Index: include/clang/AST/GlobalDecl.h =================================================================== --- include/clang/AST/GlobalDecl.h +++ include/clang/AST/GlobalDecl.h @@ -59,6 +59,7 @@ GlobalDecl(const CapturedDecl *D) { Init(D); } GlobalDecl(const ObjCMethodDecl *D) { Init(D); } GlobalDecl(const OMPDeclareReductionDecl *D) { Init(D); } + GlobalDecl(const OMPDeclareMapperDecl *D) { Init(D); } GlobalDecl(const CXXConstructorDecl *D, CXXCtorType Type) : Value(D, Type) {} GlobalDecl(const CXXDestructorDecl *D, CXXDtorType Type) : Value(D, Type) {} GlobalDecl(const VarDecl *D, DynamicInitKind StubKind) Index: lib/AST/ASTContext.cpp =================================================================== --- lib/AST/ASTContext.cpp +++ lib/AST/ASTContext.cpp @@ -9860,7 +9860,7 @@ return !D->getDeclContext()->isDependentContext(); else if (isa(D)) return !D->getDeclContext()->isDependentContext(); - else if (isa(D)) + else if (isa(D) || isa(D)) return !D->getDeclContext()->isDependentContext(); else if (isa(D)) return true; Index: lib/CodeGen/CGDecl.cpp =================================================================== --- lib/CodeGen/CGDecl.cpp +++ lib/CodeGen/CGDecl.cpp @@ -2529,10 +2529,11 @@ } void CodeGenModule::EmitOMPDeclareMapper(const OMPDeclareMapperDecl *D, - CodeGenFunction *CGF) { - if (!LangOpts.OpenMP || (!LangOpts.EmitAllDecls && !D->isUsed())) + CodeGenFunction *CGF) { + if (!LangOpts.OpenMP || LangOpts.OpenMPSimd || + (!LangOpts.EmitAllDecls && !D->isUsed())) return; - // FIXME: need to implement mapper code generation + getOpenMPRuntime().emitUserDefinedMapper(D, CGF); } void CodeGenModule::EmitOMPRequiresDecl(const OMPRequiresDecl *D) { Index: lib/CodeGen/CGOpenMPRuntime.h =================================================================== --- lib/CodeGen/CGOpenMPRuntime.h +++ lib/CodeGen/CGOpenMPRuntime.h @@ -345,6 +345,14 @@ SmallVector> FunctionUDRMapTy; FunctionUDRMapTy FunctionUDRMap; + /// Map from the user-defined mapper declaration to its corresponding + /// functions. + llvm::DenseMap UDMMap; + /// Map of functions and their local user-defined mappers. + using FunctionUDMMapTy = + llvm::DenseMap>; + FunctionUDMMapTy FunctionUDMMap; /// Type kmp_critical_name, originally defined as typedef kmp_int32 /// kmp_critical_name[8]; llvm::ArrayType *KmpCriticalNameTy; @@ -738,6 +746,14 @@ llvm::Value *Ctor, llvm::Value *CopyCtor, llvm::Value *Dtor, SourceLocation Loc); + /// Emit the array initialization or deletion portion for user-defined mapper + /// code generation. + void emitUDMapperArrayInitOrDel(CodeGenFunction &MapperCGF, + llvm::Value *Handle, llvm::Value *BasePtr, + llvm::Value *Ptr, llvm::Value *Size, + llvm::Value *MapType, CharUnits ElementSize, + llvm::BasicBlock *ExitBB, bool IsInit); + struct TaskResultTy { llvm::Value *NewTask = nullptr; llvm::Function *TaskEntry = nullptr; @@ -798,6 +814,10 @@ virtual std::pair getUserDefinedReduction(const OMPDeclareReductionDecl *D); + /// Emit the function for the user defined mapper construct. + void emitUserDefinedMapper(const OMPDeclareMapperDecl *D, + CodeGenFunction *CGF = nullptr); + /// Emits outlined function for the specified OpenMP parallel directive /// \a D. This outlined function has type void(*)(kmp_int32 *ThreadID, /// kmp_int32 BoundID, struct context_vars*). Index: lib/CodeGen/CGOpenMPRuntime.cpp =================================================================== --- lib/CodeGen/CGOpenMPRuntime.cpp +++ lib/CodeGen/CGOpenMPRuntime.cpp @@ -752,6 +752,11 @@ // arg_num, void** args_base, void **args, int64_t *arg_sizes, int64_t // *arg_types); OMPRTL__tgt_target_data_update_nowait, + // Call to int64_t __tgt_mapper_num_components(void *rt_mapper_handle); + OMPRTL__tgt_mapper_num_components, + // Call to void __tgt_push_mapper_component(void *rt_mapper_handle, void + // *base, void *begin, int64_t size, int64_t type); + OMPRTL__tgt_push_mapper_component, }; /// A basic class for pre|post-action for advanced codegen sequence for OpenMP @@ -1686,6 +1691,12 @@ UDRMap.erase(D); FunctionUDRMap.erase(CGF.CurFn); } + auto I = FunctionUDMMap.find(CGF.CurFn); + if (I != FunctionUDMMap.end()) { + for(auto *D : I->second) + UDMMap.erase(D); + FunctionUDMMap.erase(I); + } } llvm::Type *CGOpenMPRuntime::getIdentTyPointerTy() { @@ -2459,6 +2470,24 @@ RTLFn = CGM.CreateRuntimeFunction(FnTy, "__tgt_target_data_update_nowait"); break; } + case OMPRTL__tgt_mapper_num_components: { + // Build int64_t __tgt_mapper_num_components(void *rt_mapper_handle); + llvm::Type *TypeParams[] = {CGM.VoidPtrTy}; + auto *FnTy = + llvm::FunctionType::get(CGM.Int64Ty, TypeParams, /*isVarArg*/ false); + RTLFn = CGM.CreateRuntimeFunction(FnTy, "__tgt_mapper_num_components"); + break; + } + case OMPRTL__tgt_push_mapper_component: { + // Build void __tgt_push_mapper_component(void *rt_mapper_handle, void + // *base, void *begin, int64_t size, int64_t type); + llvm::Type *TypeParams[] = {CGM.VoidPtrTy, CGM.VoidPtrTy, CGM.VoidPtrTy, + CGM.Int64Ty, CGM.Int64Ty}; + auto *FnTy = + llvm::FunctionType::get(CGM.VoidTy, TypeParams, /*isVarArg*/ false); + RTLFn = CGM.CreateRuntimeFunction(FnTy, "__tgt_push_mapper_component"); + break; + } } assert(RTLFn && "Unable to find OpenMP runtime function"); return RTLFn; @@ -7085,6 +7114,15 @@ LLVM_MARK_AS_BITMASK_ENUM(/* LargestFlag = */ OMP_MAP_MEMBER_OF), }; + /// Get the offset of the OMP_MAP_MEMBER_OF field. + static unsigned getFlagMemberOffset() { + unsigned Offset = 0; + for (uint64_t Remain = OMP_MAP_MEMBER_OF; !(Remain & 1); + Remain = Remain >> 1) + Offset++; + return Offset; + } + /// Class that associates information with a base pointer to be passed to the /// runtime library. class BasePointerInfo { @@ -7148,8 +7186,11 @@ : IE(IE), VD(VD) {} }; - /// Directive from where the map clauses were extracted. - const OMPExecutableDirective &CurDir; + /// The target directive from where the mappable clauses were extracted. It + /// is either a executable directive or a user-defined mapper directive. + llvm::PointerUnion + CurDir; /// Function the directive is being generated for. CodeGenFunction &CGF; @@ -7752,9 +7793,9 @@ } static OpenMPOffloadMappingFlags getMemberOfFlag(unsigned Position) { - // Member of is given by the 16 MSB of the flag, so rotate by 48 bits. + // Rotate by getFlagMemberOffset() bits. return static_cast(((uint64_t)Position + 1) - << 48); + << getFlagMemberOffset()); } static void setCorrectMemberOfFlag(OpenMPOffloadMappingFlags &Flags, @@ -7834,7 +7875,7 @@ public: MappableExprsHandler(const OMPExecutableDirective &Dir, CodeGenFunction &CGF) - : CurDir(Dir), CGF(CGF) { + : CurDir(&Dir), CGF(CGF) { // Extract firstprivate clause information. for (const auto *C : Dir.getClausesOfKind()) for (const auto *D : C->varlists()) @@ -7846,6 +7887,10 @@ DevPointersMap[L.first].push_back(L.second); } + /// Constructor for the declare mapper directive. + MappableExprsHandler(const OMPDeclareMapperDecl &Dir, CodeGenFunction &CGF) + : CurDir(&Dir), CGF(CGF) {} + /// Generate code for the combined entry if we have a partially mapped struct /// and take care of the mapping flags of the arguments corresponding to /// individual struct members. @@ -7907,18 +7952,20 @@ IsImplicit); }; - // FIXME: MSVC 2013 seems to require this-> to find member CurDir. - for (const auto *C : this->CurDir.getClausesOfKind()) + assert(CurDir.is() && + "Expect a executable directive"); + const auto *CurExecDir = CurDir.get(); + for (const auto *C : CurExecDir->getClausesOfKind()) for (const auto &L : C->component_lists()) { InfoGen(L.first, L.second, C->getMapType(), C->getMapTypeModifiers(), /*ReturnDevicePointer=*/false, C->isImplicit()); } - for (const auto *C : this->CurDir.getClausesOfKind()) + for (const auto *C : CurExecDir->getClausesOfKind()) for (const auto &L : C->component_lists()) { InfoGen(L.first, L.second, OMPC_MAP_to, llvm::None, /*ReturnDevicePointer=*/false, C->isImplicit()); } - for (const auto *C : this->CurDir.getClausesOfKind()) + for (const auto *C : CurExecDir->getClausesOfKind()) for (const auto &L : C->component_lists()) { InfoGen(L.first, L.second, OMPC_MAP_from, llvm::None, /*ReturnDevicePointer=*/false, C->isImplicit()); @@ -7933,9 +7980,8 @@ llvm::MapVector> DeferredInfo; - // FIXME: MSVC 2013 seems to require this-> to find member CurDir. for (const auto *C : - this->CurDir.getClausesOfKind()) { + CurExecDir->getClausesOfKind()) { for (const auto &L : C->component_lists()) { assert(!L.second.empty() && "Not expecting empty list of components!"); const ValueDecl *VD = L.second.back().getAssociatedDeclaration(); @@ -7964,7 +8010,6 @@ // We didn't find any match in our map information - generate a zero // size array section - if the pointer is a struct member we defer this // action until the whole struct has been processed. - // FIXME: MSVC 2013 seems to require this-> to find member CGF. if (isa(IE)) { // Insert the pointer into Info to be processed by // generateInfoForComponentList. Because it is a member pointer @@ -7977,11 +8022,11 @@ /*ReturnDevicePointer=*/false, C->isImplicit()); DeferredInfo[nullptr].emplace_back(IE, VD); } else { - llvm::Value *Ptr = this->CGF.EmitLoadOfScalar( - this->CGF.EmitLValue(IE), IE->getExprLoc()); + llvm::Value *Ptr = + CGF.EmitLoadOfScalar(CGF.EmitLValue(IE), IE->getExprLoc()); BasePointers.emplace_back(Ptr, VD); Pointers.push_back(Ptr); - Sizes.push_back(llvm::Constant::getNullValue(this->CGF.Int64Ty)); + Sizes.push_back(llvm::Constant::getNullValue(CGF.Int64Ty)); Types.push_back(OMP_MAP_RETURN_PARAM | OMP_MAP_TARGET_PARAM); } } @@ -8005,11 +8050,10 @@ // Remember the current base pointer index. unsigned CurrentBasePointersIdx = CurBasePointers.size(); - // FIXME: MSVC 2013 seems to require this-> to find the member method. - this->generateInfoForComponentList( - L.MapType, L.MapModifiers, L.Components, CurBasePointers, - CurPointers, CurSizes, CurTypes, PartialStruct, - IsFirstComponentList, L.IsImplicit); + generateInfoForComponentList(L.MapType, L.MapModifiers, L.Components, + CurBasePointers, CurPointers, CurSizes, + CurTypes, PartialStruct, + IsFirstComponentList, L.IsImplicit); // If this entry relates with a device pointer, set the relevant // declaration and add the 'return pointer' flag. @@ -8061,6 +8105,78 @@ } } + /// Generate all the base pointers, section pointers, sizes and map types for + /// the extracted map clauses of user-defined mapper. + void generateAllInfoForMapper(MapBaseValuesArrayTy &BasePointers, + MapValuesArrayTy &Pointers, + MapValuesArrayTy &Sizes, + MapFlagsArrayTy &Types) const { + assert(CurDir.is() && + "Expect a declare mapper directive"); + const auto *CurMapperDir = CurDir.get(); + // We have to process the component lists that relate with the same + // declaration in a single chunk so that we can generate the map flags + // correctly. Therefore, we organize all lists in a map. + llvm::MapVector> Info; + + // Helper function to fill the information map for the different supported + // clauses. + auto &&InfoGen = [&Info]( + const ValueDecl *D, + OMPClauseMappableExprCommon::MappableExprComponentListRef L, + OpenMPMapClauseKind MapType, + ArrayRef MapModifiers, + bool ReturnDevicePointer, bool IsImplicit) { + const ValueDecl *VD = + D ? cast(D->getCanonicalDecl()) : nullptr; + Info[VD].emplace_back(L, MapType, MapModifiers, ReturnDevicePointer, + IsImplicit); + }; + + for (const auto *C : CurMapperDir->clauselists()) { + const auto *MC = cast(C); + for (const auto &L : MC->component_lists()) { + InfoGen(L.first, L.second, MC->getMapType(), MC->getMapTypeModifiers(), + /*ReturnDevicePointer=*/false, MC->isImplicit()); + } + } + + for (const auto &M : Info) { + // We need to know when we generate information for the first component + // associated with a capture, because the mapping flags depend on it. + bool IsFirstComponentList = true; + + // Temporary versions of arrays + MapBaseValuesArrayTy CurBasePointers; + MapValuesArrayTy CurPointers; + MapValuesArrayTy CurSizes; + MapFlagsArrayTy CurTypes; + StructRangeInfoTy PartialStruct; + + for (const MapInfo &L : M.second) { + assert(!L.Components.empty() && + "Not expecting declaration with no component lists."); + generateInfoForComponentList(L.MapType, L.MapModifiers, L.Components, + CurBasePointers, CurPointers, CurSizes, + CurTypes, PartialStruct, + IsFirstComponentList, L.IsImplicit); + IsFirstComponentList = false; + } + + // If there is an entry in PartialStruct it means we have a struct with + // individual members mapped. Emit an extra combined entry. + if (PartialStruct.Base.isValid()) + emitCombinedEntry(BasePointers, Pointers, Sizes, Types, CurTypes, + PartialStruct); + + // We need to append the results of this capture to what we already have. + BasePointers.append(CurBasePointers.begin(), CurBasePointers.end()); + Pointers.append(CurPointers.begin(), CurPointers.end()); + Sizes.append(CurSizes.begin(), CurSizes.end()); + Types.append(CurTypes.begin(), CurTypes.end()); + } + } + /// Emit capture info for lambdas for variables captured by reference. void generateInfoForLambdaCaptures( const ValueDecl *VD, llvm::Value *Arg, MapBaseValuesArrayTy &BasePointers, @@ -8184,8 +8300,10 @@ std::tuple, bool>; SmallVector DeclComponentLists; - // FIXME: MSVC 2013 seems to require this-> to find member CurDir. - for (const auto *C : this->CurDir.getClausesOfKind()) { + assert(CurDir.is() && + "Expect a executable directive"); + const auto *CurExecDir = CurDir.get(); + for (const auto *C : CurExecDir->getClausesOfKind()) { for (const auto &L : C->decl_component_lists(VD)) { assert(L.first == VD && "We got information for the wrong declaration??"); @@ -8333,9 +8451,12 @@ MapValuesArrayTy &Pointers, MapValuesArrayTy &Sizes, MapFlagsArrayTy &Types) const { + assert(CurDir.is() && + "Expect a executable directive"); + const auto *CurExecDir = CurDir.get(); // Map other list items in the map clause which are not captured variables // but "declare target link" global variables. - for (const auto *C : this->CurDir.getClausesOfKind()) { + for (const auto *C : CurExecDir->getClausesOfKind()) { for (const auto &L : C->component_lists()) { if (!L.first) continue; @@ -8562,6 +8683,7 @@ } } } + /// Emit the arguments to be passed to the runtime library based on the /// arrays of pointers, sizes and map types. static void emitOffloadingArraysArgument( @@ -8692,6 +8814,337 @@ return nullptr; } +/// Emit the user-defined mapper function. The code generation follows the +/// pattern in the example below. +/// \code +/// void .omp_mapper...(void *rt_mapper_handle, +/// void *base, void *begin, +/// int64_t size, int64_t type) { +/// // Allocate space for an array section first. +/// if (size > 1 && !maptype.IsDelete) +/// __tgt_push_mapper_component(rt_mapper_handle, base, begin, +/// size*sizeof(Ty), clearToFrom(type)); +/// // Map members. +/// for (unsigned i = 0; i < size; i++) { +/// // For each component specified by this mapper: +/// for (auto c : all_components) { +/// if (c.hasMapper()) +/// (*c.Mapper())(rt_mapper_handle, c.arg_base, c.arg_begin, c.arg_size, +/// c.arg_type); +/// else +/// __tgt_push_mapper_component(rt_mapper_handle, c.arg_base, +/// c.arg_begin, c.arg_size, c.arg_type); +/// } +/// } +/// // Delete the array section. +/// if (size > 1 && maptype.IsDelete) +/// __tgt_push_mapper_component(rt_mapper_handle, base, begin, +/// size*sizeof(Ty), clearToFrom(type)); +/// } +/// \endcode +void CGOpenMPRuntime::emitUserDefinedMapper(const OMPDeclareMapperDecl *D, + CodeGenFunction *CGF) { + if (UDMMap.count(D) > 0) + return; + ASTContext &C = CGM.getContext(); + QualType Ty = D->getType(); + QualType PtrTy = C.getPointerType(Ty).withRestrict(); + QualType Int64Ty = C.getIntTypeForBitwidth(/*DestWidth=*/64, /*Signed=*/true); + auto *MapperVarDecl = + cast(cast(D->getMapperVarRef())->getDecl()); + SourceLocation Loc = D->getLocation(); + CharUnits ElementSize = C.getTypeSizeInChars(Ty); + + // Prepare mapper function arguments and attributes. + ImplicitParamDecl HandleArg(C, /*DC=*/nullptr, Loc, /*Id=*/nullptr, + C.VoidPtrTy, ImplicitParamDecl::Other); + ImplicitParamDecl BaseArg(C, /*DC=*/nullptr, Loc, /*Id=*/nullptr, C.VoidPtrTy, + ImplicitParamDecl::Other); + ImplicitParamDecl BeginArg(C, /*DC=*/nullptr, Loc, /*Id=*/nullptr, + C.VoidPtrTy, ImplicitParamDecl::Other); + ImplicitParamDecl SizeArg(C, /*DC=*/nullptr, Loc, /*Id=*/nullptr, Int64Ty, + ImplicitParamDecl::Other); + ImplicitParamDecl TypeArg(C, /*DC=*/nullptr, Loc, /*Id=*/nullptr, Int64Ty, + ImplicitParamDecl::Other); + FunctionArgList Args; + Args.push_back(&HandleArg); + Args.push_back(&BaseArg); + Args.push_back(&BeginArg); + Args.push_back(&SizeArg); + Args.push_back(&TypeArg); + const CGFunctionInfo &FnInfo = + CGM.getTypes().arrangeBuiltinFunctionDeclaration(C.VoidTy, Args); + llvm::FunctionType *FnTy = CGM.getTypes().GetFunctionType(FnInfo); + SmallString<64> TyStr; + llvm::raw_svector_ostream Out(TyStr); + CGM.getCXXABI().getMangleContext().mangleTypeName(Ty, Out); + std::string Name = getName({"omp_mapper", TyStr, D->getName()}); + auto *Fn = llvm::Function::Create(FnTy, llvm::GlobalValue::InternalLinkage, + Name, &CGM.getModule()); + CGM.SetInternalFunctionAttributes(GlobalDecl(), Fn, FnInfo); + Fn->removeFnAttr(llvm::Attribute::OptimizeNone); + // Start the mapper function code generation. + CodeGenFunction MapperCGF(CGM); + MapperCGF.StartFunction(GlobalDecl(), C.VoidTy, Fn, FnInfo, Args, Loc, Loc); + // Compute the starting and end addreses of array elements. + llvm::Value *Size = MapperCGF.EmitLoadOfScalar( + MapperCGF.GetAddrOfLocalVar(&SizeArg), /*Volatile=*/false, + C.getPointerType(Int64Ty), Loc); + llvm::Value *PtrBegin = MapperCGF.Builder.CreateBitCast( + MapperCGF.GetAddrOfLocalVar(&BeginArg).getPointer(), + CGM.getTypes().ConvertTypeForMem(C.getPointerType(PtrTy))); + llvm::Value *PtrEnd = MapperCGF.Builder.CreateGEP(PtrBegin, Size); + llvm::Value *MapType = MapperCGF.EmitLoadOfScalar( + MapperCGF.GetAddrOfLocalVar(&TypeArg), /*Volatile=*/false, + C.getPointerType(Int64Ty), Loc); + // Prepare common arguments for array initiation and deletion. + llvm::Value *Handle = MapperCGF.EmitLoadOfScalar( + MapperCGF.GetAddrOfLocalVar(&HandleArg), + /*Volatile=*/false, C.getPointerType(C.VoidPtrTy), Loc); + llvm::Value *BaseIn = MapperCGF.EmitLoadOfScalar( + MapperCGF.GetAddrOfLocalVar(&BaseArg), + /*Volatile=*/false, C.getPointerType(C.VoidPtrTy), Loc); + llvm::Value *BeginIn = MapperCGF.EmitLoadOfScalar( + MapperCGF.GetAddrOfLocalVar(&BeginArg), + /*Volatile=*/false, C.getPointerType(C.VoidPtrTy), Loc); + + // Emit array initiation if this is an array section and \p MapType indicates + // that memory allocation is required. + llvm::BasicBlock *HeadBB = MapperCGF.createBasicBlock("omp.arraymap.head"); + emitUDMapperArrayInitOrDel(MapperCGF, Handle, BaseIn, BeginIn, Size, MapType, + ElementSize, HeadBB, /*IsInit=*/true); + + // Emit a for loop to iterate through SizeArg of elements and map all of them. + + // Emit the loop header block. + MapperCGF.EmitBlock(HeadBB); + llvm::BasicBlock *BodyBB = MapperCGF.createBasicBlock("omp.arraymap.body"); + llvm::BasicBlock *DoneBB = MapperCGF.createBasicBlock("omp.done"); + // Evaluate whether the initial condition is satisfied. + llvm::Value *IsEmpty = + MapperCGF.Builder.CreateICmpEQ(PtrBegin, PtrEnd, "omp.arraymap.isempty"); + MapperCGF.Builder.CreateCondBr(IsEmpty, DoneBB, BodyBB); + llvm::BasicBlock *EntryBB = MapperCGF.Builder.GetInsertBlock(); + + // Emit the loop body block. + MapperCGF.EmitBlock(BodyBB); + llvm::PHINode *PtrPHI = MapperCGF.Builder.CreatePHI( + PtrBegin->getType(), 2, "omp.arraymap.ptrcurrent"); + PtrPHI->addIncoming(PtrBegin, EntryBB); + Address PtrCurrent = + Address(PtrPHI, MapperCGF.GetAddrOfLocalVar(&BeginArg) + .getAlignment() + .alignmentOfArrayElement(ElementSize)); + // Privatize the declared variable of mapper to be the current array element. + CodeGenFunction::OMPPrivateScope Scope(MapperCGF); + Scope.addPrivate(MapperVarDecl, [&MapperCGF, PtrCurrent, PtrTy]() { + return MapperCGF + .EmitLoadOfPointerLValue(PtrCurrent, PtrTy->castAs()) + .getAddress(); + }); + (void)Scope.Privatize(); + + // Get map clause information. Fill up the arrays with all mapped variables. + MappableExprsHandler::MapBaseValuesArrayTy BasePointers; + MappableExprsHandler::MapValuesArrayTy Pointers; + MappableExprsHandler::MapValuesArrayTy Sizes; + MappableExprsHandler::MapFlagsArrayTy MapTypes; + MappableExprsHandler MEHandler(*D, MapperCGF); + MEHandler.generateAllInfoForMapper(BasePointers, Pointers, Sizes, MapTypes); + + // Call the runtime API __tgt_mapper_num_components to get the number of + // pre-existing components. + llvm::Value *OffloadingArgs[] = {Handle}; + llvm::Value *PreviousSize = MapperCGF.EmitRuntimeCall( + createRuntimeFunction(OMPRTL__tgt_mapper_num_components), OffloadingArgs); + llvm::Value *ShiftedPreviousSize = MapperCGF.Builder.CreateShl( + PreviousSize, + MapperCGF.Builder.getInt64(MappableExprsHandler::getFlagMemberOffset())); + + // Fill up the runtime mapper handle for all components. + for (unsigned I = 0; I < BasePointers.size(); ++I) { + llvm::Value *CurBaseArg = MapperCGF.Builder.CreateBitCast( + *BasePointers[I], CGM.getTypes().ConvertTypeForMem(C.VoidPtrTy)); + llvm::Value *CurBeginArg = MapperCGF.Builder.CreateBitCast( + Pointers[I], CGM.getTypes().ConvertTypeForMem(C.VoidPtrTy)); + llvm::Value *CurSizeArg = Sizes[I]; + + // Extract the MEMBER_OF field from the map type. + llvm::BasicBlock *MemberBB = MapperCGF.createBasicBlock("omp.member"); + MapperCGF.EmitBlock(MemberBB); + llvm::Value *OriMapType = MapperCGF.Builder.getInt64(MapTypes[I]); + llvm::Value *Member = MapperCGF.Builder.CreateAnd( + OriMapType, + MapperCGF.Builder.getInt64(MappableExprsHandler::OMP_MAP_MEMBER_OF)); + llvm::BasicBlock *MemberCombineBB = + MapperCGF.createBasicBlock("omp.member.combine"); + llvm::BasicBlock *TypeBB = MapperCGF.createBasicBlock("omp.type"); + llvm::Value *IsMember = MapperCGF.Builder.CreateIsNull(Member); + MapperCGF.Builder.CreateCondBr(IsMember, TypeBB, MemberCombineBB); + // Add the number of pre-existing components to the MEMBER_OF field if it + // is valid. + MapperCGF.EmitBlock(MemberCombineBB); + llvm::Value *CombinedMember = + MapperCGF.Builder.CreateNUWAdd(OriMapType, ShiftedPreviousSize); + // Do nothing if it is not a member of previous components. + MapperCGF.EmitBlock(TypeBB); + llvm::PHINode *MemberMapType = + MapperCGF.Builder.CreatePHI(CGM.Int64Ty, 4, "omp.membermaptype"); + MemberMapType->addIncoming(OriMapType, MemberBB); + MemberMapType->addIncoming(CombinedMember, MemberCombineBB); + + // Combine the map type inherited from user-defined mapper with that + // specified in the program. According to the OMP_MAP_TO and OMP_MAP_FROM + // bits of the \a MapType, which is the input argument of the mapper + // function, the following code will set the OMP_MAP_TO and OMP_MAP_FROM + // bits of MemberMapType. + // [OpenMP 5.0], 1.2.6. map-type decay. + // | alloc | to | from | tofrom | release | delete + // ---------------------------------------------------------- + // alloc | alloc | alloc | alloc | alloc | release | delete + // to | alloc | to | alloc | to | release | delete + // from | alloc | alloc | from | from | release | delete + // tofrom | alloc | to | from | tofrom | release | delete + llvm::Value *LeftToFrom = MapperCGF.Builder.CreateAnd( + MapType, + MapperCGF.Builder.getInt64(MappableExprsHandler::OMP_MAP_TO | + MappableExprsHandler::OMP_MAP_FROM)); + llvm::BasicBlock *AllocBB = MapperCGF.createBasicBlock("omp.type.alloc"); + llvm::BasicBlock *AllocElseBB = + MapperCGF.createBasicBlock("omp.type.alloc.else"); + llvm::BasicBlock *ToBB = MapperCGF.createBasicBlock("omp.type.to"); + llvm::BasicBlock *ToElseBB = MapperCGF.createBasicBlock("omp.type.to.else"); + llvm::BasicBlock *FromBB = MapperCGF.createBasicBlock("omp.type.from"); + llvm::BasicBlock *EndBB = MapperCGF.createBasicBlock("omp.type.end"); + llvm::Value *IsAlloc = MapperCGF.Builder.CreateIsNull(LeftToFrom); + MapperCGF.Builder.CreateCondBr(IsAlloc, AllocBB, AllocElseBB); + // In case of alloc, clear OMP_MAP_TO and OMP_MAP_FROM. + MapperCGF.EmitBlock(AllocBB); + llvm::Value *AllocMapType = MapperCGF.Builder.CreateAnd( + MemberMapType, + MapperCGF.Builder.getInt64(~(MappableExprsHandler::OMP_MAP_TO | + MappableExprsHandler::OMP_MAP_FROM))); + MapperCGF.Builder.CreateBr(EndBB); + MapperCGF.EmitBlock(AllocElseBB); + llvm::Value *IsTo = MapperCGF.Builder.CreateICmpEQ( + LeftToFrom, + MapperCGF.Builder.getInt64(MappableExprsHandler::OMP_MAP_TO)); + MapperCGF.Builder.CreateCondBr(IsTo, ToBB, ToElseBB); + // In case of to, clear OMP_MAP_FROM. + MapperCGF.EmitBlock(ToBB); + llvm::Value *ToMapType = MapperCGF.Builder.CreateAnd( + MemberMapType, + MapperCGF.Builder.getInt64(~MappableExprsHandler::OMP_MAP_FROM)); + MapperCGF.Builder.CreateBr(EndBB); + MapperCGF.EmitBlock(ToElseBB); + llvm::Value *IsFrom = MapperCGF.Builder.CreateICmpEQ( + LeftToFrom, + MapperCGF.Builder.getInt64(MappableExprsHandler::OMP_MAP_FROM)); + MapperCGF.Builder.CreateCondBr(IsFrom, FromBB, EndBB); + // In case of from, clear OMP_MAP_TO. + MapperCGF.EmitBlock(FromBB); + llvm::Value *FromMapType = MapperCGF.Builder.CreateAnd( + MemberMapType, + MapperCGF.Builder.getInt64(~MappableExprsHandler::OMP_MAP_TO)); + // In case of tofrom, do nothing. + MapperCGF.EmitBlock(EndBB); + llvm::PHINode *CurMapType = + MapperCGF.Builder.CreatePHI(CGM.Int64Ty, 4, "omp.maptype"); + CurMapType->addIncoming(AllocMapType, AllocBB); + CurMapType->addIncoming(ToMapType, ToBB); + CurMapType->addIncoming(FromMapType, FromBB); + CurMapType->addIncoming(MemberMapType, ToElseBB); + + // TODO: call the corresponding mapper function if a user-defined mapper is + // associated with this map clause. + // Call the runtime API __tgt_push_mapper_component to fill up the runtime + // data structure. + llvm::Value *OffloadingArgs[] = {Handle, CurBaseArg, CurBeginArg, + CurSizeArg, CurMapType}; + MapperCGF.EmitRuntimeCall( + createRuntimeFunction(OMPRTL__tgt_push_mapper_component), + OffloadingArgs); + } + + // Update the pointer to point to the next element that needs to be mapped, + // and check whether we have mapped all elements. + llvm::Value *PtrNext = MapperCGF.Builder.CreateConstGEP1_32( + PtrPHI, /*Idx0=*/1, "omp.arraymap.next"); + PtrPHI->addIncoming(PtrNext, BodyBB); + llvm::Value *IsDone = + MapperCGF.Builder.CreateICmpEQ(PtrNext, PtrEnd, "omp.arraymap.isdone"); + llvm::BasicBlock *ExitBB = MapperCGF.createBasicBlock("omp.arraymap.exit"); + MapperCGF.Builder.CreateCondBr(IsDone, ExitBB, BodyBB); + + MapperCGF.EmitBlock(ExitBB); + // Emit array deletion if this is an array section and \p MapType indicates + // that deletion is required. + emitUDMapperArrayInitOrDel(MapperCGF, Handle, BaseIn, BeginIn, Size, MapType, + ElementSize, DoneBB, /*IsInit=*/false); + + // Emit the function exit block. + MapperCGF.EmitBlock(DoneBB, /*IsFinished=*/true); + MapperCGF.FinishFunction(); + UDMMap.try_emplace(D, Fn); + if (CGF) { + auto &Decls = FunctionUDMMap.FindAndConstruct(CGF->CurFn); + Decls.second.push_back(D); + } +} + +/// Emit the array initialization or deletion portion for user-defined mapper +/// code generation. First, it evaluates whether an array section is mapped and +/// whether the \a MapType instructs to delete this section. If \a IsInit is +/// true, and \a MapType indicates to not delete this array, array +/// initialization code is generated. If \a IsInit is false, and \a MapType +/// indicates to not this array, array deletion code is generated. +void CGOpenMPRuntime::emitUDMapperArrayInitOrDel( + CodeGenFunction &MapperCGF, llvm::Value *Handle, llvm::Value *Base, + llvm::Value *Begin, llvm::Value *Size, llvm::Value *MapType, + CharUnits ElementSize, llvm::BasicBlock *ExitBB, bool IsInit) { + StringRef Prefix = IsInit ? ".init" : ".del"; + + // Evaluate if this is an array section. + llvm::BasicBlock *IsDeleteBB = + MapperCGF.createBasicBlock("omp.array" + Prefix + ".evaldelete"); + llvm::BasicBlock *BodyBB = MapperCGF.createBasicBlock("omp.array" + Prefix); + llvm::Value *IsArray = MapperCGF.Builder.CreateICmpSGE( + Size, MapperCGF.Builder.getInt64(1), "omp.arrayinit.isarray"); + MapperCGF.Builder.CreateCondBr(IsArray, IsDeleteBB, ExitBB); + + // Evaluate if we are going to delete this section. + MapperCGF.EmitBlock(IsDeleteBB); + llvm::Value *DeleteBit = MapperCGF.Builder.CreateAnd( + MapType, + MapperCGF.Builder.getInt64(MappableExprsHandler::OMP_MAP_DELETE)); + llvm::Value *DeleteCond; + if (IsInit) { + DeleteCond = MapperCGF.Builder.CreateIsNull( + DeleteBit, "omp.array" + Prefix + ".delete"); + } else { + DeleteCond = MapperCGF.Builder.CreateIsNotNull( + DeleteBit, "omp.array" + Prefix + ".delete"); + } + MapperCGF.Builder.CreateCondBr(DeleteCond, BodyBB, ExitBB); + + MapperCGF.EmitBlock(BodyBB); + // Get the array size by multiplying element size and element number (i.e., \p + // Size). + llvm::Value *ArraySize = MapperCGF.Builder.CreateNUWMul( + Size, MapperCGF.Builder.getInt64(ElementSize.getQuantity())); + // Remove OMP_MAP_TO and OMP_MAP_FROM from the map type, so that it achieves + // memory allocation/deletion purpose only. + llvm::Value *MapTypeArg = MapperCGF.Builder.CreateAnd( + MapType, + MapperCGF.Builder.getInt64(~(MappableExprsHandler::OMP_MAP_TO | + MappableExprsHandler::OMP_MAP_FROM))); + // Call the runtime API __tgt_push_mapper_component to fill up the runtime + // data structure. + llvm::Value *OffloadingArgs[] = {Handle, Base, Begin, ArraySize, MapTypeArg}; + MapperCGF.EmitRuntimeCall( + createRuntimeFunction(OMPRTL__tgt_push_mapper_component), OffloadingArgs); +} + void CGOpenMPRuntime::emitTargetNumIterationsCall( CodeGenFunction &CGF, const OMPExecutableDirective &D, const Expr *Device, const llvm::function_ref(Member)) { if (Ctx->DeclMustBeEmitted(DRD)) Builder->EmitGlobal(DRD); + } else if (auto *DMD = dyn_cast(Member)) { + if (Ctx->DeclMustBeEmitted(DMD)) + Builder->EmitGlobal(DMD); } } } Index: test/OpenMP/declare_mapper_codegen.cpp =================================================================== --- test/OpenMP/declare_mapper_codegen.cpp +++ test/OpenMP/declare_mapper_codegen.cpp @@ -1,92 +1,414 @@ -///==========================================================================/// -// RUN: %clang_cc1 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s -// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s -// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s -// RUN: %clang_cc1 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s -// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s -// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s - -// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY0 %s -// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s -// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY0 %s -// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY0 %s -// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s -// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY0 %s - // SIMD-ONLY0-NOT: {{__kmpc|__tgt}} // expected-no-diagnostics #ifndef HEADER #define HEADER +///==========================================================================/// +// RUN: %clang_cc1 -DCK0 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm -femit-all-decls -disable-llvm-passes %s -o - | FileCheck --check-prefix CK0 --check-prefix CK0-64 %s +// RUN: %clang_cc1 -DCK0 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -femit-all-decls -disable-llvm-passes -o %t %s +// RUN: %clang_cc1 -DCK0 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -femit-all-decls -disable-llvm-passes -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix CK0 --check-prefix CK0-64 %s +// RUN: %clang_cc1 -DCK0 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm -femit-all-decls -disable-llvm-passes %s -o - | FileCheck --check-prefix CK0 --check-prefix CK0-32 %s +// RUN: %clang_cc1 -DCK0 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -femit-all-decls -disable-llvm-passes -o %t %s +// RUN: %clang_cc1 -DCK0 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -femit-all-decls -disable-llvm-passes -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix CK0 --check-prefix CK0-32 %s + +// RUN: %clang_cc1 -DCK0 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm -femit-all-decls -disable-llvm-passes %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -DCK0 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -femit-all-decls -disable-llvm-passes -o %t %s +// RUN: %clang_cc1 -DCK0 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -femit-all-decls -disable-llvm-passes -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -DCK0 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm -femit-all-decls -disable-llvm-passes %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -DCK0 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -femit-all-decls -disable-llvm-passes -o %t %s +// RUN: %clang_cc1 -DCK0 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -femit-all-decls -disable-llvm-passes -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s + +#ifdef CK0 + +// CK0-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}.region_id = weak constant i8 0 +// CK0-64: [[SIZES:@.+]] = {{.+}}constant [1 x i64] [i64 16] +// CK0-32: [[SIZES:@.+]] = {{.+}}constant [1 x i64] [i64 8] +// CK0: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 35] +// CK0-64: [[TSIZES:@.+]] = {{.+}}constant [1 x i64] [i64 16] +// CK0-32: [[TSIZES:@.+]] = {{.+}}constant [1 x i64] [i64 8] +// CK0: [[TTYPES:@.+]] = {{.+}}constant [1 x i64] [i64 33] +// CK0-64: [[FSIZES:@.+]] = {{.+}}constant [1 x i64] [i64 16] +// CK0-32: [[FSIZES:@.+]] = {{.+}}constant [1 x i64] [i64 8] +// CK0: [[FTYPES:@.+]] = {{.+}}constant [1 x i64] [i64 34] + class C { public: int a; + double *b; }; -#pragma omp declare mapper(id: C s) map(s.a) +#pragma omp declare mapper(id: C s) map(s.a, s.b[0:2]) -// CHECK-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l54.region_id = weak constant i8 0 +// CK0-LABEL: define {{.*}}void @.omp_mapper.{{.*}}C.id{{.*}}(i8*, i8*, i8*, i64, i64) +// CK0-DAG: store i8* %0, i8** [[HANDLEADDR:%[^,]+]] +// CK0-DAG: store i8* %1, i8** [[BPTRADDR:%[^,]+]] +// CK0-DAG: store i8* %2, i8** [[VPTRADDR:%[^,]+]] +// CK0-DAG: store i64 %3, i{{64|32}}* [[SIZEADDR:%[^,]+]] +// CK0-DAG: store i64 %4, i64* [[TYPEADDR:%[^,]+]] +// CK0-DAG: [[SIZE:%.+]] = load i64, i64* [[SIZEADDR]] +// CK0-DAG: [[TYPE:%.+]] = load i64, i64* [[TYPEADDR]] +// CK0-DAG: [[HANDLE:%.+]] = load i8*, i8** [[HANDLEADDR]] +// CK0-DAG: [[PTRBEGIN:%.+]] = bitcast i8** [[VPTRADDR]] to %class.C** +// CK0-DAG: [[PTREND:%.+]] = getelementptr %class.C*, %class.C** [[PTRBEGIN]], i64 [[SIZE]] +// CK0-DAG: [[BPTR:%.+]] = load i8*, i8** [[BPTRADDR]] +// CK0-DAG: [[BEGIN:%.+]] = load i8*, i8** [[VPTRADDR]] +// CK0: [[ISARRAY:%.+]] = icmp sge i64 [[SIZE]], 1 +// CK0: br i1 [[ISARRAY]], label %[[INITEVALDEL:[^,]+]], label %[[LHEAD:[^,]+]] -// CHECK: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4] -// CHECK: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 35] -// CHECK: [[TSIZES:@.+]] = {{.+}}constant [1 x i[[sz]]] [i[[sz]] 4] -// CHECK: [[TTYPES:@.+]] = {{.+}}constant [1 x i64] [i64 33] -// CHECK: [[FSIZES:@.+]] = {{.+}}constant [1 x i[[sz]]] [i[[sz]] 4] -// CHECK: [[FTYPES:@.+]] = {{.+}}constant [1 x i64] [i64 34] +// CK0: [[INITEVALDEL]] +// CK0: [[TYPEDEL:%.+]] = and i64 [[TYPE]], 8 +// CK0: [[ISNOTDEL:%.+]] = icmp eq i64 [[TYPEDEL]], 0 +// CK0: br i1 [[ISNOTDEL]], label %[[INIT:[^,]+]], label %[[LHEAD:[^,]+]] +// CK0: [[INIT]] +// CK0-64-DAG: [[ARRSIZE:%.+]] = mul nuw i64 [[SIZE]], 16 +// CK0-32-DAG: [[ARRSIZE:%.+]] = mul nuw i64 [[SIZE]], 8 +// CK0-DAG: [[ITYPE:%.+]] = and i64 [[TYPE]], -4 +// CK0: call void @__tgt_push_mapper_component(i8* [[HANDLE]], i8* [[BPTR]], i8* [[BEGIN]], i64 [[ARRSIZE]], i64 [[ITYPE]]) +// CK0: br label %[[LHEAD:[^,]+]] -// CHECK-LABEL: foo{{.*}}( +// CK0: [[LHEAD]] +// CK0: [[ISEMPTY:%.+]] = icmp eq %class.C** [[PTRBEGIN]], [[PTREND]] +// CK0: br i1 [[ISEMPTY]], label %[[DONE:[^,]+]], label %[[LBODY:[^,]+]] +// CK0: [[LBODY]] +// CK0: [[PTR:%.+]] = phi %class.C** [ [[PTRBEGIN]], %[[LHEAD]] ], [ [[PTRNEXT:%.+]], %[[LCORRECT:[^,]+]] ] +// CK0: [[OBJ:%.+]] = load %class.C*, %class.C** [[PTR]] +// CK0-DAG: [[ABEGIN:%.+]] = getelementptr inbounds %class.C, %class.C* [[OBJ]], i32 0, i32 0 +// CK0-DAG: [[BBEGIN:%.+]] = getelementptr inbounds %class.C, %class.C* [[OBJ]], i32 0, i32 1 +// CK0-DAG: [[BBEGIN2:%.+]] = getelementptr inbounds %class.C, %class.C* [[OBJ]], i32 0, i32 1 +// CK0-DAG: [[BARRBEGIN:%.+]] = load double*, double** [[BBEGIN2]] +// CK0-DAG: [[BARRBEGINGEP:%.+]] = getelementptr inbounds double, double* [[BARRBEGIN]], i[[sz:64|32]] 0 +// CK0-DAG: [[BEND:%.+]] = getelementptr double*, double** [[BBEGIN]], i32 1 +// CK0-DAG: [[ABEGINV:%.+]] = bitcast i32* [[ABEGIN]] to i8* +// CK0-DAG: [[BENDV:%.+]] = bitcast double** [[BEND]] to i8* +// CK0-DAG: [[ABEGINI:%.+]] = ptrtoint i8* [[ABEGINV]] to i64 +// CK0-DAG: [[BENDI:%.+]] = ptrtoint i8* [[BENDV]] to i64 +// CK0-DAG: [[CSIZE:%.+]] = sub i64 [[BENDI]], [[ABEGINI]] +// CK0-DAG: [[CUSIZE:%.+]] = sdiv exact i64 [[CSIZE]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64) +// CK0-DAG: [[BPTRADDR0BC:%.+]] = bitcast %class.C* [[OBJ]] to i8* +// CK0-DAG: [[PTRADDR0BC:%.+]] = bitcast i32* [[ABEGIN]] to i8* +// CK0-DAG: [[PRESIZE:%.+]] = call i64 @__tgt_mapper_num_components(i8* [[HANDLE]]) +// CK0-DAG: [[SHIPRESIZE:%.+]] = shl i64 [[PRESIZE]], 48 +// CK0-DAG: br label %[[MEMBER:[^,]+]] +// CK0-DAG: [[MEMBER]] +// CK0-DAG: br i1 true, label %[[LTYPE:[^,]+]], label %[[MEMBERCOM:[^,]+]] +// CK0-DAG: [[MEMBERCOM]] +// CK0-DAG: [[MEMBERCOMTYPE:%.+]] = add nuw i64 32, [[SHIPRESIZE]] +// CK0-DAG: br label %[[LTYPE]] +// CK0-DAG: [[LTYPE]] +// CK0-DAG: [[MEMBERTYPE:%.+]] = phi i64 [ 32, %[[MEMBER]] ], [ [[MEMBERCOMTYPE]], %[[MEMBERCOM]] ] +// CK0-DAG: [[TYPETF:%.+]] = and i64 [[TYPE]], 3 +// CK0-DAG: [[ISALLOC:%.+]] = icmp eq i64 [[TYPETF]], 0 +// CK0-DAG: br i1 [[ISALLOC]], label %[[ALLOC:[^,]+]], label %[[ALLOCELSE:[^,]+]] +// CK0-DAG: [[ALLOC]] +// CK0-DAG: [[ALLOCTYPE:%.+]] = and i64 [[MEMBERTYPE]], -4 +// CK0-DAG: br label %[[TYEND:[^,]+]] +// CK0-DAG: [[ALLOCELSE]] +// CK0-DAG: [[ISTO:%.+]] = icmp eq i64 [[TYPETF]], 1 +// CK0-DAG: br i1 [[ISTO]], label %[[TO:[^,]+]], label %[[TOELSE:[^,]+]] +// CK0-DAG: [[TO]] +// CK0-DAG: [[TOTYPE:%.+]] = and i64 [[MEMBERTYPE]], -3 +// CK0-DAG: br label %[[TYEND]] +// CK0-DAG: [[TOELSE]] +// CK0-DAG: [[ISFROM:%.+]] = icmp eq i64 [[TYPETF]], 2 +// CK0-DAG: br i1 [[ISFROM]], label %[[FROM:[^,]+]], label %[[TYEND]] +// CK0-DAG: [[FROM]] +// CK0-DAG: [[FROMTYPE:%.+]] = and i64 [[MEMBERTYPE]], -2 +// CK0-DAG: br label %[[TYEND]] +// CK0-DAG: [[TYEND]] +// CK0-DAG: [[PHITYPE0:%.+]] = phi i64 [ [[ALLOCTYPE]], %[[ALLOC]] ], [ [[TOTYPE]], %[[TO]] ], [ [[FROMTYPE]], %[[FROM]] ], [ [[MEMBERTYPE]], %[[TOELSE]] ] +// CK0: call void @__tgt_push_mapper_component(i8* [[HANDLE]], i8* [[BPTRADDR0BC]], i8* [[PTRADDR0BC]], i64 [[CUSIZE]], i64 [[PHITYPE0]]) +// CK0-DAG: [[BPTRADDR1BC:%.+]] = bitcast %class.C* [[OBJ]] to i8* +// CK0-DAG: [[PTRADDR1BC:%.+]] = bitcast i32* [[ABEGIN]] to i8* +// CK0-DAG: br label %[[MEMBER:[^,]+]] +// CK0-DAG: [[MEMBER]] +// CK0-DAG: br i1 false, label %[[LTYPE:[^,]+]], label %[[MEMBERCOM:[^,]+]] +// CK0-DAG: [[MEMBERCOM]] +// 281474976710659 == 0x1,000,000,003 +// CK0-DAG: [[MEMBERCOMTYPE:%.+]] = add nuw i64 281474976710659, [[SHIPRESIZE]] +// CK0-DAG: br label %[[LTYPE]] +// CK0-DAG: [[LTYPE]] +// CK0-DAG: [[MEMBERTYPE:%.+]] = phi i64 [ 281474976710659, %[[MEMBER]] ], [ [[MEMBERCOMTYPE]], %[[MEMBERCOM]] ] +// CK0-DAG: [[TYPETF:%.+]] = and i64 [[TYPE]], 3 +// CK0-DAG: [[ISALLOC:%.+]] = icmp eq i64 [[TYPETF]], 0 +// CK0-DAG: br i1 [[ISALLOC]], label %[[ALLOC:[^,]+]], label %[[ALLOCELSE:[^,]+]] +// CK0-DAG: [[ALLOC]] +// CK0-DAG: [[ALLOCTYPE:%.+]] = and i64 [[MEMBERTYPE]], -4 +// CK0-DAG: br label %[[TYEND:[^,]+]] +// CK0-DAG: [[ALLOCELSE]] +// CK0-DAG: [[ISTO:%.+]] = icmp eq i64 [[TYPETF]], 1 +// CK0-DAG: br i1 [[ISTO]], label %[[TO:[^,]+]], label %[[TOELSE:[^,]+]] +// CK0-DAG: [[TO]] +// CK0-DAG: [[TOTYPE:%.+]] = and i64 [[MEMBERTYPE]], -3 +// CK0-DAG: br label %[[TYEND]] +// CK0-DAG: [[TOELSE]] +// CK0-DAG: [[ISFROM:%.+]] = icmp eq i64 [[TYPETF]], 2 +// CK0-DAG: br i1 [[ISFROM]], label %[[FROM:[^,]+]], label %[[TYEND]] +// CK0-DAG: [[FROM]] +// CK0-DAG: [[FROMTYPE:%.+]] = and i64 [[MEMBERTYPE]], -2 +// CK0-DAG: br label %[[TYEND]] +// CK0-DAG: [[TYEND]] +// CK0-DAG: [[TYPE1:%.+]] = phi i64 [ [[ALLOCTYPE]], %[[ALLOC]] ], [ [[TOTYPE]], %[[TO]] ], [ [[FROMTYPE]], %[[FROM]] ], [ [[MEMBERTYPE]], %[[TOELSE]] ] +// CK0: call void @__tgt_push_mapper_component(i8* [[HANDLE]], i8* [[BPTRADDR1BC]], i8* [[PTRADDR1BC]], i64 4, i64 [[TYPE1]]) +// CK0-DAG: [[BPTRADDR2BC:%.+]] = bitcast double** [[BBEGIN]] to i8* +// CK0-DAG: [[PTRADDR2BC:%.+]] = bitcast double* [[BARRBEGINGEP]] to i8* +// CK0-DAG: br label %[[MEMBER:[^,]+]] +// CK0-DAG: [[MEMBER]] +// CK0-DAG: br i1 false, label %[[LTYPE:[^,]+]], label %[[MEMBERCOM:[^,]+]] +// CK0-DAG: [[MEMBERCOM]] +// 281474976710675 == 0x1,000,000,013 +// CK0-DAG: [[MEMBERCOMTYPE:%.+]] = add nuw i64 281474976710675, [[SHIPRESIZE]] +// CK0-DAG: br label %[[LTYPE]] +// CK0-DAG: [[LTYPE]] +// CK0-DAG: [[MEMBERTYPE:%.+]] = phi i64 [ 281474976710675, %[[MEMBER]] ], [ [[MEMBERCOMTYPE]], %[[MEMBERCOM]] ] +// CK0-DAG: [[TYPETF:%.+]] = and i64 [[TYPE]], 3 +// CK0-DAG: [[ISALLOC:%.+]] = icmp eq i64 [[TYPETF]], 0 +// CK0-DAG: br i1 [[ISALLOC]], label %[[ALLOC:[^,]+]], label %[[ALLOCELSE:[^,]+]] +// CK0-DAG: [[ALLOC]] +// CK0-DAG: [[ALLOCTYPE:%.+]] = and i64 [[MEMBERTYPE]], -4 +// CK0-DAG: br label %[[TYEND:[^,]+]] +// CK0-DAG: [[ALLOCELSE]] +// CK0-DAG: [[ISTO:%.+]] = icmp eq i64 [[TYPETF]], 1 +// CK0-DAG: br i1 [[ISTO]], label %[[TO:[^,]+]], label %[[TOELSE:[^,]+]] +// CK0-DAG: [[TO]] +// CK0-DAG: [[TOTYPE:%.+]] = and i64 [[MEMBERTYPE]], -3 +// CK0-DAG: br label %[[TYEND]] +// CK0-DAG: [[TOELSE]] +// CK0-DAG: [[ISFROM:%.+]] = icmp eq i64 [[TYPETF]], 2 +// CK0-DAG: br i1 [[ISFROM]], label %[[FROM:[^,]+]], label %[[TYEND]] +// CK0-DAG: [[FROM]] +// CK0-DAG: [[FROMTYPE:%.+]] = and i64 [[MEMBERTYPE]], -2 +// CK0-DAG: br label %[[TYEND]] +// CK0-DAG: [[TYEND]] +// CK0-DAG: [[TYPE2:%.+]] = phi i64 [ [[ALLOCTYPE]], %[[ALLOC]] ], [ [[TOTYPE]], %[[TO]] ], [ [[FROMTYPE]], %[[FROM]] ], [ [[MEMBERTYPE]], %[[TOELSE]] ] +// CK0: call void @__tgt_push_mapper_component(i8* [[HANDLE]], i8* [[BPTRADDR2BC]], i8* [[PTRADDR2BC]], i64 16, i64 [[TYPE2]]) +// CK0: [[PTRNEXT]] = getelementptr %class.C*, %class.C** [[PTR]], i32 1 +// CK0: [[ISDONE:%.+]] = icmp eq %class.C** [[PTRNEXT]], [[PTREND]] +// CK0: br i1 [[ISDONE]], label %[[LEXIT:[^,]+]], label %[[LBODY]] + +// CK0: [[LEXIT]] +// CK0: [[ISARRAY:%.+]] = icmp sge i64 [[SIZE]], 1 +// CK0: br i1 [[ISARRAY]], label %[[EVALDEL:[^,]+]], label %[[DONE]] +// CK0: [[EVALDEL]] +// CK0: [[TYPEDEL:%.+]] = and i64 [[TYPE]], 8 +// CK0: [[ISDEL:%.+]] = icmp ne i64 [[TYPEDEL]], 0 +// CK0: br i1 [[ISDEL]], label %[[DEL:[^,]+]], label %[[DONE]] +// CK0: [[DEL]] +// CK0-64-DAG: [[ARRSIZE:%.+]] = mul nuw i64 [[SIZE]], 16 +// CK0-32-DAG: [[ARRSIZE:%.+]] = mul nuw i64 [[SIZE]], 8 +// CK0-DAG: [[DTYPE:%.+]] = and i64 [[TYPE]], -4 +// CK0: call void @__tgt_push_mapper_component(i8* [[HANDLE]], i8* [[BPTR]], i8* [[BEGIN]], i64 [[ARRSIZE]], i64 [[DTYPE]]) +// CK0: br label %[[DONE]] +// CK0: [[DONE]] +// CK0: ret void + + +// CK0-LABEL: define {{.*}}void @{{.*}}foo{{.*}} void foo(int a){ int i = a; C c; c.a = a; - // CHECK-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}}) - // CHECK-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0 - // CHECK-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0 - // CHECK-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0 - // CHECK-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0 - // CHECK-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to %class.C** - // CHECK-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to %class.C** - // CHECK-DAG: store %class.C* [[VAL:%[^,]+]], %class.C** [[CBP1]] - // CHECK-DAG: store %class.C* [[VAL]], %class.C** [[CP1]] - // CHECK: call void [[KERNEL:@.+]](%class.C* [[VAL]]) + // CK0-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}}) + // CK0-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0 + // CK0-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0 + // CK0-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0 + // CK0-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0 + // CK0-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to %class.C** + // CK0-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to %class.C** + // CK0-DAG: store %class.C* [[VAL:%[^,]+]], %class.C** [[CBP1]] + // CK0-DAG: store %class.C* [[VAL]], %class.C** [[CP1]] + // CK0: call void [[KERNEL:@.+]](%class.C* [[VAL]]) #pragma omp target map(mapper(id),tofrom: c) { ++c.a; } - // CHECK-DAG: call void @__tgt_target_data_update(i64 -1, i32 1, i8** [[TGEPBP:%.+]], i8** [[TGEPP:%.+]], i[[sz]]* getelementptr {{.+}}[1 x i[[sz]]]* [[TSIZES]], i32 0, i32 0), {{.+}}getelementptr {{.+}}[1 x i64]* [[TTYPES]]{{.+}}) - // CHECK-DAG: [[TGEPBP]] = getelementptr inbounds {{.+}}[[TBP:%[^,]+]], i{{.+}} 0, i{{.+}} 0 - // CHECK-DAG: [[TGEPP]] = getelementptr inbounds {{.+}}[[TP:%[^,]+]], i{{.+}} 0, i{{.+}} 0 - // CHECK-DAG: [[TBP0:%.+]] = getelementptr inbounds {{.+}}[[TBP]], i{{.+}} 0, i{{.+}} 0 - // CHECK-DAG: [[TP0:%.+]] = getelementptr inbounds {{.+}}[[TP]], i{{.+}} 0, i{{.+}} 0 - // CHECK-DAG: [[TCBP0:%.+]] = bitcast i8** [[TBP0]] to %class.C** - // CHECK-DAG: [[TCP0:%.+]] = bitcast i8** [[TP0]] to %class.C** - // CHECK-DAG: store %class.C* [[VAL]], %class.C** [[TCBP0]] - // CHECK-DAG: store %class.C* [[VAL]], %class.C** [[TCP0]] + // CK0-DAG: call void @__tgt_target_data_update(i64 -1, i32 1, i8** [[TGEPBP:%.+]], i8** [[TGEPP:%.+]], i64* getelementptr {{.+}}[1 x i64]* [[TSIZES]], i32 0, i32 0), {{.+}}getelementptr {{.+}}[1 x i64]* [[TTYPES]]{{.+}}) + // CK0-DAG: [[TGEPBP]] = getelementptr inbounds {{.+}}[[TBP:%[^,]+]], i{{.+}} 0, i{{.+}} 0 + // CK0-DAG: [[TGEPP]] = getelementptr inbounds {{.+}}[[TP:%[^,]+]], i{{.+}} 0, i{{.+}} 0 + // CK0-DAG: [[TBP0:%.+]] = getelementptr inbounds {{.+}}[[TBP]], i{{.+}} 0, i{{.+}} 0 + // CK0-DAG: [[TP0:%.+]] = getelementptr inbounds {{.+}}[[TP]], i{{.+}} 0, i{{.+}} 0 + // CK0-DAG: [[TCBP0:%.+]] = bitcast i8** [[TBP0]] to %class.C** + // CK0-DAG: [[TCP0:%.+]] = bitcast i8** [[TP0]] to %class.C** + // CK0-DAG: store %class.C* [[VAL]], %class.C** [[TCBP0]] + // CK0-DAG: store %class.C* [[VAL]], %class.C** [[TCP0]] #pragma omp target update to(mapper(id): c) - // CHECK-DAG: call void @__tgt_target_data_update(i64 -1, i32 1, i8** [[FGEPBP:%.+]], i8** [[FGEPP:%.+]], i[[sz]]* getelementptr {{.+}}[1 x i[[sz]]]* [[FSIZES]], i32 0, i32 0), {{.+}}getelementptr {{.+}}[1 x i64]* [[FTYPES]]{{.+}}) - // CHECK-DAG: [[FGEPBP]] = getelementptr inbounds {{.+}}[[FBP:%[^,]+]], i{{.+}} 0, i{{.+}} 0 - // CHECK-DAG: [[FGEPP]] = getelementptr inbounds {{.+}}[[FP:%[^,]+]], i{{.+}} 0, i{{.+}} 0 - // CHECK-DAG: [[FBP0:%.+]] = getelementptr inbounds {{.+}}[[FBP]], i{{.+}} 0, i{{.+}} 0 - // CHECK-DAG: [[FP0:%.+]] = getelementptr inbounds {{.+}}[[FP]], i{{.+}} 0, i{{.+}} 0 - // CHECK-DAG: [[FCBP0:%.+]] = bitcast i8** [[FBP0]] to %class.C** - // CHECK-DAG: [[FCP0:%.+]] = bitcast i8** [[FP0]] to %class.C** - // CHECK-DAG: store %class.C* [[VAL]], %class.C** [[FCBP0]] - // CHECK-DAG: store %class.C* [[VAL]], %class.C** [[FCP0]] + // CK0-DAG: call void @__tgt_target_data_update(i64 -1, i32 1, i8** [[FGEPBP:%.+]], i8** [[FGEPP:%.+]], i64* getelementptr {{.+}}[1 x i64]* [[FSIZES]], i32 0, i32 0), {{.+}}getelementptr {{.+}}[1 x i64]* [[FTYPES]]{{.+}}) + // CK0-DAG: [[FGEPBP]] = getelementptr inbounds {{.+}}[[FBP:%[^,]+]], i{{.+}} 0, i{{.+}} 0 + // CK0-DAG: [[FGEPP]] = getelementptr inbounds {{.+}}[[FP:%[^,]+]], i{{.+}} 0, i{{.+}} 0 + // CK0-DAG: [[FBP0:%.+]] = getelementptr inbounds {{.+}}[[FBP]], i{{.+}} 0, i{{.+}} 0 + // CK0-DAG: [[FP0:%.+]] = getelementptr inbounds {{.+}}[[FP]], i{{.+}} 0, i{{.+}} 0 + // CK0-DAG: [[FCBP0:%.+]] = bitcast i8** [[FBP0]] to %class.C** + // CK0-DAG: [[FCP0:%.+]] = bitcast i8** [[FP0]] to %class.C** + // CK0-DAG: store %class.C* [[VAL]], %class.C** [[FCBP0]] + // CK0-DAG: store %class.C* [[VAL]], %class.C** [[FCP0]] #pragma omp target update from(mapper(id): c) } -// CHECK: define internal void [[KERNEL]](%class.C* {{.+}}[[ARG:%.+]]) -// CHECK: [[ADDR:%.+]] = alloca %class.C*, -// CHECK: store %class.C* [[ARG]], %class.C** [[ADDR]] -// CHECK: [[CADDR:%.+]] = load %class.C*, %class.C** [[ADDR]] -// CHECK: [[CAADDR:%.+]] = getelementptr inbounds %class.C, %class.C* [[CADDR]], i32 0, i32 0 -// CHECK: [[VAL:%[^,]+]] = load i32, i32* [[CAADDR]] -// CHECK: {{.+}} = add nsw i32 [[VAL]], 1 -// CHECK: } +// CK0: define internal void [[KERNEL]](%class.C* {{.+}}[[ARG:%.+]]) +// CK0: [[ADDR:%.+]] = alloca %class.C*, +// CK0: store %class.C* [[ARG]], %class.C** [[ADDR]] +// CK0: [[CADDR:%.+]] = load %class.C*, %class.C** [[ADDR]] +// CK0: [[CAADDR:%.+]] = getelementptr inbounds %class.C, %class.C* [[CADDR]], i32 0, i32 0 +// CK0: [[VAL:%[^,]+]] = load i32, i32* [[CAADDR]] +// CK0: {{.+}} = add nsw i32 [[VAL]], 1 +// CK0: } + +#endif + + +///==========================================================================/// +// RUN: %clang_cc1 -DCK1 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm -femit-all-decls -disable-llvm-passes %s -o - | FileCheck --check-prefix CK1 --check-prefix CK1-64 %s +// RUN: %clang_cc1 -DCK1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -femit-all-decls -disable-llvm-passes -o %t %s +// RUN: %clang_cc1 -DCK1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -femit-all-decls -disable-llvm-passes -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix CK1 --check-prefix CK1-64 %s +// RUN: %clang_cc1 -DCK1 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm -femit-all-decls -disable-llvm-passes %s -o - | FileCheck --check-prefix CK1 --check-prefix CK1-32 %s +// RUN: %clang_cc1 -DCK1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -femit-all-decls -disable-llvm-passes -o %t %s +// RUN: %clang_cc1 -DCK1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -femit-all-decls -disable-llvm-passes -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix CK1 --check-prefix CK1-32 %s + +// RUN: %clang_cc1 -DCK1 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm -femit-all-decls -disable-llvm-passes %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -DCK1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -femit-all-decls -disable-llvm-passes -o %t %s +// RUN: %clang_cc1 -DCK1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -femit-all-decls -disable-llvm-passes -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -DCK1 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm -femit-all-decls -disable-llvm-passes %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s +// RUN: %clang_cc1 -DCK1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -femit-all-decls -disable-llvm-passes -o %t %s +// RUN: %clang_cc1 -DCK1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -femit-all-decls -disable-llvm-passes -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s + +#ifdef CK1 + +template +class C { +public: + T a; +}; + +#pragma omp declare mapper(id: C s) map(s.a) + +// CK1-LABEL: define {{.*}}void @.omp_mapper.{{.*}}C{{.*}}.id{{.*}}(i8*, i8*, i8*, i64, i64) +// CK1-DAG: store i8* %0, i8** [[HANDLEADDR:%[^,]+]] +// CK1-DAG: store i8* %1, i8** [[BPTRADDR:%[^,]+]] +// CK1-DAG: store i8* %2, i8** [[VPTRADDR:%[^,]+]] +// CK1-DAG: store i64 %3, i{{64|32}}* [[SIZEADDR:%[^,]+]] +// CK1-DAG: store i64 %4, i64* [[TYPEADDR:%[^,]+]] +// CK1-DAG: [[SIZE:%.+]] = load i64, i64* [[SIZEADDR]] +// CK1-DAG: [[TYPE:%.+]] = load i64, i64* [[TYPEADDR]] +// CK1-DAG: [[HANDLE:%.+]] = load i8*, i8** [[HANDLEADDR]] +// CK1-DAG: [[PTRBEGIN:%.+]] = bitcast i8** [[VPTRADDR]] to %class.C** +// CK1-DAG: [[PTREND:%.+]] = getelementptr %class.C*, %class.C** [[PTRBEGIN]], i64 [[SIZE]] +// CK1-DAG: [[BPTR:%.+]] = load i8*, i8** [[BPTRADDR]] +// CK1-DAG: [[BEGIN:%.+]] = load i8*, i8** [[VPTRADDR]] +// CK1: [[ISARRAY:%.+]] = icmp sge i64 [[SIZE]], 1 +// CK1: br i1 [[ISARRAY]], label %[[INITEVALDEL:[^,]+]], label %[[LHEAD:[^,]+]] + +// CK1: [[INITEVALDEL]] +// CK1: [[TYPEDEL:%.+]] = and i64 [[TYPE]], 8 +// CK1: [[ISNOTDEL:%.+]] = icmp eq i64 [[TYPEDEL]], 0 +// CK1: br i1 [[ISNOTDEL]], label %[[INIT:[^,]+]], label %[[LHEAD:[^,]+]] +// CK1: [[INIT]] +// CK1-DAG: [[ARRSIZE:%.+]] = mul nuw i64 [[SIZE]], 4 +// CK1-DAG: [[ITYPE:%.+]] = and i64 [[TYPE]], -4 +// CK1: call void @__tgt_push_mapper_component(i8* [[HANDLE]], i8* [[BPTR]], i8* [[BEGIN]], i64 [[ARRSIZE]], i64 [[ITYPE]]) +// CK1: br label %[[LHEAD:[^,]+]] + +// CK1: [[LHEAD]] +// CK1: [[ISEMPTY:%.+]] = icmp eq %class.C** [[PTRBEGIN]], [[PTREND]] +// CK1: br i1 [[ISEMPTY]], label %[[DONE:[^,]+]], label %[[LBODY:[^,]+]] +// CK1: [[LBODY]] +// CK1: [[PTR:%.+]] = phi %class.C** [ [[PTRBEGIN]], %[[LHEAD]] ], [ [[PTRNEXT:%.+]], %[[LCORRECT:[^,]+]] ] +// CK1: [[OBJ:%.+]] = load %class.C*, %class.C** [[PTR]] +// CK1-DAG: [[ABEGIN:%.+]] = getelementptr inbounds %class.C, %class.C* [[OBJ]], i32 0, i32 0 +// CK1-DAG: [[AEND:%.+]] = getelementptr i32, i32* [[ABEGIN]], i32 1 +// CK1-DAG: [[ABEGINV:%.+]] = bitcast i32* [[ABEGIN]] to i8* +// CK1-DAG: [[AENDV:%.+]] = bitcast i32* [[AEND]] to i8* +// CK1-DAG: [[ABEGINI:%.+]] = ptrtoint i8* [[ABEGINV]] to i64 +// CK1-DAG: [[AENDI:%.+]] = ptrtoint i8* [[AENDV]] to i64 +// CK1-DAG: [[CSIZE:%.+]] = sub i64 [[AENDI]], [[ABEGINI]] +// CK1-DAG: [[CUSIZE:%.+]] = sdiv exact i64 [[CSIZE]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64) +// CK1-DAG: [[BPTRADDR0BC:%.+]] = bitcast %class.C* [[OBJ]] to i8* +// CK1-DAG: [[PTRADDR0BC:%.+]] = bitcast i32* [[ABEGIN]] to i8* +// CK1-DAG: [[PRESIZE:%.+]] = call i64 @__tgt_mapper_num_components(i8* [[HANDLE]]) +// CK1-DAG: [[SHIPRESIZE:%.+]] = shl i64 [[PRESIZE]], 48 +// CK1-DAG: br label %[[MEMBER:[^,]+]] +// CK1-DAG: [[MEMBER]] +// CK1-DAG: br i1 true, label %[[LTYPE:[^,]+]], label %[[MEMBERCOM:[^,]+]] +// CK1-DAG: [[MEMBERCOM]] +// CK1-DAG: [[MEMBERCOMTYPE:%.+]] = add nuw i64 32, [[SHIPRESIZE]] +// CK1-DAG: br label %[[LTYPE]] +// CK1-DAG: [[LTYPE]] +// CK1-DAG: [[MEMBERTYPE:%.+]] = phi i64 [ 32, %[[MEMBER]] ], [ [[MEMBERCOMTYPE]], %[[MEMBERCOM]] ] +// CK1-DAG: [[TYPETF:%.+]] = and i64 [[TYPE]], 3 +// CK1-DAG: [[ISALLOC:%.+]] = icmp eq i64 [[TYPETF]], 0 +// CK1-DAG: br i1 [[ISALLOC]], label %[[ALLOC:[^,]+]], label %[[ALLOCELSE:[^,]+]] +// CK1-DAG: [[ALLOC]] +// CK1-DAG: [[ALLOCTYPE:%.+]] = and i64 [[MEMBERTYPE]], -4 +// CK1-DAG: br label %[[TYEND:[^,]+]] +// CK1-DAG: [[ALLOCELSE]] +// CK1-DAG: [[ISTO:%.+]] = icmp eq i64 [[TYPETF]], 1 +// CK1-DAG: br i1 [[ISTO]], label %[[TO:[^,]+]], label %[[TOELSE:[^,]+]] +// CK1-DAG: [[TO]] +// CK1-DAG: [[TOTYPE:%.+]] = and i64 [[MEMBERTYPE]], -3 +// CK1-DAG: br label %[[TYEND]] +// CK1-DAG: [[TOELSE]] +// CK1-DAG: [[ISFROM:%.+]] = icmp eq i64 [[TYPETF]], 2 +// CK1-DAG: br i1 [[ISFROM]], label %[[FROM:[^,]+]], label %[[TYEND]] +// CK1-DAG: [[FROM]] +// CK1-DAG: [[FROMTYPE:%.+]] = and i64 [[MEMBERTYPE]], -2 +// CK1-DAG: br label %[[TYEND]] +// CK1-DAG: [[TYEND]] +// CK1-DAG: [[TYPE0:%.+]] = phi i64 [ [[ALLOCTYPE]], %[[ALLOC]] ], [ [[TOTYPE]], %[[TO]] ], [ [[FROMTYPE]], %[[FROM]] ], [ [[MEMBERTYPE]], %[[TOELSE]] ] +// CK1-64: call void @__tgt_push_mapper_component(i8* [[HANDLE]], i8* [[BPTRADDR0BC]], i8* [[PTRADDR0BC]], i64 [[CUSIZE]], i64 [[TYPE0]]) +// CK1-DAG: [[BPTRADDR1BC:%.+]] = bitcast %class.C* [[OBJ]] to i8* +// CK1-DAG: [[PTRADDR1BC:%.+]] = bitcast i32* [[ABEGIN]] to i8* +// CK1-DAG: br label %[[MEMBER:[^,]+]] +// CK1-DAG: [[MEMBER]] +// CK1-DAG: br i1 false, label %[[LTYPE:[^,]+]], label %[[MEMBERCOM:[^,]+]] +// CK1-DAG: [[MEMBERCOM]] +// 281474976710659 == 0x1,000,000,003 +// CK1-DAG: [[MEMBERCOMTYPE:%.+]] = add nuw i64 281474976710659, [[SHIPRESIZE]] +// CK1-DAG: br label %[[LTYPE]] +// CK1-DAG: [[LTYPE]] +// CK1-DAG: [[MEMBERTYPE:%.+]] = phi i64 [ 281474976710659, %[[MEMBER]] ], [ [[MEMBERCOMTYPE]], %[[MEMBERCOM]] ] +// CK1-DAG: [[TYPETF:%.+]] = and i64 [[TYPE]], 3 +// CK1-DAG: [[ISALLOC:%.+]] = icmp eq i64 [[TYPETF]], 0 +// CK1-DAG: br i1 [[ISALLOC]], label %[[ALLOC:[^,]+]], label %[[ALLOCELSE:[^,]+]] +// CK1-DAG: [[ALLOC]] +// CK1-DAG: [[ALLOCTYPE:%.+]] = and i64 [[MEMBERTYPE]], -4 +// CK1-DAG: br label %[[TYEND:[^,]+]] +// CK1-DAG: [[ALLOCELSE]] +// CK1-DAG: [[ISTO:%.+]] = icmp eq i64 [[TYPETF]], 1 +// CK1-DAG: br i1 [[ISTO]], label %[[TO:[^,]+]], label %[[TOELSE:[^,]+]] +// CK1-DAG: [[TO]] +// CK1-DAG: [[TOTYPE:%.+]] = and i64 [[MEMBERTYPE]], -3 +// CK1-DAG: br label %[[TYEND]] +// CK1-DAG: [[TOELSE]] +// CK1-DAG: [[ISFROM:%.+]] = icmp eq i64 [[TYPETF]], 2 +// CK1-DAG: br i1 [[ISFROM]], label %[[FROM:[^,]+]], label %[[TYEND]] +// CK1-DAG: [[FROM]] +// CK1-DAG: [[FROMTYPE:%.+]] = and i64 [[MEMBERTYPE]], -2 +// CK1-DAG: br label %[[TYEND]] +// CK1-DAG: [[TYEND]] +// CK1-DAG: [[TYPE1:%.+]] = phi i64 [ [[ALLOCTYPE]], %[[ALLOC]] ], [ [[TOTYPE]], %[[TO]] ], [ [[FROMTYPE]], %[[FROM]] ], [ [[MEMBERTYPE]], %[[TOELSE]] ] +// CK1: call void @__tgt_push_mapper_component(i8* [[HANDLE]], i8* [[BPTRADDR1BC]], i8* [[PTRADDR1BC]], i64 4, i64 [[TYPE1]]) +// CK1: [[PTRNEXT]] = getelementptr %class.C*, %class.C** [[PTR]], i32 1 +// CK1: [[ISDONE:%.+]] = icmp eq %class.C** [[PTRNEXT]], [[PTREND]] +// CK1: br i1 [[ISDONE]], label %[[LEXIT:[^,]+]], label %[[LBODY]] + +// CK1: [[LEXIT]] +// CK1: [[ISARRAY:%.+]] = icmp sge i64 [[SIZE]], 1 +// CK1: br i1 [[ISARRAY]], label %[[EVALDEL:[^,]+]], label %[[DONE]] +// CK1: [[EVALDEL]] +// CK1: [[TYPEDEL:%.+]] = and i64 [[TYPE]], 8 +// CK1: [[ISDEL:%.+]] = icmp ne i64 [[TYPEDEL]], 0 +// CK1: br i1 [[ISDEL]], label %[[DEL:[^,]+]], label %[[DONE]] +// CK1: [[DEL]] +// CK1-DAG: [[ARRSIZE:%.+]] = mul nuw i64 [[SIZE]], 4 +// CK1-DAG: [[DTYPE:%.+]] = and i64 [[TYPE]], -4 +// CK1: call void @__tgt_push_mapper_component(i8* [[HANDLE]], i8* [[BPTR]], i8* [[BEGIN]], i64 [[ARRSIZE]], i64 [[DTYPE]]) +// CK1: br label %[[DONE]] +// CK1: [[DONE]] +// CK1: ret void + +#endif #endif