Skip to content

Commit

Permalink
[FMV] Allow mixing target_version with target_clones.
Browse files Browse the repository at this point in the history 
The latest ACLE allows it and further clarifies the following
in regards to the combination of the two attributes:

"If the `default` matches with another explicitly provided
 version in the same translation unit, then the compiler can
 emit only one function instead of the two. The explicitly
 provided version shall be preferred."

("default" refers to the default clone here)

ARM-software/acle#310
  • Loading branch information
@labrinea
labrinea committed Mar 25, 2024
1 parent 13078cb commit dfef9d0
Show file tree
Hide file tree
Showing 8 changed files with 537 additions and 189 deletions.
14 changes: 14 additions & 0 deletions clang/include/clang/Basic/Attr.td
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3088,6 +3088,20 @@ def TargetClones : InheritableAttr {
StringRef getFeatureStr(unsigned Index) const {
return *(featuresStrs_begin() + Index);
}
bool isDefaultVersion(unsigned Index) const {
return getFeatureStr(Index) == "default";
}
void getFeatures(llvm::SmallVectorImpl<StringRef> &Out,
unsigned Index) const {
if (isDefaultVersion(Index)) return;
StringRef Features = getFeatureStr(Index);
SmallVector<StringRef, 8> AttrFeatures;
Features.split(AttrFeatures, "+");
for (auto &Feature : AttrFeatures) {
Feature = Feature.trim();
Out.push_back(Feature);
}
}
// Given an index into the 'featuresStrs' sequence, compute a unique
// ID to be used with function name mangling for the associated variant.
// This mapping is necessary due to a requirement that the mangling ID
Expand Down
15 changes: 6 additions & 9 deletions clang/lib/AST/ASTContext.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -13676,22 +13676,19 @@ void ASTContext::getFunctionFeatureMap(llvm::StringMap<bool> &FeatureMap,
Target->initFeatureMap(FeatureMap, getDiagnostics(), TargetCPU, Features);
} else if (const auto *TC = FD->getAttr<TargetClonesAttr>()) {
std::vector<std::string> Features;
StringRef VersionStr = TC->getFeatureStr(GD.getMultiVersionIndex());
if (Target->getTriple().isAArch64()) {
// TargetClones for AArch64
if (VersionStr != "default") {
SmallVector<StringRef, 1> VersionFeatures;
VersionStr.split(VersionFeatures, "+");
for (auto &VFeature : VersionFeatures) {
VFeature = VFeature.trim();
llvm::SmallVector<StringRef, 8> Feats;
TC->getFeatures(Feats, GD.getMultiVersionIndex());
for (StringRef Feat : Feats)
if (Target->validateCpuSupports(Feat.str()))
// Use '?' to mark features that came from AArch64 TargetClones.
Features.push_back((StringRef{"?"} + VFeature).str());
}
}
Features.push_back("?" + Feat.str());
Features.insert(Features.begin(),
Target->getTargetOpts().FeaturesAsWritten.begin(),
Target->getTargetOpts().FeaturesAsWritten.end());
} else {
StringRef VersionStr = TC->getFeatureStr(GD.getMultiVersionIndex());
if (VersionStr.starts_with("arch="))
TargetCPU = VersionStr.drop_front(sizeof("arch=") - 1);
else if (VersionStr != "default")
Expand Down
105 changes: 50 additions & 55 deletions clang/lib/CodeGen/CodeGenModule.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3712,7 +3712,8 @@ void CodeGenModule::EmitGlobal(GlobalDecl GD) {
// Forward declarations are emitted lazily on first use.
if (!FD->doesThisDeclarationHaveABody()) {
if (!FD->doesDeclarationForceExternallyVisibleDefinition() &&
!FD->isTargetVersionMultiVersion())
(!FD->isMultiVersion() ||
!FD->getASTContext().getTargetInfo().getTriple().isAArch64()))
return;

StringRef MangledName = getMangledName(GD);
Expand Down Expand Up @@ -3994,10 +3995,11 @@ void CodeGenModule::EmitMultiVersionFunctionDefinition(GlobalDecl GD,
auto *Spec = FD->getAttr<CPUSpecificAttr>();
for (unsigned I = 0; I < Spec->cpus_size(); ++I)
EmitGlobalFunctionDefinition(GD.getWithMultiVersionIndex(I), nullptr);
} else if (FD->isTargetClonesMultiVersion()) {
auto *Clone = FD->getAttr<TargetClonesAttr>();
for (unsigned I = 0; I < Clone->featuresStrs_size(); ++I)
if (Clone->isFirstOfVersion(I))
} else if (auto *TC = FD->getAttr<TargetClonesAttr>()) {
for (unsigned I = 0; I < TC->featuresStrs_size(); ++I)
// AArch64 favors the default target version over the clone if any.
if ((!TC->isDefaultVersion(I) || !getTarget().getTriple().isAArch64()) &&
TC->isFirstOfVersion(I))
EmitGlobalFunctionDefinition(GD.getWithMultiVersionIndex(I), nullptr);
// Ensure that the resolver function is also emitted.
GetOrCreateMultiVersionResolver(GD);
Expand Down Expand Up @@ -4137,57 +4139,49 @@ void CodeGenModule::emitMultiVersionFunctions() {
};

bool HasDefaultDecl = !FD->isTargetVersionMultiVersion();
bool ShouldEmitResolver = !FD->isTargetVersionMultiVersion();
bool ShouldEmitResolver =
!getContext().getTargetInfo().getTriple().isAArch64();
SmallVector<CodeGenFunction::MultiVersionResolverOption, 10> Options;
if (FD->isTargetMultiVersion()) {
getContext().forEachMultiversionedFunctionVersion(
FD, [&](const FunctionDecl *CurFD) {
llvm::SmallVector<StringRef, 8> Feats;
llvm::Function *Func = createFunction(CurFD);

if (const auto *TA = CurFD->getAttr<TargetAttr>()) {
TA->getAddedFeatures(Feats);
Options.emplace_back(Func, TA->getArchitecture(), Feats);
} else if (const auto *TVA = CurFD->getAttr<TargetVersionAttr>()) {
bool HasDefaultDef = TVA->isDefaultVersion() &&
CurFD->doesThisDeclarationHaveABody();
HasDefaultDecl |= TVA->isDefaultVersion();
ShouldEmitResolver |= (CurFD->isUsed() || HasDefaultDef);
TVA->getFeatures(Feats);
Options.emplace_back(Func, /*Architecture*/ "", Feats);
} else
llvm_unreachable("unexpected MultiVersionKind");
});
} else if (const auto *TC = FD->getAttr<TargetClonesAttr>()) {
for (unsigned I = 0; I < TC->featuresStrs_size(); ++I) {
if (!TC->isFirstOfVersion(I))
continue;
getContext().forEachMultiversionedFunctionVersion(
FD, [&](const FunctionDecl *CurFD) {
llvm::SmallVector<StringRef, 8> Feats;

llvm::Function *Func = createFunction(FD, I);
StringRef Version = TC->getFeatureStr(I);
StringRef Architecture;
llvm::SmallVector<StringRef, 1> Feature;

if (getTarget().getTriple().isAArch64()) {
if (Version != "default") {
llvm::SmallVector<StringRef, 8> VerFeats;
Version.split(VerFeats, "+");
for (auto &CurFeat : VerFeats)
Feature.push_back(CurFeat.trim());
}
} else {
if (Version.starts_with("arch="))
Architecture = Version.drop_front(sizeof("arch=") - 1);
else if (Version != "default")
Feature.push_back(Version);
}

Options.emplace_back(Func, Architecture, Feature);
}
} else {
assert(0 && "Expected a target or target_clones multiversion function");
continue;
}
if (const auto *TA = CurFD->getAttr<TargetAttr>()) {
TA->getAddedFeatures(Feats);
llvm::Function *Func = createFunction(CurFD);
Options.emplace_back(Func, TA->getArchitecture(), Feats);
} else if (const auto *TVA = CurFD->getAttr<TargetVersionAttr>()) {
bool HasDefaultDef = TVA->isDefaultVersion() &&
CurFD->doesThisDeclarationHaveABody();
HasDefaultDecl |= TVA->isDefaultVersion();
ShouldEmitResolver |= (CurFD->isUsed() || HasDefaultDef);
TVA->getFeatures(Feats);
llvm::Function *Func = createFunction(CurFD);
Options.emplace_back(Func, /*Architecture*/ "", Feats);
} else if (const auto *TC = CurFD->getAttr<TargetClonesAttr>()) {
ShouldEmitResolver |= CurFD->doesThisDeclarationHaveABody();
for (unsigned I = 0; I < TC->featuresStrs_size(); ++I) {
if (!TC->isFirstOfVersion(I))
continue;

llvm::Function *Func = createFunction(CurFD, I);
StringRef Architecture;
Feats.clear();
if (getTarget().getTriple().isAArch64())
TC->getFeatures(Feats, I);
else {
StringRef Version = TC->getFeatureStr(I);
if (Version.starts_with("arch="))
Architecture = Version.drop_front(sizeof("arch=") - 1);
else if (Version != "default")
Feats.push_back(Version);
}
Options.emplace_back(Func, Architecture, Feats);
}
} else
llvm_unreachable("unexpected MultiVersionKind");
});

if (!ShouldEmitResolver)
continue;
Expand Down Expand Up @@ -4378,7 +4372,7 @@ void CodeGenModule::AddDeferredMultiVersionResolverToEmit(GlobalDecl GD) {
const auto *FD = cast<FunctionDecl>(GD.getDecl());
assert(FD && "Not a FunctionDecl?");

if (FD->isTargetVersionMultiVersion()) {
if (FD->isTargetVersionMultiVersion() || FD->isTargetClonesMultiVersion()) {
std::string MangledName =
getMangledNameImpl(*this, GD, FD, /*OmitMultiVersionMangling=*/true);
if (!DeferredResolversToEmit.insert(MangledName).second)
Expand Down Expand Up @@ -4489,7 +4483,8 @@ llvm::Constant *CodeGenModule::GetOrCreateLLVMFunction(

if (FD->isMultiVersion()) {
UpdateMultiVersionNames(GD, FD, MangledName);
if (FD->isTargetVersionMultiVersion() && !FD->isUsed())
if (FD->getASTContext().getTargetInfo().getTriple().isAArch64() &&
!FD->isUsed())
AddDeferredMultiVersionResolverToEmit(GD);
else if (!IsForDefinition)
return GetOrCreateMultiVersionResolver(GD);
Expand Down
Loading

0 comments on commit dfef9d0

Please sign in to comment.