Index: clang/include/clang/Driver/Action.h =================================================================== --- clang/include/clang/Driver/Action.h +++ clang/include/clang/Driver/Action.h @@ -71,9 +71,10 @@ VerifyPCHJobClass, OffloadBundlingJobClass, OffloadUnbundlingJobClass, + OffloadWrapperJobClass, JobClassFirst = PreprocessJobClass, - JobClassLast = OffloadUnbundlingJobClass + JobClassLast = OffloadWrapperJobClass }; // The offloading kind determines if this action is binded to a particular @@ -613,6 +614,17 @@ } }; +class OffloadWrapperJobAction : public JobAction { + void anchor() override; + +public: + OffloadWrapperJobAction(ActionList &Inputs, types::ID Type); + + static bool classof(const Action *A) { + return A->getKind() == OffloadWrapperJobClass; + } +}; + } // namespace driver } // namespace clang Index: clang/include/clang/Driver/Options.td =================================================================== --- clang/include/clang/Driver/Options.td +++ clang/include/clang/Driver/Options.td @@ -1589,8 +1589,6 @@ Flags<[CC1Option, NoArgumentUnused, HelpHidden]>; def fopenmp_targets_EQ : CommaJoined<["-"], "fopenmp-targets=">, Flags<[DriverOption, CC1Option]>, HelpText<"Specify comma-separated list of triples OpenMP offloading targets to be supported">; -def fopenmp_dump_offload_linker_script : Flag<["-"], "fopenmp-dump-offload-linker-script">, - Group, Flags<[NoArgumentUnused, HelpHidden]>; def fopenmp_relocatable_target : Flag<["-"], "fopenmp-relocatable-target">, Group, Flags<[CC1Option, NoArgumentUnused, HelpHidden]>; def fnoopenmp_relocatable_target : Flag<["-"], "fnoopenmp-relocatable-target">, Index: clang/include/clang/Driver/ToolChain.h =================================================================== --- clang/include/clang/Driver/ToolChain.h +++ clang/include/clang/Driver/ToolChain.h @@ -137,12 +137,14 @@ mutable std::unique_ptr Assemble; mutable std::unique_ptr Link; mutable std::unique_ptr OffloadBundler; + mutable std::unique_ptr OffloadWrapper; Tool *getClang() const; Tool *getAssemble() const; Tool *getLink() const; Tool *getClangAs() const; Tool *getOffloadBundler() const; + Tool *getOffloadWrapper() const; mutable std::unique_ptr SanitizerArguments; mutable std::unique_ptr XRayArguments; Index: clang/lib/CodeGen/CGOpenMPRuntime.h =================================================================== --- clang/lib/CodeGen/CGOpenMPRuntime.h +++ clang/lib/CodeGen/CGOpenMPRuntime.h @@ -655,14 +655,6 @@ /// Device routines are specific to the bool HasEmittedDeclareTargetRegion = false; - /// Creates and registers offloading binary descriptor for the current - /// compilation unit. The function that does the registration is returned. - llvm::Function *createOffloadingBinaryDescriptorRegistration(); - - /// Creates all the offload entries in the current compilation unit - /// along with the associated metadata. - void createOffloadEntriesAndInfoMetadata(); - /// Loads all the offload entries information from the host IR /// metadata. void loadOffloadInfoMetadata(); @@ -1469,10 +1461,9 @@ /// requires directives was used in the current module. llvm::Function *emitRequiresDirectiveRegFun(); - /// Creates the offloading descriptor in the event any target region - /// was emitted in the current module and return the function that registers - /// it. - virtual llvm::Function *emitRegistrationFunction(); + /// Creates all the offload entries in the current compilation unit + /// along with the associated metadata. + void createOffloadEntriesAndInfoMetadata(); /// Emits code for teams call of the \a OutlinedFn with /// variables captured in a record which address is stored in \a @@ -2137,11 +2128,6 @@ /// \param GD Global to scan. bool emitTargetGlobal(GlobalDecl GD) override; - /// Creates the offloading descriptor in the event any target region - /// was emitted in the current module and return the function that registers - /// it. - llvm::Function *emitRegistrationFunction() override; - /// Emits code for teams call of the \a OutlinedFn with /// variables captured in a record which address is stored in \a /// CapturedStruct. Index: clang/lib/CodeGen/CGOpenMPRuntime.cpp =================================================================== --- clang/lib/CodeGen/CGOpenMPRuntime.cpp +++ clang/lib/CodeGen/CGOpenMPRuntime.cpp @@ -3949,157 +3949,6 @@ Action(E.getKey(), E.getValue()); } -llvm::Function * -CGOpenMPRuntime::createOffloadingBinaryDescriptorRegistration() { - // If we don't have entries or if we are emitting code for the device, we - // don't need to do anything. - if (CGM.getLangOpts().OpenMPIsDevice || OffloadEntriesInfoManager.empty()) - return nullptr; - - llvm::Module &M = CGM.getModule(); - ASTContext &C = CGM.getContext(); - - // Get list of devices we care about - const std::vector &Devices = CGM.getLangOpts().OMPTargetTriples; - - // We should be creating an offloading descriptor only if there are devices - // specified. - assert(!Devices.empty() && "No OpenMP offloading devices??"); - - // Create the external variables that will point to the begin and end of the - // host entries section. These will be defined by the linker. - llvm::Type *OffloadEntryTy = - CGM.getTypes().ConvertTypeForMem(getTgtOffloadEntryQTy()); - std::string EntriesBeginName = getName({"omp_offloading", "entries_begin"}); - auto *HostEntriesBegin = new llvm::GlobalVariable( - M, OffloadEntryTy, /*isConstant=*/true, - llvm::GlobalValue::ExternalLinkage, /*Initializer=*/nullptr, - EntriesBeginName); - std::string EntriesEndName = getName({"omp_offloading", "entries_end"}); - auto *HostEntriesEnd = - new llvm::GlobalVariable(M, OffloadEntryTy, /*isConstant=*/true, - llvm::GlobalValue::ExternalLinkage, - /*Initializer=*/nullptr, EntriesEndName); - - // Create all device images - auto *DeviceImageTy = cast( - CGM.getTypes().ConvertTypeForMem(getTgtDeviceImageQTy())); - ConstantInitBuilder DeviceImagesBuilder(CGM); - ConstantArrayBuilder DeviceImagesEntries = - DeviceImagesBuilder.beginArray(DeviceImageTy); - - for (const llvm::Triple &Device : Devices) { - StringRef T = Device.getTriple(); - std::string BeginName = getName({"omp_offloading", "img_start", ""}); - auto *ImgBegin = new llvm::GlobalVariable( - M, CGM.Int8Ty, /*isConstant=*/true, - llvm::GlobalValue::ExternalWeakLinkage, - /*Initializer=*/nullptr, Twine(BeginName).concat(T)); - std::string EndName = getName({"omp_offloading", "img_end", ""}); - auto *ImgEnd = new llvm::GlobalVariable( - M, CGM.Int8Ty, /*isConstant=*/true, - llvm::GlobalValue::ExternalWeakLinkage, - /*Initializer=*/nullptr, Twine(EndName).concat(T)); - - llvm::Constant *Data[] = {ImgBegin, ImgEnd, HostEntriesBegin, - HostEntriesEnd}; - createConstantGlobalStructAndAddToParent(CGM, getTgtDeviceImageQTy(), Data, - DeviceImagesEntries); - } - - // Create device images global array. - std::string ImagesName = getName({"omp_offloading", "device_images"}); - llvm::GlobalVariable *DeviceImages = - DeviceImagesEntries.finishAndCreateGlobal(ImagesName, - CGM.getPointerAlign(), - /*isConstant=*/true); - DeviceImages->setUnnamedAddr(llvm::GlobalValue::UnnamedAddr::Global); - - // This is a Zero array to be used in the creation of the constant expressions - llvm::Constant *Index[] = {llvm::Constant::getNullValue(CGM.Int32Ty), - llvm::Constant::getNullValue(CGM.Int32Ty)}; - - // Create the target region descriptor. - llvm::Constant *Data[] = { - llvm::ConstantInt::get(CGM.Int32Ty, Devices.size()), - llvm::ConstantExpr::getGetElementPtr(DeviceImages->getValueType(), - DeviceImages, Index), - HostEntriesBegin, HostEntriesEnd}; - std::string Descriptor = getName({"omp_offloading", "descriptor"}); - llvm::GlobalVariable *Desc = createGlobalStruct( - CGM, getTgtBinaryDescriptorQTy(), /*IsConstant=*/true, Data, Descriptor); - - // Emit code to register or unregister the descriptor at execution - // startup or closing, respectively. - - llvm::Function *UnRegFn; - { - FunctionArgList Args; - ImplicitParamDecl DummyPtr(C, C.VoidPtrTy, ImplicitParamDecl::Other); - Args.push_back(&DummyPtr); - - CodeGenFunction CGF(CGM); - // Disable debug info for global (de-)initializer because they are not part - // of some particular construct. - CGF.disableDebugInfo(); - const auto &FI = - CGM.getTypes().arrangeBuiltinFunctionDeclaration(C.VoidTy, Args); - llvm::FunctionType *FTy = CGM.getTypes().GetFunctionType(FI); - std::string UnregName = getName({"omp_offloading", "descriptor_unreg"}); - UnRegFn = CGM.CreateGlobalInitOrDestructFunction(FTy, UnregName, FI); - CGF.StartFunction(GlobalDecl(), C.VoidTy, UnRegFn, FI, Args); - CGF.EmitRuntimeCall(createRuntimeFunction(OMPRTL__tgt_unregister_lib), - Desc); - CGF.FinishFunction(); - } - llvm::Function *RegFn; - { - CodeGenFunction CGF(CGM); - // Disable debug info for global (de-)initializer because they are not part - // of some particular construct. - CGF.disableDebugInfo(); - const auto &FI = CGM.getTypes().arrangeNullaryFunction(); - llvm::FunctionType *FTy = CGM.getTypes().GetFunctionType(FI); - - // Encode offload target triples into the registration function name. It - // will serve as a comdat key for the registration/unregistration code for - // this particular combination of offloading targets. - SmallVector RegFnNameParts(Devices.size() + 2U); - RegFnNameParts[0] = "omp_offloading"; - RegFnNameParts[1] = "descriptor_reg"; - llvm::transform(Devices, std::next(RegFnNameParts.begin(), 2), - [](const llvm::Triple &T) -> const std::string& { - return T.getTriple(); - }); - llvm::sort(std::next(RegFnNameParts.begin(), 2), RegFnNameParts.end()); - std::string Descriptor = getName(RegFnNameParts); - RegFn = CGM.CreateGlobalInitOrDestructFunction(FTy, Descriptor, FI); - CGF.StartFunction(GlobalDecl(), C.VoidTy, RegFn, FI, FunctionArgList()); - CGF.EmitRuntimeCall(createRuntimeFunction(OMPRTL__tgt_register_lib), Desc); - // Create a variable to drive the registration and unregistration of the - // descriptor, so we can reuse the logic that emits Ctors and Dtors. - ImplicitParamDecl RegUnregVar(C, C.getTranslationUnitDecl(), - SourceLocation(), nullptr, C.CharTy, - ImplicitParamDecl::Other); - CGM.getCXXABI().registerGlobalDtor(CGF, RegUnregVar, UnRegFn, Desc); - CGF.FinishFunction(); - } - if (CGM.supportsCOMDAT()) { - // It is sufficient to call registration function only once, so create a - // COMDAT group for registration/unregistration functions and associated - // data. That would reduce startup time and code size. Registration - // function serves as a COMDAT group key. - llvm::Comdat *ComdatKey = M.getOrInsertComdat(RegFn->getName()); - RegFn->setLinkage(llvm::GlobalValue::LinkOnceAnyLinkage); - RegFn->setVisibility(llvm::GlobalValue::HiddenVisibility); - RegFn->setComdat(ComdatKey); - UnRegFn->setComdat(ComdatKey); - DeviceImages->setComdat(ComdatKey); - Desc->setComdat(ComdatKey); - } - return RegFn; -} - void CGOpenMPRuntime::createOffloadEntry( llvm::Constant *ID, llvm::Constant *Addr, uint64_t Size, int32_t Flags, llvm::GlobalValue::LinkageTypes Linkage) { @@ -4141,8 +3990,9 @@ // Right now we only generate metadata for function that contain target // regions. - // If we do not have entries, we don't need to do anything. - if (OffloadEntriesInfoManager.empty()) + // If we are in simd mode or there are no entries, we don't need to do + // anything. + if (CGM.getLangOpts().OpenMPSimd || OffloadEntriesInfoManager.empty()) return; llvm::Module &M = CGM.getModule(); @@ -9927,17 +9777,6 @@ return RequiresRegFn; } -llvm::Function *CGOpenMPRuntime::emitRegistrationFunction() { - // If we have offloading in the current module, we need to emit the entries - // now and register the offloading descriptor. - createOffloadEntriesAndInfoMetadata(); - - // Create and register the offloading binary descriptors. This is the main - // entity that captures all the information about offloading in the current - // compilation unit. - return createOffloadingBinaryDescriptorRegistration(); -} - void CGOpenMPRuntime::emitTeamsCall(CodeGenFunction &CGF, const OMPExecutableDirective &D, SourceLocation Loc, @@ -11301,10 +11140,6 @@ return false; } -llvm::Function *CGOpenMPSIMDRuntime::emitRegistrationFunction() { - return nullptr; -} - void CGOpenMPSIMDRuntime::emitTeamsCall(CodeGenFunction &CGF, const OMPExecutableDirective &D, SourceLocation Loc, Index: clang/lib/CodeGen/CodeGenModule.cpp =================================================================== --- clang/lib/CodeGen/CodeGenModule.cpp +++ clang/lib/CodeGen/CodeGenModule.cpp @@ -414,12 +414,7 @@ OpenMPRuntime->emitRequiresDirectiveRegFun()) { AddGlobalCtor(OpenMPRequiresDirectiveRegFun, 0); } - if (llvm::Function *OpenMPRegistrationFunction = - OpenMPRuntime->emitRegistrationFunction()) { - auto ComdatKey = OpenMPRegistrationFunction->hasComdat() ? - OpenMPRegistrationFunction : nullptr; - AddGlobalCtor(OpenMPRegistrationFunction, 0, ComdatKey); - } + OpenMPRuntime->createOffloadEntriesAndInfoMetadata(); OpenMPRuntime->clear(); } if (PGOReader) { Index: clang/lib/Driver/Action.cpp =================================================================== --- clang/lib/Driver/Action.cpp +++ clang/lib/Driver/Action.cpp @@ -40,6 +40,8 @@ return "clang-offload-bundler"; case OffloadUnbundlingJobClass: return "clang-offload-unbundler"; + case OffloadWrapperJobClass: + return "clang-offload-wrapper"; } llvm_unreachable("invalid class"); @@ -401,3 +403,9 @@ OffloadUnbundlingJobAction::OffloadUnbundlingJobAction(Action *Input) : JobAction(OffloadUnbundlingJobClass, Input, Input->getType()) {} + +void OffloadWrapperJobAction::anchor() {} + +OffloadWrapperJobAction::OffloadWrapperJobAction(ActionList &Inputs, + types::ID Type) + : JobAction(OffloadWrapperJobClass, Inputs, Type) {} Index: clang/lib/Driver/Driver.cpp =================================================================== --- clang/lib/Driver/Driver.cpp +++ clang/lib/Driver/Driver.cpp @@ -2282,12 +2282,13 @@ return ABRT_Inactive; } - /// Append top level actions generated by the builder. Return true if errors - /// were found. + /// Append top level actions generated by the builder. virtual void appendTopLevelActions(ActionList &AL) {} - /// Append linker actions generated by the builder. Return true if errors - /// were found. + /// Append linker actions generated by the builder. + virtual void appendLinkActions(ActionList &AL) {} + + /// Append linker actions generated by the builder. virtual void appendLinkDependences(OffloadAction::DeviceDependences &DA) {} /// Initialize the builder. Return true if any initialization errors are @@ -2876,19 +2877,23 @@ OpenMPDeviceActions.clear(); } - void appendLinkDependences(OffloadAction::DeviceDependences &DA) override { + void appendLinkActions(ActionList &AL) override { assert(ToolChains.size() == DeviceLinkerInputs.size() && "Toolchains and linker inputs sizes do not match."); // Append a new link action for each device. - auto TC = ToolChains.begin(); + auto TI = ToolChains.begin(); for (auto &LI : DeviceLinkerInputs) { - auto *DeviceLinkAction = - C.MakeAction(LI, types::TY_Image); - DA.add(*DeviceLinkAction, **TC, /*BoundArch=*/nullptr, - Action::OFK_OpenMP); - ++TC; + auto *A = C.MakeAction(LI, types::TY_Image); + OffloadAction::DeviceDependences Dep; + Dep.add(*A, **TI, /*BoundArch=*/nullptr, Action::OFK_OpenMP); + AL.push_back(C.MakeAction(Dep, A->getType())); + ++TI; } + DeviceLinkerInputs.clear(); + } + + void appendLinkDependences(OffloadAction::DeviceDependences &DA) override { } bool initialize() override { @@ -3114,6 +3119,25 @@ return false; } + Action* makeHostLinkAction() { + // Build a list of device linking actions. + ActionList DeviceAL; + for (auto *SB : SpecializedBuilders) { + if (!SB->isValid()) + continue; + SB->appendLinkActions(DeviceAL); + } + + if (DeviceAL.empty()) + return nullptr; + + // Create wrapper bitcode from the result of device link actions and compile + // it to an object which will be added to the host link command. + auto *BC = C.MakeAction(DeviceAL, types::TY_LLVM_BC); + auto *ASM = C.MakeAction(BC, types::TY_PP_Asm); + return C.MakeAction(ASM, types::TY_Object); + } + /// Processes the host linker action. This currently consists of replacing it /// with an offload action if there are device link objects and propagate to /// the host action all the offload kinds used in the current compilation. The @@ -3407,6 +3431,8 @@ // Add a link action if necessary. if (!LinkerInputs.empty()) { + if (auto *Wrapper = OffloadBuilder.makeHostLinkAction()) + LinkerInputs.push_back(Wrapper); Action *LA = C.MakeAction(LinkerInputs, types::TY_Image); LA = OffloadBuilder.processHostLinkAction(LA); Actions.push_back(LA); @@ -3784,18 +3810,8 @@ if (!AJ || !BJ) return nullptr; - // Retrieve the compile job, backend action must always be preceded by one. - ActionList CompileJobOffloadActions; - auto *CJ = getPrevDependentAction(BJ->getInputs(), CompileJobOffloadActions, - /*CanBeCollapsed=*/false); - if (!AJ || !BJ || !CJ) - return nullptr; - - assert(isa(CJ) && - "Expecting compile job preceding backend job."); - - // Get compiler tool. - const Tool *T = TC.SelectTool(*CJ); + // Get backend tool. + const Tool *T = TC.SelectTool(*BJ); if (!T) return nullptr; @@ -4200,6 +4216,13 @@ A->getOffloadingDeviceKind(), TC->getTriple().normalize(), /*CreatePrefixForHost=*/!!A->getOffloadingHostActiveKinds() && !AtTopLevel); + if (isa(JA)) { + OffloadingPrefix += "-devices"; + if (Arg *FinalOutput = C.getArgs().getLastArg(options::OPT_o)) + BaseInput = FinalOutput->getValue(); + else + BaseInput = getDefaultImageName(); + } Result = InputInfo(A, GetNamedOutputPath(C, *JA, BaseInput, BoundArch, AtTopLevel, MultipleArchs, OffloadingPrefix), Index: clang/lib/Driver/ToolChain.cpp =================================================================== --- clang/lib/Driver/ToolChain.cpp +++ clang/lib/Driver/ToolChain.cpp @@ -285,6 +285,12 @@ return OffloadBundler.get(); } +Tool *ToolChain::getOffloadWrapper() const { + if (!OffloadWrapper) + OffloadWrapper.reset(new tools::OffloadWrapper(*this)); + return OffloadWrapper.get(); +} + Tool *ToolChain::getTool(Action::ActionClass AC) const { switch (AC) { case Action::AssembleJobClass: @@ -314,6 +320,9 @@ case Action::OffloadBundlingJobClass: case Action::OffloadUnbundlingJobClass: return getOffloadBundler(); + + case Action::OffloadWrapperJobClass: + return getOffloadWrapper(); } llvm_unreachable("Invalid tool kind."); Index: clang/lib/Driver/ToolChains/Clang.h =================================================================== --- clang/lib/Driver/ToolChains/Clang.h +++ clang/lib/Driver/ToolChains/Clang.h @@ -152,6 +152,20 @@ const llvm::opt::ArgList &TCArgs, const char *LinkingOutput) const override; }; + +/// Offload wrapper tool. +class LLVM_LIBRARY_VISIBILITY OffloadWrapper final : public Tool { +public: + OffloadWrapper(const ToolChain &TC) + : Tool("offload wrapper", "clang-offload-wrapper", TC) {} + + bool hasIntegratedCPP() const override { return false; } + void ConstructJob(Compilation &C, const JobAction &JA, + const InputInfo &Output, const InputInfoList &Inputs, + const llvm::opt::ArgList &TCArgs, + const char *LinkingOutput) const override; +}; + } // end namespace tools } // end namespace driver Index: clang/lib/Driver/ToolChains/Clang.cpp =================================================================== --- clang/lib/Driver/ToolChains/Clang.cpp +++ clang/lib/Driver/ToolChains/Clang.cpp @@ -6467,3 +6467,33 @@ TCArgs.MakeArgString(getToolChain().GetProgramPath(getShortName())), CmdArgs, None)); } + +void OffloadWrapper::ConstructJob(Compilation &C, const JobAction &JA, + const InputInfo &Output, + const InputInfoList &Inputs, + const ArgList &Args, + const char *LinkingOutput) const { + ArgStringList CmdArgs; + + const auto &Triple = getToolChain().getEffectiveTriple(); + + // Add the "effective" target triple. + CmdArgs.push_back("-target"); + CmdArgs.push_back(Args.MakeArgString(Triple.getTriple())); + + // Add the output file name. + assert(Output.isFilename() && "Invalid output."); + CmdArgs.push_back("-o"); + CmdArgs.push_back(Output.getFilename()); + + // Add inputs. + for (const auto &I : Inputs) { + assert(I.isFilename() && "Invalid input."); + CmdArgs.push_back(I.getFilename()); + } + + C.addCommand(std::make_unique( + JA, *this, + Args.MakeArgString(getToolChain().GetProgramPath(getShortName())), + CmdArgs, Inputs)); +} Index: clang/lib/Driver/ToolChains/CommonArgs.h =================================================================== --- clang/lib/Driver/ToolChains/CommonArgs.h +++ clang/lib/Driver/ToolChains/CommonArgs.h @@ -45,13 +45,6 @@ llvm::opt::ArgStringList &CmdArgs, const llvm::opt::ArgList &Args); -void AddOpenMPLinkerScript(const ToolChain &TC, Compilation &C, - const InputInfo &Output, - const InputInfoList &Inputs, - const llvm::opt::ArgList &Args, - llvm::opt::ArgStringList &CmdArgs, - const JobAction &JA); - void AddHIPLinkerScript(const ToolChain &TC, Compilation &C, const InputInfo &Output, const InputInfoList &Inputs, const llvm::opt::ArgList &Args, Index: clang/lib/Driver/ToolChains/CommonArgs.cpp =================================================================== --- clang/lib/Driver/ToolChains/CommonArgs.cpp +++ clang/lib/Driver/ToolChains/CommonArgs.cpp @@ -1245,131 +1245,6 @@ } } -/// Add OpenMP linker script arguments at the end of the argument list so that -/// the fat binary is built by embedding each of the device images into the -/// host. The linker script also defines a few symbols required by the code -/// generation so that the images can be easily retrieved at runtime by the -/// offloading library. This should be used only in tool chains that support -/// linker scripts. -void tools::AddOpenMPLinkerScript(const ToolChain &TC, Compilation &C, - const InputInfo &Output, - const InputInfoList &Inputs, - const ArgList &Args, ArgStringList &CmdArgs, - const JobAction &JA) { - - // If this is not an OpenMP host toolchain, we don't need to do anything. - if (!JA.isHostOffloading(Action::OFK_OpenMP)) - return; - - // Create temporary linker script. Keep it if save-temps is enabled. - const char *LKS; - SmallString<256> Name = llvm::sys::path::filename(Output.getFilename()); - if (C.getDriver().isSaveTempsEnabled()) { - llvm::sys::path::replace_extension(Name, "lk"); - LKS = C.getArgs().MakeArgString(Name.c_str()); - } else { - llvm::sys::path::replace_extension(Name, ""); - Name = C.getDriver().GetTemporaryPath(Name, "lk"); - LKS = C.addTempFile(C.getArgs().MakeArgString(Name.c_str())); - } - - // Add linker script option to the command. - CmdArgs.push_back("-T"); - CmdArgs.push_back(LKS); - - // Create a buffer to write the contents of the linker script. - std::string LksBuffer; - llvm::raw_string_ostream LksStream(LksBuffer); - - // Get the OpenMP offload tool chains so that we can extract the triple - // associated with each device input. - auto OpenMPToolChains = C.getOffloadToolChains(); - assert(OpenMPToolChains.first != OpenMPToolChains.second && - "No OpenMP toolchains??"); - - // Track the input file name and device triple in order to build the script, - // inserting binaries in the designated sections. - SmallVector, 8> InputBinaryInfo; - - // Add commands to embed target binaries. We ensure that each section and - // image is 16-byte aligned. This is not mandatory, but increases the - // likelihood of data to be aligned with a cache block in several main host - // machines. - LksStream << "/*\n"; - LksStream << " OpenMP Offload Linker Script\n"; - LksStream << " *** Automatically generated by Clang ***\n"; - LksStream << "*/\n"; - LksStream << "TARGET(binary)\n"; - auto DTC = OpenMPToolChains.first; - for (auto &II : Inputs) { - const Action *A = II.getAction(); - // Is this a device linking action? - if (A && isa(A) && - A->isDeviceOffloading(Action::OFK_OpenMP)) { - assert(DTC != OpenMPToolChains.second && - "More device inputs than device toolchains??"); - InputBinaryInfo.push_back(std::make_pair( - DTC->second->getTriple().normalize(), II.getFilename())); - ++DTC; - LksStream << "INPUT(" << II.getFilename() << ")\n"; - } - } - - assert(DTC == OpenMPToolChains.second && - "Less device inputs than device toolchains??"); - - LksStream << "SECTIONS\n"; - LksStream << "{\n"; - - // Put each target binary into a separate section. - for (const auto &BI : InputBinaryInfo) { - LksStream << " .omp_offloading." << BI.first << " :\n"; - LksStream << " ALIGN(0x10)\n"; - LksStream << " {\n"; - LksStream << " PROVIDE_HIDDEN(.omp_offloading.img_start." << BI.first - << " = .);\n"; - LksStream << " " << BI.second << "\n"; - LksStream << " PROVIDE_HIDDEN(.omp_offloading.img_end." << BI.first - << " = .);\n"; - LksStream << " }\n"; - } - - // Add commands to define host entries begin and end. We use 1-byte subalign - // so that the linker does not add any padding and the elements in this - // section form an array. - LksStream << " .omp_offloading.entries :\n"; - LksStream << " ALIGN(0x10)\n"; - LksStream << " SUBALIGN(0x01)\n"; - LksStream << " {\n"; - LksStream << " PROVIDE_HIDDEN(.omp_offloading.entries_begin = .);\n"; - LksStream << " *(.omp_offloading.entries)\n"; - LksStream << " PROVIDE_HIDDEN(.omp_offloading.entries_end = .);\n"; - LksStream << " }\n"; - LksStream << "}\n"; - LksStream << "INSERT BEFORE .data\n"; - LksStream.flush(); - - // Dump the contents of the linker script if the user requested that. We - // support this option to enable testing of behavior with -###. - if (C.getArgs().hasArg(options::OPT_fopenmp_dump_offload_linker_script)) - llvm::errs() << LksBuffer; - - // If this is a dry run, do not create the linker script file. - if (C.getArgs().hasArg(options::OPT__HASH_HASH_HASH)) - return; - - // Open script file and write the contents. - std::error_code EC; - llvm::raw_fd_ostream Lksf(LKS, EC, llvm::sys::fs::OF_None); - - if (EC) { - C.getDriver().Diag(clang::diag::err_unable_to_make_temp) << EC.message(); - return; - } - - Lksf << LksBuffer; -} - /// Add HIP linker script arguments at the end of the argument list so that /// the fat binary is built by embedding the device images into the host. The /// linker script also defines a symbol required by the code generation so that Index: clang/lib/Driver/ToolChains/Cuda.cpp =================================================================== --- clang/lib/Driver/ToolChains/Cuda.cpp +++ clang/lib/Driver/ToolChains/Cuda.cpp @@ -563,8 +563,6 @@ CmdArgs.push_back(CubinF); } - AddOpenMPLinkerScript(getToolChain(), C, Output, Inputs, Args, CmdArgs, JA); - const char *Exec = Args.MakeArgString(getToolChain().GetProgramPath("nvlink")); C.addCommand(std::make_unique(JA, *this, Exec, CmdArgs, Inputs)); Index: clang/lib/Driver/ToolChains/Gnu.cpp =================================================================== --- clang/lib/Driver/ToolChains/Gnu.cpp +++ clang/lib/Driver/ToolChains/Gnu.cpp @@ -499,7 +499,11 @@ P = ToolChain.GetFilePath(crtbegin); } CmdArgs.push_back(Args.MakeArgString(P)); - } + } + + if (JA.isHostOffloading(Action::OFK_OpenMP)) + CmdArgs.push_back( + Args.MakeArgString(ToolChain.GetFilePath("omptargetbegin.o"))); // Add crtfastmath.o if available and fast math is enabled. ToolChain.AddFastMathRuntimeIfAvailable(Args, CmdArgs); @@ -596,6 +600,10 @@ } } + if (JA.isHostOffloading(Action::OFK_OpenMP)) + CmdArgs.push_back( + Args.MakeArgString(ToolChain.GetFilePath("omptargetend.o"))); + if (!Args.hasArg(options::OPT_nostartfiles) && !IsIAMCU) { if (HasCRTBeginEndFiles) { std::string P; @@ -623,9 +631,6 @@ } } - // Add OpenMP offloading linker script args if required. - AddOpenMPLinkerScript(getToolChain(), C, Output, Inputs, Args, CmdArgs, JA); - // Add HIP offloading linker script args if required. AddHIPLinkerScript(getToolChain(), C, Output, Inputs, Args, CmdArgs, JA, *this); Index: clang/test/Driver/clang-offload-wrapper.c =================================================================== --- /dev/null +++ clang/test/Driver/clang-offload-wrapper.c @@ -0,0 +1,53 @@ +// REQUIRES: x86-registered-target + +// +// Check help message. +// +// RUN: clang-offload-wrapper --help | FileCheck %s --check-prefix CHECK-HELP +// CHECK-HELP: {{.*}}OVERVIEW: A tool to create a wrapper bitcode for offload target binaries. +// CHECK-HELP: {{.*}}Takes offload target binaries as input and produces bitcode file containing +// CHECK-HELP: {{.*}}target binaries packaged as data and initialization code which registers target +// CHECK-HELP: {{.*}}binaries in offload runtime. +// CHECK-HELP: {{.*}}USAGE: clang-offload-wrapper [options] +// CHECK-HELP: {{.*}}-o= - Output filename +// CHECK-HELP: {{.*}}-target= - Target triple + +// +// Generate a file to wrap. +// +// RUN: echo 'Content of device file' > %t.tgt + +// +// Check bitcode produced by the wrapper tool. +// +// RUN: clang-offload-wrapper -target=x86_64-pc-linux-gnu -o - %t.tgt | llvm-dis | FileCheck %s --check-prefix CHECK-IR + +// CHECK-IR: target triple = "x86_64-pc-linux-gnu" + +// CHECK-IR-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } +// CHECK-IR-DAG: [[IMAGETY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } +// CHECK-IR-DAG: [[DESCTY:%.+]] = type { i32, [[IMAGETY]]*, [[ENTTY]]*, [[ENTTY]]* } + +// CHECK-IR: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] +// CHECK-IR: [[ENTEND:@.+]] = external constant [[ENTTY]] + +// CHECK-IR: [[BIN:@.+]] = internal unnamed_addr constant [[BINTY:\[[0-9]+ x i8\]]] c"Content of device file{{.+}}" + +// CHECK-IR: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[IMAGETY]]] [{{.+}} { i8* getelementptr inbounds ([[BINTY]], [[BINTY]]* [[BIN]], i64 0, i64 0), i8* getelementptr inbounds ([[BINTY]], [[BINTY]]* [[BIN]], i64 1, i64 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }] + +// CHECK-IR: [[DESC:@.+]] = internal constant [[DESCTY]] { i32 1, [[IMAGETY]]* getelementptr inbounds ([1 x [[IMAGETY]]], [1 x [[IMAGETY]]]* [[IMAGES]], i64 0, i64 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] } + +// CHECK-IR: @llvm.global_ctors = appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* [[REGFN:@.+]], i8* null }] +// CHECK-IR: @llvm.global_dtors = appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* [[UNREGFN:@.+]], i8* null }] + +// CHECK-IR: define internal void [[REGFN]]() +// CHECK-IR: call void @__tgt_register_lib([[DESCTY]]* [[DESC]]) +// CHECK-IR: ret void + +// CHECK-IR: declare void @__tgt_register_lib([[DESCTY]]*) + +// CHECK-IR: define internal void [[UNREGFN]]() +// CHECK-IR: call void @__tgt_unregister_lib([[DESCTY]]* [[DESC]]) +// CHECK-IR: ret void + +// CHECK-IR: declare void @__tgt_unregister_lib([[DESCTY]]*) Index: clang/test/Driver/openmp-offload-gpu.c =================================================================== --- clang/test/Driver/openmp-offload-gpu.c +++ clang/test/Driver/openmp-offload-gpu.c @@ -55,7 +55,7 @@ // RUN: -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \ // RUN: | FileCheck -check-prefix=CHK-CUBIN-NVLINK %s -// CHK-CUBIN-NVLINK: clang{{.*}}" "-o" "[[PTX:.*\.s]]" +// CHK-CUBIN-NVLINK: clang{{.*}}" {{.*}}"-fopenmp-is-device" {{.*}}"-o" "[[PTX:.*\.s]]" // CHK-CUBIN-NVLINK-NEXT: ptxas{{.*}}" "--output-file" "[[CUBIN:.*\.cubin]]" {{.*}}"[[PTX]]" // CHK-CUBIN-NVLINK-NEXT: nvlink{{.*}}" {{.*}}"[[CUBIN]]" Index: clang/test/Driver/openmp-offload.c =================================================================== --- clang/test/Driver/openmp-offload.c +++ clang/test/Driver/openmp-offload.c @@ -106,15 +106,18 @@ // CHK-PHASES: 2: compiler, {1}, ir, (host-openmp) // CHK-PHASES: 3: backend, {2}, assembler, (host-openmp) // CHK-PHASES: 4: assembler, {3}, object, (host-openmp) -// CHK-PHASES: 5: linker, {4}, image, (host-openmp) -// CHK-PHASES: 6: input, "[[INPUT]]", c, (device-openmp) -// CHK-PHASES: 7: preprocessor, {6}, cpp-output, (device-openmp) -// CHK-PHASES: 8: compiler, {7}, ir, (device-openmp) -// CHK-PHASES: 9: offload, "host-openmp (powerpc64le-ibm-linux-gnu)" {2}, "device-openmp (x86_64-pc-linux-gnu)" {8}, ir -// CHK-PHASES: 10: backend, {9}, assembler, (device-openmp) -// CHK-PHASES: 11: assembler, {10}, object, (device-openmp) -// CHK-PHASES: 12: linker, {11}, image, (device-openmp) -// CHK-PHASES: 13: offload, "host-openmp (powerpc64le-ibm-linux-gnu)" {5}, "device-openmp (x86_64-pc-linux-gnu)" {12}, image +// CHK-PHASES: 5: input, "[[INPUT]]", c, (device-openmp) +// CHK-PHASES: 6: preprocessor, {5}, cpp-output, (device-openmp) +// CHK-PHASES: 7: compiler, {6}, ir, (device-openmp) +// CHK-PHASES: 8: offload, "host-openmp (powerpc64le-ibm-linux-gnu)" {2}, "device-openmp (x86_64-pc-linux-gnu)" {7}, ir +// CHK-PHASES: 9: backend, {8}, assembler, (device-openmp) +// CHK-PHASES: 10: assembler, {9}, object, (device-openmp) +// CHK-PHASES: 11: linker, {10}, image, (device-openmp) +// CHK-PHASES: 12: offload, "device-openmp (x86_64-pc-linux-gnu)" {11}, image +// CHK-PHASES: 13: clang-offload-wrapper, {12}, ir, (host-openmp) +// CHK-PHASES: 14: backend, {13}, assembler, (host-openmp) +// CHK-PHASES: 15: assembler, {14}, object, (host-openmp) +// CHK-PHASES: 16: linker, {4, 15}, image, (host-openmp) /// ########################################################################### @@ -128,15 +131,15 @@ // CHK-PHASES-LIB: 3: compiler, {2}, ir, (host-openmp) // CHK-PHASES-LIB: 4: backend, {3}, assembler, (host-openmp) // CHK-PHASES-LIB: 5: assembler, {4}, object, (host-openmp) -// CHK-PHASES-LIB: 6: linker, {0, 5}, image, (host-openmp) -// CHK-PHASES-LIB: 7: input, "somelib", object, (device-openmp) -// CHK-PHASES-LIB: 8: input, "[[INPUT]]", c, (device-openmp) -// CHK-PHASES-LIB: 9: preprocessor, {8}, cpp-output, (device-openmp) -// CHK-PHASES-LIB: 10: compiler, {9}, ir, (device-openmp) -// CHK-PHASES-LIB: 11: offload, "host-openmp (powerpc64-ibm-linux-gnu)" {3}, "device-openmp (x86_64-pc-linux-gnu)" {10}, ir -// CHK-PHASES-LIB: 12: backend, {11}, assembler, (device-openmp) -// CHK-PHASES-LIB: 13: assembler, {12}, object, (device-openmp) -// CHK-PHASES-LIB: 14: linker, {7, 13}, image, (device-openmp) +// CHK-PHASES-LIB: 6: input, "somelib", object, (device-openmp) +// CHK-PHASES-LIB: 7: input, "[[INPUT]]", c, (device-openmp) +// CHK-PHASES-LIB: 8: preprocessor, {7}, cpp-output, (device-openmp) +// CHK-PHASES-LIB: 9: compiler, {8}, ir, (device-openmp) +// CHK-PHASES-LIB: 10: offload, "host-openmp (powerpc64-ibm-linux-gnu)" {3}, "device-openmp (x86_64-pc-linux-gnu)" {9}, ir +// CHK-PHASES-LIB: 11: backend, {10}, assembler, (device-openmp) +// CHK-PHASES-LIB: 12: assembler, {11}, object, (device-openmp) +// CHK-PHASES-LIB: 13: linker, {6, 12}, image, (device-openmp) +// CHK-PHASES-LIB: 14: offload, "device-openmp (x86_64-pc-linux-gnu)" {13}, image // CHK-PHASES-LIB: 15: input, "somelib", object, (device-openmp) // CHK-PHASES-LIB: 16: input, "[[INPUT]]", c, (device-openmp) // CHK-PHASES-LIB: 17: preprocessor, {16}, cpp-output, (device-openmp) @@ -145,8 +148,11 @@ // CHK-PHASES-LIB: 20: backend, {19}, assembler, (device-openmp) // CHK-PHASES-LIB: 21: assembler, {20}, object, (device-openmp) // CHK-PHASES-LIB: 22: linker, {15, 21}, image, (device-openmp) -// CHK-PHASES-LIB: 23: offload, "host-openmp (powerpc64-ibm-linux-gnu)" {6}, "device-openmp (x86_64-pc-linux-gnu)" {14}, "device-openmp (powerpc64-ibm-linux-gnu)" {22}, image - +// CHK-PHASES-LIB: 23: offload, "device-openmp (powerpc64-ibm-linux-gnu)" {22}, image +// CHK-PHASES-LIB: 24: clang-offload-wrapper, {14, 23}, ir, (host-openmp) +// CHK-PHASES-LIB: 25: backend, {24}, assembler, (host-openmp) +// CHK-PHASES-LIB: 26: assembler, {25}, object, (host-openmp) +// CHK-PHASES-LIB: 27: linker, {0, 5, 26}, image, (host-openmp) /// ########################################################################### @@ -165,21 +171,21 @@ // CHK-PHASES-FILES: 8: compiler, {7}, ir, (host-openmp) // CHK-PHASES-FILES: 9: backend, {8}, assembler, (host-openmp) // CHK-PHASES-FILES: 10: assembler, {9}, object, (host-openmp) -// CHK-PHASES-FILES: 11: linker, {0, 5, 10}, image, (host-openmp) -// CHK-PHASES-FILES: 12: input, "somelib", object, (device-openmp) -// CHK-PHASES-FILES: 13: input, "[[INPUT1]]", c, (device-openmp) -// CHK-PHASES-FILES: 14: preprocessor, {13}, cpp-output, (device-openmp) -// CHK-PHASES-FILES: 15: compiler, {14}, ir, (device-openmp) -// CHK-PHASES-FILES: 16: offload, "host-openmp (powerpc64-ibm-linux-gnu)" {3}, "device-openmp (x86_64-pc-linux-gnu)" {15}, ir -// CHK-PHASES-FILES: 17: backend, {16}, assembler, (device-openmp) -// CHK-PHASES-FILES: 18: assembler, {17}, object, (device-openmp) -// CHK-PHASES-FILES: 19: input, "[[INPUT2]]", c, (device-openmp) -// CHK-PHASES-FILES: 20: preprocessor, {19}, cpp-output, (device-openmp) -// CHK-PHASES-FILES: 21: compiler, {20}, ir, (device-openmp) -// CHK-PHASES-FILES: 22: offload, "host-openmp (powerpc64-ibm-linux-gnu)" {8}, "device-openmp (x86_64-pc-linux-gnu)" {21}, ir -// CHK-PHASES-FILES: 23: backend, {22}, assembler, (device-openmp) -// CHK-PHASES-FILES: 24: assembler, {23}, object, (device-openmp) -// CHK-PHASES-FILES: 25: linker, {12, 18, 24}, image, (device-openmp) +// CHK-PHASES-FILES: 11: input, "somelib", object, (device-openmp) +// CHK-PHASES-FILES: 12: input, "[[INPUT1]]", c, (device-openmp) +// CHK-PHASES-FILES: 13: preprocessor, {12}, cpp-output, (device-openmp) +// CHK-PHASES-FILES: 14: compiler, {13}, ir, (device-openmp) +// CHK-PHASES-FILES: 15: offload, "host-openmp (powerpc64-ibm-linux-gnu)" {3}, "device-openmp (x86_64-pc-linux-gnu)" {14}, ir +// CHK-PHASES-FILES: 16: backend, {15}, assembler, (device-openmp) +// CHK-PHASES-FILES: 17: assembler, {16}, object, (device-openmp) +// CHK-PHASES-FILES: 18: input, "[[INPUT2]]", c, (device-openmp) +// CHK-PHASES-FILES: 19: preprocessor, {18}, cpp-output, (device-openmp) +// CHK-PHASES-FILES: 20: compiler, {19}, ir, (device-openmp) +// CHK-PHASES-FILES: 21: offload, "host-openmp (powerpc64-ibm-linux-gnu)" {8}, "device-openmp (x86_64-pc-linux-gnu)" {20}, ir +// CHK-PHASES-FILES: 22: backend, {21}, assembler, (device-openmp) +// CHK-PHASES-FILES: 23: assembler, {22}, object, (device-openmp) +// CHK-PHASES-FILES: 24: linker, {11, 17, 23}, image, (device-openmp) +// CHK-PHASES-FILES: 25: offload, "device-openmp (x86_64-pc-linux-gnu)" {24}, image // CHK-PHASES-FILES: 26: input, "somelib", object, (device-openmp) // CHK-PHASES-FILES: 27: input, "[[INPUT1]]", c, (device-openmp) // CHK-PHASES-FILES: 28: preprocessor, {27}, cpp-output, (device-openmp) @@ -194,7 +200,11 @@ // CHK-PHASES-FILES: 37: backend, {36}, assembler, (device-openmp) // CHK-PHASES-FILES: 38: assembler, {37}, object, (device-openmp) // CHK-PHASES-FILES: 39: linker, {26, 32, 38}, image, (device-openmp) -// CHK-PHASES-FILES: 40: offload, "host-openmp (powerpc64-ibm-linux-gnu)" {11}, "device-openmp (x86_64-pc-linux-gnu)" {25}, "device-openmp (powerpc64-ibm-linux-gnu)" {39}, image +// CHK-PHASES-FILES: 40: offload, "device-openmp (powerpc64-ibm-linux-gnu)" {39}, image +// CHK-PHASES-FILES: 41: clang-offload-wrapper, {25, 40}, ir, (host-openmp) +// CHK-PHASES-FILES: 42: backend, {41}, assembler, (host-openmp) +// CHK-PHASES-FILES: 43: assembler, {42}, object, (host-openmp) +// CHK-PHASES-FILES: 44: linker, {0, 5, 10, 43}, image, (host-openmp) /// ########################################################################### @@ -216,15 +226,18 @@ // CHK-PHASES-WITH-CUDA: 11: offload, "host-cuda-openmp (powerpc64le-ibm-linux-gnu)" {2}, "device-cuda (nvptx64-nvidia-cuda)" {10}, ir // CHK-PHASES-WITH-CUDA: 12: backend, {11}, assembler, (host-cuda-openmp) // CHK-PHASES-WITH-CUDA: 13: assembler, {12}, object, (host-cuda-openmp) -// CHK-PHASES-WITH-CUDA: 14: linker, {13}, image, (host-cuda-openmp) -// CHK-PHASES-WITH-CUDA: 15: input, "[[INPUT]]", cuda, (device-openmp) -// CHK-PHASES-WITH-CUDA: 16: preprocessor, {15}, cuda-cpp-output, (device-openmp) -// CHK-PHASES-WITH-CUDA: 17: compiler, {16}, ir, (device-openmp) -// CHK-PHASES-WITH-CUDA: 18: offload, "host-cuda-openmp (powerpc64le-ibm-linux-gnu)" {2}, "device-openmp (nvptx64-nvidia-cuda)" {17}, ir -// CHK-PHASES-WITH-CUDA: 19: backend, {18}, assembler, (device-openmp) -// CHK-PHASES-WITH-CUDA: 20: assembler, {19}, object, (device-openmp) -// CHK-PHASES-WITH-CUDA: 21: linker, {20}, image, (device-openmp) -// CHK-PHASES-WITH-CUDA: 22: offload, "host-cuda-openmp (powerpc64le-ibm-linux-gnu)" {14}, "device-openmp (nvptx64-nvidia-cuda)" {21}, image +// CHK-PHASES-WITH-CUDA: 14: input, "[[INPUT]]", cuda, (device-openmp) +// CHK-PHASES-WITH-CUDA: 15: preprocessor, {14}, cuda-cpp-output, (device-openmp) +// CHK-PHASES-WITH-CUDA: 16: compiler, {15}, ir, (device-openmp) +// CHK-PHASES-WITH-CUDA: 17: offload, "host-cuda-openmp (powerpc64le-ibm-linux-gnu)" {2}, "device-openmp (nvptx64-nvidia-cuda)" {16}, ir +// CHK-PHASES-WITH-CUDA: 18: backend, {17}, assembler, (device-openmp) +// CHK-PHASES-WITH-CUDA: 19: assembler, {18}, object, (device-openmp) +// CHK-PHASES-WITH-CUDA: 20: linker, {19}, image, (device-openmp) +// CHK-PHASES-WITH-CUDA: 21: offload, "device-openmp (nvptx64-nvidia-cuda)" {20}, image +// CHK-PHASES-WITH-CUDA: 22: clang-offload-wrapper, {21}, ir, (host-cuda-openmp) +// CHK-PHASES-WITH-CUDA: 23: backend, {22}, assembler, (host-cuda-openmp) +// CHK-PHASES-WITH-CUDA: 24: assembler, {23}, object, (host-cuda-openmp) +// CHK-PHASES-WITH-CUDA: 25: linker, {13, 24}, image, (host-cuda-openmp) /// ########################################################################### @@ -237,73 +250,31 @@ /// -fopenmp-host-ir-file-path: specifies the host IR file that can be loaded by /// the target code generation to gather information about which declaration /// really need to be emitted. -/// We use -fopenmp-dump-offload-linker-script to dump the linker script and -/// check its contents. /// -// RUN: %clang -### -fopenmp=libomp -o %t.out -target powerpc64le-linux -fopenmp-targets=powerpc64le-ibm-linux-gnu,x86_64-pc-linux-gnu %s -fopenmp-dump-offload-linker-script -no-canonical-prefixes 2>&1 \ -// RUN: | FileCheck -check-prefix=CHK-COMMANDS -check-prefix=CHK-LKS -check-prefix=CHK-LKS-REG %s -// RUN: %clang -### -fopenmp=libomp -o %t.out -target powerpc64le-linux -fopenmp-targets=powerpc64le-ibm-linux-gnu,x86_64-pc-linux-gnu %s -save-temps -fopenmp-dump-offload-linker-script -no-canonical-prefixes 2>&1 \ -// RUN: | FileCheck -check-prefix=CHK-COMMANDS-ST -check-prefix=CHK-LKS -check-prefix=CHK-LKS-ST %s - -// Make sure we are not dumping the script unless the user requested it. // RUN: %clang -### -fopenmp=libomp -o %t.out -target powerpc64le-linux -fopenmp-targets=powerpc64le-ibm-linux-gnu,x86_64-pc-linux-gnu %s -no-canonical-prefixes 2>&1 \ -// RUN: | FileCheck -check-prefix=CHK-LKS-NODUMP %s +// RUN: | FileCheck -check-prefix=CHK-COMMANDS %s // RUN: %clang -### -fopenmp=libomp -o %t.out -target powerpc64le-linux -fopenmp-targets=powerpc64le-ibm-linux-gnu,x86_64-pc-linux-gnu %s -save-temps -no-canonical-prefixes 2>&1 \ -// RUN: | FileCheck -check-prefix=CHK-LKS-NODUMP %s - -// -// Check the linker script contains what we expect. -// -// CHK-LKS: /* -// CHK-LKS: OpenMP Offload Linker Script -// CHK-LKS: *** Automatically generated by Clang *** -// CHK-LKS-NODUMP-NOT: OpenMP Offload Linker Script. -// CHK-LKS: */ -// CHK-LKS: TARGET(binary) -// CHK-LKS-REG: INPUT([[T1BIN:.+\.out]]) -// CHK-LKS-REG: INPUT([[T2BIN:.+\.out]]) -// CHK-LKS-ST: INPUT([[T1BIN:.+\.out-openmp-powerpc64le-ibm-linux-gnu]]) -// CHK-LKS-ST: INPUT([[T2BIN:.+\.out-openmp-x86_64-pc-linux-gnu]]) -// CHK-LKS: SECTIONS -// CHK-LKS: { -// CHK-LKS: .omp_offloading.powerpc64le-ibm-linux-gnu : -// CHK-LKS: ALIGN(0x10) -// CHK-LKS: { -// CHK-LKS: PROVIDE_HIDDEN(.omp_offloading.img_start.powerpc64le-ibm-linux-gnu = .); -// CHK-LKS: [[T1BIN]] -// CHK-LKS: PROVIDE_HIDDEN(.omp_offloading.img_end.powerpc64le-ibm-linux-gnu = .); -// CHK-LKS: } -// CHK-LKS: .omp_offloading.x86_64-pc-linux-gnu : -// CHK-LKS: ALIGN(0x10) -// CHK-LKS: { -// CHK-LKS: PROVIDE_HIDDEN(.omp_offloading.img_start.x86_64-pc-linux-gnu = .); -// CHK-LKS: [[T2BIN]] -// CHK-LKS: PROVIDE_HIDDEN(.omp_offloading.img_end.x86_64-pc-linux-gnu = .); -// CHK-LKS: } -// CHK-LKS: .omp_offloading.entries : -// CHK-LKS: ALIGN(0x10) -// CHK-LKS: SUBALIGN(0x01) -// CHK-LKS: { -// CHK-LKS: PROVIDE_HIDDEN(.omp_offloading.entries_begin = .); -// CHK-LKS: *(.omp_offloading.entries) -// CHK-LKS: PROVIDE_HIDDEN(.omp_offloading.entries_end = .); -// CHK-LKS: } -// CHK-LKS: } -// CHK-LKS: INSERT BEFORE .data +// RUN: | FileCheck -check-prefix=CHK-COMMANDS-ST %s // -// Generate host BC file. +// Generate host BC file and host object. // // CHK-COMMANDS: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-emit-llvm-bc" // CHK-COMMANDS-SAME: "-fopenmp-targets=powerpc64le-ibm-linux-gnu,x86_64-pc-linux-gnu" // CHK-COMMANDS-SAME: "-o" " // CHK-COMMANDS-SAME: [[HOSTBC:[^\\/]+\.bc]]" "-x" "c" " // CHK-COMMANDS-SAME: [[INPUT:[^\\/]+\.c]]" +// CHK-COMMANDS: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-emit-obj" {{.*}}"-fopenmp" {{.*}}"-o" " +// CHK-COMMANDS-SAME: [[HOSTOBJ:[^\\/]+\.o]]" "-x" "ir" "{{.*}}[[HOSTBC]]" // CHK-COMMANDS-ST: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-E" {{.*}}"-fopenmp" {{.*}}"-o" " // CHK-COMMANDS-ST-SAME: [[HOSTPP:[^\\/]+\.i]]" "-x" "c" " // CHK-COMMANDS-ST-SAME: [[INPUT:[^\\/]+\.c]]" // CHK-COMMANDS-ST: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-emit-llvm-bc" {{.*}}"-fopenmp" {{.*}}"-fopenmp-targets=powerpc64le-ibm-linux-gnu,x86_64-pc-linux-gnu" {{.*}}"-o" " // CHK-COMMANDS-ST-SAME: [[HOSTBC:[^\\/]+\.bc]]" "-x" "cpp-output" "{{.*}}[[HOSTPP]]" +// CHK-COMMANDS-ST: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-S" {{.*}}"-fopenmp" {{.*}}"-o" " +// CHK-COMMANDS-ST-SAME: [[HOSTASM:[^\\/]+\.s]]" "-x" "ir" "{{.*}}[[HOSTBC]]" +// CHK-COMMANDS-ST: clang{{.*}}" "-cc1as" "-triple" "powerpc64le-unknown-linux" "-filetype" "obj" {{.*}}"-o" " +// CHK-COMMANDS-ST-SAME: [[HOSTOBJ:[^\\/]+\.o]]" "{{.*}}[[HOSTASM]]" // // Compile for the powerpc device. @@ -343,21 +314,26 @@ // CHK-COMMANDS-ST-SAME: [[T2BIN:[^\\/]+\.out-openmp-x86_64-pc-linux-gnu]]" {{.*}}"{{.*}}[[T2OBJ]]" // -// Generate host object from the BC file and link using the linker script. +// Create wrapper BC file and wrapper object. // +// CHK-COMMANDS: clang-offload-wrapper{{(\.exe)?}}" "-target" "powerpc64le-unknown-linux" "-o" " +// CHK-COMMANDS-SAME: [[WRAPPERBC:[^\\/]+\.bc]]" "{{.*}}[[T1BIN]]" "{{.*}}[[T2BIN]]" // CHK-COMMANDS: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-emit-obj" {{.*}}"-fopenmp" {{.*}}"-o" " -// CHK-COMMANDS-SAME: [[HOSTOBJ:[^\\/]+\.o]]" "-x" "ir" "{{.*}}[[HOSTBC]]" -// CHK-COMMANDS: ld{{(\.exe)?}}" {{.*}}"-o" " -// CHK-COMMANDS-SAME: [[HOSTBIN:[^\\/]+\.out]]" {{.*}}"-lomptarget" {{.*}}"-T" " -// CHK-COMMANDS-SAME: [[HOSTLK:[^\\/]+\.lk]]" +// CHK-COMMANDS-SAME: [[WRAPPEROBJ:[^\\/]+\.o]]" "-x" "ir" "{{.*}}[[WRAPPERBC]]" +// CHK-COMMANDS-ST: clang-offload-wrapper{{(\.exe)?}}" "-target" "powerpc64le-unknown-linux" "-o" " +// CHK-COMMANDS-ST-SAME: [[WRAPPERBC:[^\\/]+\.bc]]" "{{.*}}[[T1BIN]]" "{{.*}}[[T2BIN]]" // CHK-COMMANDS-ST: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-S" {{.*}}"-fopenmp" {{.*}}"-o" " -// CHK-COMMANDS-ST-SAME: [[HOSTASM:[^\\/]+\.s]]" "-x" "ir" "{{.*}}[[HOSTBC]]" +// CHK-COMMANDS-ST-SAME: [[WRAPPERASM:[^\\/]+\.s]]" "-x" "ir" "{{.*}}[[WRAPPERBC]]" // CHK-COMMANDS-ST: clang{{.*}}" "-cc1as" "-triple" "powerpc64le-unknown-linux" "-filetype" "obj" {{.*}}"-o" " -// CHK-COMMANDS-ST-SAME: [[HOSTOBJ:[^\\/]+\.o]]" "{{.*}}[[HOSTASM]]" -// CHK-COMMANDS-ST: ld{{(\.exe)?}}" {{.*}}"-o" " -// CHK-COMMANDS-ST-SAME: [[HOSTBIN:[^\\/]+\.out]]" {{.*}}"-lomptarget" {{.*}}"-T" " -// CHK-COMMANDS-ST-SAME: [[HOSTLK:[^\\/]+\.lk]]" +// CHK-COMMANDS-ST-SAME: [[WRAPPEROBJ:[^\\/]+\.o]]" "{{.*}}[[WRAPPERASM]]" +// +// Link host binary. +// +// CHK-COMMANDS: ld{{(\.exe)?}}" {{.*}}"-o" " +// CHK-COMMANDS-SAME: [[HOSTBIN:[^\\/]+\.out]]" {{.*}}omptargetbegin.o" {{.*}}"{{.*}}[[HOSTOBJ]]" "{{.*}}[[WRAPPEROBJ]]" {{.*}}"-lomptarget" {{.*}}omptargetend.o" +// CHK-COMMANDS-ST: ld{{(\.exe)?}}" {{.*}}"-o" " +// CHK-COMMANDS-ST-SAME: [[HOSTBIN:[^\\/]+\.out]]" {{.*}}omptargetbegin.o" {{.*}}"{{.*}}[[HOSTOBJ]]" "{{.*}}[[WRAPPEROBJ]]" {{.*}}"-lomptarget" {{.*}}omptargetend.o" /// ########################################################################### @@ -399,20 +375,24 @@ // CHK-UBACTIONS: 3: compiler, {2}, ir, (host-openmp) // CHK-UBACTIONS: 4: backend, {3}, assembler, (host-openmp) // CHK-UBACTIONS: 5: assembler, {4}, object, (host-openmp) -// CHK-UBACTIONS: 6: linker, {0, 5}, image, (host-openmp) -// CHK-UBACTIONS: 7: input, "somelib", object, (device-openmp) -// CHK-UBACTIONS: 8: compiler, {2}, ir, (device-openmp) -// CHK-UBACTIONS: 9: offload, "host-openmp (powerpc64le-unknown-linux)" {3}, "device-openmp (powerpc64le-ibm-linux-gnu)" {8}, ir -// CHK-UBACTIONS: 10: backend, {9}, assembler, (device-openmp) -// CHK-UBACTIONS: 11: assembler, {10}, object, (device-openmp) -// CHK-UBACTIONS: 12: linker, {7, 11}, image, (device-openmp) +// CHK-UBACTIONS: 6: input, "somelib", object, (device-openmp) +// CHK-UBACTIONS: 7: compiler, {2}, ir, (device-openmp) +// CHK-UBACTIONS: 8: offload, "host-openmp (powerpc64le-unknown-linux)" {3}, "device-openmp (powerpc64le-ibm-linux-gnu)" {7}, ir +// CHK-UBACTIONS: 9: backend, {8}, assembler, (device-openmp) +// CHK-UBACTIONS: 10: assembler, {9}, object, (device-openmp) +// CHK-UBACTIONS: 11: linker, {6, 10}, image, (device-openmp) +// CHK-UBACTIONS: 12: offload, "device-openmp (powerpc64le-ibm-linux-gnu)" {11}, image // CHK-UBACTIONS: 13: input, "somelib", object, (device-openmp) // CHK-UBACTIONS: 14: compiler, {2}, ir, (device-openmp) // CHK-UBACTIONS: 15: offload, "host-openmp (powerpc64le-unknown-linux)" {3}, "device-openmp (x86_64-pc-linux-gnu)" {14}, ir // CHK-UBACTIONS: 16: backend, {15}, assembler, (device-openmp) // CHK-UBACTIONS: 17: assembler, {16}, object, (device-openmp) // CHK-UBACTIONS: 18: linker, {13, 17}, image, (device-openmp) -// CHK-UBACTIONS: 19: offload, "host-openmp (powerpc64le-unknown-linux)" {6}, "device-openmp (powerpc64le-ibm-linux-gnu)" {12}, "device-openmp (x86_64-pc-linux-gnu)" {18}, image +// CHK-UBACTIONS: 19: offload, "device-openmp (x86_64-pc-linux-gnu)" {18}, image +// CHK-UBACTIONS: 20: clang-offload-wrapper, {12, 19}, ir, (host-openmp) +// CHK-UBACTIONS: 21: backend, {20}, assembler, (host-openmp) +// CHK-UBACTIONS: 22: assembler, {21}, object, (host-openmp) +// CHK-UBACTIONS: 23: linker, {0, 5, 22}, image, (host-openmp) /// ########################################################################### @@ -515,6 +495,8 @@ // CHK-UBJOBS-SAME: [[T2PP:[^\\/]+\.i]]" "-unbundle" // CHK-UBJOBS: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-emit-llvm-bc" {{.*}}"-fopenmp" {{.*}}"-fopenmp-targets=powerpc64le-ibm-linux-gnu,x86_64-pc-linux-gnu" {{.*}}"-o" " // CHK-UBJOBS-SAME: [[HOSTBC:[^\\/]+\.bc]]" "-x" "cpp-output" "{{.*}}[[HOSTPP]]" +// CHK-UBJOBS: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-emit-obj" {{.*}}"-fopenmp" {{.*}}"-o" " +// CHK-UBJOBS-SAME: [[HOSTOBJ:[^\\/]+\.o]]" "-x" "ir" "{{.*}}[[HOSTBC]]" // CHK-UBJOBS-ST: clang-offload-bundler{{.*}}" "-type=i" "-targets=host-powerpc64le-unknown-linux,openmp-powerpc64le-ibm-linux-gnu,openmp-x86_64-pc-linux-gnu" "-inputs= // CHK-UBJOBS-ST-SAME: [[INPUT:[^\\/]+\.i]]" "-outputs= // CHK-UBJOBS-ST-SAME: [[HOSTPP:[^\\/,]+\.i]], @@ -522,6 +504,10 @@ // CHK-UBJOBS-ST-SAME: [[T2PP:[^\\/,]+\.i]]" "-unbundle" // CHK-UBJOBS-ST: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-emit-llvm-bc" {{.*}}"-fopenmp" {{.*}}"-fopenmp-targets=powerpc64le-ibm-linux-gnu,x86_64-pc-linux-gnu" {{.*}}"-o" " // CHK-UBJOBS-ST-SAME: [[HOSTBC:[^\\/]+\.bc]]" "-x" "cpp-output" "{{.*}}[[HOSTPP]]" +// CHK-UBJOBS-ST: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-S" {{.*}}"-fopenmp" {{.*}}"-o" " +// CHK-UBJOBS-ST-SAME: [[HOSTASM:[^\\/]+\.s]]" "-x" "ir" "{{.*}}[[HOSTBC]]" +// CHK-UBJOBS-ST: clang{{.*}}" "-cc1as" "-triple" "powerpc64le-unknown-linux" "-filetype" "obj" {{.*}}"-o" " +// CHK-UBJOBS-ST-SAME: [[HOSTOBJ:[^\\/]+\.o]]" "{{.*}}[[HOSTASM]]" // Create target 1 object. // CHK-UBJOBS: clang{{.*}}" "-cc1" "-triple" "powerpc64le-ibm-linux-gnu" "-aux-triple" "powerpc64le-unknown-linux" {{.*}}"-emit-obj" {{.*}}"-fopenmp" {{.*}}"-fopenmp-is-device" "-fopenmp-host-ir-file-path" "{{.*}}[[HOSTBC]]" {{.*}}"-o" " @@ -551,19 +537,23 @@ // CHK-UBJOBS-ST: ld{{(\.exe)?}}" {{.*}}"-o" " // CHK-UBJOBS-ST-SAME: [[T2BIN:[^\\/]+\.out-openmp-x86_64-pc-linux-gnu]]" {{.*}}"{{.*}}[[T2OBJ]]" -// Create binary. +// Create wrapper BC file and wrapper object. +// CHK-UBJOBS: clang-offload-wrapper{{(\.exe)?}}" "-target" "powerpc64le-unknown-linux" "-o" " +// CHK-UBJOBS-SAME: [[WRAPPERBC:[^\\/]+\.bc]]" "{{.*}}[[T1BIN]]" "{{.*}}[[T2BIN]]" // CHK-UBJOBS: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-emit-obj" {{.*}}"-fopenmp" {{.*}}"-o" " -// CHK-UBJOBS-SAME: [[HOSTOBJ:[^\\/]+\.o]]" "-x" "ir" "{{.*}}[[HOSTBC]]" -// CHK-UBJOBS: ld{{(\.exe)?}}" {{.*}}"-o" " -// CHK-UBJOBS-SAME: [[HOSTBIN:[^\\/]+\.out]]" {{.*}}"{{.*}}[[HOSTOBJ]]" {{.*}}"-T" " -// CHK-UBJOBS-SAME: [[LKS:[^\\/]+\.lk]]" +// CHK-UBJOBS-SAME: [[WRAPPEROBJ:[^\\/]+\.o]]" "-x" "ir" "{{.*}}[[WRAPPERBC]]" +// CHK-UBJOBS-ST: clang-offload-wrapper{{(\.exe)?}}" "-target" "powerpc64le-unknown-linux" "-o" " +// CHK-UBJOBS-ST-SAME: [[WRAPPERBC:[^\\/]+\.bc]]" "{{.*}}[[T1BIN]]" "{{.*}}[[T2BIN]]" // CHK-UBJOBS-ST: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" {{.*}}"-S" {{.*}}"-fopenmp" {{.*}}"-o" " -// CHK-UBJOBS-ST-SAME: [[HOSTASM:[^\\/]+\.s]]" "-x" "ir" "{{.*}}[[HOSTBC]]" +// CHK-UBJOBS-ST-SAME: [[WRAPPERASM:[^\\/]+\.s]]" "-x" "ir" "{{.*}}[[WRAPPERBC]]" // CHK-UBJOBS-ST: clang{{.*}}" "-cc1as" "-triple" "powerpc64le-unknown-linux" "-filetype" "obj" {{.*}}"-o" " -// CHK-UBJOBS-ST-SAME: [[HOSTOBJ:[^\\/]+\.o]]" "{{.*}}[[HOSTASM]]" +// CHK-UBJOBS-ST-SAME: [[WRAPPEROBJ:[^\\/]+\.o]]" "{{.*}}[[WRAPPERASM]]" + +// Create binary. +// CHK-UBJOBS: ld{{(\.exe)?}}" {{.*}}"-o" " +// CHK-UBJOBS-SAME: [[HOSTBIN:[^\\/]+\.out]]" {{.*}}omptargetbegin.o" {{.*}}"{{.*}}[[HOSTOBJ]]" "{{.*}}[[WRAPPEROBJ]]" {{.*}}omptargetend.o" // CHK-UBJOBS-ST: ld{{(\.exe)?}}" {{.*}}"-o" " -// CHK-UBJOBS-ST-SAME: [[HOSTBIN:[^\\/]+\.out]]" {{.*}}"{{.*}}[[HOSTOBJ]]" {{.*}}"-T" " -// CHK-UBJOBS-ST-SAME: [[LKS:[^\\/]+\.lk]]" +// CHK-UBJOBS-ST-SAME: [[HOSTBIN:[^\\/]+\.out]]" {{.*}}omptargetbegin.o" {{.*}}"{{.*}}[[HOSTOBJ]]" "{{.*}}[[WRAPPEROBJ]]" {{.*}}omptargetend.o" // Unbundle object file. // CHK-UBJOBS2: clang-offload-bundler{{.*}}" "-type=o" "-targets=host-powerpc64le-unknown-linux,openmp-powerpc64le-ibm-linux-gnu,openmp-x86_64-pc-linux-gnu" "-inputs= @@ -575,9 +565,12 @@ // CHK-UBJOBS2-SAME: [[T1BIN:[^\\/]+\.out]]" {{.*}}"{{.*}}[[T1OBJ]]" // CHK-UBJOBS2: ld{{(\.exe)?}}" {{.*}}"-o" " // CHK-UBJOBS2-SAME: [[T2BIN:[^\\/]+\.out]]" {{.*}}"{{.*}}[[T2OBJ]]" +// CHK-UBJOBS2: clang-offload-wrapper{{(\.exe)?}}" "-target" "powerpc64le-unknown-linux" "-o" " +// CHK-UBJOBS2-SAME: [[WRAPPERBC:[^\\/]+\.bc]]" "{{.*}}[[T1BIN]]" "{{.*}}[[T2BIN]]" +// CHK-UBJOBS2: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" "-emit-obj" {{.*}}"-fopenmp" {{.*}}"-o" " +// CHK-UBJOBS2-SAME: [[WRAPPEROBJ:[^\\/]+\.o]]" "-x" "ir" "{{.*}}[[WRAPPERBC]]" // CHK-UBJOBS2: ld{{(\.exe)?}}" {{.*}}"-o" " -// CHK-UBJOBS2-SAME: [[HOSTBIN:[^\\/]+\.out]]" {{.*}}"{{.*}}[[HOSTOBJ]]" {{.*}}"-T" " -// CHK-UBJOBS2-SAME: [[LKS:[^\\/]+\.lk]]" +// CHK-UBJOBS2-SAME: [[HOSTBIN:[^\\/]+\.out]]" {{.*}}omptargetbegin.o" {{.*}}"{{.*}}[[HOSTOBJ]]" "{{.*}}[[WRAPPEROBJ]]" {{.*}}omptargetend.o" // CHK-UBJOBS2-ST-NOT: clang-offload-bundler{{.*}}in.so // CHK-UBJOBS2-ST: clang-offload-bundler{{.*}}" "-type=o" "-targets=host-powerpc64le-unknown-linux,openmp-powerpc64le-ibm-linux-gnu,openmp-x86_64-pc-linux-gnu" "-inputs= // CHK-UBJOBS2-ST-SAME: [[INPUT:[^\\/]+\.o]]" "-outputs= @@ -589,9 +582,14 @@ // CHK-UBJOBS2-ST-SAME: [[T1BIN:[^\\/]+\.out-openmp-powerpc64le-ibm-linux-gnu]]" {{.*}}"{{.*}}[[T1OBJ]]" // CHK-UBJOBS2-ST: ld{{(\.exe)?}}" {{.*}}"-o" " // CHK-UBJOBS2-ST-SAME: [[T2BIN:[^\\/]+\.out-openmp-x86_64-pc-linux-gnu]]" {{.*}}"{{.*}}[[T2OBJ]]" +// CHK-UBJOBS2-ST: clang-offload-wrapper{{(\.exe)?}}" "-target" "powerpc64le-unknown-linux" "-o" " +// CHK-UBJOBS2-ST-SAME: [[WRAPPERBC:[^\\/]+\.bc]]" "{{.*}}[[T1BIN]]" "{{.*}}[[T2BIN]]" +// CHK-UBJOBS2-ST: clang{{.*}}" "-cc1" "-triple" "powerpc64le-unknown-linux" "-S" {{.*}}"-fopenmp" {{.*}}"-o" " +// CHK-UBJOBS2-ST-SAME: [[WRAPPERASM:[^\\/]+\.s]]" "-x" "ir" "{{.*}}[[WRAPPERBC]]" +// CHK-UBJOBS2-ST: clang{{.*}}" "-cc1as" "-triple" "powerpc64le-unknown-linux" "-filetype" "obj" {{.*}}"-o" " +// CHK-UBJOBS2-ST-SAME: [[WRAPPEROBJ:[^\\/]+\.o]]" "{{.*}}[[WRAPPERASM]]" // CHK-UBJOBS2-ST: ld{{(\.exe)?}}" {{.*}}"-o" " -// CHK-UBJOBS2-ST-SAME: [[HOSTBIN:[^\\/]+\.out]]" {{.*}}"{{.*}}[[HOSTOBJ]]" {{.*}}"-T" " -// CHK-UBJOBS2-ST-SAME: [[LKS:[^\\/]+\.lk]]" +// CHK-UBJOBS2-ST-SAME: [[HOSTBIN:[^\\/]+\.out]]" {{.*}}omptargetbegin.o" {{.*}}"{{.*}}[[HOSTOBJ]]" "{{.*}}[[WRAPPEROBJ]]" {{.*}}omptargetend.o" /// ########################################################################### Index: clang/test/OpenMP/openmp_offload_registration.cpp =================================================================== --- clang/test/OpenMP/openmp_offload_registration.cpp +++ clang/test/OpenMP/openmp_offload_registration.cpp @@ -8,25 +8,9 @@ } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } - -// Comdat key for the offload registration code. Should have sorted offload -// target triples encoded into the name. -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+\.powerpc64le-ibm-linux-gnu\.x86_64-pc-linux-gnu+]] = comdat any - -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEV1BEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEV1END:@.+]] = extern_weak constant i8 -// CHECK: [[DEV2BEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEV2END:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [2 x [[DEVTY]]] [{{.+}} { i8* [[DEV1BEGIN]], i8* [[DEV1END]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, {{.+}} { i8* [[DEV2BEGIN]], i8* [[DEV2END]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 2, [[DEVTY]]* getelementptr inbounds ([2 x [[DEVTY]]], [2 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] // Check presence of foo() and the outlined target region // CHECK: define void [[FOO:@.+]]() @@ -37,17 +21,3 @@ // CHECK: define internal void @.omp_offloading.requires_reg() // CHECK: call void @__tgt_register_requires(i64 1) // CHECK: ret void - -// CHECK: define internal void @[[UNREGFN:.+]](i8* %0) -// CHECK-SAME: comdat($[[REGFN]]) { -// CHECK: call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]]) -// CHECK: ret void -// CHECK: declare i32 @__tgt_unregister_lib([[DSCTY]]*) - -// CHECK: define linkonce hidden void @[[REGFN]]() -// CHECK-SAME: comdat { -// CHECK: call i32 @__tgt_register_lib([[DSCTY]]* [[DESC]]) -// CHECK: call i32 @__cxa_atexit(void (i8*)* @[[UNREGFN]], i8* bitcast ([[DSCTY]]* [[DESC]] to i8*), -// CHECK: ret void -// CHECK: declare i32 @__tgt_register_lib([[DSCTY]]*) - Index: clang/test/OpenMP/target_codegen.cpp =================================================================== --- clang/test/OpenMP/target_codegen.cpp +++ clang/test/OpenMP/target_codegen.cpp @@ -42,13 +42,9 @@ // CHECK-DAG: [[S1:%.+]] = type { double } // CHECK-DAG: [[S2:%.+]] = type { i32, i32, i32 } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // We have 9 target regions, but only 8 that actually will generate offloading // code and have mapped arguments, and only 6 have all-constant map sizes. @@ -87,17 +83,8 @@ // TCHECK: @{{.+}} = weak constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_codegen_registration.cpp =================================================================== --- clang/test/OpenMP/target_codegen_registration.cpp +++ clang/test/OpenMP/target_codegen_registration.cpp @@ -52,13 +52,9 @@ // CHECK-DAG: [[ST1:%.+]] = type { [228 x i32] } // CHECK-DAG: [[ST2:%.+]] = type { [1128 x i32] } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[A1:@.+]] = internal global [[SA]] // CHECK-DAG: [[A2:@.+]] = global [[SA]] // CHECK-DAG: [[B1:@.+]] = global [[SB]] @@ -172,20 +168,12 @@ // TCHECK-DAG: [[NAMEPTR12:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME12:.+]]\00" // TCHECK-DAG: @.omp_offloading.entry.[[NAME12]] = weak constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR12]], i32 0, i32 0), i[[SZ]] 0, i32 0, i32 0 }, section ".omp_offloading.entries", align 1 -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // We have 4 initializers, one for the 500 priority, another one for 501, or more for the default priority, and the last one for the offloading registration function. -// CHECK: @llvm.global_ctors = appending global [5 x { i32, void ()*, i8* }] [ +// CHECK: @llvm.global_ctors = appending global [4 x { i32, void ()*, i8* }] [ // CHECK-SAME: { i32, void ()*, i8* } { i32 500, void ()* [[P500:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 501, void ()* [[P501:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 65535, void ()* [[PMAX:@[^,]+]], i8* null }, -// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, -// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] +// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null } // CHECK-NTARGET: @llvm.global_ctors = appending global [3 x { i32, void ()*, i8* }] [ @@ -356,12 +344,8 @@ // CHECK-NTARGET-NOT: __tgt_target // CHECK-NTARGET-NOT: __tgt_register_requires -// CHECK-NTARGET-NOT: __tgt_register_lib -// CHECK-NTARGET-NOT: __tgt_unregister_lib // TCHECK-NOT: __tgt_target -// TCHECK-NOT: __tgt_register_lib -// TCHECK-NOT: __tgt_unregister_lib // We have 2 initializers with priority 500 //CHECK: define internal void [[P500]]( @@ -387,25 +371,6 @@ //CHECK-NOT: call void @{{.+}}() //CHECK: ret void -// Check registration and unregistration - -//CHECK: define internal void @.omp_offloading.requires_reg() -//CHECK: call void @__tgt_register_requires(i64 1) -//CHECK: ret void - -//CHECK: define internal void @[[UNREGFN:.+]](i8* %0) -//CHECK-SAME: comdat($[[REGFN]]) { -//CHECK: call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]]) -//CHECK: ret void -//CHECK: declare i32 @__tgt_unregister_lib([[DSCTY]]*) - -//CHECK: define linkonce hidden void @[[REGFN]]() -//CHECK-SAME: comdat { -//CHECK: call i32 @__tgt_register_lib([[DSCTY]]* [[DESC]]) -//CHECK: call i32 @__cxa_atexit(void (i8*)* @[[UNREGFN]], i8* bitcast ([[DSCTY]]* [[DESC]] to i8*), -//CHECK: ret void -//CHECK: declare i32 @__tgt_register_lib([[DSCTY]]*) - static __attribute__((init_priority(500))) SA a1; SA a2; SB __attribute__((init_priority(500))) b1; @@ -438,31 +403,31 @@ // Check metadata is properly generated: // CHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 217, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 267, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 283, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 289, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 300, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 306, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 433, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 306, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 300, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 205, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 255, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 271, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 277, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 288, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 294, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 398, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 294, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 288, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} // TCHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 217, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 267, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 283, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 289, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 300, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 306, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 433, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 306, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 300, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 205, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 255, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 271, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 277, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 288, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 294, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 398, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 294, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 288, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} #endif Index: clang/test/OpenMP/target_depend_codegen.cpp =================================================================== --- clang/test/OpenMP/target_depend_codegen.cpp +++ clang/test/OpenMP/target_depend_codegen.cpp @@ -40,13 +40,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[SIZET:@.+]] = private unnamed_addr constant [2 x i64] [i64 0, i64 4] // CHECK-DAG: [[MAPT:@.+]] = private unnamed_addr constant [2 x i64] [i64 544, i64 800] // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -55,17 +51,8 @@ // TCHECK: @{{.+}} = {{.*}}constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_parallel_codegen.cpp =================================================================== --- clang/test/OpenMP/target_parallel_codegen.cpp +++ clang/test/OpenMP/target_parallel_codegen.cpp @@ -45,13 +45,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[S1:%.+]] = type { double } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // We have 8 target regions, but only 6 that actually will generate offloading // code and have mapped arguments, and only 4 have all-constant map sizes. @@ -82,17 +78,8 @@ // TCHECK: @{{.+}} = weak constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_parallel_codegen_registration.cpp =================================================================== --- clang/test/OpenMP/target_parallel_codegen_registration.cpp +++ clang/test/OpenMP/target_parallel_codegen_registration.cpp @@ -52,13 +52,9 @@ // CHECK-DAG: [[ST1:%.+]] = type { [228 x i32] } // CHECK-DAG: [[ST2:%.+]] = type { [1128 x i32] } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[A1:@.+]] = internal global [[SA]] // CHECK-DAG: [[A2:@.+]] = global [[SA]] // CHECK-DAG: [[B1:@.+]] = global [[SB]] @@ -172,19 +168,11 @@ // TCHECK-DAG: [[NAMEPTR12:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME12:.+]]\00" // TCHECK-DAG: [[ENTRY12:@.+]] = weak constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR12]], i32 0, i32 0), i[[SZ]] 0, i32 0, i32 0 }, section ".omp_offloading.entries", align 1 -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // We have 4 initializers, one for the 500 priority, another one for 501, or more for the default priority, and the last one for the offloading registration function. -// CHECK: @llvm.global_ctors = appending global [5 x { i32, void ()*, i8* }] [ +// CHECK: @llvm.global_ctors = appending global [4 x { i32, void ()*, i8* }] [ // CHECK-SAME: { i32, void ()*, i8* } { i32 500, void ()* [[P500:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 501, void ()* [[P501:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 65535, void ()* [[PMAX:@[^,]+]], i8* null }, -// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] // CHECK-NTARGET: @llvm.global_ctors = appending global [3 x { i32, void ()*, i8* }] [ @@ -354,12 +342,8 @@ //TCHECK-DAG: define weak void @[[NAME12]]( // CHECK-NTARGET-NOT: __tgt_target -// CHECK-NTARGET-NOT: __tgt_register_lib -// CHECK-NTARGET-NOT: __tgt_unregister_lib // TCHECK-NOT: __tgt_target -// TCHECK-NOT: __tgt_register_lib -// TCHECK-NOT: __tgt_unregister_lib // We have 2 initializers with priority 500 //CHECK: define internal void [[P500]]( @@ -385,25 +369,6 @@ //CHECK-NOT: call void @{{.+}}() //CHECK: ret void -// Check registration and unregistration - -//CHECK: define internal void @.omp_offloading.requires_reg() -//CHECK: call void @__tgt_register_requires(i64 1) -//CHECK: ret void - -//CHECK: define internal void @[[UNREGFN:.+]](i8* %0) -//CHECK-SAME: comdat($[[REGFN]]) { -//CHECK: call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]]) -//CHECK: ret void -//CHECK: declare i32 @__tgt_unregister_lib([[DSCTY]]*) - -//CHECK: define linkonce hidden void @[[REGFN]]() -//CHECK-SAME: comdat { -//CHECK: call i32 @__tgt_register_lib([[DSCTY]]* [[DESC]]) -//CHECK: call i32 @__cxa_atexit(void (i8*)* @[[UNREGFN]], i8* bitcast ([[DSCTY]]* [[DESC]] to i8*), -//CHECK: ret void -//CHECK: declare i32 @__tgt_register_lib([[DSCTY]]*) - static __attribute__((init_priority(500))) SA a1; SA a2; SB __attribute__((init_priority(500))) b1; @@ -436,31 +401,31 @@ // Check metadata is properly generated: // CHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 266, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 282, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 288, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 299, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 431, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 311, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 311, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 299, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 241, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 254, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 270, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 276, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 287, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 396, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 299, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 299, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 287, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 229, i32 {{[0-9]+}}} // TCHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 266, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 282, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 288, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 299, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 431, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 311, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 311, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 299, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 241, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 254, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 270, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 276, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 287, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 396, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 299, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 299, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 287, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 229, i32 {{[0-9]+}}} #endif Index: clang/test/OpenMP/target_parallel_depend_codegen.cpp =================================================================== --- clang/test/OpenMP/target_parallel_depend_codegen.cpp +++ clang/test/OpenMP/target_parallel_depend_codegen.cpp @@ -40,13 +40,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[SIZET:@.+]] = private unnamed_addr constant [2 x i64] [i64 0, i64 4] // CHECK-DAG: [[MAPT:@.+]] = private unnamed_addr constant [2 x i64] [i64 544, i64 800] // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -55,17 +51,8 @@ // TCHECK: @{{.+}} = {{.*}}constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_parallel_for_codegen.cpp =================================================================== --- clang/test/OpenMP/target_parallel_for_codegen.cpp +++ clang/test/OpenMP/target_parallel_for_codegen.cpp @@ -45,13 +45,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[S1:%.+]] = type { double } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // We have 8 target regions, but only 7 that actually will generate offloading // code, only 6 will have mapped arguments, and only 4 have all-constant map // sizes. @@ -83,17 +79,8 @@ // TCHECK: @{{.+}} = weak constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_parallel_for_codegen_registration.cpp =================================================================== --- clang/test/OpenMP/target_parallel_for_codegen_registration.cpp +++ clang/test/OpenMP/target_parallel_for_codegen_registration.cpp @@ -52,13 +52,9 @@ // CHECK-DAG: [[ST1:%.+]] = type { [228 x i32] } // CHECK-DAG: [[ST2:%.+]] = type { [1128 x i32] } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[A1:@.+]] = internal global [[SA]] // CHECK-DAG: [[A2:@.+]] = global [[SA]] // CHECK-DAG: [[B1:@.+]] = global [[SB]] @@ -172,19 +168,11 @@ // TCHECK-DAG: [[NAMEPTR12:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME12:.+]]\00" // TCHECK-DAG: [[ENTRY12:@.+]] = weak constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR12]], i32 0, i32 0), i[[SZ]] 0, i32 0, i32 0 }, section ".omp_offloading.entries", align 1 -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // We have 4 initializers, one for the 500 priority, another one for 501, or more for the default priority, and the last one for the offloading registration function. -// CHECK: @llvm.global_ctors = appending global [5 x { i32, void ()*, i8* }] [ +// CHECK: @llvm.global_ctors = appending global [4 x { i32, void ()*, i8* }] [ // CHECK-SAME: { i32, void ()*, i8* } { i32 500, void ()* [[P500:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 501, void ()* [[P501:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 65535, void ()* [[PMAX:@[^,]+]], i8* null }, -// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] // CHECK-NTARGET: @llvm.global_ctors = appending global [3 x { i32, void ()*, i8* }] [ @@ -363,12 +351,8 @@ //TCHECK-DAG: define weak void @[[NAME12]]( // CHECK-NTARGET-NOT: __tgt_target -// CHECK-NTARGET-NOT: __tgt_register_lib -// CHECK-NTARGET-NOT: __tgt_unregister_lib // TCHECK-NOT: __tgt_target -// TCHECK-NOT: __tgt_register_lib -// TCHECK-NOT: __tgt_unregister_lib // We have 2 initializers with priority 500 //CHECK: define internal void [[P500]]( @@ -394,25 +378,6 @@ //CHECK-NOT: call void @{{.+}}() //CHECK: ret void -// Check registration and unregistration - -//CHECK: define internal void @.omp_offloading.requires_reg() -//CHECK: call void @__tgt_register_requires(i64 1) -//CHECK: ret void - -//CHECK: define internal void @[[UNREGFN:.+]](i8* %0) -//CHECK-SAME: comdat($[[REGFN]]) { -//CHECK: call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]]) -//CHECK: ret void -//CHECK: declare i32 @__tgt_unregister_lib([[DSCTY]]*) - -//CHECK: define linkonce hidden void @[[REGFN]]() -//CHECK-SAME: comdat { -//CHECK: call i32 @__tgt_register_lib([[DSCTY]]* [[DESC]]) -//CHECK: call i32 @__cxa_atexit(void (i8*)* @[[UNREGFN]], i8* bitcast ([[DSCTY]]* [[DESC]] to i8*), -//CHECK: ret void -//CHECK: declare i32 @__tgt_register_lib([[DSCTY]]*) - static __attribute__((init_priority(500))) SA a1; SA a2; SB __attribute__((init_priority(500))) b1; @@ -446,31 +411,31 @@ // Check metadata is properly generated: // CHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 268, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 286, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 293, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 440, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 319, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 319, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 256, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 274, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 281, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 405, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 307, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 307, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} // TCHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 268, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 286, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 293, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 440, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 319, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 319, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 256, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 274, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 281, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 405, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 307, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 307, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} #endif Index: clang/test/OpenMP/target_parallel_for_depend_codegen.cpp =================================================================== --- clang/test/OpenMP/target_parallel_for_depend_codegen.cpp +++ clang/test/OpenMP/target_parallel_for_depend_codegen.cpp @@ -40,13 +40,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[SIZET:@.+]] = private unnamed_addr constant [2 x i64] [i64 0, i64 4] // CHECK-DAG: [[MAPT:@.+]] = private unnamed_addr constant [2 x i64] [i64 544, i64 800] // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -55,17 +51,8 @@ // TCHECK: @{{.+}} = {{.*}}constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_parallel_for_simd_codegen.cpp =================================================================== --- clang/test/OpenMP/target_parallel_for_simd_codegen.cpp +++ clang/test/OpenMP/target_parallel_for_simd_codegen.cpp @@ -44,13 +44,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[S1:%.+]] = type { double } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // We have 8 target regions, but only 7 that actually will generate offloading // code, only 6 will have mapped arguments, and only 4 have all-constant map // sizes. @@ -82,17 +78,8 @@ // TCHECK: @{{.+}} = weak constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_parallel_for_simd_codegen_registration.cpp =================================================================== --- clang/test/OpenMP/target_parallel_for_simd_codegen_registration.cpp +++ clang/test/OpenMP/target_parallel_for_simd_codegen_registration.cpp @@ -52,13 +52,9 @@ // CHECK-DAG: [[ST1:%.+]] = type { [228 x i32] } // CHECK-DAG: [[ST2:%.+]] = type { [1128 x i32] } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[A1:@.+]] = internal global [[SA]] // CHECK-DAG: [[A2:@.+]] = global [[SA]] // CHECK-DAG: [[B1:@.+]] = global [[SB]] @@ -172,19 +168,11 @@ // TCHECK-DAG: [[NAMEPTR12:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME12:.+]]\00" // TCHECK-DAG: [[ENTRY12:@.+]] = weak constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR12]], i32 0, i32 0), i[[SZ]] 0, i32 0, i32 0 }, section ".omp_offloading.entries", align 1 -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // We have 4 initializers, one for the 500 priority, another one for 501, or more for the default priority, and the last one for the offloading registration function. -// CHECK: @llvm.global_ctors = appending global [5 x { i32, void ()*, i8* }] [ +// CHECK: @llvm.global_ctors = appending global [4 x { i32, void ()*, i8* }] [ // CHECK-SAME: { i32, void ()*, i8* } { i32 500, void ()* [[P500:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 501, void ()* [[P501:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 65535, void ()* [[PMAX:@[^,]+]], i8* null }, -// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] // CHECK-NTARGET: @llvm.global_ctors = appending global [3 x { i32, void ()*, i8* }] [ @@ -363,12 +351,8 @@ //TCHECK-DAG: define weak void @[[NAME12]]( // CHECK-NTARGET-NOT: __tgt_target -// CHECK-NTARGET-NOT: __tgt_register_lib -// CHECK-NTARGET-NOT: __tgt_unregister_lib // TCHECK-NOT: __tgt_target -// TCHECK-NOT: __tgt_register_lib -// TCHECK-NOT: __tgt_unregister_lib // We have 2 initializers with priority 500 //CHECK: define internal void [[P500]]( @@ -394,25 +378,6 @@ //CHECK-NOT: call void @{{.+}}() //CHECK: ret void -// Check registration and unregistration - -//CHECK: define internal void @.omp_offloading.requires_reg() -//CHECK: call void @__tgt_register_requires(i64 1) -//CHECK: ret void - -//CHECK: define internal void @[[UNREGFN:.+]](i8* %0) -//CHECK-SAME: comdat($[[REGFN]]) { -//CHECK: call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]]) -//CHECK: ret void -//CHECK: declare i32 @__tgt_unregister_lib([[DSCTY]]*) - -//CHECK: define linkonce hidden void @[[REGFN]]() -//CHECK-SAME: comdat { -//CHECK: call i32 @__tgt_register_lib([[DSCTY]]* [[DESC]]) -//CHECK: call i32 @__cxa_atexit(void (i8*)* @[[UNREGFN]], i8* bitcast ([[DSCTY]]* [[DESC]] to i8*), -//CHECK: ret void -//CHECK: declare i32 @__tgt_register_lib([[DSCTY]]*) - static __attribute__((init_priority(500))) SA a1; SA a2; SB __attribute__((init_priority(500))) b1; @@ -446,31 +411,31 @@ // Check metadata is properly generated: // CHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 268, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 286, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 293, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 440, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 319, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 319, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 256, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 274, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 281, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 405, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 307, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 307, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} // TCHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 268, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 286, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 293, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 440, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 319, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 319, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 256, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 274, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 281, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 405, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 307, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 307, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} #endif Index: clang/test/OpenMP/target_parallel_for_simd_depend_codegen.cpp =================================================================== --- clang/test/OpenMP/target_parallel_for_simd_depend_codegen.cpp +++ clang/test/OpenMP/target_parallel_for_simd_depend_codegen.cpp @@ -40,13 +40,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[SIZET:@.+]] = private unnamed_addr constant [2 x i64] [i64 0, i64 4] // CHECK-DAG: [[MAPT:@.+]] = private unnamed_addr constant [2 x i64] [i64 544, i64 800] // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -55,17 +51,8 @@ // TCHECK: @{{.+}} = {{.*}}constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_parallel_if_codegen.cpp =================================================================== --- clang/test/OpenMP/target_parallel_if_codegen.cpp +++ clang/test/OpenMP/target_parallel_if_codegen.cpp @@ -44,13 +44,9 @@ // CHECK-DAG: [[S1:%.+]] = type { double } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // We have 6 target regions // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -67,17 +63,8 @@ // TCHECK: @{{.+}} = weak constant [[ENTTY]] // TCHECK: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template tx ftemplate(int n) { Index: clang/test/OpenMP/target_parallel_num_threads_codegen.cpp =================================================================== --- clang/test/OpenMP/target_parallel_num_threads_codegen.cpp +++ clang/test/OpenMP/target_parallel_num_threads_codegen.cpp @@ -44,13 +44,9 @@ // CHECK-DAG: [[S1:%.+]] = type { double } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // We have 6 target regions // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -67,17 +63,8 @@ // TCHECK: @{{.+}} = weak constant [[ENTTY]] // TCHECK: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template tx ftemplate(int n) { Index: clang/test/OpenMP/target_simd_codegen.cpp =================================================================== --- clang/test/OpenMP/target_simd_codegen.cpp +++ clang/test/OpenMP/target_simd_codegen.cpp @@ -41,13 +41,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[S1:%.+]] = type { double } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // We have 8 target regions, but only 7 that actually will generate offloading // code, only 6 will have mapped arguments, and only 4 have all-constant map // sizes. @@ -79,17 +75,8 @@ // TCHECK: @{{.+}} = weak constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_simd_codegen_registration.cpp =================================================================== --- clang/test/OpenMP/target_simd_codegen_registration.cpp +++ clang/test/OpenMP/target_simd_codegen_registration.cpp @@ -52,13 +52,9 @@ // CHECK-DAG: [[ST1:%.+]] = type { [228 x i32] } // CHECK-DAG: [[ST2:%.+]] = type { [1128 x i32] } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[A1:@.+]] = internal global [[SA]] // CHECK-DAG: [[A2:@.+]] = global [[SA]] // CHECK-DAG: [[B1:@.+]] = global [[SB]] @@ -172,19 +168,11 @@ // TCHECK-DAG: [[NAMEPTR12:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME12:.+]]\00" // TCHECK-DAG: [[ENTRY12:@.+]] = weak constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR12]], i32 0, i32 0), i[[SZ]] 0, i32 0, i32 0 }, section ".omp_offloading.entries", align 1 -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // We have 4 initializers, one for the 500 priority, another one for 501, or more for the default priority, and the last one for the offloading registration function. -// CHECK: @llvm.global_ctors = appending global [5 x { i32, void ()*, i8* }] [ +// CHECK: @llvm.global_ctors = appending global [4 x { i32, void ()*, i8* }] [ // CHECK-SAME: { i32, void ()*, i8* } { i32 500, void ()* [[P500:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 501, void ()* [[P501:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 65535, void ()* [[PMAX:@[^,]+]], i8* null }, -// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] // CHECK-NTARGET: @llvm.global_ctors = appending global [3 x { i32, void ()*, i8* }] [ @@ -363,12 +351,8 @@ //TCHECK-DAG: define weak void @[[NAME12]]( // CHECK-NTARGET-NOT: __tgt_target -// CHECK-NTARGET-NOT: __tgt_register_lib -// CHECK-NTARGET-NOT: __tgt_unregister_lib // TCHECK-NOT: __tgt_target -// TCHECK-NOT: __tgt_register_lib -// TCHECK-NOT: __tgt_unregister_lib // We have 2 initializers with priority 500 //CHECK: define internal void [[P500]]( @@ -394,25 +378,6 @@ //CHECK-NOT: call void @{{.+}}() //CHECK: ret void -// Check registration and unregistration - -//CHECK: define internal void @.omp_offloading.requires_reg() -//CHECK: call void @__tgt_register_requires(i64 1) -//CHECK: ret void - -//CHECK: define internal void @[[UNREGFN:.+]](i8* %0) -//CHECK-SAME: comdat($[[REGFN]]) { -//CHECK: call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]]) -//CHECK: ret void -//CHECK: declare i32 @__tgt_unregister_lib([[DSCTY]]*) - -//CHECK: define linkonce hidden void @[[REGFN]]() -//CHECK-SAME: comdat { -//CHECK: call i32 @__tgt_register_lib([[DSCTY]]* [[DESC]]) -//CHECK: call i32 @__cxa_atexit(void (i8*)* @[[UNREGFN]], i8* bitcast ([[DSCTY]]* [[DESC]] to i8*), -//CHECK: ret void -//CHECK: declare i32 @__tgt_register_lib([[DSCTY]]*) - static __attribute__((init_priority(500))) SA a1; SA a2; SB __attribute__((init_priority(500))) b1; @@ -446,31 +411,31 @@ // Check metadata is properly generated: // CHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 268, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 286, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 293, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 440, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 319, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 319, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 256, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 274, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 281, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 405, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 307, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 307, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} // TCHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 268, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 286, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 293, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 440, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 319, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 319, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 256, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 274, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 281, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 405, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 307, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 307, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} #endif Index: clang/test/OpenMP/target_simd_depend_codegen.cpp =================================================================== --- clang/test/OpenMP/target_simd_depend_codegen.cpp +++ clang/test/OpenMP/target_simd_depend_codegen.cpp @@ -40,13 +40,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[SIZET:@.+]] = private unnamed_addr constant [2 x i64] [i64 0, i64 4] // CHECK-DAG: [[MAPT:@.+]] = private unnamed_addr constant [2 x i64] [i64 544, i64 800] // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -55,17 +51,8 @@ // TCHECK: @{{.+}} = {{.*}}constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_teams_codegen.cpp =================================================================== --- clang/test/OpenMP/target_teams_codegen.cpp +++ clang/test/OpenMP/target_teams_codegen.cpp @@ -45,13 +45,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[S1:%.+]] = type { double } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // We have 8 target regions, but only 6 that actually will generate offloading // code and have mapped arguments, and only 4 have all-constant map sizes. @@ -88,17 +84,8 @@ // TCHECK: @{{.+}} = weak constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_teams_codegen_registration.cpp =================================================================== --- clang/test/OpenMP/target_teams_codegen_registration.cpp +++ clang/test/OpenMP/target_teams_codegen_registration.cpp @@ -52,13 +52,9 @@ // CHECK-DAG: [[ST1:%.+]] = type { [228 x i32] } // CHECK-DAG: [[ST2:%.+]] = type { [1128 x i32] } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[A1:@.+]] = internal global [[SA]] // CHECK-DAG: [[A2:@.+]] = global [[SA]] // CHECK-DAG: [[B1:@.+]] = global [[SB]] @@ -172,19 +168,11 @@ // TCHECK-DAG: [[NAMEPTR12:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME12:.+]]\00" // TCHECK-DAG: [[ENTRY12:@.+]] = weak constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR12]], i32 0, i32 0), i[[SZ]] 0, i32 0, i32 0 }, section ".omp_offloading.entries", align 1 -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // We have 4 initializers, one for the 500 priority, another one for 501, or more for the default priority, and the last one for the offloading registration function. -// CHECK: @llvm.global_ctors = appending global [5 x { i32, void ()*, i8* }] [ +// CHECK: @llvm.global_ctors = appending global [4 x { i32, void ()*, i8* }] [ // CHECK-SAME: { i32, void ()*, i8* } { i32 500, void ()* [[P500:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 501, void ()* [[P501:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 65535, void ()* [[PMAX:@[^,]+]], i8* null }, -// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] // CHECK-NTARGET: @llvm.global_ctors = appending global [3 x { i32, void ()*, i8* }] [ @@ -354,12 +342,8 @@ //TCHECK-DAG: define weak void @[[NAME12]]( // CHECK-NTARGET-NOT: __tgt_target -// CHECK-NTARGET-NOT: __tgt_register_lib -// CHECK-NTARGET-NOT: __tgt_unregister_lib // TCHECK-NOT: __tgt_target -// TCHECK-NOT: __tgt_register_lib -// TCHECK-NOT: __tgt_unregister_lib // We have 2 initializers with priority 500 //CHECK: define internal void [[P500]]( @@ -385,25 +369,6 @@ //CHECK-NOT: call void @{{.+}}() //CHECK: ret void -// Check registration and unregistration - -//CHECK: define internal void @.omp_offloading.requires_reg() -//CHECK: call void @__tgt_register_requires(i64 1) -//CHECK: ret void - -//CHECK: define internal void @[[UNREGFN:.+]](i8* %0) -//CHECK-SAME: comdat($[[REGFN]]) { -//CHECK: call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]]) -//CHECK: ret void -//CHECK: declare i32 @__tgt_unregister_lib([[DSCTY]]*) - -//CHECK: define linkonce hidden void @[[REGFN]]() -//CHECK-SAME: comdat { -//CHECK: call i32 @__tgt_register_lib([[DSCTY]]* [[DESC]]) -//CHECK: call i32 @__cxa_atexit(void (i8*)* @[[UNREGFN]], i8* bitcast ([[DSCTY]]* [[DESC]] to i8*), -//CHECK: ret void -//CHECK: declare i32 @__tgt_register_lib([[DSCTY]]*) - static __attribute__((init_priority(500))) SA a1; SA a2; SB __attribute__((init_priority(500))) b1; @@ -436,31 +401,31 @@ // Check metadata is properly generated: // CHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 266, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 282, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 288, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 299, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 431, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 311, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 311, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 299, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 241, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 254, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 270, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 276, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 287, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 396, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 299, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 299, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 287, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 229, i32 {{[0-9]+}}} // TCHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 266, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 282, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 288, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 299, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 431, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 311, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 311, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 299, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 241, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 254, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 270, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 276, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 287, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 396, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 299, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 299, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 287, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 229, i32 {{[0-9]+}}} #endif Index: clang/test/OpenMP/target_teams_depend_codegen.cpp =================================================================== --- clang/test/OpenMP/target_teams_depend_codegen.cpp +++ clang/test/OpenMP/target_teams_depend_codegen.cpp @@ -40,13 +40,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[SIZET:@.+]] = private unnamed_addr constant [2 x i64] [i64 0, i64 4] // CHECK-DAG: [[MAPT:@.+]] = private unnamed_addr constant [2 x i64] [i64 544, i64 800] // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -55,17 +51,8 @@ // TCHECK: @{{.+}} = {{.*}}constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_teams_distribute_codegen.cpp =================================================================== --- clang/test/OpenMP/target_teams_distribute_codegen.cpp +++ clang/test/OpenMP/target_teams_distribute_codegen.cpp @@ -45,13 +45,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[S1:%.+]] = type { double } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // We have 8 target regions, but only 7 that actually will generate offloading // code, only 6 will have mapped arguments, and only 4 have all-constant map // sizes. @@ -85,17 +81,8 @@ // TCHECK: @{{.+}} = weak constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_teams_distribute_codegen_registration.cpp =================================================================== --- clang/test/OpenMP/target_teams_distribute_codegen_registration.cpp +++ clang/test/OpenMP/target_teams_distribute_codegen_registration.cpp @@ -52,13 +52,9 @@ // CHECK-DAG: [[ST1:%.+]] = type { [228 x i32] } // CHECK-DAG: [[ST2:%.+]] = type { [1128 x i32] } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[A1:@.+]] = internal global [[SA]] // CHECK-DAG: [[A2:@.+]] = global [[SA]] // CHECK-DAG: [[B1:@.+]] = global [[SB]] @@ -172,19 +168,11 @@ // TCHECK-DAG: [[NAMEPTR12:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME12:.+]]\00" // TCHECK-DAG: [[ENTRY12:@.+]] = weak constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR12]], i32 0, i32 0), i[[SZ]] 0, i32 0, i32 0 }, section ".omp_offloading.entries", align 1 -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // We have 4 initializers, one for the 500 priority, another one for 501, or more for the default priority, and the last one for the offloading registration function. -// CHECK: @llvm.global_ctors = appending global [5 x { i32, void ()*, i8* }] [ +// CHECK: @llvm.global_ctors = appending global [4 x { i32, void ()*, i8* }] [ // CHECK-SAME: { i32, void ()*, i8* } { i32 500, void ()* [[P500:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 501, void ()* [[P501:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 65535, void ()* [[PMAX:@[^,]+]], i8* null }, -// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] // CHECK-NTARGET: @llvm.global_ctors = appending global [3 x { i32, void ()*, i8* }] [ @@ -363,12 +351,8 @@ //TCHECK-DAG: define weak void @[[NAME12]]( // CHECK-NTARGET-NOT: __tgt_target -// CHECK-NTARGET-NOT: __tgt_register_lib -// CHECK-NTARGET-NOT: __tgt_unregister_lib // TCHECK-NOT: __tgt_target -// TCHECK-NOT: __tgt_register_lib -// TCHECK-NOT: __tgt_unregister_lib // We have 2 initializers with priority 500 //CHECK: define internal void [[P500]]( @@ -394,25 +378,6 @@ //CHECK-NOT: call void @{{.+}}() //CHECK: ret void -// Check registration and unregistration - -//CHECK: define internal void @.omp_offloading.requires_reg() -//CHECK: call void @__tgt_register_requires(i64 1) -//CHECK: ret void - -//CHECK: define internal void @[[UNREGFN:.+]](i8* %0) -//CHECK-SAME: comdat($[[REGFN]]) { -//CHECK: call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]]) -//CHECK: ret void -//CHECK: declare i32 @__tgt_unregister_lib([[DSCTY]]*) - -//CHECK: define linkonce hidden void @[[REGFN]]() -//CHECK-SAME: comdat { -//CHECK: call i32 @__tgt_register_lib([[DSCTY]]* [[DESC]]) -//CHECK: call i32 @__cxa_atexit(void (i8*)* @[[UNREGFN]], i8* bitcast ([[DSCTY]]* [[DESC]] to i8*), -//CHECK: ret void -//CHECK: declare i32 @__tgt_register_lib([[DSCTY]]*) - static __attribute__((init_priority(500))) SA a1; SA a2; SB __attribute__((init_priority(500))) b1; @@ -446,31 +411,31 @@ // Check metadata is properly generated: // CHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 268, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 286, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 293, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 440, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 319, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 319, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 256, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 274, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 281, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 405, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 307, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 307, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} // TCHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 268, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 286, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 293, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 440, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 319, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 319, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 256, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 274, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 281, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 405, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 307, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 307, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} #endif Index: clang/test/OpenMP/target_teams_distribute_depend_codegen.cpp =================================================================== --- clang/test/OpenMP/target_teams_distribute_depend_codegen.cpp +++ clang/test/OpenMP/target_teams_distribute_depend_codegen.cpp @@ -40,13 +40,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[SIZET:@.+]] = private unnamed_addr constant [2 x i64] [i64 0, i64 4] // CHECK-DAG: [[MAPT:@.+]] = private unnamed_addr constant [2 x i64] [i64 544, i64 800] // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -55,17 +51,8 @@ // TCHECK: @{{.+}} = {{.*}}constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_teams_distribute_parallel_for_depend_codegen.cpp =================================================================== --- clang/test/OpenMP/target_teams_distribute_parallel_for_depend_codegen.cpp +++ clang/test/OpenMP/target_teams_distribute_parallel_for_depend_codegen.cpp @@ -40,13 +40,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[SIZET:@.+]] = private unnamed_addr constant [2 x i64] [i64 0, i64 4] // CHECK-DAG: [[MAPT:@.+]] = private unnamed_addr constant [2 x i64] [i64 544, i64 800] // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -55,17 +51,8 @@ // TCHECK: @{{.+}} = {{.*}}constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_teams_distribute_parallel_for_simd_codegen_registration.cpp =================================================================== --- clang/test/OpenMP/target_teams_distribute_parallel_for_simd_codegen_registration.cpp +++ clang/test/OpenMP/target_teams_distribute_parallel_for_simd_codegen_registration.cpp @@ -52,13 +52,9 @@ // CHECK-DAG: [[ST1:%.+]] = type { [228 x i32] } // CHECK-DAG: [[ST2:%.+]] = type { [1128 x i32] } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[A1:@.+]] = internal global [[SA]] // CHECK-DAG: [[A2:@.+]] = global [[SA]] // CHECK-DAG: [[B1:@.+]] = global [[SB]] @@ -172,19 +168,11 @@ // TCHECK-DAG: [[NAMEPTR12:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME12:.+]]\00" // TCHECK-DAG: [[ENTRY12:@.+]] = weak constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR12]], i32 0, i32 0), i[[SZ]] 0, i32 0, i32 0 }, section ".omp_offloading.entries", align 1 -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // We have 4 initializers, one for the 500 priority, another one for 501, or more for the default priority, and the last one for the offloading registration function. -// CHECK: @llvm.global_ctors = appending global [5 x { i32, void ()*, i8* }] [ +// CHECK: @llvm.global_ctors = appending global [4 x { i32, void ()*, i8* }] [ // CHECK-SAME: { i32, void ()*, i8* } { i32 500, void ()* [[P500:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 501, void ()* [[P501:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 65535, void ()* [[PMAX:@[^,]+]], i8* null }, -// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] // CHECK-NTARGET: @llvm.global_ctors = appending global [3 x { i32, void ()*, i8* }] [ @@ -363,12 +351,8 @@ //TCHECK-DAG: define weak void @[[NAME12]]( // CHECK-NTARGET-NOT: __tgt_target -// CHECK-NTARGET-NOT: __tgt_register_lib -// CHECK-NTARGET-NOT: __tgt_unregister_lib // TCHECK-NOT: __tgt_target -// TCHECK-NOT: __tgt_register_lib -// TCHECK-NOT: __tgt_unregister_lib // We have 2 initializers with priority 500 //CHECK: define internal void [[P500]]( @@ -394,25 +378,6 @@ //CHECK-NOT: call void @{{.+}}() //CHECK: ret void -// Check registration and unregistration - -//CHECK: define internal void @.omp_offloading.requires_reg() -//CHECK: call void @__tgt_register_requires(i64 1) -//CHECK: ret void - -//CHECK: define internal void @[[UNREGFN:.+]](i8* %0) -//CHECK-SAME: comdat($[[REGFN]]) { -//CHECK: call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]]) -//CHECK: ret void -//CHECK: declare i32 @__tgt_unregister_lib([[DSCTY]]*) - -//CHECK: define linkonce hidden void @[[REGFN]]() -//CHECK-SAME: comdat { -//CHECK: call i32 @__tgt_register_lib([[DSCTY]]* [[DESC]]) -//CHECK: call i32 @__cxa_atexit(void (i8*)* @[[UNREGFN]], i8* bitcast ([[DSCTY]]* [[DESC]] to i8*), -//CHECK: ret void -//CHECK: declare i32 @__tgt_register_lib([[DSCTY]]*) - static __attribute__((init_priority(500))) SA a1; SA a2; SB __attribute__((init_priority(500))) b1; @@ -446,31 +411,31 @@ // Check metadata is properly generated: // CHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 268, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 286, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 293, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 440, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 319, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 319, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 256, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 274, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 281, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 405, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 307, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 307, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} // TCHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 268, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 286, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 293, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 440, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 319, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 319, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 256, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 274, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 281, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 405, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 307, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 307, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} #endif Index: clang/test/OpenMP/target_teams_distribute_parallel_for_simd_depend_codegen.cpp =================================================================== --- clang/test/OpenMP/target_teams_distribute_parallel_for_simd_depend_codegen.cpp +++ clang/test/OpenMP/target_teams_distribute_parallel_for_simd_depend_codegen.cpp @@ -40,13 +40,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[SIZET:@.+]] = private unnamed_addr constant [2 x i64] [i64 0, i64 4] // CHECK-DAG: [[MAPT:@.+]] = private unnamed_addr constant [2 x i64] [i64 544, i64 800] // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -55,17 +51,8 @@ // TCHECK: @{{.+}} = {{.*}}constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_teams_distribute_simd_codegen.cpp =================================================================== --- clang/test/OpenMP/target_teams_distribute_simd_codegen.cpp +++ clang/test/OpenMP/target_teams_distribute_simd_codegen.cpp @@ -45,13 +45,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[S1:%.+]] = type { double } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // We have 8 target regions, but only 7 that actually will generate offloading // code, only 6 will have mapped arguments, and only 4 have all-constant map // sizes. @@ -85,17 +81,8 @@ // TCHECK: @{{.+}} = weak constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_teams_distribute_simd_codegen_registration.cpp =================================================================== --- clang/test/OpenMP/target_teams_distribute_simd_codegen_registration.cpp +++ clang/test/OpenMP/target_teams_distribute_simd_codegen_registration.cpp @@ -52,13 +52,9 @@ // CHECK-DAG: [[ST1:%.+]] = type { [228 x i32] } // CHECK-DAG: [[ST2:%.+]] = type { [1128 x i32] } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[A1:@.+]] = internal global [[SA]] // CHECK-DAG: [[A2:@.+]] = global [[SA]] // CHECK-DAG: [[B1:@.+]] = global [[SB]] @@ -172,19 +168,11 @@ // TCHECK-DAG: [[NAMEPTR12:@.+]] = internal unnamed_addr constant [{{.*}} x i8] c"[[NAME12:.+]]\00" // TCHECK-DAG: [[ENTRY12:@.+]] = weak constant [[ENTTY]] { i8* bitcast (void (i[[SZ]])* @{{.*}} to i8*), i8* getelementptr inbounds ([{{.*}} x i8], [{{.*}} x i8]* [[NAMEPTR12]], i32 0, i32 0), i[[SZ]] 0, i32 0, i32 0 }, section ".omp_offloading.entries", align 1 -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // We have 4 initializers, one for the 500 priority, another one for 501, or more for the default priority, and the last one for the offloading registration function. -// CHECK: @llvm.global_ctors = appending global [5 x { i32, void ()*, i8* }] [ +// CHECK: @llvm.global_ctors = appending global [4 x { i32, void ()*, i8* }] [ // CHECK-SAME: { i32, void ()*, i8* } { i32 500, void ()* [[P500:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 501, void ()* [[P501:@[^,]+]], i8* null }, // CHECK-SAME: { i32, void ()*, i8* } { i32 65535, void ()* [[PMAX:@[^,]+]], i8* null }, -// CHECK-SAME: { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] // CHECK-NTARGET: @llvm.global_ctors = appending global [3 x { i32, void ()*, i8* }] [ @@ -363,12 +351,8 @@ //TCHECK-DAG: define weak void @[[NAME12]]( // CHECK-NTARGET-NOT: __tgt_target -// CHECK-NTARGET-NOT: __tgt_register_lib -// CHECK-NTARGET-NOT: __tgt_unregister_lib // TCHECK-NOT: __tgt_target -// TCHECK-NOT: __tgt_register_lib -// TCHECK-NOT: __tgt_unregister_lib // We have 2 initializers with priority 500 //CHECK: define internal void [[P500]]( @@ -394,25 +378,6 @@ //CHECK-NOT: call void @{{.+}}() //CHECK: ret void -// Check registration and unregistration - -//CHECK: define internal void @.omp_offloading.requires_reg() -//CHECK: call void @__tgt_register_requires(i64 1) -//CHECK: ret void - -//CHECK: define internal void @[[UNREGFN:.+]](i8* %0) -//CHECK-SAME: comdat($[[REGFN]]) { -//CHECK: call i32 @__tgt_unregister_lib([[DSCTY]]* [[DESC]]) -//CHECK: ret void -//CHECK: declare i32 @__tgt_unregister_lib([[DSCTY]]*) - -//CHECK: define linkonce hidden void @[[REGFN]]() -//CHECK-SAME: comdat { -//CHECK: call i32 @__tgt_register_lib([[DSCTY]]* [[DESC]]) -//CHECK: call i32 @__cxa_atexit(void (i8*)* @[[UNREGFN]], i8* bitcast ([[DSCTY]]* [[DESC]] to i8*), -//CHECK: ret void -//CHECK: declare i32 @__tgt_register_lib([[DSCTY]]*) - static __attribute__((init_priority(500))) SA a1; SA a2; SB __attribute__((init_priority(500))) b1; @@ -446,32 +411,32 @@ // Check metadata is properly generated: // CHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 268, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 286, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 293, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 440, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 319, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 312, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 319, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 305, i32 {{[0-9]+}}} -// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 256, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 274, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 281, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 405, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 307, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 300, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 307, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 293, i32 {{[0-9]+}}} +// CHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} // TCHECK: !omp_offload.info = !{!{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}, !{{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 216, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 268, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 286, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 293, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 440, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 319, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 312, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 319, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 305, i32 {{[0-9]+}}} -// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 242, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID:-?[0-9]+]], i32 [[FILEID:-?[0-9]+]], !"_ZN2SB3fooEv", i32 204, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SDD1Ev", i32 256, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SEC1Ev", i32 274, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SED1Ev", i32 281, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EE3fooEv", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EEC1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_Z3bari", i32 405, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EED1Ev", i32 307, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EEC1Ev", i32 300, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi1000EED1Ev", i32 307, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2STILi100EE3fooEv", i32 293, i32 {{[0-9]+}}} +// TCHECK-DAG: = !{i32 0, i32 [[DEVID]], i32 [[FILEID]], !"_ZN2SCC1Ev", i32 230, i32 {{[0-9]+}}} // TCHECK-DAG: !{!"llvm.loop.vectorize.enable", i1 true} // CHECK-DAG: !{!"llvm.loop.vectorize.enable", i1 true} Index: clang/test/OpenMP/target_teams_distribute_simd_depend_codegen.cpp =================================================================== --- clang/test/OpenMP/target_teams_distribute_simd_depend_codegen.cpp +++ clang/test/OpenMP/target_teams_distribute_simd_depend_codegen.cpp @@ -40,13 +40,9 @@ // CHECK-DAG: [[TT:%.+]] = type { i64, i8 } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // CHECK-DAG: [[SIZET:@.+]] = private unnamed_addr constant [2 x i64] [i64 0, i64 4] // CHECK-DAG: [[MAPT:@.+]] = private unnamed_addr constant [2 x i64] [i64 544, i64 800] // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -55,17 +51,8 @@ // TCHECK: @{{.+}} = {{.*}}constant [[ENTTY]] // TCHECK-NOT: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template struct TT{ Index: clang/test/OpenMP/target_teams_num_teams_codegen.cpp =================================================================== --- clang/test/OpenMP/target_teams_num_teams_codegen.cpp +++ clang/test/OpenMP/target_teams_num_teams_codegen.cpp @@ -44,13 +44,9 @@ // CHECK-DAG: [[S1:%.+]] = type { double } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // We have 6 target regions // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -67,17 +63,8 @@ // TCHECK: @{{.+}} = weak constant [[ENTTY]] // TCHECK: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template tx ftemplate(int n) { Index: clang/test/OpenMP/target_teams_thread_limit_codegen.cpp =================================================================== --- clang/test/OpenMP/target_teams_thread_limit_codegen.cpp +++ clang/test/OpenMP/target_teams_thread_limit_codegen.cpp @@ -44,13 +44,9 @@ // CHECK-DAG: [[S1:%.+]] = type { double } // CHECK-DAG: [[ENTTY:%.+]] = type { i8*, i8*, i[[SZ:32|64]], i32, i32 } -// CHECK-DAG: [[DEVTY:%.+]] = type { i8*, i8*, [[ENTTY]]*, [[ENTTY]]* } -// CHECK-DAG: [[DSCTY:%.+]] = type { i32, [[DEVTY]]*, [[ENTTY]]*, [[ENTTY]]* } // TCHECK: [[ENTTY:%.+]] = type { i8*, i8*, i{{32|64}}, i32, i32 } -// CHECK-DAG: $[[REGFN:\.omp_offloading\..+]] = comdat - // We have 6 target regions // CHECK-DAG: @{{.*}} = weak constant i8 0 @@ -67,17 +63,8 @@ // TCHECK: @{{.+}} = weak constant [[ENTTY]] // TCHECK: @{{.+}} = weak constant [[ENTTY]] -// Check if offloading descriptor is created. -// CHECK: [[ENTBEGIN:@.+]] = external constant [[ENTTY]] -// CHECK: [[ENTEND:@.+]] = external constant [[ENTTY]] -// CHECK: [[DEVBEGIN:@.+]] = extern_weak constant i8 -// CHECK: [[DEVEND:@.+]] = extern_weak constant i8 -// CHECK: [[IMAGES:@.+]] = internal unnamed_addr constant [1 x [[DEVTY]]] [{{.+}} { i8* [[DEVBEGIN]], i8* [[DEVEND]], [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }], comdat($[[REGFN]]) -// CHECK: [[DESC:@.+]] = internal constant [[DSCTY]] { i32 1, [[DEVTY]]* getelementptr inbounds ([1 x [[DEVTY]]], [1 x [[DEVTY]]]* [[IMAGES]], i32 0, i32 0), [[ENTTY]]* [[ENTBEGIN]], [[ENTTY]]* [[ENTEND]] }, comdat($[[REGFN]]) - // Check target registration is registered as a Ctor. -// CHECK: appending global [2 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }, { i32, void ()*, i8* } { i32 0, void ()* @[[REGFN]], i8* bitcast (void ()* @[[REGFN]] to i8*) }] - +// CHECK: appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 0, void ()* @.omp_offloading.requires_reg, i8* null }] template tx ftemplate(int n) { Index: clang/tools/CMakeLists.txt =================================================================== --- clang/tools/CMakeLists.txt +++ clang/tools/CMakeLists.txt @@ -8,6 +8,7 @@ add_clang_subdirectory(clang-fuzzer) add_clang_subdirectory(clang-import-test) add_clang_subdirectory(clang-offload-bundler) +add_clang_subdirectory(clang-offload-wrapper) add_clang_subdirectory(clang-scan-deps) add_clang_subdirectory(c-index-test) Index: clang/tools/clang-offload-wrapper/CMakeLists.txt =================================================================== --- /dev/null +++ clang/tools/clang-offload-wrapper/CMakeLists.txt @@ -0,0 +1,25 @@ +set(LLVM_LINK_COMPONENTS BitWriter Core Support TransformUtils) + +if(NOT CLANG_BUILT_STANDALONE) + set(tablegen_deps intrinsics_gen) +endif() + +add_clang_executable(clang-offload-wrapper + ClangOffloadWrapper.cpp + + DEPENDS + ${tablegen_deps} + ) + +set(CLANG_OFFLOAD_WRAPPER_LIB_DEPS + clangBasic + ) + +add_dependencies(clang clang-offload-wrapper) + +target_link_libraries(clang-offload-wrapper + PRIVATE + ${CLANG_OFFLOAD_WRAPPER_LIB_DEPS} + ) + +install(TARGETS clang-offload-wrapper RUNTIME DESTINATION bin) Index: clang/tools/clang-offload-wrapper/ClangOffloadWrapper.cpp =================================================================== --- /dev/null +++ clang/tools/clang-offload-wrapper/ClangOffloadWrapper.cpp @@ -0,0 +1,360 @@ +//===-- clang-offload-wrapper/ClangOffloadWrapper.cpp -----------*- C++ -*-===// +// +// 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 +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// Implementation of the offload wrapper tool. It takes offload target binaries +/// as input and creates wrapper bitcode from them which registers given +/// binaries in offload runtime. +/// +//===----------------------------------------------------------------------===// + +#include "clang/Basic/Version.h" +#include "llvm/ADT/ArrayRef.h" +#include "llvm/ADT/Triple.h" +#include "llvm/Bitcode/BitcodeWriter.h" +#include "llvm/IR/Constants.h" +#include "llvm/IR/GlobalVariable.h" +#include "llvm/IR/IRBuilder.h" +#include "llvm/IR/LLVMContext.h" +#include "llvm/IR/Module.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/Errc.h" +#include "llvm/Support/Error.h" +#include "llvm/Support/ErrorOr.h" +#include "llvm/Support/MemoryBuffer.h" +#include "llvm/Support/Signals.h" +#include "llvm/Support/ToolOutputFile.h" +#include "llvm/Support/WithColor.h" +#include "llvm/Support/raw_ostream.h" +#include "llvm/Transforms/Utils/ModuleUtils.h" +#include +#include + +using namespace llvm; + +static cl::opt Help("h", cl::desc("Alias for -help"), cl::Hidden); + +// Mark all our options with this category, everything else (except for -version +// and -help) will be hidden. +static cl::OptionCategory + ClangOffloadWrapperCategory("clang-offload-wrapper options"); + +static cl::opt Output("o", cl::Required, + cl::desc("Output filename"), + cl::value_desc("filename"), + cl::cat(ClangOffloadWrapperCategory)); + +static cl::list Inputs(cl::Positional, cl::OneOrMore, + cl::desc(""), + cl::cat(ClangOffloadWrapperCategory)); + +static cl::opt Target("target", cl::Required, + cl::desc("Target triple"), + cl::value_desc("triple"), + cl::cat(ClangOffloadWrapperCategory)); + +namespace { + +class BinaryWrapper { + LLVMContext C; + Module M; + + StructType *EntryTy = nullptr; + StructType *ImageTy = nullptr; + StructType *DescTy = nullptr; + +private: + IntegerType *getSizeTTy() { + switch (M.getDataLayout().getPointerTypeSize(Type::getInt8PtrTy(C))) { + case 4u: + return Type::getInt32Ty(C); + case 8u: + return Type::getInt64Ty(C); + } + llvm_unreachable("unsupported pointer type size"); + } + + // struct __tgt_offload_entry { + // void *addr; + // char *name; + // size_t size; + // int32_t flags; + // int32_t reserved; + // }; + StructType *getEntryTy() { + if (!EntryTy) + EntryTy = StructType::create("__tgt_offload_entry", Type::getInt8PtrTy(C), + Type::getInt8PtrTy(C), getSizeTTy(), + Type::getInt32Ty(C), Type::getInt32Ty(C)); + return EntryTy; + } + + PointerType *getEntryPtrTy() { return PointerType::getUnqual(getEntryTy()); } + + // struct __tgt_device_image { + // void *ImageStart; + // void *ImageEnd; + // __tgt_offload_entry *EntriesBegin; + // __tgt_offload_entry *EntriesEnd; + // }; + StructType *getDeviceImageTy() { + if (!ImageTy) + ImageTy = StructType::create("__tgt_device_image", Type::getInt8PtrTy(C), + Type::getInt8PtrTy(C), getEntryPtrTy(), + getEntryPtrTy()); + return ImageTy; + } + + PointerType *getDeviceImagePtrTy() { + return PointerType::getUnqual(getDeviceImageTy()); + } + + // struct __tgt_bin_desc { + // int32_t NumDeviceImages; + // __tgt_device_image *DeviceImages; + // __tgt_offload_entry *HostEntriesBegin; + // __tgt_offload_entry *HostEntriesEnd; + // }; + StructType *getBinDescTy() { + if (!DescTy) + DescTy = StructType::create("__tgt_bin_desc", Type::getInt32Ty(C), + getDeviceImagePtrTy(), getEntryPtrTy(), + getEntryPtrTy()); + return DescTy; + } + + PointerType *getBinDescPtrTy() { + return PointerType::getUnqual(getBinDescTy()); + } + + /// Creates binary descriptor for the given device images. Binary descriptor + /// is an object that is passed to the offloading runtime at program startup + /// and it describes all device images available in the executable or shared + /// library. It is defined as follows + /// + /// extern __tgt_offload_entry *__omp_offloading_entries_begin; + /// extern __tgt_offload_entry *__omp_offloading_entries_end; + /// + /// static const char Image0[] = { }; + /// ... + /// static const char ImageN[] = { }; + /// + /// static const __tgt_device_image Images[] = { + /// { + /// Image0, /*ImageStart*/ + /// Image0 + sizeof(Image0), /*ImageEnd*/ + /// __omp_offloading_entries_begin, /*EntriesBegin*/ + /// __omp_offloading_entries_end /*EntriesEnd*/ + /// }, + /// ... + /// { + /// ImageN, /*ImageStart*/ + /// ImageN + sizeof(ImageN), /*ImageEnd*/ + /// __omp_offloading_entries_begin, /*EntriesBegin*/ + /// __omp_offloading_entries_end /*EntriesEnd*/ + /// } + /// }; + /// + /// static const __tgt_bin_desc BinDesc = { + /// sizeof(Images) / sizeof(Images[0]), /*NumDeviceImages*/ + /// Images, /*DeviceImages*/ + /// __omp_offloading_entries_begin, /*HostEntriesBegin*/ + /// __omp_offloading_entries_end /*HostEntriesEnd*/ + /// }; + /// + /// Global variable that represents BinDesc is returned. + GlobalVariable *createBinDesc(ArrayRef> Bufs) { + // Create external begin/end symbols for the offload entries table. + auto *EntriesB = new GlobalVariable( + M, getEntryTy(), /*isConstant*/ true, GlobalValue::ExternalLinkage, + /*Initializer*/ nullptr, "__omp_offloading_entries_begin"); + auto *EntriesE = new GlobalVariable( + M, getEntryTy(), /*isConstant*/ true, GlobalValue::ExternalLinkage, + /*Initializer*/ nullptr, "__omp_offloading_entries_end"); + + auto *Zero = ConstantInt::get(getSizeTTy(), 0u); + Constant *ZeroZero[] = {Zero, Zero}; + + // Create initializer for the images array. + SmallVector ImagesInits; + ImagesInits.reserve(Bufs.size()); + for (const ArrayRef &Buf : Bufs) { + auto *Data = ConstantDataArray::get(C, Buf); + auto *Image = new GlobalVariable(M, Data->getType(), /*isConstant*/ true, + GlobalVariable::InternalLinkage, Data, + ".omp_offloading.device_image"); + Image->setUnnamedAddr(GlobalValue::UnnamedAddr::Global); + + auto *Size = ConstantInt::get(getSizeTTy(), Buf.size()); + Constant *ZeroSize[] = {Zero, Size}; + + auto *ImageB = ConstantExpr::getGetElementPtr(Image->getValueType(), + Image, ZeroZero); + auto *ImageE = ConstantExpr::getGetElementPtr(Image->getValueType(), + Image, ZeroSize); + + ImagesInits.push_back(ConstantStruct::get(getDeviceImageTy(), ImageB, + ImageE, EntriesB, EntriesE)); + } + + // Then create images array. + auto *ImagesData = ConstantArray::get( + ArrayType::get(getDeviceImageTy(), ImagesInits.size()), ImagesInits); + + auto *Images = + new GlobalVariable(M, ImagesData->getType(), /*isConstant*/ true, + GlobalValue::InternalLinkage, ImagesData, + ".omp_offloading.device_images"); + Images->setUnnamedAddr(GlobalValue::UnnamedAddr::Global); + + auto *ImagesB = ConstantExpr::getGetElementPtr(Images->getValueType(), + Images, ZeroZero); + + // And finally create the binary descriptor object. + auto *DescInit = ConstantStruct::get( + getBinDescTy(), + ConstantInt::get(Type::getInt32Ty(C), ImagesInits.size()), ImagesB, + EntriesB, EntriesE); + + return new GlobalVariable(M, DescInit->getType(), /*isConstant*/ true, + GlobalValue::InternalLinkage, DescInit, + ".omp_offloading.descriptor"); + } + + void createRegisterFunction(GlobalVariable *BinDesc) { + auto *FuncTy = FunctionType::get(Type::getVoidTy(C), /*isVarArg*/ false); + auto *Func = Function::Create(FuncTy, GlobalValue::InternalLinkage, + ".omp_offloading.descriptor_reg", &M); + Func->setSection(".text.startup"); + + // Get __tgt_register_lib function declaration. + auto *RegFuncTy = FunctionType::get(Type::getVoidTy(C), getBinDescPtrTy(), + /*isVarArg*/ false); + FunctionCallee RegFuncC = + M.getOrInsertFunction("__tgt_register_lib", RegFuncTy); + + // Construct function body + IRBuilder<> Builder(BasicBlock::Create(C, "entry", Func)); + Builder.CreateCall(RegFuncC, BinDesc); + Builder.CreateRetVoid(); + + // Add this function to constructors. + appendToGlobalCtors(M, Func, 0); + } + + void createUnregisterFunction(GlobalVariable *BinDesc) { + auto *FuncTy = FunctionType::get(Type::getVoidTy(C), /*isVarArg*/ false); + auto *Func = Function::Create(FuncTy, GlobalValue::InternalLinkage, + ".omp_offloading.descriptor_unreg", &M); + Func->setSection(".text.startup"); + + // Get __tgt_unregister_lib function declaration. + auto *UnRegFuncTy = FunctionType::get(Type::getVoidTy(C), getBinDescPtrTy(), + /*isVarArg*/ false); + FunctionCallee UnRegFuncC = + M.getOrInsertFunction("__tgt_unregister_lib", UnRegFuncTy); + + // Construct function body + IRBuilder<> Builder(BasicBlock::Create(C, "entry", Func)); + Builder.CreateCall(UnRegFuncC, BinDesc); + Builder.CreateRetVoid(); + + // Add this function to global destructors. + appendToGlobalDtors(M, Func, 0); + } + +public: + BinaryWrapper(StringRef Target) : M("offload.wrapper.object", C) { + M.setTargetTriple(Target); + } + + const Module &wrapBinaries(ArrayRef> Binaries) { + GlobalVariable *Desc = createBinDesc(Binaries); + assert(Desc && "no binary descriptor"); + createRegisterFunction(Desc); + createUnregisterFunction(Desc); + return M; + } +}; + +} // anonymous namespace + +static void reportError(Error E, StringRef ToolName) { + logAllUnhandledErrors(std::move(E), WithColor::error(errs(), ToolName)); +} + +static void reportFileError(StringRef File, std::error_code EC, + StringRef ToolName) { + reportError(createFileError(File, EC), ToolName); +} + +int main(int argc, const char **argv) { + sys::PrintStackTraceOnErrorSignal(argv[0]); + + cl::HideUnrelatedOptions(ClangOffloadWrapperCategory); + cl::SetVersionPrinter([](raw_ostream &OS) { + OS << clang::getClangToolFullVersion("clang-offload-wrapper") << '\n'; + }); + cl::ParseCommandLineOptions( + argc, argv, + "A tool to create a wrapper bitcode for offload target binaries.\n" + "Takes offload target binaries as input and produces bitcode file " + "containing\ntarget binaries packaged as data and initialization code " + "which registers target\nbinaries in offload runtime."); + + if (Help) { + cl::PrintHelpMessage(); + return 0; + } + + if (Triple(Target).getArch() == Triple::UnknownArch) { + reportError( + createStringError(errc::invalid_argument, + "'" + Target + "': unsupported target triple"), + argv[0]); + return 1; + } + + // Read device binaries. + SmallVector, 4u> Buffers; + SmallVector, 4u> Images; + Buffers.reserve(Inputs.size()); + Images.reserve(Inputs.size()); + for (const std::string &File : Inputs) { + ErrorOr> BufOrErr = + MemoryBuffer::getFileOrSTDIN(File); + if (!BufOrErr) { + reportFileError(File, BufOrErr.getError(), argv[0]); + return 1; + } + const std::unique_ptr &Buf = + Buffers.emplace_back(std::move(*BufOrErr)); + Images.emplace_back(Buf->getBufferStart(), Buf->getBufferSize()); + } + + // Create the output file to write the resulting bitcode to. + std::error_code EC; + ToolOutputFile Out(Output, EC, sys::fs::OF_None); + if (EC) { + reportFileError(Output, EC, argv[0]); + return 1; + } + + // Create a wrapper for device binaries and write its bitcode to the file. + WriteBitcodeToFile(BinaryWrapper(Target).wrapBinaries( + makeArrayRef(Images.data(), Images.size())), + Out.os()); + if (Out.os().has_error()) { + reportFileError(Output, Out.os().error(), argv[0]); + return 1; + } + + // Success. + Out.keep(); + return 0; +} Index: openmp/libomptarget/src/CMakeLists.txt =================================================================== --- openmp/libomptarget/src/CMakeLists.txt +++ openmp/libomptarget/src/CMakeLists.txt @@ -29,3 +29,30 @@ # Install libomptarget under the lib destination folder. install(TARGETS omptarget LIBRARY COMPONENT omptarget DESTINATION "${OPENMP_INSTALL_LIBDIR}") + +# Begin/end object for libomptarget. +set(omptargetbegin_src "${CMAKE_CURRENT_SOURCE_DIR}/omptargetbegin.c") +set(omptargetend_src "${CMAKE_CURRENT_SOURCE_DIR}/omptargetend.c") + +set(omptargetbegin_obj "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/omptargetbegin${CMAKE_C_OUTPUT_EXTENSION}") +set(omptargetend_obj "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/omptargetend${CMAKE_C_OUTPUT_EXTENSION}") + +add_custom_command( + OUTPUT ${omptargetbegin_obj} + COMMAND ${CMAKE_C_COMPILER} -c -fPIC ${omptargetbegin_src} -o ${omptargetbegin_obj} + DEPENDS ${omptargetbegin_src} + COMMENT "Building C object ${omptargetbegin_obj}" + VERBATIM) + +add_custom_command( + OUTPUT ${omptargetend_obj} + COMMAND ${CMAKE_C_COMPILER} -c -fPIC ${omptargetend_src} -o ${omptargetend_obj} + DEPENDS ${omptargetend_src} + COMMENT "Building C object ${omptargetend_obj}" + VERBATIM) + +add_custom_target(omptargetbeginend ALL DEPENDS ${omptargetbegin_obj} ${omptargetend_obj}) + +install(FILES ${omptargetbegin_obj} ${omptargetend_obj} + DESTINATION "${OPENMP_INSTALL_LIBDIR}" + COMPONENT omptarget) Index: openmp/libomptarget/src/omptargetbegin.c =================================================================== --- /dev/null +++ openmp/libomptarget/src/omptargetbegin.c @@ -0,0 +1,15 @@ +//===-- omptargetbegin.c - OpenMP offload entry table start -------*- C -*-===// +// +// 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 +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// This file defines 'begin' symbol for the OpenMP offload entry table. +/// +//===----------------------------------------------------------------------===// + +__attribute__((visibility("hidden"), section(".omp_offloading.entries"))) +char __omp_offloading_entries_begin[0]; Index: openmp/libomptarget/src/omptargetend.c =================================================================== --- /dev/null +++ openmp/libomptarget/src/omptargetend.c @@ -0,0 +1,15 @@ +//===-- omptargetend.c - OpenMP offload entry table end -----------*- C -*-===// +// +// 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 +// +//===----------------------------------------------------------------------===// +/// +/// \file +/// This file defines 'end' symbol for the OpenMP offload entry table. +/// +//===----------------------------------------------------------------------===// + +__attribute__((visibility("hidden"), section(".omp_offloading.entries"))) +char __omp_offloading_entries_end[0];