As an optimization, we maintain a cache of generated

___Block_byref_id_object_dispose and ___Block_byref_id_object_copy
functions so that we can simply reuse instead of creating a new one.
Additionally, add an assert to ensure no one yet tries to align a
__block variable beyond the alignment of a pointer as the codegen is
incomplete.

llvm-svn: 72974
This commit is contained in:
Mike Stump 2009-06-05 23:26:36 +00:00
parent a03705c82d
commit cbc2bcaf17
4 changed files with 70 additions and 15 deletions

View File

@ -724,6 +724,8 @@ GenerateCopyHelperFunction(bool BlockHasCopyDispose, const llvm::StructType *T,
const CGFunctionInfo &FI =
CGM.getTypes().getFunctionInfo(R, Args);
// FIXME: We'd like to put these into a mergable by content, with
// internal linkage.
std::string Name = std::string("__copy_helper_block_");
CodeGenTypes &Types = CGM.getTypes();
const llvm::FunctionType *LTy = Types.GetFunctionType(FI, false);
@ -803,6 +805,8 @@ GenerateDestroyHelperFunction(bool BlockHasCopyDispose,
const CGFunctionInfo &FI =
CGM.getTypes().getFunctionInfo(R, Args);
// FIXME: We'd like to put these into a mergable by content, with
// internal linkage.
std::string Name = std::string("__destroy_helper_block_");
CodeGenTypes &Types = CGM.getTypes();
const llvm::FunctionType *LTy = Types.GetFunctionType(FI, false);
@ -889,6 +893,8 @@ GeneratebyrefCopyHelperFunction(const llvm::Type *T, int flag) {
CodeGenTypes &Types = CGM.getTypes();
const llvm::FunctionType *LTy = Types.GetFunctionType(FI, false);
// FIXME: We'd like to put these into a mergable by content, with
// internal linkage.
llvm::Function *Fn =
llvm::Function::Create(LTy, llvm::GlobalValue::InternalLinkage,
Name,
@ -950,6 +956,8 @@ BlockFunction::GeneratebyrefDestroyHelperFunction(const llvm::Type *T,
CodeGenTypes &Types = CGM.getTypes();
const llvm::FunctionType *LTy = Types.GetFunctionType(FI, false);
// FIXME: We'd like to put these into a mergable by content, with
// internal linkage.
llvm::Function *Fn =
llvm::Function::Create(LTy, llvm::GlobalValue::InternalLinkage,
Name,
@ -980,13 +988,36 @@ BlockFunction::GeneratebyrefDestroyHelperFunction(const llvm::Type *T,
}
llvm::Constant *BlockFunction::BuildbyrefCopyHelper(const llvm::Type *T,
int flag) {
return CodeGenFunction(CGM).GeneratebyrefCopyHelperFunction(T, flag);
int flag, unsigned Align) {
// All alignments below that of pointer alignment collpase down to just
// pointer alignment, as we always have at least that much alignment to begin
// with.
Align /= unsigned(CGF.Target.getPointerAlign(0)/8);
// As an optimization, we only generate a single function of each kind we
// might need. We need a different one for each alignment and for each
// setting of flags. We mix Align and flag to get the kind.
uint64_t kind = (uint64_t)Align*BLOCK_BYREF_CURRENT_MAX + flag;
llvm::Constant *& Entry = CGM.AssignCache[kind];
if (Entry)
return Entry;
return Entry=CodeGenFunction(CGM).GeneratebyrefCopyHelperFunction(T, flag);
}
llvm::Constant *BlockFunction::BuildbyrefDestroyHelper(const llvm::Type *T,
int flag) {
return CodeGenFunction(CGM).GeneratebyrefDestroyHelperFunction(T, flag);
int flag,
unsigned Align) {
// All alignments below that of pointer alignment collpase down to just
// pointer alignment, as we always have at least that much alignment to begin
// with.
Align /= unsigned(CGF.Target.getPointerAlign(0)/8);
// As an optimization, we only generate a single function of each kind we
// might need. We need a different one for each alignment and for each
// setting of flags. We mix Align and flag to get the kind.
uint64_t kind = (uint64_t)Align*BLOCK_BYREF_CURRENT_MAX + flag;
llvm::Constant *& Entry = CGM.DestroyCache[kind];
if (Entry)
return Entry;
return Entry=CodeGenFunction(CGM).GeneratebyrefDestroyHelperFunction(T, flag);
}
llvm::Value *BlockFunction::getBlockObjectDispose() {

View File

@ -98,6 +98,9 @@ public:
llvm::Value *BlockObjectDispose;
const llvm::Type *PtrToInt8Ty;
std::map<uint64_t, llvm::Constant *> AssignCache;
std::map<uint64_t, llvm::Constant *> DestroyCache;
BlockModule(ASTContext &C, llvm::Module &M, const llvm::TargetData &TD,
CodeGenTypes &T, CodeGenModule &CodeGen)
: Context(C), TheModule(M), TheTargetData(TD), Types(T),
@ -131,8 +134,9 @@ public:
variable */
BLOCK_FIELD_IS_WEAK = 16, /* declared __weak, only used in byref copy
helpers */
BLOCK_BYREF_CALLER = 128 /* called from __block (byref) copy/dispose
BLOCK_BYREF_CALLER = 128, /* called from __block (byref) copy/dispose
support routines */
BLOCK_BYREF_CURRENT_MAX = 256
};
/// BlockInfo - Information to generate a block literal.
@ -199,8 +203,10 @@ public:
llvm::Constant *GeneratebyrefCopyHelperFunction(const llvm::Type *, int flag);
llvm::Constant *GeneratebyrefDestroyHelperFunction(const llvm::Type *T, int);
llvm::Constant *BuildbyrefCopyHelper(const llvm::Type *T, int flag);
llvm::Constant *BuildbyrefDestroyHelper(const llvm::Type *T, int flag);
llvm::Constant *BuildbyrefCopyHelper(const llvm::Type *T, int flag,
unsigned Align);
llvm::Constant *BuildbyrefDestroyHelper(const llvm::Type *T, int flag,
unsigned Align);
llvm::Value *getBlockObjectAssign();
llvm::Value *getBlockObjectDispose();

View File

@ -232,7 +232,9 @@ const llvm::Type *CodeGenFunction::BuildByRefType(QualType Ty,
Types[4] = PtrToInt8Ty;
Types[5] = PtrToInt8Ty;
}
// FIXME: Align this on at least an Align boundary.
// FIXME: Align this on at least an Align boundary, assert if we can't.
assert((Align <= unsigned(Target.getPointerAlign(0))/8)
&& "Can't align more thqn pointer yet");
Types[needsCopyDispose*2 + 4] = LTy;
return llvm::StructType::get(Types, false);
}
@ -244,22 +246,22 @@ void CodeGenFunction::EmitLocalBlockVarDecl(const VarDecl &D) {
QualType Ty = D.getType();
bool isByRef = D.hasAttr<BlocksAttr>();
bool needsDispose = false;
unsigned Align = 0;
llvm::Value *DeclPtr;
if (Ty->isConstantSizeType()) {
if (!Target.useGlobalsForAutomaticVariables()) {
// A normal fixed sized variable becomes an alloca in the entry block.
const llvm::Type *LTy = ConvertTypeForMem(Ty);
Align = getContext().getDeclAlignInBytes(&D);
if (isByRef)
LTy = BuildByRefType(Ty, getContext().getDeclAlignInBytes(&D));
LTy = BuildByRefType(Ty, Align);
llvm::AllocaInst *Alloc = CreateTempAlloca(LTy);
Alloc->setName(D.getNameAsString().c_str());
if (isByRef)
Alloc->setAlignment(std::max(getContext().getDeclAlignInBytes(&D),
unsigned(Target.getPointerAlign(0) / 8)));
else
Alloc->setAlignment(getContext().getDeclAlignInBytes(&D));
Align = std::max(Align, unsigned(Target.getPointerAlign(0) / 8));
Alloc->setAlignment(Align);
DeclPtr = Alloc;
} else {
// Targets that don't support recursion emit locals as globals.
@ -401,11 +403,12 @@ void CodeGenFunction::EmitLocalBlockVarDecl(const VarDecl &D) {
if (flags & BLOCK_HAS_COPY_DISPOSE) {
BlockHasCopyDispose = true;
llvm::Value *copy_helper = Builder.CreateStructGEP(DeclPtr, 4);
Builder.CreateStore(BuildbyrefCopyHelper(DeclPtr->getType(), flag),
Builder.CreateStore(BuildbyrefCopyHelper(DeclPtr->getType(), flag, Align),
copy_helper);
llvm::Value *destroy_helper = Builder.CreateStructGEP(DeclPtr, 5);
Builder.CreateStore(BuildbyrefDestroyHelper(DeclPtr->getType(), flag),
Builder.CreateStore(BuildbyrefDestroyHelper(DeclPtr->getType(), flag,
Align),
destroy_helper);
}
}

View File

@ -0,0 +1,15 @@
// RUN: clang-cc -triple x86_64-apple-darwin9 -emit-llvm -fblocks -o %t %s &&
// RUN: grep 'object_assign' %t | count 11 &&
// RUN: grep 'object_dispose' %t | count 29
int main() {
typedef id aid __attribute__((aligned(1)));
__block aid a1;
__block id a2 __attribute__((aligned(2)));
__block id a3 __attribute__((aligned(4)));
__block id a4 __attribute__((aligned(8)));
__block id a5, a6, a7;
__block void (^b)();
^{ a1=a2=a3=a4=a5=a6=a7=0; b = 0; }();
return 0;
}