constant *CodeGenModule::getBuiltinLibFunction(const FunctionDecl *FD,
unsigned BuiltinID) {
assert(Context.BuiltinInfo.isLibFunction(BuiltinID));
// Get the name, skip over the __builtin_ prefix (if necessary).
StringRef Name;
GlobalDecl D(FD);
// If the builtin has been declared explicitly with an assembler label,
// use the mangled name. This differs from the plain label on platforms
// that prefix labels.
if (FD->hasAttr<AsmLabelAttr>())
Name = getMangledName(D);
else
Name = Context.BuiltinInfo.getName(BuiltinID) + 10;
llvm::FunctionType *Ty =
cast<llvm::FunctionType>(getTypes().ConvertType(FD->getType()));
return GetOrCreateLLVMFunction(Name, Ty, D, /*ForVTable=*/false);
}
/// Emit the conversions required to turn the given value into an
/// integer of the given size.
static Value *EmitToInt(CodeGenFunction &CGF, llvm::Value *V,
QualType T, llvm::IntegerType *IntType) {
V = CGF.EmitToMemory(V, T);
if (V->getType()->isPointerTy())
return CGF.Builder.CreatePtrToInt(V, IntType);
assert(V->getType() == IntType);
return V;
}
static Value *EmitFromInt(CodeGenFunction &CGF, llvm::Value *V,
QualType T, llvm::Type *ResultType) {
V = CGF.EmitFromMemory(V, T);
if (ResultType->isPointerTy())
return CGF.Builder.CreateIntToPtr(V, ResultType);
assert(V->getType() == ResultType);
return V;
}
/// Utility to insert an atomic instruction based on Intrinsic::ID
/// and the expression node.
static Value *MakeBinaryAtomicValue(
CodeGenFunction &CGF, llvm::AtomicRMWInst::BinOp Kind, const CallExpr *E,
AtomicOrdering Ordering = AtomicOrdering::SequentiallyConsistent) {
QualType T = E->getType();
assert(E->getArg(0)->getType()->isPointerType());
assert(CGF.getContext().hasSameUnqualifiedType(T,
E->getArg(0)->getType()->getPointeeType()));
assert(CGF.getContext().hasSameUnqualifiedType(T, E->getArg(1)->getType()));
llvm::Value *DestPtr = CGF.EmitScalarExpr(E->getArg(0));
unsigned AddrSpace = DestPtr->getType()->getPointerAddressSpace();
llvm::IntegerType *IntType =
llvm::IntegerType::get(CGF.getLLVMContext(),
CGF.getContext().getTypeSize(T));
llvm::Type *IntPtrType = IntType->getPointerTo(AddrSpace);
llvm::Value *Args[2];
Args[0] = CGF.Builder.CreateBitCast(DestPtr, IntPtrType);
Args[1] = CGF.EmitScalarExpr(E->getArg(1));
llvm::Type *ValueType = Args[1]->getType();
Args[1] = EmitToInt(CGF, Args[1], T, IntType);
llvm::Value *Result = CGF.Builder.CreateAtomicRMW(
Kind, Args[0], Args[1], Ordering);
return EmitFromInt(CGF, Result, T, ValueType);
}
static Value *EmitNontemporalStore(CodeGenFunction &CGF, const CallExpr *E) {
Value *Val = CGF.EmitScalarExpr(E->getArg(0));
Value *Address = CGF.EmitScalarExpr(E->getArg(1));
// Convert the type of the pointer to a pointer to the stored type.
Val = CGF.EmitToMemory(Val, E->getArg(0)->getType());
Value *BC = CGF.Builder.CreateBitCast(
Address, llvm::PointerType::getUnqual(Val->getType()), "cast");
LValue LV = CGF.MakeNaturalAlignAddrLValue(BC, E->getArg(0)->getType());
LV.setNontemporal(true);
CGF.EmitStoreOfScalar(Val, LV, false);
return nullptr;
}
static Value *EmitNontemporalLoad(CodeGenFunction &CGF, const CallExpr *E) {
Value *Address = CGF.EmitScalarExpr(E->getArg(0));
LValue LV = CGF.MakeNaturalAlignAddrLValue(Address, E->getType());
LV.setNontemporal(true);
return CGF.EmitLoadOfScalar(LV, E->getExprLoc());
}
static RValue EmitBinaryAtomic(CodeGenFunction &CGF,
llvm::AtomicRMWInst::BinOp Kind,
const CallExpr *E) {
return RValue::get(MakeBinaryAtomicValue(CGF, Kind, E));
}
/// Utility to insert an atomic instruction based Intrinsic::ID and
/// the expression node, where the return value is the result of the
/// operation.
static RValue EmitBinaryAtomicPost(CodeGenFunction &CGF,
llvm::AtomicRMWInst::BinOp Kind,
const CallExpr *E,
Instruction::BinaryOps Op,
bool Invert = false) {
QualType T = E->getType();
assert(E->getArg(0)->getType()->isPointerType());
assert(CGF.getContext().hasSameUnqualifiedType(T,
E->getArg(0)->getType()->getPointeeType()));
assert(CGF.getContext().hasSameUnqualifiedType(T, E->getArg(1)->getType()));
llvm::Value *DestPtr = CGF.EmitScalarExpr(E->getArg(0));
unsigned AddrSpace = DestPtr->getType()->getPointerAddressSpace();
llvm::IntegerType *IntType =
llvm::IntegerType::get(CGF.getLLVMContext(),
CGF.getContext().getTypeSize(T));
llvm::Type *IntPtrType = IntType->getPointerTo(AddrSpace);
llvm::Value *Args[2];
Args[1] = CGF.EmitScalarExpr(E->getArg(1));
llvm::Type *ValueType = Args[1]->getType();
Args[1] = EmitToInt(CGF, Args[1], T, IntType);
Args[0] = CGF.Builder.CreateBitCast(DestPtr, IntPtrType);
llvm::Value *Result = CGF.Builder.CreateAtomicRMW(
Kind, Args[0], Args[1], llvm::AtomicOrdering::SequentiallyConsistent);
Result = CGF.Builder.CreateBinOp(Op, Result, Args[1]);
if (Invert)
Result =
CGF.Builder.CreateBinOp(llvm::Instruction::Xor, Result,
llvm::ConstantInt::getAllOnesValue(IntType));
Result = EmitFromInt(CGF, Result, T, ValueType);
return RValue::get(Result);
}
/// Utility to insert an atomic cmpxchg instruction.
///
/// @param CGF The current codegen function.
/// @param E Builtin call expression to convert to cmpxchg.
/// arg0 - address to operate on
/// arg1 - value to compare with
/// arg2 - new value
/// @param ReturnBool Specifies whether to return success flag of
/// cmpxchg result or the old value.
///
/// @returns result of cmpxchg, according to ReturnBool
///
/// Note: In order to lower Microsoft's _InterlockedCompareExchange* intrinsics
/// invoke the function EmitAtomicCmpXchgForMSIntrin.
static Value *MakeAtomicCmpXchgValue(CodeGenFunction &CGF, const CallExpr *E,
bool ReturnBool) {
QualType T = ReturnBool ? E->getArg(1)->getType() : E->getType();
llvm::Value *DestPtr = CGF.EmitScalarExpr(E->getArg(0));
unsigned AddrSpace = DestPtr->getType()->getPointerAddressSpace();
llvm::IntegerType *IntType = llvm::IntegerType::get(
CGF.getLLVMContext(), CGF.getContext().getTypeSize(T));
llvm::Type *IntPtrType = IntType->getPointerTo(AddrSpace);
Value *Args[3];
Args[0] = CGF.Builder.CreateBitCast(DestPtr, IntPtrType);
Args[1] = CGF.EmitScalarExpr(E->getArg(1));
llvm::Type *ValueType = Args[1]->getType();
Args[1] = EmitToInt(CGF, Args[1], T, IntType);
Args[2] = EmitToInt(CGF, CGF.EmitScalarExpr(E->getArg(2)), T, IntType);
Value *Pair = CGF.Builder.CreateAtomicCmpXchg(
Args[0], Args[1], Args[2], llvm::AtomicOrdering::SequentiallyConsistent,
llvm::AtomicOrdering::SequentiallyConsistent);
if (ReturnBool)
// Extract boolean success flag and zext it to int.
return CGF.Builder.CreateZExt(CGF.Builder.CreateExtractValue(Pair, 1),
CGF.ConvertType(E->getType()));
else
// Extract old value and emit it using the same type as compare value.
return EmitFromInt(CGF, CGF.Builder.CreateExtractValue(Pair, 0), T,
ValueType);
}
/// This function should be invoked to emit atomic cmpxchg for Microsoft's
/// _InterlockedCompareExchange* intrinsics which have the following signature:
/// T _InterlockedCompareExchange(T volatile *Destination,
/// T Exchange,
/// T Comparand);
///
/// Whereas the llvm 'cmpxchg' instruction has the following syntax:
/// cmpxchg *Destination, Comparand, Exchange.
/// So we need to swap Comparand and Exchange when invoking
/// CreateAtomicCmpXchg. That is the reason we could not use the above utility
/// function MakeAtomicCmpXchgValue since it expects the arguments to be
/// already swapped.
static
Value *EmitAtomicCmpXchgForMSIntrin(CodeGenFunction &CGF, const CallExpr *E,
AtomicOrdering SuccessOrdering = AtomicOrdering::SequentiallyConsistent) {
assert(E->getArg(0)->getType()->isPointerType());
assert(CGF.getContext().hasSameUnqualifiedType(
E->getType(), E->getArg(0)->getType()->getPointeeType()));
assert(CGF.getContext().hasSameUnqualifiedType(E->getType(),
E->getArg(1)->getType()));
assert(CGF.getContext().hasSameUnqualifiedType(E->getType(),
E->getArg(2)->getType()));
auto *Destination = CGF.EmitScalarExpr(E->getArg(0));
auto *Comparand = CGF.EmitScalarExpr(E->getArg(2));
auto *Exchange = CGF.EmitScalarExpr(E->getArg(1));
// For Release ordering, the failure ordering should be Monotonic.
auto FailureOrdering = SuccessOrdering == AtomicOrdering::Release ?
AtomicOrdering::Monotonic :
SuccessOrdering;
// The atomic instruction is marked volatile for consistency with MSVC. This
// blocks the few atomics optimizations that LLVM has. If we want to optimize
// _Interlocked* operations in the future, we will have to remove the volatile
// marker.
auto *Result = CGF.Builder.CreateAtomicCmpXchg(
Destination, Comparand, Exchange,
SuccessOrdering, FailureOrdering);
Result->setVolatile(true);
return CGF.Builder.CreateExtractValue(Result, 0);
}
// 64-bit Microsoft platforms support 128 bit cmpxchg operations. They are
// prototyped like this:
//
// unsigned char _InterlockedCompareExchange128...(
// __int64 volatile * _Destination,
// __int64 _ExchangeHigh,
// __int64 _ExchangeLow,
// __int64 * _ComparandResult);
static Value *EmitAtomicCmpXchg128ForMSIntrin(CodeGenFunction &CGF,
const CallExpr *E,
AtomicOrdering SuccessOrdering) {
assert(E->getNumArgs() == 4);
llvm::Value *Destination = CGF.EmitScalarExpr(E->getArg(0));
llvm::Value *ExchangeHigh = CGF.EmitScalarExpr(E->getArg(1));
llvm::Value *ExchangeLow = CGF.EmitScalarExpr(E->getArg(2));
llvm::Value *ComparandPtr = CGF.EmitScalarExpr(E->getArg(3));
assert(Destination->getType()->isPointerTy());
assert(!ExchangeHigh->getType()->isPointerTy());
assert(!ExchangeLow->getType()->isPointerTy());
assert(ComparandPtr->getType()->isPointerTy());
// For Release ordering, the failure ordering should be Monotonic.
auto FailureOrdering = SuccessOrdering == AtomicOrdering::Release
? AtomicOrdering::Monotonic
: SuccessOrdering;
// Convert to i128 pointers and values.
llvm::Type *Int128Ty = llvm::IntegerType::get(CGF.getLLVMContext(), 128);
llvm::Type *Int128PtrTy = Int128Ty->getPointerTo();
Destination = CGF.Builder.CreateBitCast(Destination, Int128PtrTy);
Address ComparandResult(CGF.Builder.CreateBitCast(ComparandPtr, Int128PtrTy),
CGF.getContext().toCharUnitsFromBits(128));
// (((i128)hi) << 64) | ((i128)lo)
ExchangeHigh = CGF.Builder.CreateZExt(ExchangeHigh, Int128Ty);
ExchangeLow = CGF.Builder.CreateZExt(ExchangeLow, Int128Ty);
ExchangeHigh =
CGF.Builder.CreateShl(ExchangeHigh, llvm::ConstantInt::get(Int128Ty, 64));
llvm::Value *Exchange = CGF.Builder.CreateOr(ExchangeHigh, ExchangeLow);
// Load the comparand for the instruction.
llvm::Value *Comparand = CGF.Builder.CreateLoad(ComparandResult);
auto *CXI = CGF.Builder.CreateAtomicCmpXchg(Destination, Comparand, Exchange,
SuccessOrdering, FailureOrdering);
// The atomic instruction is marked volatile for consistency with MSVC. This
// blocks the few atomics optimizations that LLVM has. If we want to optimize
// _Interlocked* operations in the future, we will have to remove the volatile
// marker.
CXI->setVolatile(true);
// Store the result as an outparameter.
CGF.Builder.CreateStore(CGF.Builder.CreateExtractValue(CXI, 0),
ComparandResult);
// Get the success boolean and zero extend it to i8.
Value *Success = CGF.Builder.CreateExtractValue(CXI, 1);
return CGF.Builder.CreateZExt(Success, CGF.Int8Ty);
}
static Value *EmitAtomicIncrementValue(CodeGenFunction &CGF, const CallExpr *E,
AtomicOrdering Ordering = AtomicOrdering::SequentiallyConsistent) {
assert(E->getArg(0)->getType()->isPointerType());
auto *IntTy = CGF.ConvertType(E->getType());
auto *Result = CGF.Builder.CreateAtomicRMW(
AtomicRMWInst::Add,
CGF.EmitScalarExpr(E->getArg(0)),
ConstantInt::get(IntTy, 1),
Ordering);
return CGF.Builder.CreateAdd(Result, ConstantInt::get(IntTy, 1));
}
static Value *EmitAtomicDecrementValue(CodeGenFunction &CGF, const CallExpr *E,
AtomicOrdering Ordering = AtomicOrdering::SequentiallyConsistent) {
assert(E->getArg(0)->getType()->isPointerType());
auto *IntTy = CGF.ConvertType(E->getType());
auto *Result = CGF.Builder.CreateAtomicRMW(
AtomicRMWInst::Sub,
CGF.EmitScalarExpr(E->getArg(0)),
ConstantInt::get(IntTy, 1),
Ordering);
return CGF.Builder.CreateSub(Result, ConstantInt::get(IntTy, 1));
}
// Build a plain volatile load.
static Value *EmitISOVolatileLoad(CodeGenFunction &CGF, const CallExpr *E) {
Value *Ptr = CGF.EmitScalarExpr(E->getArg(0));
QualType ElTy = E->getArg(0)->getType()->getPointeeType();
CharUnits LoadSize = CGF.getContext().getTypeSizeInChars(ElTy);
llvm::Type *ITy =
llvm::IntegerType::get(CGF.getLLVMContext(), LoadSize.getQuantity() * 8);
Ptr = CGF.Builder.CreateBitCast(Ptr, ITy->getPointerTo());
llvm::LoadInst *Load = CGF.Builder.CreateAlignedLoad(ITy, Ptr, LoadSize);
Load->setVolatile(true);
return Load;
}
// Build a plain volatile store.
static Value *EmitISOVolatileStore(CodeGenFunction &CGF, const CallExpr *E) {
Value *Ptr = CGF.EmitScalarExpr(E->getArg(0));
Value *Value = CGF.EmitScalarExpr(E->getArg(1));
QualType ElTy = E->getArg(0)->getType()->getPointeeType();
CharUnits StoreSize = CGF.getContext().getTypeSizeInChars(ElTy);
llvm::Type *ITy =
llvm::IntegerType::get(CGF.getLLVMContext(), StoreSize.getQuantity() * 8);
Ptr = CGF.Builder.CreateBitCast(Ptr, ITy->getPointerTo());
llvm::StoreInst *Store =
CGF.Builder.CreateAlignedStore(Value, Ptr, StoreSize);
Store->setVolatile(true);
return Store;
}
// Emit a simple mangled intrinsic that has 1 argument and a return type
// matching the argument type. Depending on mode, this may be a constrained
// floating-point intrinsic.
static Value *emitUnaryMaybeConstrainedFPBuiltin(CodeGenFunction &CGF,
const CallExpr *E, unsigned IntrinsicID,
unsigned ConstrainedIntrinsicID) {
llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0));
if (CGF.Builder.getIsFPConstrained()) {
CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, E);
Function *F = CGF.CGM.getIntrinsic(ConstrainedIntrinsicID, Src0->getType());
return CGF.Builder.CreateConstrainedFPCall(F, { Src0 });
} else {
Function *F = CGF.CGM.getIntrinsic(IntrinsicID, Src0->getType());
return CGF.Builder.CreateCall(F, Src0);
}
}
// Emit an intrinsic that has 2 operands of the same type as its result.
// Depending on mode, this may be a constrained floating-point intrinsic.
static Value *emitBinaryMaybeConstrainedFPBuiltin(CodeGenFunction &CGF,
const CallExpr *E, unsigned IntrinsicID,
unsigned ConstrainedIntrinsicID) {
llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0));
llvm::Value *Src1 = CGF.EmitScalarExpr(E->getArg(1));
if (CGF.Builder.getIsFPConstrained()) {
CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, E);
Function *F = CGF.CGM.getIntrinsic(ConstrainedIntrinsicID, Src0->getType());
return CGF.Builder.CreateConstrainedFPCall(F, { Src0, Src1 });
} else {
Function *F = CGF.CGM.getIntrinsic(IntrinsicID, Src0->getType());
return CGF.Builder.CreateCall(F, { Src0, Src1 });
}
}
// Emit an intrinsic that has 3 operands of the same type as its result.
// Depending on mode, this may be a constrained floating-point intrinsic.
static Value *emitTernaryMaybeConstrainedFPBuiltin(CodeGenFunction &CGF,
const CallExpr *E, unsigned IntrinsicID,
unsigned ConstrainedIntrinsicID) {
llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0));
llvm::Value *Src1 = CGF.EmitScalarExpr(E->getArg(1));
llvm::Value *Src2 = CGF.EmitScalarExpr(E->getArg(2));
if (CGF.Builder.getIsFPConstrained()) {
CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, E);
Function *F = CGF.CGM.getIntrinsic(ConstrainedIntrinsicID, Src0->getType());
return CGF.Builder.CreateConstrainedFPCall(F, { Src0, Src1, Src2 });
} else {
Function *F = CGF.CGM.getIntrinsic(IntrinsicID, Src0->getType());
return CGF.Builder.CreateCall(F, { Src0, Src1, Src2 });
}
}
// Emit an intrinsic where all operands are of the same type as the result.
// Depending on mode, this may be a constrained floating-point intrinsic.
static Value *emitCallMaybeConstrainedFPBuiltin(CodeGenFunction &CGF,
unsigned IntrinsicID,
unsigned ConstrainedIntrinsicID,
llvm::Type *Ty,
ArrayRef<Value *> Args) {
Function *F;
if (CGF.Builder.getIsFPConstrained())
F = CGF.CGM.getIntrinsic(ConstrainedIntrinsicID, Ty);
else
F = CGF.CGM.getIntrinsic(IntrinsicID, Ty);
if (CGF.Builder.getIsFPConstrained())
return CGF.Builder.CreateConstrainedFPCall(F, Args);
else
return CGF.Builder.CreateCall(F, Args);
}
// Emit a simple mangled intrinsic that has 1 argument and a return type
// matching the argument type.
static Value *emitUnaryBuiltin(CodeGenFunction &CGF,
const CallExpr *E,
unsigned IntrinsicID) {
llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0));
Function *F = CGF.CGM.getIntrinsic(IntrinsicID, Src0->getType());
return CGF.Builder.CreateCall(F, Src0);
}
// Emit an intrinsic that has 2 operands of the same type as its result.
static Value *emitBinaryBuiltin(CodeGenFunction &CGF,
const CallExpr *E,
unsigned IntrinsicID) {
llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0));
llvm::Value *Src1 = CGF.EmitScalarExpr(E->getArg(1));
Function *F = CGF.CGM.getIntrinsic(IntrinsicID, Src0->getType());
return CGF.Builder.CreateCall(F, { Src0, Src1 });
}
// Emit an intrinsic that has 3 operands of the same type as its result.
static Value *emitTernaryBuiltin(CodeGenFunction &CGF,
const CallExpr *E,
unsigned IntrinsicID) {
llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0));
llvm::Value *Src1 = CGF.EmitScalarExpr(E->getArg(1));
llvm::Value *Src2 = CGF.EmitScalarExpr(E->getArg(2));
Function *F = CGF.CGM.getIntrinsic(IntrinsicID, Src0->getType());
return CGF.Builder.CreateCall(F, { Src0, Src1, Src2 });
}
// Emit an intrinsic that has 1 float or double operand, and 1 integer.
static Value *emitFPIntBuiltin(CodeGenFunction &CGF,
const CallExpr *E,
unsigned IntrinsicID) {
llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0));
llvm::Value *Src1 = CGF.EmitScalarExpr(E->getArg(1));
Function *F = CGF.CGM.getIntrinsic(IntrinsicID, Src0->getType());
return CGF.Builder.CreateCall(F, {Src0, Src1});
}
// Emit an intrinsic that has overloaded integer result and fp operand.
static Value *
emitMaybeConstrainedFPToIntRoundBuiltin(CodeGenFunction &CGF, const CallExpr *E,
unsigned IntrinsicID,
unsigned ConstrainedIntrinsicID) {
llvm::Type *ResultType = CGF.ConvertType(E->getType());
llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0));
if (CGF.Builder.getIsFPConstrained()) {
CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, E);
Function *F = CGF.CGM.getIntrinsic(ConstrainedIntrinsicID,
{ResultType, Src0->getType()});
return CGF.Builder.CreateConstrainedFPCall(F, {Src0});
} else {
Function *F =
CGF.CGM.getIntrinsic(IntrinsicID, {ResultType, Src0->getType()});
return CGF.Builder.CreateCall(F, Src0);
}
}
/// EmitFAbs - Emit a call to @llvm.fabs().
static Value *EmitFAbs(CodeGenFunction &CGF, Value *V) {
Function *F = CGF.CGM.getIntrinsic(Intrinsic::fabs, V->getType());
llvm::CallInst *Call = CGF.Builder.CreateCall(F, V);
Call->setDoesNotAccessMemory();
return Call;
}
/// Emit the computation of the sign bit for a floating point value. Returns
/// the i1 sign bit value.
static Value *EmitSignBit(CodeGenFunction &CGF, Value *V) {
LLVMContext &C = CGF.CGM.getLLVMContext();
llvm::Type *Ty = V->getType();
int Width = Ty->getPrimitiveSizeInBits();
llvm::Type *IntTy = llvm::IntegerType::get(C, Width);
V = CGF.Builder.CreateBitCast(V, IntTy);
if (Ty->isPPC_FP128Ty()) {
// We want the sign bit of the higher-order double. The bitcast we just
// did works as if the double-double was stored to memory and then
// read as an i128. The "store" will put the higher-order double in the
// lower address in both little- and big-Endian modes, but the "load"
// will treat those bits as a different part of the i128: the low bits in
// little-Endian, the high bits in big-Endian. Therefore, on big-Endian
// we need to shift the high bits down to the low before truncating.
Width >>= 1;
if (CGF.getTarget().isBigEndian()) {
Value *ShiftCst = llvm::ConstantInt::get(IntTy, Width);
V = CGF.Builder.CreateLShr(V, ShiftCst);
}
// We are truncating value in order to extract the higher-order
// double, which we will be using to extract the sign from.
IntTy = llvm::IntegerType::get(C, Width);
V = CGF.Builder.CreateTrunc(V, IntTy);
}
Value *Zero = llvm::Constant::getNullValue(IntTy);
return CGF.Builder.CreateICmpSLT(V, Zero);
}
static RValue emitLibraryCall(CodeGenFunction &CGF, const FunctionDecl *FD,
const CallExpr *E, llvm::Constant *calleeValue) {
CGCallee callee = CGCallee::forDirect(calleeValue, GlobalDecl(FD));
return CGF.EmitCall(E->getCallee()->getType(), callee, E, ReturnValueSlot());
}
/// Emit a call to llvm.{sadd,uadd,ssub,usub,smul,umul}.with.overflow.*
/// depending on IntrinsicID.
///
/// \arg CGF The current codegen function.
/// \arg IntrinsicID The ID for the Intrinsic we wish to generate.
/// \arg X The first argument to the llvm.*.with.overflow.*.
/// \arg Y The second argument to the llvm.*.with.overflow.*.
/// \arg Carry The carry returned by the llvm.*.with.overflow.*.
/// \returns The result (i.e. sum/product) returned by the intrinsic.
static llvm::Value *EmitOverflowIntrinsic(CodeGenFunction &CGF,
const llvm::Intrinsic::ID IntrinsicID,
llvm::Value *X, llvm::Value *Y,
llvm::Value *&Carry) {
// Make sure we have integers of the same width.
assert(X->getType() == Y->getType() &&
"Arguments must be the same type. (Did you forget to make sure both "
"arguments have the same integer width?)");
Function *Callee = CGF.CGM.getIntrinsic(IntrinsicID, X->getType());
llvm::Value *Tmp = CGF.Builder.CreateCall(Callee, {X, Y});
Carry = CGF.Builder.CreateExtractValue(Tmp, 1);
return CGF.Builder.CreateExtractValue(Tmp, 0);
}
static Value *emitRangedBuiltin(CodeGenFunction &CGF,
unsigned IntrinsicID,
int low, int high) {
llvm::MDBuilder MDHelper(CGF.getLLVMContext());
llvm::MDNode *RNode = MDHelper.createRange(APInt(32, low), APInt(32, high));
Function *F = CGF.CGM.getIntrinsic(IntrinsicID, {});
llvm::Instruction *Call = CGF.Builder.CreateCall(F);
Call->setMetadata(llvm::LLVMContext::MD_range, RNode);
return Call;
}
namespace {
struct WidthAndSignedness {
unsigned Width;
bool Signed;
};
}
static WidthAndSignedness
getIntegerWidthAndSignedness(const clang::ASTContext &context,
const clang::QualType Type) {
assert(Type->isIntegerType() && "Given type is not an integer.");
unsigned Width = Type->isBooleanType() ? 1
: Type->isExtIntType() ? context.getIntWidth(Type)
: context.getTypeInfo(Type).Width;
bool Signed = Type->isSignedIntegerType();
return {Width, Signed};
}
// Given one or more integer types, this function produces an integer type that
// encompasses them: any value in one of the given types could be expressed in
// the encompassing type.
static struct WidthAndSignedness
EncompassingIntegerType(ArrayRef<struct WidthAndSignedness> Types) {
assert(Types.size() > 0 && "Empty list of types.");
// If any of the given types is signed, we must return a signed type.
bool Signed = false;
for (const auto &Type : Types) {
Signed |= Type.Signed;
}
// The encompassing type must have a width greater than or equal to the width
// of the specified types. Additionally, if the encompassing type is signed,
// its width must be strictly greater than the width of any unsigned types
// given.
unsigned Width = 0;
for (const auto &Type : Types) {
unsigned MinWidth = Type.Width + (Signed && !Type.Signed);
if (Width < MinWidth) {
Width = MinWidth;
}
}
return {Width, Signed};
}
Value *CodeGenFunction::EmitVAStartEnd(Value *ArgValue, bool IsStart) {
llvm::Type *DestType = Int8PtrTy;
if (ArgValue->getType() != DestType)
ArgValue =
Builder.CreateBitCast(ArgValue, DestType, ArgValue->getName().data());
Intrinsic::ID inst = IsStart ? Intrinsic::vastart : Intrinsic::vaend;
return Builder.CreateCall(CGM.getIntrinsic(inst), ArgValue);
}
/// Checks if using the result of __builtin_object_size(p, @p From) in place of
/// __builtin_object_size(p, @p To) is correct
static bool areBOSTypesCompatible(int From, int To) {
// Note: Our __builtin_object_size implementation currently treats Type=0 and
// Type=2 identically. Encoding this implementation detail here may make
// improving __builtin_object_size difficult in the future, so it's omitted.
return From == To || (From == 0 && To == 1) || (From == 3 && To == 2);
}
static llvm::Value *
getDefaultBuiltinObjectSizeResult(unsigned Type, llvm::IntegerType *ResType) {
return ConstantInt::get(ResType, (Type & 2) ? 0 : -1, /*isSigned=*/true);
}
llvm::Value *
CodeGenFunction::evaluateOrEmitBuiltinObjectSize(const Expr *E, unsigned Type,
llvm::IntegerType *ResType,
llvm::Value *EmittedE,
bool IsDynamic) {
uint64_t ObjectSize;
if (!E->tryEvaluateObjectSize(ObjectSize, getContext(), Type))
return emitBuiltinObjectSize(E, Type, ResType, EmittedE, IsDynamic);
return ConstantInt::get(ResType, ObjectSize, /*isSigned=*/true);
}
/// Returns a Value corresponding to the size of the given expression.
/// This Value may be either of the following:
/// - A llvm::Argument (if E is a param with the pass_object_size attribute on
/// it)
/// - A call to the @llvm.objectsize intrinsic
///
/// EmittedE is the result of emitting `E` as a scalar expr. If it's non-null
/// and we wouldn't otherwise try to reference a pass_object_size parameter,
/// we'll call @llvm.objectsize on EmittedE, rather than emitting E.
llvm::Value *
CodeGenFunction::emitBuiltinObjectSize(const Expr *E, unsigned Type,
llvm::IntegerType *ResType,
llvm::Value *EmittedE, bool IsDynamic) {
// We need to reference an argument if the pointer is a parameter with the
// pass_object_size attribute.
if (auto *D = dyn_cast<DeclRefExpr>(E->IgnoreParenImpCasts())) {
auto *Param = dyn_cast<ParmVarDecl>(D->getDecl());
auto *PS = D->getDecl()->getAttr<PassObjectSizeAttr>();
if (Param != nullptr && PS != nullptr &&
areBOSTypesCompatible(PS->getType(), Type)) {
auto Iter = SizeArguments.find(Param);
assert(Iter != SizeArguments.end());
const ImplicitParamDecl *D = Iter->second;
auto DIter = LocalDeclMap.find(D);
assert(DIter != LocalDeclMap.end());
return EmitLoadOfScalar(DIter->second, /*Volatile=*/false,
getContext().getSizeType(), E->getBeginLoc());
}
}
// LLVM can't handle Type=3 appropriately, and __builtin_object_size shouldn't
// evaluate E for side-effects. In either case, we shouldn't lower to
// @llvm.objectsize.
if (Type == 3 || (!EmittedE && E->HasSideEffects(getContext())))
return getDefaultBuiltinObjectSizeResult(Type, ResType);
Value *Ptr = EmittedE ? EmittedE : EmitScalarExpr(E);
assert(Ptr->getType()->isPointerTy() &&
"Non-pointer passed to __builtin_object_size?");
Function *F =
CGM.getIntrinsic(Intrinsic::objectsize, {ResType, Ptr->getType()});
// LLVM only supports 0 and 2, make sure that we pass along that as a boolean.
Value *Min = Builder.getInt1((Type & 2) != 0);
// For GCC compatibility, __builtin_object_size treat NULL as unknown size.
Value *NullIsUnknown = Builder.getTrue();
Value *Dynamic = Builder.getInt1(IsDynamic);
return Builder.CreateCall(F, {Ptr, Min, NullIsUnknown, Dynamic});
}
namespace {
/// A struct to generically describe a bit test intrinsic.
struct BitTest {
enum ActionKind : uint8_t { TestOnly, Complement, Reset, Set };
enum InterlockingKind : uint8_t {
Unlocked,
Sequential,
Acquire,
Release,
NoFence
};
ActionKind Action;
InterlockingKind Interlocking;
bool Is64Bit;
static BitTest decodeBitTestBuiltin(unsigned BuiltinID);
};
} // namespace
BitTest BitTest::decodeBitTestBuiltin(unsigned BuiltinID) {
switch (BuiltinID) {
// Main portable variants.
case Builtin::BI_bittest:
return {TestOnly, Unlocked, false};
case Builtin::BI_bittestandcomplement:
return {Complement, Unlocked, false};
case Builtin::BI_bittestandreset:
return {Reset, Unlocked, false};
case Builtin::BI_bittestandset:
return {Set, Unlocked, false};
case Builtin::BI_interlockedbittestandreset:
return {Reset, Sequential, false};
case Builtin::BI_interlockedbittestandset:
return {Set, Sequential, false};
// X86-specific 64-bit variants.
case Builtin::BI_bittest64:
return {TestOnly, Unlocked, true};
case Builtin::BI_bittestandcomplement64:
return {Complement, Unlocked, true};
case Builtin::BI_bittestandreset64:
return {Reset, Unlocked, true};
case Builtin::BI_bittestandset64:
return {Set, Unlocked, true};
case Builtin::BI_interlockedbittestandreset64:
return {Reset, Sequential, true};
case Builtin::BI_interlockedbittestandset64:
return {Set, Sequential, true};
// ARM/AArch64-specific ordering variants.
case Builtin::BI_interlockedbittestandset_acq:
return {Set, Acquire, false};
case Builtin::BI_interlockedbittestandset_rel:
return {Set, Release, false};
case Builtin::BI_interlockedbittestandset_nf:
return {Set, NoFence, false};
case Builtin::BI_interlockedbittestandreset_acq:
return {Reset, Acquire, false};
case Builtin::BI_interlockedbittestandreset_rel:
return {Reset, Release, false};
case Builtin::BI_interlockedbittestandreset_nf:
return {Reset, NoFence, false};
}
llvm_unreachable("expected only bittest intrinsics");
}
static char bitActionToX86BTCode(BitTest::ActionKind A) {
switch (A) {
case BitTest::TestOnly: return '\0';
case BitTest::Complement: return 'c';
case BitTest::Reset: return 'r';
case BitTest::Set: return 's';
}
llvm_unreachable("invalid action");
}
static llvm::Value *EmitX86BitTestIntrinsic(CodeGenFunction &CGF,
BitTest BT,
const CallExpr *E, Value *BitBase,
Value *BitPos) {
char Action = bitActionToX86BTCode(BT.Action);
char SizeSuffix = BT.Is64Bit ? 'q' : 'l';
// Build the assembly.
SmallString<64> Asm;
raw_svector_ostream AsmOS(Asm);
if (BT.Interlocking != BitTest::Unlocked)
AsmOS << "lock ";
AsmOS << "bt";
if (Action)
AsmOS << Action;
AsmOS << SizeSuffix << " $2, ($1)";
// Build the constraints. FIXME: We should support immediates when possible.
std::string Constraints = "={@ccc},r,r,~{cc},~{memory}";
std::string MachineClobbers = CGF.getTarget().getClobbers();
if (!MachineClobbers.empty()) {
Constraints += ',';
Constraints += MachineClobbers;
}
llvm::IntegerType *IntType = llvm::IntegerType::get(
CGF.getLLVMContext(),
CGF.getContext().getTypeSize(E->getArg(1)->getType()));
llvm::Type *IntPtrType = IntType->getPointerTo();
llvm::FunctionType *FTy =
llvm::FunctionType::get(CGF.Int8Ty, {IntPtrType, IntType}, false);
llvm::InlineAsm *IA =
llvm::InlineAsm::get(FTy, Asm, Constraints, /*hasSideEffects=*/true);
return CGF.Builder.CreateCall(IA, {BitBase, BitPos});
}
static llvm::AtomicOrdering
getBitTestAtomicOrdering(BitTest::InterlockingKind I) {
switch (I) {
case BitTest::Unlocked: return llvm::AtomicOrdering::NotAtomic;
case BitTest::Sequential: return llvm::AtomicOrdering::SequentiallyConsistent;
case BitTest::Acquire: return llvm::AtomicOrdering::Acquire;
case BitTest::Release: return llvm::AtomicOrdering::Release;
case BitTest::NoFence: return llvm::AtomicOrdering::Monotonic;
}
llvm_unreachable("invalid interlocking");
}
/// Emit a _bittest* intrinsic. These intrinsics take a pointer to an array of
/// bits and a bit position and read and optionally modify the bit at that
/// position. The position index can be arbitrarily large, i.e. it can be larger
/// than 31 or 63, so we need an indexed load in the general case.
static llvm::Value *EmitBitTestIntrinsic(CodeGenFunction &CGF,
unsigned BuiltinID,
const CallExpr *E) {
Value *BitBase = CGF.EmitScalarExpr(E->getArg(0));
Value *BitPos = CGF.EmitScalarExpr(E->getArg(1));
BitTest BT = BitTest::decodeBitTestBuiltin(BuiltinID);
// X86 has special BT, BTC, BTR, and BTS instructions that handle the array
// indexing operation internally. Use them if possible.
if (CGF.getTarget().getTriple().isX86())
return EmitX86BitTestIntrinsic(CGF, BT, E, BitBase, BitPos);
// Otherwise, use generic code to load one byte and test the bit. Use all but
// the bottom three bits as the array index, and the bottom three bits to form
// a mask.
// Bit = BitBaseI8[BitPos >> 3] & (1 << (BitPos & 0x7)) != 0;
Value *ByteIndex = CGF.Builder.CreateAShr(
BitPos, llvm::ConstantInt::get(BitPos->getType(), 3), "bittest.byteidx");
Value *BitBaseI8 = CGF.Builder.CreatePointerCast(BitBase, CGF.Int8PtrTy);
Address ByteAddr(CGF.Builder.CreateInBoundsGEP(CGF.Int8Ty, BitBaseI8,
ByteIndex, "bittest.byteaddr"),
CharUnits::One());
Value *PosLow =
CGF.Builder.CreateAnd(CGF.Builder.CreateTrunc(BitPos, CGF.Int8Ty),
llvm::ConstantInt::get(CGF.Int8Ty, 0x7));
// The updating instructions will need a mask.
Value *Mask = nullptr;
if (BT.Action != BitTest::TestOnly) {
Mask = CGF.Builder.CreateShl(llvm::ConstantInt::get(CGF.Int8Ty, 1), PosLow,
"bittest.mask");
}
// Check the action and ordering of the interlocked intrinsics.
llvm::AtomicOrdering Ordering = getBitTestAtomicOrdering(BT.Interlocking);
Value *OldByte = nullptr;
if (Ordering != llvm::AtomicOrdering::NotAtomic) {
// Emit a combined atomicrmw load/store operation for the interlocked
// intrinsics.
llvm::AtomicRMWInst::BinOp RMWOp = llvm::AtomicRMWInst::Or;
if (BT.Action == BitTest::Reset) {
Mask = CGF.Builder.CreateNot(Mask);
RMWOp = llvm::AtomicRMWInst::And;
}
OldByte = CGF.Builder.CreateAtomicRMW(RMWOp, ByteAddr.getPointer(), Mask,
Ordering);
} else {
// Emit a plain load for the non-interlocked intrinsics.
OldByte = CGF.Builder.CreateLoad(ByteAddr, "bittest.byte");
Value *NewByte = nullptr;
switch (BT.Action) {
case BitTest::TestOnly:
// Don't store anything.
break;
case BitTest::Complement:
NewByte = CGF.Builder.CreateXor(OldByte, Mask);
break;
case BitTest::Reset:
NewByte = CGF.Builder.CreateAnd(OldByte, CGF.Builder.CreateNot(Mask));
break;
case BitTest::Set:
NewByte = CGF.Builder.CreateOr(OldByte, Mask);
break;
}
if (NewByte)
CGF.Builder.CreateStore(NewByte, ByteAddr);
}
// However we loaded the old byte, either by plain load or atomicrmw, shift
// the bit into the low position and mask it to 0 or 1.
Value *ShiftedByte = CGF.Builder.CreateLShr(OldByte, PosLow, "bittest.shr");
return CGF.Builder.CreateAnd(
ShiftedByte, llvm::ConstantInt::get(CGF.Int8Ty, 1), "bittest.res");
}
static llvm::Value *emitPPCLoadReserveIntrinsic(CodeGenFunction &CGF,
unsigned BuiltinID,
const CallExpr *E) {
Value *Addr = CGF.EmitScalarExpr(E->getArg(0));
SmallString<64> Asm;
raw_svector_ostream AsmOS(Asm);
llvm::IntegerType *RetType = CGF.Int32Ty;
switch (BuiltinID) {
case clang::PPC::BI__builtin_ppc_ldarx:
AsmOS << "ldarx ";
RetType = CGF.Int64Ty;
break;
case clang::PPC::BI__builtin_ppc_lwarx:
AsmOS << "lwarx ";
RetType = CGF.Int32Ty;
break;
case clang::PPC::BI__builtin_ppc_lharx:
AsmOS << "lharx ";
RetType = CGF.Int16Ty;
break;
case clang::PPC::BI__builtin_ppc_lbarx:
AsmOS << "lbarx ";
RetType = CGF.Int8Ty;
break;
default:
llvm_unreachable("Expected only PowerPC load reserve intrinsics");
}
AsmOS << "$0, ${1:y}";
std::string Constraints = "=r,*Z,~{memory}";
std::string MachineClobbers = CGF.getTarget().getClobbers();
if (!MachineClobbers.empty()) {
Constraints += ',';
Constraints += MachineClobbers;
}
llvm::Type *IntPtrType = RetType->getPointerTo();
llvm::FunctionType *FTy =
llvm::FunctionType::get(RetType, {IntPtrType}, false);
llvm::InlineAsm *IA =
llvm::InlineAsm::get(FTy, Asm, Constraints, /*hasSideEffects=*/true);
return CGF.Builder.CreateCall(IA, {Addr});
}
namespace {
enum class MSVCSetJmpKind {
_setjmpex,
_setjmp3,
_setjmp
};
}
/// MSVC handles setjmp a bit differently on different platforms. On every
/// architecture except 32-bit x86, the frame address is passed. On x86, extra
/// parameters can be passed as variadic arguments, but we always pass none.
static RValue EmitMSVCRTSetJmp(CodeGenFunction &CGF, MSVCSetJmpKind SJKind,
const CallExpr *E) {
llvm::Value *Arg1 = nullptr;
llvm::Type *Arg1Ty = nullptr;
StringRef Name;
bool IsVarArg = false;
if (SJKind == MSVCSetJmpKind::_setjmp3) {
Name = "_setjmp3";
Arg1Ty = CGF.Int32Ty;
Arg1 = llvm::ConstantInt::get(CGF.IntTy, 0);
IsVarArg = true;
} else {
Name = SJKind == MSVCSetJmpKind::_setjmp ? "_setjmp" : "_setjmpex";
Arg1Ty = CGF.Int8PtrTy;
if (CGF.getTarget().getTriple().getArch() == llvm::Triple::aarch64) {
Arg1 = CGF.Builder.CreateCall(
CGF.CGM.getIntrinsic(Intrinsic::sponentry, CGF.AllocaInt8PtrTy));
} else
Arg1 = CGF.Builder.CreateCall(
CGF.CGM.getIntrinsic(Intrinsic::frameaddress, CGF.AllocaInt8PtrTy),
llvm::ConstantInt::get(CGF.Int32Ty, 0));
}
// Mark the call site and declaration with ReturnsTwice.
llvm::Type *ArgTypes[2] = {CGF.Int8PtrTy, Arg1Ty};
llvm::AttributeList ReturnsTwiceAttr = llvm::AttributeList::get(
CGF.getLLVMContext(), llvm::AttributeList::FunctionIndex,
llvm::Attribute::ReturnsTwice);
llvm::FunctionCallee SetJmpFn = CGF.CGM.CreateRuntimeFunction(
llvm::FunctionType::get(CGF.IntTy, ArgTypes, IsVarArg), Name,
ReturnsTwiceAttr, /*Local=*/true);
llvm::Value *Buf = CGF.Builder.CreateBitOrPointerCast(
CGF.EmitScalarExpr(E->getArg(0)), CGF.Int8PtrTy);
llvm::Value *Args[] = {Buf, Arg1};
llvm::CallBase *CB = CGF.EmitRuntimeCallOrInvoke(SetJmpFn, Args);
CB->setAttributes(ReturnsTwiceAttr);
return RValue::get(CB);
}
// Many of MSVC builtins are on x64, ARM and AArch64; to avoid repeating code,
// we handle them here.
enum class CodeGenFunction::MSVCIntrin {
_BitScanForward,
_BitScanReverse,
_InterlockedAnd,
_InterlockedDecrement,
_InterlockedExchange,
_InterlockedExchangeAdd,
_InterlockedExchangeSub,
_InterlockedIncrement,
_InterlockedOr,
_InterlockedXor,
_InterlockedExchangeAdd_acq,
_InterlockedExchangeAdd_rel,
_InterlockedExchangeAdd_nf,
_InterlockedExchange_acq,
_InterlockedExchange_rel,
_InterlockedExchange_nf,
_InterlockedCompareExchange_acq,
_InterlockedCompareExchange_rel,
_InterlockedCompareExchange_nf,
_InterlockedCompareExchange128,
_InterlockedCompareExchange128_acq,
_InterlockedCompareExchange128_rel,
_InterlockedCompareExchange128_nf,
_InterlockedOr_acq,
_InterlockedOr_rel,
_InterlockedOr_nf,
_InterlockedXor_acq,
_InterlockedXor_rel,
_InterlockedXor_nf,
_InterlockedAnd_acq,
_InterlockedAnd_rel,
_InterlockedAnd_nf,
_InterlockedIncrement_acq,
_InterlockedIncrement_rel,
_InterlockedIncrement_nf,
_InterlockedDecrement_acq,
_InterlockedDecrement_rel,
_InterlockedDecrement_nf,
__fastfail,
};
static Optional<CodeGenFunction::MSVCIntrin>
translateArmToMsvcIntrin(unsigned BuiltinID) {
using MSVCIntrin = CodeGenFunction::MSVCIntrin;
switch (BuiltinID) {
default:
return None;
case ARM::BI_BitScanForward:
case ARM::BI_BitScanForward64:
return MSVCIntrin::_BitScanForward;
case ARM::BI_BitScanReverse:
case ARM::BI_BitScanReverse64:
return MSVCIntrin::_BitScanReverse;
case ARM::BI_InterlockedAnd64:
return MSVCIntrin::_InterlockedAnd;
case ARM::BI_InterlockedExchange64:
return MSVCIntrin::_InterlockedExchange;
case ARM::BI_InterlockedExchangeAdd64:
return MSVCIntrin::_InterlockedExchangeAdd;
case ARM::BI_InterlockedExchangeSub64:
return MSVCIntrin::_InterlockedExchangeSub;
case ARM::BI_InterlockedOr64:
return MSVCIntrin::_InterlockedOr;
case ARM::BI_InterlockedXor64:
return MSVCIntrin::_InterlockedXor;
case ARM::BI_InterlockedDecrement64:
return MSVCIntrin::_InterlockedDecrement;
case ARM::BI_InterlockedIncrement64:
return MSVCIntrin::_InterlockedIncrement;
case ARM::BI_InterlockedExchangeAdd8_acq:
case ARM::BI_InterlockedExchangeAdd16_acq:
case ARM::BI_InterlockedExchangeAdd_acq:
case ARM::BI_InterlockedExchangeAdd64_acq:
return MSVCIntrin::_InterlockedExchangeAdd_acq;
case ARM::BI_InterlockedExchangeAdd8_rel:
case ARM::BI_InterlockedExchangeAdd16_rel:
case ARM::BI_InterlockedExchangeAdd_rel:
case ARM::BI_InterlockedExchangeAdd64_rel:
return MSVCIntrin::_InterlockedExchangeAdd_rel;
case ARM::BI_InterlockedExchangeAdd8_nf:
case ARM::BI_InterlockedExchangeAdd16_nf:
case ARM::BI_InterlockedExchangeAdd_nf:
case ARM::BI_InterlockedExchangeAdd64_nf:
return MSVCIntrin::_InterlockedExchangeAdd_nf;
case ARM::BI_InterlockedExchange8_acq:
case ARM::BI_InterlockedExchange16_acq:
case ARM::BI_InterlockedExchange_acq:
case ARM::BI_InterlockedExchange64_acq:
return MSVCIntrin::_InterlockedExchange_acq;
case ARM::BI_InterlockedExchange8_rel:
case ARM::BI_InterlockedExchange16_rel:
case ARM::BI_InterlockedExchange_rel:
case ARM::BI_InterlockedExchange64_rel:
return MSVCIntrin::_InterlockedExchange_rel;
case ARM::BI_InterlockedExchange8_nf:
case ARM::BI_InterlockedExchange16_nf:
case ARM::BI_InterlockedExchange_nf:
case ARM::BI_InterlockedExchange64_nf:
return MSVCIntrin::_InterlockedExchange_nf;
case ARM::BI_InterlockedCompareExchange8_acq:
case ARM::BI_InterlockedCompareExchange16_acq:
case ARM::BI_InterlockedCompareExchange_acq:
case ARM::BI_InterlockedCompareExchange64_acq:
return MSVCIntrin::_InterlockedCompareExchange_acq;
case ARM::BI_InterlockedCompareExchange8_rel:
case ARM::BI_InterlockedCompareExchange16_rel:
case ARM::BI_InterlockedCompareExchange_rel:
case ARM::BI_InterlockedCompareExchange64_rel:
return MSVCIntrin::_InterlockedCompareExchange_rel;
case ARM::BI_InterlockedCompareExchange8_nf:
case ARM::BI_InterlockedCompareExchange16_nf:
case ARM::BI_InterlockedCompareExchange_nf:
case ARM::BI_InterlockedCompareExchange64_nf:
return MSVCIntrin::_InterlockedCompareExchange_nf;
case ARM::BI_InterlockedOr8_acq:
case ARM::BI_InterlockedOr16_acq:
case ARM::BI_InterlockedOr_acq:
case ARM::BI_InterlockedOr64_acq:
return MSVCIntrin::_InterlockedOr_acq;
case ARM::BI_InterlockedOr8_rel:
case ARM::BI_InterlockedOr16_rel:
case ARM::BI_InterlockedOr_rel:
case ARM::BI_InterlockedOr64_rel:
return MSVCIntrin::_InterlockedOr_rel;
case ARM::BI_InterlockedOr8_nf:
case ARM::BI_InterlockedOr16_nf:
case ARM::BI_InterlockedOr_nf:
case ARM::BI_InterlockedOr64_nf:
return MSVCIntrin::_InterlockedOr_nf;
case ARM::BI_InterlockedXor8_acq:
case ARM::BI_InterlockedXor16_acq:
case ARM::BI_InterlockedXor_acq:
case ARM::BI_InterlockedXor64_acq:
return MSVCIntrin::_InterlockedXor_acq;
case ARM::BI_InterlockedXor8_rel:
case ARM::BI_InterlockedXor16_rel:
case ARM::BI_InterlockedXor_rel:
case ARM::BI_InterlockedXor64_rel:
return MSVCIntrin::_InterlockedXor_rel;
case ARM::BI_InterlockedXor8_nf:
case ARM::BI_InterlockedXor16_nf:
case ARM::BI_InterlockedXor_nf:
case ARM::BI_InterlockedXor64_nf:
return MSVCIntrin::_InterlockedXor_nf;
case ARM::BI_InterlockedAnd8_acq:
case ARM::BI_InterlockedAnd16_acq:
case ARM::BI_InterlockedAnd_acq:
case ARM::BI_InterlockedAnd64_acq:
return MSVCIntrin::_InterlockedAnd_acq;
case ARM::BI_InterlockedAnd8_rel:
case ARM::BI_InterlockedAnd16_rel:
case ARM::BI_InterlockedAnd_rel:
case ARM::BI_InterlockedAnd64_rel:
return MSVCIntrin::_InterlockedAnd_rel;
case ARM::BI_InterlockedAnd8_nf:
case ARM::BI_InterlockedAnd16_nf:
case ARM::BI_InterlockedAnd_nf:
case ARM::BI_InterlockedAnd64_nf:
return MSVCIntrin::_InterlockedAnd_nf;
case ARM::BI_InterlockedIncrement16_acq:
case ARM::BI_InterlockedIncrement_acq:
case ARM::BI_InterlockedIncrement64_acq:
return MSVCIntrin::_InterlockedIncrement_acq;
case ARM::BI_InterlockedIncrement16_rel:
case ARM::BI_InterlockedIncrement_rel:
case ARM::BI_InterlockedIncrement64_rel:
return MSVCIntrin::_InterlockedIncrement_rel;
case ARM::BI_InterlockedIncrement16_nf:
case ARM::BI_InterlockedIncrement_nf:
case ARM::BI_InterlockedIncrement64_nf:
return MSVCIntrin::_InterlockedIncrement_nf;
case ARM::BI_InterlockedDecrement16_acq:
case ARM::BI_InterlockedDecrement_acq:
case ARM::BI_InterlockedDecrement64_acq:
return MSVCIntrin::_InterlockedDecrement_acq;
case ARM::BI_InterlockedDecrement16_rel:
case ARM::BI_InterlockedDecrement_rel:
case ARM::BI_InterlockedDecrement64_rel:
return MSVCIntrin::_InterlockedDecrement_rel;
case ARM::BI_InterlockedDecrement16_nf:
case ARM::BI_InterlockedDecrement_nf:
case ARM::BI_InterlockedDecrement64_nf:
return MSVCIntrin::_InterlockedDecrement_nf;
}
llvm_unreachable("must return from switch");
}
static Optional<CodeGenFunction::MSVCIntrin>
translateAarch64ToMsvcIntrin(unsigned BuiltinID) {
using MSVCIntrin = CodeGenFunction::MSVCIntrin;
switch (BuiltinID) {
default:
return None;
case AArch64::BI_BitScanForward:
case AArch64::BI_BitScanForward64:
return MSVCIntrin::_BitScanForward;
case AArch64::BI_BitScanReverse:
case AArch64::BI_BitScanReverse64:
return MSVCIntrin::_BitScanReverse;
case AArch64::BI_InterlockedAnd64:
return MSVCIntrin::_InterlockedAnd;
case AArch64::BI_InterlockedExchange64:
return MSVCIntrin::_InterlockedExchange;
case AArch64::BI_InterlockedExchangeAdd64:
return MSVCIntrin::_InterlockedExchangeAdd;
case AArch64::BI_InterlockedExchangeSub64:
return MSVCIntrin::_InterlockedExchangeSub;
case AArch64::BI_InterlockedOr64:
return MSVCIntrin::_InterlockedOr;
case AArch64::BI_InterlockedXor64:
return MSVCIntrin::_InterlockedXor;
case AArch64::BI_InterlockedDecrement64:
return MSVCIntrin::_InterlockedDecrement;
case AArch64::BI_InterlockedIncrement64:
return MSVCIntrin::_InterlockedIncrement;
case AArch64::BI_InterlockedExchangeAdd8_acq:
case AArch64::BI_InterlockedExchangeAdd16_acq:
case AArch64::BI_InterlockedExchangeAdd_acq:
case AArch64::BI_InterlockedExchangeAdd64_acq:
return MSVCIntrin::_InterlockedExchangeAdd_acq;
case AArch64::BI_InterlockedExchangeAdd8_rel:
case AArch64::BI_InterlockedExchangeAdd16_rel:
case AArch64::BI_InterlockedExchangeAdd_rel:
case AArch64::BI_InterlockedExchangeAdd64_rel:
return MSVCIntrin::_InterlockedExchangeAdd_rel;
case AArch64::BI_InterlockedExchangeAdd8_nf:
case AArch64::BI_InterlockedExchangeAdd16_nf:
case AArch64::BI_InterlockedExchangeAdd_nf:
case AArch64::BI_InterlockedExchangeAdd64_nf:
return MSVCIntrin::_InterlockedExchangeAdd_nf;
case AArch64::BI_InterlockedExchange8_acq:
case AArch64::BI_InterlockedExchange16_acq:
case AArch64::BI_InterlockedExchange_acq:
case AArch64::BI_InterlockedExchange64_acq:
return MSVCIntrin::_InterlockedExchange_acq;
case AArch64::BI_InterlockedExchange8_rel:
case AArch64::BI_InterlockedExchange16_rel:
case AArch64::BI_InterlockedExchange_rel:
case AArch64::BI_InterlockedExchange64_rel:
return MSVCIntrin::_InterlockedExchange_rel;
case AArch64::BI_InterlockedExchange8_nf:
case AArch64::BI_InterlockedExchange16_nf:
case AArch64::BI_InterlockedExchange_nf:
case AArch64::BI_InterlockedExchange64_nf:
return MSVCIntrin::_InterlockedExchange_nf;
case AArch64::BI_InterlockedCompareExchange8_acq:
case AArch64::BI_InterlockedCompareExchange16_acq:
case AArch64::BI_InterlockedCompareExchange_acq:
case AArch64::BI_InterlockedCompareExchange64_acq:
return MSVCIntrin::_InterlockedCompareExchange_acq;
case AArch64::BI_InterlockedCompareExchange8_rel:
case AArch64::BI_InterlockedCompareExchange16_rel:
case AArch64::BI_InterlockedCompareExchange_rel:
case AArch64::BI_InterlockedCompareExchange64_rel:
return MSVCIntrin::_InterlockedCompareExchange_rel;
case AArch64::BI_InterlockedCompareExchange8_nf:
case AArch64::BI_InterlockedCompareExchange16_nf:
case AArch64::BI_InterlockedCompareExchange_nf:
case AArch64::BI_InterlockedCompareExchange64_nf:
return MSVCIntrin::_InterlockedCompareExchange_nf;
case AArch64::BI_InterlockedCompareExchange128:
return MSVCIntrin::_InterlockedCompareExchange128;
case AArch64::BI_InterlockedCompareExchange128_acq:
return MSVCIntrin::_InterlockedCompareExchange128_acq;
case AArch64::BI_InterlockedCompareExchange128_nf:
return MSVCIntrin::_InterlockedCompareExchange128_nf;
case AArch64::BI_InterlockedCompareExchange128_rel:
return MSVCIntrin::_InterlockedCompareExchange128_rel;
case AArch64::BI_InterlockedOr8_acq:
case AArch64::BI_InterlockedOr16_acq:
case AArch64::BI_InterlockedOr_acq:
case AArch64::BI_InterlockedOr64_acq:
return MSVCIntrin::_InterlockedOr_acq;
case AArch64::BI_InterlockedOr8_rel:
case AArch64::BI_InterlockedOr16_rel:
case AArch64::BI_InterlockedOr_rel:
case AArch64::BI_InterlockedOr64_rel:
return MSVCIntrin::_InterlockedOr_rel;
case AArch64::BI_InterlockedOr8_nf:
case AArch64::BI_InterlockedOr16_nf:
case AArch64::BI_InterlockedOr_nf:
case AArch64::BI_InterlockedOr64_nf:
return MSVCIntrin::_InterlockedOr_nf;
case AArch64::BI_InterlockedXor8_acq:
case AArch64::BI_InterlockedXor16_acq:
case AArch64::BI_InterlockedXor_acq:
case AArch64::BI_InterlockedXor64_acq:
return MSVCIntrin::_InterlockedXor_acq;
case AArch64::BI_InterlockedXor8_rel:
case AArch64::BI_InterlockedXor16_rel:
case AArch64::BI_InterlockedXor_rel:
case AArch64::BI_InterlockedXor64_rel:
return MSVCIntrin::_InterlockedXor_rel;
case AArch64::BI_InterlockedXor8_nf:
case AArch64::BI_InterlockedXor16_nf:
case AArch64::BI_InterlockedXor_nf:
case AArch64::BI_InterlockedXor64_nf:
return MSVCIntrin::_InterlockedXor_nf;
case AArch64::BI_InterlockedAnd8_acq:
case AArch64::BI_InterlockedAnd16_acq:
case AArch64::BI_InterlockedAnd_acq:
case AArch64::BI_InterlockedAnd64_acq:
return MSVCIntrin::_InterlockedAnd_acq;
case AArch64::BI_InterlockedAnd8_rel:
case AArch64::BI_InterlockedAnd16_rel:
case AArch64::BI_InterlockedAnd_rel:
case AArch64::BI_InterlockedAnd64_rel:
return MSVCIntrin::_InterlockedAnd_rel;
case AArch64::BI_InterlockedAnd8_nf:
case AArch64::BI_InterlockedAnd16_nf:
case AArch64::BI_InterlockedAnd_nf:
case AArch64::BI_InterlockedAnd64_nf:
return MSVCIntrin::_InterlockedAnd_nf;
case AArch64::BI_InterlockedIncrement16_acq:
case AArch64::BI_InterlockedIncrement_acq:
case AArch64::BI_InterlockedIncrement64_acq:
return MSVCIntrin::_InterlockedIncrement_acq;
case AArch64::BI_InterlockedIncrement16_rel:
case AArch64::BI_InterlockedIncrement_rel:
case AArch64::BI_InterlockedIncrement64_rel:
return MSVCIntrin::_InterlockedIncrement_rel;
case AArch64::BI_InterlockedIncrement16_nf:
case AArch64::BI_InterlockedIncrement_nf:
case AArch64::BI_InterlockedIncrement64_nf:
return MSVCIntrin::_InterlockedIncrement_nf;
case AArch64::BI_InterlockedDecrement16_acq:
case AArch64::BI_InterlockedDecrement_acq:
case AArch64::BI_InterlockedDecrement64_acq:
return MSVCIntrin::_InterlockedDecrement_acq;
case AArch64::BI_InterlockedDecrement16_rel:
case AArch64::BI_InterlockedDecrement_rel:
case AArch64::BI_InterlockedDecrement64_rel:
return MSVCIntrin::_InterlockedDecrement_rel;
case AArch64::BI_InterlockedDecrement16_nf:
case AArch64::BI_InterlockedDecrement_nf:
case AArch64::BI_InterlockedDecrement64_nf:
return MSVCIntrin::_InterlockedDecrement_nf;
}
llvm_unreachable("must return from switch");
}
static Optional<CodeGenFunction::MSVCIntrin>
translateX86ToMsvcIntrin(unsigned BuiltinID) {
using MSVCIntrin = CodeGenFunction::MSVCIntrin;
switch (BuiltinID) {
default:
return None;
case clang::X86::BI_BitScanForward:
case clang::X86::BI_BitScanForward64:
return MSVCIntrin::_BitScanForward;
case clang::X86::BI_BitScanReverse:
case clang::X86::BI_BitScanReverse64:
return MSVCIntrin::_BitScanReverse;
case clang::X86::BI_InterlockedAnd64:
return MSVCIntrin::_InterlockedAnd;
case clang::X86::BI_InterlockedCompareExchange128:
return MSVCIntrin::_InterlockedCompareExchange128;
case clang::X86::BI_InterlockedExchange64:
return MSVCIntrin::_InterlockedExchange;
case clang::X86::BI_InterlockedExchangeAdd64:
return MSVCIntrin::_InterlockedExchangeAdd;
case clang::X86::BI_InterlockedExchangeSub64:
return MSVCIntrin::_InterlockedExchangeSub;
case clang::X86::BI_InterlockedOr64:
return MSVCIntrin::_InterlockedOr;
case clang::X86::BI_InterlockedXor64:
return MSVCIntrin::_InterlockedXor;
case clang::X86::BI_InterlockedDecrement64:
return MSVCIntrin::_InterlockedDecrement;
case clang::X86::BI_InterlockedIncrement64:
return MSVCIntrin::_InterlockedIncrement;
}
llvm_unreachable("must return from switch");
}
// Emit an MSVC intrinsic. Assumes that arguments have *not* been evaluated.
Value *CodeGenFunction::EmitMSVCBuiltinExpr(MSVCIntrin BuiltinID,
const CallExpr *E) {
switch (BuiltinID) {
case MSVCIntrin::_BitScanForward:
case MSVCIntrin::_BitScanReverse: {
Address IndexAddress(EmitPointerWithAlignment(E->getArg(0)));
Value *ArgValue = EmitScalarExpr(E->getArg(1));
llvm::Type *ArgType = ArgValue->getType();
llvm::Type *IndexType =
IndexAddress.getPointer()->getType()->getPointerElementType();
llvm::Type *ResultType = ConvertType(E->getType());
Value *ArgZero = llvm::Constant::getNullValue(ArgType);
Value *ResZero = llvm::Constant::getNullValue(ResultType);
Value *ResOne = llvm::ConstantInt::get(ResultType, 1);
BasicBlock *Begin = Builder.GetInsertBlock();
BasicBlock *End = createBasicBlock("bitscan_end", this->CurFn);
Builder.SetInsertPoint(End);
PHINode *Result = Builder.CreatePHI(ResultType, 2, "bitscan_result");
Builder.SetInsertPoint(Begin);
Value *IsZero = Builder.CreateICmpEQ(ArgValue, ArgZero);
BasicBlock *NotZero = createBasicBlock("bitscan_not_zero", this->CurFn);
Builder.CreateCondBr(IsZero, End, NotZero);
Result->addIncoming(ResZero, Begin);
Builder.SetInsertPoint(NotZero);
if (BuiltinID == MSVCIntrin::_BitScanForward) {
Function *F = CGM.getIntrinsic(Intrinsic::cttz, ArgType);
Value *ZeroCount = Builder.CreateCall(F, {ArgValue, Builder.getTrue()});
ZeroCount = Builder.CreateIntCast(ZeroCount, IndexType, false);
Builder.CreateStore(ZeroCount, IndexAddress, false);
} else {
unsigned ArgWidth = cast<llvm::IntegerType>(ArgType)->getBitWidth();
Value *ArgTypeLastIndex = llvm::ConstantInt::get(IndexType, ArgWidth - 1);
Function *F = CGM.getIntrinsic(Intrinsic::ctlz, ArgType);
Value *ZeroCount = Builder.CreateCall(F, {ArgValue, Builder.getTrue()});
ZeroCount = Builder.CreateIntCast(ZeroCount, IndexType, false);
Value *Index = Builder.CreateNSWSub(ArgTypeLastIndex, ZeroCount);
Builder.CreateStore(Index, IndexAddress, false);
}
Builder.CreateBr(End);
Result->addIncoming(ResOne, NotZero);
Builder.SetInsertPoint(End);
return Result;
}
case MSVCIntrin::_InterlockedAnd:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::And, E);
case MSVCIntrin::_InterlockedExchange:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Xchg, E);
case MSVCIntrin::_InterlockedExchangeAdd:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Add, E);
case MSVCIntrin::_InterlockedExchangeSub:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Sub, E);
case MSVCIntrin::_InterlockedOr:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Or, E);
case MSVCIntrin::_InterlockedXor:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Xor, E);
case MSVCIntrin::_InterlockedExchangeAdd_acq:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Add, E,
AtomicOrdering::Acquire);
case MSVCIntrin::_InterlockedExchangeAdd_rel:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Add, E,
AtomicOrdering::Release);
case MSVCIntrin::_InterlockedExchangeAdd_nf:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Add, E,
AtomicOrdering::Monotonic);
case MSVCIntrin::_InterlockedExchange_acq:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Xchg, E,
AtomicOrdering::Acquire);
case MSVCIntrin::_InterlockedExchange_rel:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Xchg, E,
AtomicOrdering::Release);
case MSVCIntrin::_InterlockedExchange_nf:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Xchg, E,
AtomicOrdering::Monotonic);
case MSVCIntrin::_InterlockedCompareExchange_acq:
return EmitAtomicCmpXchgForMSIntrin(*this, E, AtomicOrdering::Acquire);
case MSVCIntrin::_InterlockedCompareExchange_rel:
return EmitAtomicCmpXchgForMSIntrin(*this, E, AtomicOrdering::Release);
case MSVCIntrin::_InterlockedCompareExchange_nf:
return EmitAtomicCmpXchgForMSIntrin(*this, E, AtomicOrdering::Monotonic);
case MSVCIntrin::_InterlockedCompareExchange128:
return EmitAtomicCmpXchg128ForMSIntrin(
*this, E, AtomicOrdering::SequentiallyConsistent);
case MSVCIntrin::_InterlockedCompareExchange128_acq:
return EmitAtomicCmpXchg128ForMSIntrin(*this, E, AtomicOrdering::Acquire);
case MSVCIntrin::_InterlockedCompareExchange128_rel:
return EmitAtomicCmpXchg128ForMSIntrin(*this, E, AtomicOrdering::Release);
case MSVCIntrin::_InterlockedCompareExchange128_nf:
return EmitAtomicCmpXchg128ForMSIntrin(*this, E, AtomicOrdering::Monotonic);
case MSVCIntrin::_InterlockedOr_acq:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Or, E,
AtomicOrdering::Acquire);
case MSVCIntrin::_InterlockedOr_rel:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Or, E,
AtomicOrdering::Release);
case MSVCIntrin::_InterlockedOr_nf:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Or, E,
AtomicOrdering::Monotonic);
case MSVCIntrin::_InterlockedXor_acq:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Xor, E,
AtomicOrdering::Acquire);
case MSVCIntrin::_InterlockedXor_rel:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Xor, E,
AtomicOrdering::Release);
case MSVCIntrin::_InterlockedXor_nf:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::Xor, E,
AtomicOrdering::Monotonic);
case MSVCIntrin::_InterlockedAnd_acq:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::And, E,
AtomicOrdering::Acquire);
case MSVCIntrin::_InterlockedAnd_rel:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::And, E,
AtomicOrdering::Release);
case MSVCIntrin::_InterlockedAnd_nf:
return MakeBinaryAtomicValue(*this, AtomicRMWInst::And, E,
AtomicOrdering::Monotonic);
case MSVCIntrin::_InterlockedIncrement_acq:
return EmitAtomicIncrementValue(*this, E, AtomicOrdering::Acquire);
case MSVCIntrin::_InterlockedIncrement_rel:
return EmitAtomicIncrementValue(*this, E, AtomicOrdering::Release);
case MSVCIntrin::_InterlockedIncrement_nf:
return EmitAtomicIncrementValue(*this, E, AtomicOrdering::Monotonic);
case MSVCIntrin::_InterlockedDecrement_acq:
return EmitAtomicDecrementValue(*this, E, AtomicOrdering::Acquire);
case MSVCIntrin::_InterlockedDecrement_rel:
return EmitAtomicDecrementValue(*this, E, AtomicOrdering::Release);
case MSVCIntrin::_InterlockedDecrement_nf:
return EmitAtomicDecrementValue(*this, E, AtomicOrdering::Monotonic);
case MSVCIntrin::_InterlockedDecrement:
return EmitAtomicDecrementValue(*this, E);
case MSVCIntrin::_InterlockedIncrement:
return EmitAtomicIncrementValue(*this, E);
case MSVCIntrin::__fastfail: {
// Request immediate process termination from the kernel. The instruction
// sequences to do this are documented on MSDN:
// https://msdn.microsoft.com/en-us/library/dn774154.aspx
llvm::Triple::ArchType ISA = getTarget().getTriple().getArch();
StringRef Asm, Constraints;
switch (ISA) {
default:
ErrorUnsupported(E, "__fastfail call for this architecture");
break;
case llvm::Triple::x86:
case llvm::Triple::x86_64:
Asm = "int $$0x29";
Constraints = "{cx}";
break;
case llvm::Triple::thumb:
Asm = "udf #251";
Constraints = "{r0}";
break;
case llvm::Triple::aarch64:
Asm = "brk #0xF003";
Constraints = "{w0}";
}
llvm::FunctionType *FTy = llvm::FunctionType::get(VoidTy, {Int32Ty}, false);
llvm::InlineAsm *IA =
llvm::InlineAsm::get(FTy, Asm, Constraints, /*hasSideEffects=*/true);
llvm::AttributeList NoReturnAttr = llvm::AttributeList::get(
getLLVMContext(), llvm::AttributeList::FunctionIndex,
llvm::Attribute::NoReturn);
llvm::CallInst *CI = Builder.CreateCall(IA, EmitScalarExpr(E->getArg(0)));
CI->setAttributes(NoReturnAttr);
return CI;
}
}
llvm_unreachable("Incorrect MSVC intrinsic!");
}
namespace {
// ARC cleanup for __builtin_os_log_format
struct CallObjCArcUse final : EHScopeStack::Cleanup {
CallObjCArcUse(llvm::Value *object) : object(object) {}
llvm::Value *object;
void Emit(CodeGenFunction &CGF, Flags flags) override {
CGF.EmitARCIntrinsicUse(object);
}
};
}
Value *CodeGenFunction::EmitCheckedArgForBuiltin(const Expr *E,
BuiltinCheckKind Kind) {
assert((Kind == BCK_CLZPassedZero || Kind == BCK_CTZPassedZero)
&& "Unsupported builtin check kind");
Value *ArgValue = EmitScalarExpr(E);
if (!SanOpts.has(SanitizerKind::Builtin) || !getTarget().isCLZForZeroUndef())
return ArgValue;
SanitizerScope SanScope(this);
Value *Cond = Builder.CreateICmpNE(
ArgValue, llvm::Constant::getNullValue(ArgValue->getType()));
EmitCheck(std::make_pair(Cond, SanitizerKind::Builtin),
SanitizerHandler::InvalidBuiltin,
{EmitCheckSourceLocation(E->getExprLoc()),
llvm::ConstantInt::get(Builder.getInt8Ty(), Kind)},
None);
return ArgValue;
}
/// Get the argument type for arguments to os_log_helper.
static CanQualType getOSLogArgType(ASTContext &C, int Size) {
QualType UnsignedTy = C.getIntTypeForBitwidth(Size * 8, /*Signed=*/false);
return C.getCanonicalType(UnsignedTy);
}
llvm::Function *CodeGenFunction::generateBuiltinOSLogHelperFunction(
const analyze_os_log::OSLogBufferLayout &Layout,
CharUnits BufferAlignment) {
ASTContext &Ctx = getContext();
llvm::SmallString<64> Name;
{
raw_svector_ostream OS(Name);
OS << "__os_log_helper";
OS << "_" << BufferAlignment.getQuantity();
OS << "_" << int(Layout.getSummaryByte());
OS << "_" << int(Layout.getNumArgsByte());
for (const auto &Item : Layout.Items)
OS << "_" << int(Item.getSizeByte()) << "_"
<< int(Item.getDescriptorByte());
}
if (llvm::Function *F = CGM.getModule().getFunction(Name))
return F;
llvm::SmallVector<QualType, 4> ArgTys;
FunctionArgList Args;
Args.push_back(ImplicitParamDecl::Create(
Ctx, nullptr, SourceLocation(), &Ctx.Idents.get("buffer"), Ctx.VoidPtrTy,
ImplicitParamDecl::Other));
ArgTys.emplace_back(Ctx.VoidPtrTy);
for (unsigned int I = 0, E = Layout.Items.size(); I < E; ++I) {
char Size = Layout.Items[I].getSizeByte();
if (!Size)
continue;
QualType ArgTy = getOSLogArgType(Ctx, Size);
Args.push_back(ImplicitParamDecl::Create(
Ctx, nullptr, SourceLocation(),
&Ctx.Idents.get(std::string("arg") + llvm::to_string(I)), ArgTy,
ImplicitParamDecl::Other));
ArgTys.emplace_back(ArgTy);
}
QualType ReturnTy = Ctx.VoidTy;
// The helper function has linkonce_odr linkage to enable the linker to merge
// identical functions. To ensure the merging always happens, 'noinline' is
// attached to the function when compiling with -Oz.
const CGFunctionInfo &FI =
CGM.getTypes().arrangeBuiltinFunctionDeclaration(ReturnTy, Args);
llvm::FunctionType *FuncTy = CGM.getTypes().GetFunctionType(FI);
llvm::Function *Fn = llvm::Function::Create(
FuncTy, llvm::GlobalValue::LinkOnceODRLinkage, Name, &CGM.getModule());
Fn->setVisibility(llvm::GlobalValue::HiddenVisibility);
CGM.SetLLVMFunctionAttributes(GlobalDecl(), FI, Fn, /*IsThunk=*/false);
CGM.SetLLVMFunctionAttributesForDefinition(nullptr, Fn);
Fn->setDoesNotThrow();
// Attach 'noinline' at -Oz.
if (CGM.getCodeGenOpts().OptimizeSize == 2)
Fn->addFnAttr(llvm::Attribute::NoInline);
auto NL = ApplyDebugLocation::CreateEmpty(*this);
StartFunction(GlobalDecl(), ReturnTy, Fn, FI, Args);
// Create a scope with an artificial location for the body of this function.
auto AL = ApplyDebugLocation::CreateArtificial(*this);
CharUnits Offset;
Address BufAddr(Builder.CreateLoad(GetAddrOfLocalVar(Args[0]), "buf"),
BufferAlignment);
Builder.CreateStore(Builder.getInt8(Layout.getSummaryByte()),
Builder.CreateConstByteGEP(BufAddr, Offset++, "summary"));
Builder.CreateStore(Builder.getInt8(Layout.getNumArgsByte()),
Builder.CreateConstByteGEP(BufAddr, Offset++, "numArgs"));
unsigned I = 1;
for (const auto &Item : Layout.Items) {
Builder.CreateStore(
Builder.getInt8(Item.getDescriptorByte()),
Builder.CreateConstByteGEP(BufAddr, Offset++, "argDescriptor"));
Builder.CreateStore(
Builder.getInt8(Item.getSizeByte()),
Builder.CreateConstByteGEP(BufAddr, Offset++, "argSize"));
CharUnits Size = Item.size();
if (!Size.getQuantity())
continue;
Address Arg = GetAddrOfLocalVar(Args[I]);
Address Addr = Builder.CreateConstByteGEP(BufAddr, Offset, "argData");
Addr = Builder.CreateBitCast(Addr, Arg.getPointer()->getType(),
"argDataCast");
Builder.CreateStore(Builder.CreateLoad(Arg), Addr);
Offset += Size;
++I;
}
FinishFunction();
return Fn;
}
RValue CodeGenFunction::emitBuiltinOSLogFormat(const CallExpr &E) {
assert(E.getNumArgs() >= 2 &&
"__builtin_os_log_format takes at least 2 arguments");
ASTContext &Ctx = getContext();
analyze_os_log::OSLogBufferLayout Layout;
analyze_os_log::computeOSLogBufferLayout(Ctx, &E, Layout);
Address BufAddr = EmitPointerWithAlignment(E.getArg(0));
llvm::SmallVector<llvm::Value *, 4> RetainableOperands;
// Ignore argument 1, the format string. It is not currently used.
CallArgList Args;
Args.add(RValue::get(BufAddr.getPointer()), Ctx.VoidPtrTy);
for (const auto &Item : Layout.Items) {
int Size = Item.getSizeByte();
if (!Size)
continue;
llvm::Value *ArgVal;
if (Item.getKind() == analyze_os_log::OSLogBufferItem::MaskKind) {
uint64_t Val = 0;
for (unsigned I = 0, E = Item.getMaskType().size(); I < E; ++I)
Val |= ((uint64_t)Item.getMaskType()[I]) << I * 8;
ArgVal = llvm::Constant::getIntegerValue(Int64Ty, llvm::APInt(64, Val));
} else if (const Expr *TheExpr = Item.getExpr()) {
ArgVal = EmitScalarExpr(TheExpr, /*Ignore*/ false);
// If a temporary object that requires destruction after the full
// expression is passed, push a lifetime-extended cleanup to extend its
// lifetime to the end of the enclosing block scope.
auto LifetimeExtendObject = [&](const Expr *E) {
E = E->IgnoreParenCasts();
// Extend lifetimes of objects returned by function calls and message
// sends.
// FIXME: We should do this in other cases in which temporaries are
// created including arguments of non-ARC types (e.g., C++
// temporaries).
if (isa<CallExpr>(E) || isa<ObjCMessageExpr>(E))
return true;
return false;
};
if (TheExpr->getType()->isObjCRetainableType() &&
getLangOpts().ObjCAutoRefCount && LifetimeExtendObject(TheExpr)) {
assert(getEvaluationKind(TheExpr->getType()) == TEK_Scalar &&
"Only scalar can be a ObjC retainable type");
if (!isa<Constant>(ArgVal)) {
CleanupKind Cleanup = getARCCleanupKind();
QualType Ty = TheExpr->getType();
Address Alloca = Address::invalid();
Address Addr = CreateMemTemp(Ty, "os.log.arg", &Alloca);
ArgVal = EmitARCRetain(Ty, ArgVal);
Builder.CreateStore(ArgVal, Addr);
pushLifetimeExtendedDestroy(Cleanup, Alloca, Ty,
CodeGenFunction::destroyARCStrongPrecise,
Cleanup & EHCleanup);
// Push a clang.arc.use call to ensure ARC optimizer knows that the
// argument has to be alive.
if (CGM.getCodeGenOpts().OptimizationLevel != 0)
pushCleanupAfterFullExpr<CallObjCArcUse>(Cleanup, ArgVal);
}
}
} else {
ArgVal = Builder.getInt32(Item.getConstValue().getQuantity());
}
unsigned ArgValSize =
CGM.getDataLayout().getTypeSizeInBits(ArgVal->getType());
llvm::IntegerType *IntTy = llvm::Type::getIntNTy(getLLVMContext(),
ArgValSize);
ArgVal = Builder.CreateBitOrPointerCast(ArgVal, IntTy);
CanQualType ArgTy = getOSLogArgType(Ctx, Size);
// If ArgVal has type x86_fp80, zero-extend ArgVal.
ArgVal = Builder.CreateZExtOrBitCast(ArgVal, ConvertType(ArgTy));
Args.add(RValue::get(ArgVal), ArgTy);
}
const CGFunctionInfo &FI =
CGM.getTypes().arrangeBuiltinFunctionCall(Ctx.VoidTy, Args);
llvm::Function *F = CodeGenFunction(CGM).generateBuiltinOSLogHelperFunction(
Layout, BufAddr.getAlignment());
EmitCall(FI, CGCallee::forDirect(F), ReturnValueSlot(), Args);
return RValue::get(BufAddr.getPointer());
}
static bool isSpecialUnsignedMultiplySignedResult(
unsigned BuiltinID, WidthAndSignedness Op1Info, WidthAndSignedness Op2Info,
WidthAndSignedness ResultInfo) {
return BuiltinID == Builtin::BI__builtin_mul_overflow &&
Op1Info.Width == Op2Info.Width && Op2Info.Width == ResultInfo.Width &&
!Op1Info.Signed && !Op2Info.Signed && ResultInfo.Signed;
}
static RValue EmitCheckedUnsignedMultiplySignedResult(
CodeGenFunction &CGF, const clang::Expr *Op1, WidthAndSignedness Op1Info,
const clang::Expr *Op2, WidthAndSignedness Op2Info,
const clang::Expr *ResultArg, QualType ResultQTy,
WidthAndSignedness ResultInfo) {
assert(isSpecialUnsignedMultiplySignedResult(
Builtin::BI__builtin_mul_overflow, Op1Info, Op2Info, ResultInfo) &&
"Cannot specialize this multiply");
llvm::Value *V1 = CGF.EmitScalarExpr(Op1);
llvm::Value *V2 = CGF.EmitScalarExpr(Op2);
llvm::Value *HasOverflow;
llvm::Value *Result = EmitOverflowIntrinsic(
CGF, llvm::Intrinsic::umul_with_overflow, V1, V2, HasOverflow);
// The intrinsic call will detect overflow when the value is > UINT_MAX,
// however, since the original builtin had a signed result, we need to report
// an overflow when the result is greater than INT_MAX.
auto IntMax = llvm::APInt::getSignedMaxValue(ResultInfo.Width);
llvm::Value *IntMaxValue = llvm::ConstantInt::get(Result->getType(), IntMax);
llvm::Value *IntMaxOverflow = CGF.Builder.CreateICmpUGT(Result, IntMaxValue);
HasOverflow = CGF.Builder.CreateOr(HasOverflow, IntMaxOverflow);
bool isVolatile =
ResultArg->getType()->getPointeeType().isVolatileQualified();
Address ResultPtr = CGF.EmitPointerWithAlignment(ResultArg);
CGF.Builder.CreateStore(CGF.EmitToMemory(Result, ResultQTy), ResultPtr,
isVolatile);
return RValue::get(HasOverflow);
}
/// Determine if a binop is a checked mixed-sign multiply we can specialize.
static bool isSpecialMixedSignMultiply(unsigned BuiltinID,
WidthAndSignedness Op1Info,
WidthAndSignedness Op2Info,
WidthAndSignedness ResultInfo) {
return BuiltinID == Builtin::BI__builtin_mul_overflow &&
std::max(Op1Info.Width, Op2Info.Width) >= ResultInfo.Width &&
Op1Info.Signed != Op2Info.Signed;
}
/// Emit a checked mixed-sign multiply. This is a cheaper specialization of
/// the generic checked-binop irgen.
static RValue
EmitCheckedMixedSignMultiply(CodeGenFunction &CGF, const clang::Expr *Op1,
WidthAndSignedness Op1Info, const clang::Expr *Op2,
WidthAndSignedness Op2Info,
const clang::Expr *ResultArg, QualType ResultQTy,
WidthAndSignedness ResultInfo) {
assert(isSpecialMixedSignMultiply(Builtin::BI__builtin_mul_overflow, Op1Info,
Op2Info, ResultInfo) &&
"Not a mixed-sign multipliction we can specialize");
// Emit the signed and unsigned operands.
const clang::Expr *SignedOp = Op1Info.Signed ? Op1 : Op2;
const clang::Expr *UnsignedOp = Op1Info.Signed ? Op2 : Op1;
llvm::Value *Signed = CGF.EmitScalarExpr(SignedOp);
llvm::Value *Unsigned = CGF.EmitScalarExpr(UnsignedOp);
unsigned SignedOpWidth = Op1Info.Signed ? Op1Info.Width : Op2Info.Width;
unsigned UnsignedOpWidth = Op1Info.Signed ? Op2Info.Width : Op1Info.Width;
// One of the operands may be smaller than the other. If so, [s|z]ext it.
if (SignedOpWidth < UnsignedOpWidth)
Signed = CGF.Builder.CreateSExt(Signed, Unsigned->getType(), "op.sext");
if (UnsignedOpWidth < SignedOpWidth)
Unsigned = CGF.Builder.CreateZExt(Unsigned, Signed->getType(), "op.zext");
llvm::Type *OpTy = Signed->getType();
llvm::Value *Zero = llvm::Constant::getNullValue(OpTy);
Address ResultPtr = CGF.EmitPointerWithAlignment(ResultArg);
llvm::Type *ResTy = ResultPtr.getElementType();
unsigned OpWidth = std::max(Op1Info.Width, Op2Info.Width);
// Take the absolute value of the signed operand.
llvm::Value *IsNegative = CGF.Builder.CreateICmpSLT(Signed, Zero);
llvm::Value *AbsOfNegative = CGF.Builder.CreateSub(Zero, Signed);
llvm::Value *AbsSigned =
CGF.Builder.CreateSelect(IsNegative, AbsOfNegative, Signed);
// Perform a checked unsigned multiplication.
llvm::Value *UnsignedOverflow;
llvm::Value *UnsignedResult =
EmitOverflowIntrinsic(CGF, llvm::Intrinsic::umul_with_overflow, AbsSigned,
Unsigned, UnsignedOverflow);
llvm::Value *Overflow, *Result;
if (ResultInfo.Signed) {
// Signed overflow occurs if the result is greater than INT_MAX or lesser
// than INT_MIN, i.e when |Result| > (INT_MAX + IsNegative).
auto IntMax =
llvm::APInt::getSignedMaxValue(ResultInfo.Width).zextOrSelf(OpWidth);
llvm::Value *MaxResult =
CGF.Builder.CreateAdd(llvm::ConstantInt::get(OpTy, IntMax),
CGF.Builder.CreateZExt(IsNegative, OpTy));
llvm::Value *SignedOverflow =
CGF.Builder.CreateICmpUGT(UnsignedResult, MaxResult);
Overflow = CGF.Builder.CreateOr(UnsignedOverflow, SignedOverflow);
// Prepare the signed result (possibly by negating it).
llvm::Value *NegativeResult = CGF.Builder.CreateNeg(UnsignedResult);
llvm::Value *SignedResult =
CGF.Builder.CreateSelect(IsNegative, NegativeResult, UnsignedResult);
Result = CGF.Builder.CreateTrunc(SignedResult, ResTy);
} else {
// Unsigned overflow occurs if the result is < 0 or greater than UINT_MAX.
llvm::Value *Underflow = CGF.Builder.CreateAnd(
IsNegative, CGF.Builder.CreateIsNotNull(UnsignedResult));
Overflow = CGF.Builder.CreateOr(UnsignedOverflow, Underflow);
if (ResultInfo.Width < OpWidth) {
auto IntMax =
llvm::APInt::getMaxValue(ResultInfo.Width).zext(OpWidth);
llvm::Value *TruncOverflow = CGF.Builder.CreateICmpUGT(
UnsignedResult, llvm::ConstantInt::get(OpTy, IntMax));
Overflow = CGF.Builder.CreateOr(Overflow, TruncOverflow);
}
// Negate the product if it would be negative in infinite precision.
Result = CGF.Builder.CreateSelect(
IsNegative, CGF.Builder.CreateNeg(UnsignedResult), UnsignedResult);
Result = CGF.Builder.CreateTrunc(Result, ResTy);
}
assert(Overflow && Result && "Missing overflow or result");
bool isVolatile =
ResultArg->getType()->getPointeeType().isVolatileQualified();
CGF.Builder.CreateStore(CGF.EmitToMemory(Result, ResultQTy), ResultPtr,
isVolatile);
return RValue::get(Overflow);
}
static llvm::Value *dumpRecord(CodeGenFunction &CGF, QualType RType,
Value *&RecordPtr, CharUnits Align,
llvm::FunctionCallee Func, int Lvl) {
ASTContext &Context = CGF.getContext();
RecordDecl *RD = RType->castAs<RecordType>()->getDecl()->getDefinition();
std::string Pad = std::string(Lvl * 4, ' ');
Value *GString =
CGF.Builder.CreateGlobalStringPtr(RType.getAsString() + " {\n");
Value *Res = CGF.Builder.CreateCall(Func, {GString});
static llvm::DenseMap<QualType, const char *> Types;
if (Types.empty()) {
Types[Context.CharTy] = "%c";
Types[Context.BoolTy] = "%d";
Types[Context.SignedCharTy] = "%hhd";
Types[Context.UnsignedCharTy] = "%hhu";
Types[Context.IntTy] = "%d";
Types[Context.UnsignedIntTy] = "%u";
Types[Context.LongTy] = "%ld";
Types[Context.UnsignedLongTy] = "%lu";
Types[Context.LongLongTy] = "%lld";
Types[Context.UnsignedLongLongTy] = "%llu";
Types[Context.ShortTy] = "%hd";
Types[Context.UnsignedShortTy] = "%hu";
Types[Context.VoidPtrTy] = "%p";
Types[Context.FloatTy] = "%f";
Types[Context.DoubleTy] = "%f";
Types[Context.LongDoubleTy] = "%Lf";
Types[Context.getPointerType(Context.CharTy)] = "%s";
Types[Context.getPointerType(Context.getConstType(Context.CharTy))] = "%s";
}
for (const auto *FD : RD->fields()) {
Value *FieldPtr = RecordPtr;
if (RD->isUnion())
FieldPtr = CGF.Builder.CreatePointerCast(
FieldPtr, CGF.ConvertType(Context.getPointerType(FD->getType())));
else
FieldPtr = CGF.Builder.CreateStructGEP(CGF.ConvertType(RType), FieldPtr,
FD->getFieldIndex());
GString = CGF.Builder.CreateGlobalStringPtr(
llvm::Twine(Pad)
.concat(FD->getType().getAsString())
.concat(llvm::Twine(' '))
.concat(FD->getNameAsString())
.concat(" : ")
.str());
Value *TmpRes = CGF.Builder.CreateCall(Func, {GString});
Res = CGF.Builder.CreateAdd(Res, TmpRes);
QualType CanonicalType =
FD->getType().getUnqualifiedType().getCanonicalType();
// We check whether we are in a recursive type
if (CanonicalType->isRecordType()) {
TmpRes = dumpRecord(CGF, CanonicalType, FieldPtr, Align, Func, Lvl + 1);
Res = CGF.Builder.CreateAdd(TmpRes, Res);
continue;
}
// We try to determine the best format to print the current field
llvm::Twine Format = Types.find(CanonicalType) == Types.end()
? Types[Context.VoidPtrTy]
: Types[CanonicalType];
Address FieldAddress = Address(FieldPtr, Align);
FieldPtr = CGF.Builder.CreateLoad(FieldAddress);
// FIXME Need to handle bitfield here
GString = CGF.Builder.CreateGlobalStringPtr(
Format.concat(llvm::Twine('\n')).str());
TmpRes = CGF.Builder.CreateCall(Func, {GString, FieldPtr});
Res = CGF.Builder.CreateAdd(Res, TmpRes);
}
GString = CGF.Builder.CreateGlobalStringPtr(Pad + "}\n");
Value *TmpRes = CGF.Builder.CreateCall(Func, {GString});
Res = CGF.Builder.CreateAdd(Res, TmpRes);
return Res;
}
static bool
TypeRequiresBuiltinLaunderImp(const ASTContext &Ctx, QualType Ty,
llvm::SmallPtrSetImpl<const Decl *> &Seen) {
if (const auto *Arr = Ctx.getAsArrayType(Ty))
Ty = Ctx.getBaseElementType(Arr);
const auto *Record = Ty->getAsCXXRecordDecl();
if (!Record)
return false;
// We've already checked this type, or are in the process of checking it.
if (!Seen.insert(Record).second)
return false;
assert(Record->hasDefinition() &&
"Incomplete types should already be diagnosed");
if (Record->isDynamicClass())
return true;
for (FieldDecl *F : Record->fields()) {
if (TypeRequiresBuiltinLaunderImp(Ctx, F->getType(), Seen))
return true;
}
return false;
}
/// Determine if the specified type requires laundering by checking if it is a
/// dynamic class type or contains a subobject which is a dynamic class type.
static bool TypeRequiresBuiltinLaunder(CodeGenModule &CGM, QualType Ty) {
if (!CGM.getCodeGenOpts().StrictVTablePointers)
return false;
llvm::SmallPtrSet<const Decl *, 16> Seen;
return TypeRequiresBuiltinLaunderImp(CGM.getContext(), Ty, Seen);
}
RValue CodeGenFunction::emitRotate(const CallExpr *E, bool IsRotateRight) {
llvm::Value *Src = EmitScalarExpr(E->getArg(0));
llvm::Value *ShiftAmt = EmitScalarExpr(E->getArg(1));
// The builtin's shift arg may have a different type than the source arg and
// result, but the LLVM intrinsic uses the same type for all values.
llvm::Type *Ty = Src->getType();
ShiftAmt = Builder.CreateIntCast(ShiftAmt, Ty, false);
// Rotate is a special case of LLVM funnel shift - 1st 2 args are the same.
unsigned IID = IsRotateRight ? Intrinsic::fshr : Intrinsic::fshl;
Function *F = CGM.getIntrinsic(IID, Ty);
return RValue::get(Builder.CreateCall(F, { Src, Src, ShiftAmt }));
}
// Map math builtins for long-double to f128 version.
static unsigned mutateLongDoubleBuiltin(unsigned BuiltinID) {
switch (BuiltinID) {
#define MUTATE_LDBL(func) \
case Builtin::BI__builtin_##func##l: \
return Builtin::BI__builtin_##func##f128;
MUTATE_LDBL(sqrt)
MUTATE_LDBL(cbrt)
MUTATE_LDBL(fabs)
MUTATE_LDBL(log)
MUTATE_LDBL(log2)
MUTATE_LDBL(log10)
MUTATE_LDBL(log1p)
MUTATE_LDBL(logb)
MUTATE_LDBL(exp)
MUTATE_LDBL(exp2)
MUTATE_LDBL(expm1)
MUTATE_LDBL(fdim)
MUTATE_LDBL(hypot)
MUTATE_LDBL(ilogb)
MUTATE_LDBL(pow)
MUTATE_LDBL(fmin)
MUTATE_LDBL(fmax)
MUTATE_LDBL(ceil)
MUTATE_LDBL(trunc)
MUTATE_LDBL(rint)
MUTATE_LDBL(nearbyint)
MUTATE_LDBL(round)
MUTATE_LDBL(floor)
MUTATE_LDBL(lround)
MUTATE_LDBL(llround)
MUTATE_LDBL(lrint)
MUTATE_LDBL(llrint)
MUTATE_LDBL(fmod)
MUTATE_LDBL(modf)
MUTATE_LDBL(nan)
MUTATE_LDBL(nans)
MUTATE_LDBL(inf)
MUTATE_LDBL(fma)
MUTATE_LDBL(sin)
MUTATE_LDBL(cos)
MUTATE_LDBL(tan)
MUTATE_LDBL(sinh)
MUTATE_LDBL(cosh)
MUTATE_LDBL(tanh)
MUTATE_LDBL(asin)
MUTATE_LDBL(acos)
MUTATE_LDBL(atan)
MUTATE_LDBL(asinh)
MUTATE_LDBL(acosh)
MUTATE_LDBL(atanh)
MUTATE_LDBL(atan2)
MUTATE_LDBL(erf)
MUTATE_LDBL(erfc)
MUTATE_LDBL(ldexp)
MUTATE_LDBL(frexp)
MUTATE_LDBL(huge_val)
MUTATE_LDBL(copysign)
MUTATE_LDBL(nextafter)
MUTATE_LDBL(nexttoward)
MUTATE_LDBL(remainder)
MUTATE_LDBL(remquo)
MUTATE_LDBL(scalbln)
MUTATE_LDBL(scalbn)
MUTATE_LDBL(tgamma)
MUTATE_LDBL(lgamma)
#undef MUTATE_LDBL
default:
return BuiltinID;
}
}
RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
const CallExpr *E,
ReturnValueSlot ReturnValue) {
const FunctionDecl *FD = GD.getDecl()->getAsFunction();
// See if we can constant fold this builtin. If so, don't emit it at all.
Expr::EvalResult Result;
if (E->EvaluateAsRValue(Result, CGM.getContext()) &&
!Result.hasSideEffects()) {
if (Result.Val.isInt())
return RValue::get(llvm::ConstantInt::get(getLLVMContext(),
Result.Val.getInt()));
if (Result.Val.isFloat())
return RValue::get(llvm::ConstantFP::get(getLLVMContext(),
Result.Val.getFloat()));
}
// If current long-double semantics is IEEE 128-bit, replace math builtins
// of long-double with f128 equivalent.
// TODO: This mutation should also be applied to other targets other than PPC,
// after backend supports IEEE 128-bit style libcalls.
if (getTarget().getTriple().isPPC64() &&
&getTarget().getLongDoubleFormat() == &llvm::APFloat::IEEEquad())
BuiltinID = mutateLongDoubleBuiltin(BuiltinID);
// If the builtin has been declared explicitly with an assembler label,
// disable the specialized emitting below. Ideally we should communicate the
// rename in IR, or at least avoid generating the intrinsic calls that are
// likely to get lowered to the renamed library functions.
const unsigned BuiltinIDIfNoAsmLabel =
FD->hasAttr<AsmLabelAttr>() ? 0 : BuiltinID;
// There are LLVM math intrinsics/instructions corresponding to math library
// functions except the LLVM op will never set errno while the math library
// might. Also, math builtins have the same semantics as their math library
// twins. Thus, we can transform math library and builtin calls to their
// LLVM counterparts if the call is marked 'const' (known to never set errno).
if (FD->hasAttr<ConstAttr>()) {
switch (BuiltinIDIfNoAsmLabel) {
case Builtin::BIceil:
case Builtin::BIceilf:
case Builtin::BIceill:
case Builtin::BI__builtin_ceil:
case Builtin::BI__builtin_ceilf:
case Builtin::BI__builtin_ceilf16:
case Builtin::BI__builtin_ceill:
case Builtin::BI__builtin_ceilf128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::ceil,
Intrinsic::experimental_constrained_ceil));
case Builtin::BIcopysign:
case Builtin::BIcopysignf:
case Builtin::BIcopysignl:
case Builtin::BI__builtin_copysign:
case Builtin::BI__builtin_copysignf:
case Builtin::BI__builtin_copysignf16:
case Builtin::BI__builtin_copysignl:
case Builtin::BI__builtin_copysignf128:
return RValue::get(emitBinaryBuiltin(*this, E, Intrinsic::copysign));
case Builtin::BIcos:
case Builtin::BIcosf:
case Builtin::BIcosl:
case Builtin::BI__builtin_cos:
case Builtin::BI__builtin_cosf:
case Builtin::BI__builtin_cosf16:
case Builtin::BI__builtin_cosl:
case Builtin::BI__builtin_cosf128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::cos,
Intrinsic::experimental_constrained_cos));
case Builtin::BIexp:
case Builtin::BIexpf:
case Builtin::BIexpl:
case Builtin::BI__builtin_exp:
case Builtin::BI__builtin_expf:
case Builtin::BI__builtin_expf16:
case Builtin::BI__builtin_expl:
case Builtin::BI__builtin_expf128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::exp,
Intrinsic::experimental_constrained_exp));
case Builtin::BIexp2:
case Builtin::BIexp2f:
case Builtin::BIexp2l:
case Builtin::BI__builtin_exp2:
case Builtin::BI__builtin_exp2f:
case Builtin::BI__builtin_exp2f16:
case Builtin::BI__builtin_exp2l:
case Builtin::BI__builtin_exp2f128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::exp2,
Intrinsic::experimental_constrained_exp2));
case Builtin::BIfabs:
case Builtin::BIfabsf:
case Builtin::BIfabsl:
case Builtin::BI__builtin_fabs:
case Builtin::BI__builtin_fabsf:
case Builtin::BI__builtin_fabsf16:
case Builtin::BI__builtin_fabsl:
case Builtin::BI__builtin_fabsf128:
return RValue::get(emitUnaryBuiltin(*this, E, Intrinsic::fabs));
case Builtin::BIfloor:
case Builtin::BIfloorf:
case Builtin::BIfloorl:
case Builtin::BI__builtin_floor:
case Builtin::BI__builtin_floorf:
case Builtin::BI__builtin_floorf16:
case Builtin::BI__builtin_floorl:
case Builtin::BI__builtin_floorf128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::floor,
Intrinsic::experimental_constrained_floor));
case Builtin::BIfma:
case Builtin::BIfmaf:
case Builtin::BIfmal:
case Builtin::BI__builtin_fma:
case Builtin::BI__builtin_fmaf:
case Builtin::BI__builtin_fmaf16:
case Builtin::BI__builtin_fmal:
case Builtin::BI__builtin_fmaf128:
return RValue::get(emitTernaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::fma,
Intrinsic::experimental_constrained_fma));
case Builtin::BIfmax:
case Builtin::BIfmaxf:
case Builtin::BIfmaxl:
case Builtin::BI__builtin_fmax:
case Builtin::BI__builtin_fmaxf:
case Builtin::BI__builtin_fmaxf16:
case Builtin::BI__builtin_fmaxl:
case Builtin::BI__builtin_fmaxf128:
return RValue::get(emitBinaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::maxnum,
Intrinsic::experimental_constrained_maxnum));
case Builtin::BIfmin:
case Builtin::BIfminf:
case Builtin::BIfminl:
case Builtin::BI__builtin_fmin:
case Builtin::BI__builtin_fminf:
case Builtin::BI__builtin_fminf16:
case Builtin::BI__builtin_fminl:
case Builtin::BI__builtin_fminf128:
return RValue::get(emitBinaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::minnum,
Intrinsic::experimental_constrained_minnum));
// fmod() is a special-case. It maps to the frem instruction rather than an
// LLVM intrinsic.
case Builtin::BIfmod:
case Builtin::BIfmodf:
case Builtin::BIfmodl:
case Builtin::BI__builtin_fmod:
case Builtin::BI__builtin_fmodf:
case Builtin::BI__builtin_fmodf16:
case Builtin::BI__builtin_fmodl:
case Builtin::BI__builtin_fmodf128: {
CodeGenFunction::CGFPOptionsRAII FPOptsRAII(*this, E);
Value *Arg1 = EmitScalarExpr(E->getArg(0));
Value *Arg2 = EmitScalarExpr(E->getArg(1));
return RValue::get(Builder.CreateFRem(Arg1, Arg2, "fmod"));
}
case Builtin::BIlog:
case Builtin::BIlogf:
case Builtin::BIlogl:
case Builtin::BI__builtin_log:
case Builtin::BI__builtin_logf:
case Builtin::BI__builtin_logf16:
case Builtin::BI__builtin_logl:
case Builtin::BI__builtin_logf128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::log,
Intrinsic::experimental_constrained_log));
case Builtin::BIlog10:
case Builtin::BIlog10f:
case Builtin::BIlog10l:
case Builtin::BI__builtin_log10:
case Builtin::BI__builtin_log10f:
case Builtin::BI__builtin_log10f16:
case Builtin::BI__builtin_log10l:
case Builtin::BI__builtin_log10f128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::log10,
Intrinsic::experimental_constrained_log10));
case Builtin::BIlog2:
case Builtin::BIlog2f:
case Builtin::BIlog2l:
case Builtin::BI__builtin_log2:
case Builtin::BI__builtin_log2f:
case Builtin::BI__builtin_log2f16:
case Builtin::BI__builtin_log2l:
case Builtin::BI__builtin_log2f128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::log2,
Intrinsic::experimental_constrained_log2));
case Builtin::BInearbyint:
case Builtin::BInearbyintf:
case Builtin::BInearbyintl:
case Builtin::BI__builtin_nearbyint:
case Builtin::BI__builtin_nearbyintf:
case Builtin::BI__builtin_nearbyintl:
case Builtin::BI__builtin_nearbyintf128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::nearbyint,
Intrinsic::experimental_constrained_nearbyint));
case Builtin::BIpow:
case Builtin::BIpowf:
case Builtin::BIpowl:
case Builtin::BI__builtin_pow:
case Builtin::BI__builtin_powf:
case Builtin::BI__builtin_powf16:
case Builtin::BI__builtin_powl:
case Builtin::BI__builtin_powf128:
return RValue::get(emitBinaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::pow,
Intrinsic::experimental_constrained_pow));
case Builtin::BIrint:
case Builtin::BIrintf:
case Builtin::BIrintl:
case Builtin::BI__builtin_rint:
case Builtin::BI__builtin_rintf:
case Builtin::BI__builtin_rintf16:
case Builtin::BI__builtin_rintl:
case Builtin::BI__builtin_rintf128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::rint,
Intrinsic::experimental_constrained_rint));
case Builtin::BIround:
case Builtin::BIroundf:
case Builtin::BIroundl:
case Builtin::BI__builtin_round:
case Builtin::BI__builtin_roundf:
case Builtin::BI__builtin_roundf16:
case Builtin::BI__builtin_roundl:
case Builtin::BI__builtin_roundf128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::round,
Intrinsic::experimental_constrained_round));
case Builtin::BIsin:
case Builtin::BIsinf:
case Builtin::BIsinl:
case Builtin::BI__builtin_sin:
case Builtin::BI__builtin_sinf:
case Builtin::BI__builtin_sinf16:
case Builtin::BI__builtin_sinl:
case Builtin::BI__builtin_sinf128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::sin,
Intrinsic::experimental_constrained_sin));
case Builtin::BIsqrt:
case Builtin::BIsqrtf:
case Builtin::BIsqrtl:
case Builtin::BI__builtin_sqrt:
case Builtin::BI__builtin_sqrtf:
case Builtin::BI__builtin_sqrtf16:
case Builtin::BI__builtin_sqrtl:
case Builtin::BI__builtin_sqrtf128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::sqrt,
Intrinsic::experimental_constrained_sqrt));
case Builtin::BItrunc:
case Builtin::BItruncf:
case Builtin::BItruncl:
case Builtin::BI__builtin_trunc:
case Builtin::BI__builtin_truncf:
case Builtin::BI__builtin_truncf16:
case Builtin::BI__builtin_truncl:
case Builtin::BI__builtin_truncf128:
return RValue::get(emitUnaryMaybeConstrainedFPBuiltin(*this, E,
Intrinsic::trunc,
Intrinsic::experimental_constrained_trunc));