// FIXME: this could be a transitional option, and we probably need to remove
// it if only we are sure this optimization could always benefit all targets.
-static cl::opt<bool>
+static cl::opt<cl::boolOrDefault>
EnableGlobalMergeOnExternal("global-merge-on-external", cl::Hidden,
- cl::desc("Enable global merge pass on external linkage"),
- cl::init(false));
+ cl::desc("Enable global merge pass on external linkage"));
STATISTIC(NumMerged, "Number of globals merged");
namespace {
class GlobalMerge : public FunctionPass {
const TargetMachine *TM;
- const DataLayout *DL;
// FIXME: Infer the maximum possible offset depending on the actual users
// (these max offsets are different for the users inside Thumb or ARM
// functions), see the code that passes in the offset in the ARM backend
// for more information.
unsigned MaxOffset;
+ /// Whether we should try to optimize for size only.
+ /// Currently, this applies a dead simple heuristic: only consider globals
+ /// used in minsize functions for merging.
+ /// FIXME: This could learn about optsize, and be used in the cost model.
+ bool OnlyOptimizeForSize;
+
+ /// Whether we should merge global variables that have external linkage.
+ bool MergeExternalGlobals;
+
bool doMerge(SmallVectorImpl<GlobalVariable*> &Globals,
Module &M, bool isConst, unsigned AddrSpace) const;
/// \brief Merge everything in \p Globals for which the corresponding bit
public:
static char ID; // Pass identification, replacement for typeid.
explicit GlobalMerge(const TargetMachine *TM = nullptr,
- unsigned MaximalOffset = 0)
- : FunctionPass(ID), TM(TM), DL(TM->getDataLayout()),
- MaxOffset(MaximalOffset) {
+ unsigned MaximalOffset = 0,
+ bool OnlyOptimizeForSize = false,
+ bool MergeExternalGlobals = false)
+ : FunctionPass(ID), TM(TM), MaxOffset(MaximalOffset),
+ OnlyOptimizeForSize(OnlyOptimizeForSize),
+ MergeExternalGlobals(MergeExternalGlobals) {
initializeGlobalMergePass(*PassRegistry::getPassRegistry());
}
bool GlobalMerge::doMerge(SmallVectorImpl<GlobalVariable*> &Globals,
Module &M, bool isConst, unsigned AddrSpace) const {
+ auto &DL = M.getDataLayout();
// FIXME: Find better heuristics
std::stable_sort(Globals.begin(), Globals.end(),
- [this](const GlobalVariable *GV1, const GlobalVariable *GV2) {
- Type *Ty1 = cast<PointerType>(GV1->getType())->getElementType();
- Type *Ty2 = cast<PointerType>(GV2->getType())->getElementType();
-
- return (DL->getTypeAllocSize(Ty1) < DL->getTypeAllocSize(Ty2));
- });
+ [&DL](const GlobalVariable *GV1, const GlobalVariable *GV2) {
+ return DL.getTypeAllocSize(GV1->getValueType()) <
+ DL.getTypeAllocSize(GV2->getValueType());
+ });
// If we want to just blindly group all globals together, do so.
if (!GlobalMergeGroupByUse) {
// If we want to be smarter, look at all uses of each global, to try to
// discover all sets of globals used together, and how many times each of
- // these sets occured.
+ // these sets occurred.
//
// Keep this reasonably efficient, by having an append-only list of all sets
// discovered so far (UsedGlobalSet), and mapping each "together-ness" unit of
// users, so look through ConstantExpr...
Use *UI, *UE;
if (ConstantExpr *CE = dyn_cast<ConstantExpr>(U.getUser())) {
+ if (CE->use_empty())
+ continue;
UI = &*CE->use_begin();
UE = nullptr;
} else if (isa<Instruction>(U.getUser())) {
continue;
Function *ParentFn = I->getParent()->getParent();
+
+ // If we're only optimizing for size, ignore non-minsize functions.
+ if (OnlyOptimizeForSize && !ParentFn->optForMinSize())
+ continue;
+
size_t UGSIdx = GlobalUsesByFunction[ParentFn];
// If this is the first global the basic block uses, map it to the set
unsigned AddrSpace) const {
Type *Int32Ty = Type::getInt32Ty(M.getContext());
+ auto &DL = M.getDataLayout();
assert(Globals.size() > 1);
std::vector<Type*> Tys;
std::vector<Constant*> Inits;
- bool HasExternal = false;
- GlobalVariable *TheFirstExternal = 0;
for (j = i; j != -1; j = GlobalSet.find_next(j)) {
- Type *Ty = Globals[j]->getType()->getElementType();
- MergedSize += DL->getTypeAllocSize(Ty);
+ Type *Ty = Globals[j]->getValueType();
+ MergedSize += DL.getTypeAllocSize(Ty);
if (MergedSize > MaxOffset) {
break;
}
Tys.push_back(Ty);
Inits.push_back(Globals[j]->getInitializer());
-
- if (Globals[j]->hasExternalLinkage() && !HasExternal) {
- HasExternal = true;
- TheFirstExternal = Globals[j];
- }
}
- // If merged variables doesn't have external linkage, we needn't to expose
- // the symbol after merging.
- GlobalValue::LinkageTypes Linkage = HasExternal
- ? GlobalValue::ExternalLinkage
- : GlobalValue::InternalLinkage;
-
StructType *MergedTy = StructType::get(M.getContext(), Tys);
Constant *MergedInit = ConstantStruct::get(MergedTy, Inits);
- // If merged variables have external linkage, we use symbol name of the
- // first variable merged as the suffix of global symbol name. This would
- // be able to avoid the link-time naming conflict for globalm symbols.
GlobalVariable *MergedGV = new GlobalVariable(
- M, MergedTy, isConst, Linkage, MergedInit,
- HasExternal ? "_MergedGlobals_" + TheFirstExternal->getName()
- : "_MergedGlobals",
- nullptr, GlobalVariable::NotThreadLocal, AddrSpace);
+ M, MergedTy, isConst, GlobalValue::PrivateLinkage, MergedInit,
+ "_MergedGlobals", nullptr, GlobalVariable::NotThreadLocal, AddrSpace);
for (ssize_t k = i, idx = 0; k != j; k = GlobalSet.find_next(k)) {
GlobalValue::LinkageTypes Linkage = Globals[k]->getLinkage();
Globals[k]->replaceAllUsesWith(GEP);
Globals[k]->eraseFromParent();
- if (Linkage != GlobalValue::InternalLinkage) {
- // Generate a new alias...
+ // When the linkage is not internal we must emit an alias for the original
+ // variable name as it may be accessed from another object. On non-Mach-O
+ // we can also emit an alias for internal linkage as it's safe to do so.
+ // It's not safe on Mach-O as the alias (and thus the portion of the
+ // MergedGlobals variable) may be dead stripped at link time.
+ if (Linkage != GlobalValue::InternalLinkage ||
+ !TM->getTargetTriple().isOSBinFormatMachO()) {
auto *PTy = cast<PointerType>(GEP->getType());
GlobalAlias::create(PTy, Linkage, Name, GEP, &M);
}
if (!EnableGlobalMerge)
return false;
+ auto &DL = M.getDataLayout();
DenseMap<unsigned, SmallVector<GlobalVariable*, 16> > Globals, ConstGlobals,
BSSGlobals;
bool Changed = false;
if (I->isDeclaration() || I->isThreadLocal() || I->hasSection())
continue;
- if (!(EnableGlobalMergeOnExternal && I->hasExternalLinkage()) &&
+ if (!(MergeExternalGlobals && I->hasExternalLinkage()) &&
!I->hasInternalLinkage())
continue;
unsigned AddressSpace = PT->getAddressSpace();
// Ignore fancy-aligned globals for now.
- unsigned Alignment = DL->getPreferredAlignment(I);
- Type *Ty = I->getType()->getElementType();
- if (Alignment > DL->getABITypeAlignment(Ty))
+ unsigned Alignment = DL.getPreferredAlignment(I);
+ Type *Ty = I->getValueType();
+ if (Alignment > DL.getABITypeAlignment(Ty))
continue;
// Ignore all 'special' globals.
if (isMustKeepGlobalVariable(I))
continue;
- if (DL->getTypeAllocSize(Ty) < MaxOffset) {
+ if (DL.getTypeAllocSize(Ty) < MaxOffset) {
if (TargetLoweringObjectFile::getKindForGlobal(I, *TM).isBSSLocal())
BSSGlobals[AddressSpace].push_back(I);
else if (I->isConstant())
return false;
}
-Pass *llvm::createGlobalMergePass(const TargetMachine *TM, unsigned Offset) {
- return new GlobalMerge(TM, Offset);
+Pass *llvm::createGlobalMergePass(const TargetMachine *TM, unsigned Offset,
+ bool OnlyOptimizeForSize,
+ bool MergeExternalByDefault) {
+ bool MergeExternal = (EnableGlobalMergeOnExternal == cl::BOU_UNSET) ?
+ MergeExternalByDefault : (EnableGlobalMergeOnExternal == cl::BOU_TRUE);
+ return new GlobalMerge(TM, Offset, OnlyOptimizeForSize, MergeExternal);
}
projects / oota-llvm.git / blobdiff