Index: include/clang/Basic/Builtins.h =================================================================== --- include/clang/Basic/Builtins.h +++ include/clang/Basic/Builtins.h @@ -36,7 +36,7 @@ CXX_LANG = 0x4, // builtin for cplusplus only. OBJC_LANG = 0x8, // builtin for objective-c and objective-c++ MS_LANG = 0x10, // builtin requires MS mode. - OCLC_LANG = 0x20, // builtin for OpenCL C only. + OCLC20_LANG = 0x20, // builtin for OpenCL C only. ALL_LANGUAGES = C_LANG | CXX_LANG | OBJC_LANG, // builtin for all languages. ALL_GNU_LANGUAGES = ALL_LANGUAGES | GNU_LANG, // builtin requires GNU mode. ALL_MS_LANGUAGES = ALL_LANGUAGES | MS_LANG // builtin requires MS mode. Index: include/clang/Basic/Builtins.def =================================================================== --- include/clang/Basic/Builtins.def +++ include/clang/Basic/Builtins.def @@ -1281,34 +1281,40 @@ // OpenCL v2.0 s6.13.16, s9.17.3.5 - Pipe functions. // We need the generic prototype, since the packet type could be anything. -LANGBUILTIN(read_pipe, "i.", "tn", OCLC_LANG) -LANGBUILTIN(write_pipe, "i.", "tn", OCLC_LANG) +LANGBUILTIN(read_pipe, "i.", "tn", OCLC20_LANG) +LANGBUILTIN(write_pipe, "i.", "tn", OCLC20_LANG) -LANGBUILTIN(reserve_read_pipe, "i.", "tn", OCLC_LANG) -LANGBUILTIN(reserve_write_pipe, "i.", "tn", OCLC_LANG) +LANGBUILTIN(reserve_read_pipe, "i.", "tn", OCLC20_LANG) +LANGBUILTIN(reserve_write_pipe, "i.", "tn", OCLC20_LANG) -LANGBUILTIN(commit_write_pipe, "v.", "tn", OCLC_LANG) -LANGBUILTIN(commit_read_pipe, "v.", "tn", OCLC_LANG) +LANGBUILTIN(commit_write_pipe, "v.", "tn", OCLC20_LANG) +LANGBUILTIN(commit_read_pipe, "v.", "tn", OCLC20_LANG) -LANGBUILTIN(sub_group_reserve_read_pipe, "i.", "tn", OCLC_LANG) -LANGBUILTIN(sub_group_reserve_write_pipe, "i.", "tn", OCLC_LANG) +LANGBUILTIN(sub_group_reserve_read_pipe, "i.", "tn", OCLC20_LANG) +LANGBUILTIN(sub_group_reserve_write_pipe, "i.", "tn", OCLC20_LANG) -LANGBUILTIN(sub_group_commit_read_pipe, "v.", "tn", OCLC_LANG) -LANGBUILTIN(sub_group_commit_write_pipe, "v.", "tn", OCLC_LANG) +LANGBUILTIN(sub_group_commit_read_pipe, "v.", "tn", OCLC20_LANG) +LANGBUILTIN(sub_group_commit_write_pipe, "v.", "tn", OCLC20_LANG) -LANGBUILTIN(work_group_reserve_read_pipe, "i.", "tn", OCLC_LANG) -LANGBUILTIN(work_group_reserve_write_pipe, "i.", "tn", OCLC_LANG) +LANGBUILTIN(work_group_reserve_read_pipe, "i.", "tn", OCLC20_LANG) +LANGBUILTIN(work_group_reserve_write_pipe, "i.", "tn", OCLC20_LANG) -LANGBUILTIN(work_group_commit_read_pipe, "v.", "tn", OCLC_LANG) -LANGBUILTIN(work_group_commit_write_pipe, "v.", "tn", OCLC_LANG) +LANGBUILTIN(work_group_commit_read_pipe, "v.", "tn", OCLC20_LANG) +LANGBUILTIN(work_group_commit_write_pipe, "v.", "tn", OCLC20_LANG) -LANGBUILTIN(get_pipe_num_packets, "Ui.", "tn", OCLC_LANG) -LANGBUILTIN(get_pipe_max_packets, "Ui.", "tn", OCLC_LANG) +LANGBUILTIN(get_pipe_num_packets, "Ui.", "tn", OCLC20_LANG) +LANGBUILTIN(get_pipe_max_packets, "Ui.", "tn", OCLC20_LANG) + +// OpenCL v2.0 s6.13.17 - Enqueue kernel functions. +// Custom builtin check allows to perform special check of passed block arguments. +LANGBUILTIN(enqueue_kernel, "i.", "tn", OCLC20_LANG) +LANGBUILTIN(get_kernel_work_group_size, "i.", "tn", OCLC20_LANG) +LANGBUILTIN(get_kernel_preferred_work_group_size_multiple, "i.", "tn", OCLC20_LANG) // OpenCL v2.0 s6.13.9 - Address space qualifier functions. -LANGBUILTIN(to_global, "v*v*", "tn", OCLC_LANG) -LANGBUILTIN(to_local, "v*v*", "tn", OCLC_LANG) -LANGBUILTIN(to_private, "v*v*", "tn", OCLC_LANG) +LANGBUILTIN(to_global, "v*v*", "tn", OCLC20_LANG) +LANGBUILTIN(to_local, "v*v*", "tn", OCLC20_LANG) +LANGBUILTIN(to_private, "v*v*", "tn", OCLC20_LANG) #undef BUILTIN #undef LIBBUILTIN Index: include/clang/Basic/DiagnosticSemaKinds.td =================================================================== --- include/clang/Basic/DiagnosticSemaKinds.td +++ include/clang/Basic/DiagnosticSemaKinds.td @@ -7856,8 +7856,6 @@ def warn_opencl_attr_deprecated_ignored : Warning < "%0 attribute is deprecated and ignored in OpenCL version %1">, InGroup; -def err_opencl_builtin_requires_version : Error< - "%0 requires OpenCL version %1%select{| or above}2">; // OpenCL v2.0 s6.13.6 -- Builtin Pipe Functions def err_opencl_builtin_pipe_first_arg : Error< @@ -7894,6 +7892,18 @@ "invalid number of arguments to function: %0">; def err_opencl_builtin_to_addr_invalid_arg : Error< "invalid argument %0 to function: %1, expecting a generic pointer argument">; + +// OpenCL v2.0 s6.13.17 Enqueue kernel restrictions. +def err_opencl_enqueue_kernel_incorrect_args : Error< + "illegal call to enqueue_kernel, incorrect argument types">; +def err_opencl_enqueue_kernel_expected_type : Error< + "illegal call to enqueue_kernel, expected %0 argument type">; +def err_opencl_enqueue_kernel_local_size_args : Error< + "mismatch in number of block parameters and local size arguments passed">; +def err_opencl_enqueue_kernel_invalid_local_size_type : Error< + "local memory sizes need to be specified as uint">; +def err_opencl_enqueue_kernel_blocks_non_local_void_args : Error< + "blocks used in device side enqueue are expected to have parameters of type 'local void*'">; } // end of sema category let CategoryName = "OpenMP Issue" in { Index: lib/Basic/Builtins.cpp =================================================================== --- lib/Basic/Builtins.cpp +++ lib/Basic/Builtins.cpp @@ -69,7 +69,8 @@ bool MSModeUnsupported = !LangOpts.MicrosoftExt && (BuiltinInfo.Langs & MS_LANG); bool ObjCUnsupported = !LangOpts.ObjC1 && BuiltinInfo.Langs == OBJC_LANG; - bool OclCUnsupported = !LangOpts.OpenCL && BuiltinInfo.Langs == OCLC_LANG; + bool OclCUnsupported = LangOpts.OpenCLVersion != 200 && + BuiltinInfo.Langs == OCLC20_LANG; return !BuiltinsUnsupported && !MathBuiltinsUnsupported && !OclCUnsupported && !GnuModeUnsupported && !MSModeUnsupported && !ObjCUnsupported; } Index: lib/CodeGen/CGBuiltin.cpp =================================================================== --- lib/CodeGen/CGBuiltin.cpp +++ lib/CodeGen/CGBuiltin.cpp @@ -2071,7 +2071,7 @@ return RValue::get( Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name), {Arg0, Arg1})); } - // OpenCL v2.0 s6.13.16 ,s9.17.3.5 - Built-in pipe commit read and write + // OpenCL v2.0 s6.13.16, s9.17.3.5 - Built-in pipe commit read and write // functions case Builtin::BIcommit_read_pipe: case Builtin::BIcommit_write_pipe: @@ -2147,6 +2147,132 @@ ConvertType(E->getType()))); } + // OpenCL v2.0, s6.13.17 - Enqueue kernel function. + // It contains four different overload formats specified in Table 6.13.17.1. + case Builtin::BIenqueue_kernel: { + StringRef Name; // Generated function call name + unsigned NumArgs = E->getNumArgs(); + + llvm::Type *QueueTy = ConvertType(getContext().OCLQueueTy); + llvm::Type *RangeTy = ConvertType(getContext().OCLNDRangeTy); + + llvm::Value *Queue = EmitScalarExpr(E->getArg(0)); + llvm::Value *Flags = EmitScalarExpr(E->getArg(1)); + llvm::Value *Range = EmitScalarExpr(E->getArg(2)); + + if (NumArgs == 4) { + // The most basic form of the call with parameters: + // queue_t, kernel_enqueue_flags_t, ndrange_t, block(void) + Name = "__enqueue_kernel_basic"; + llvm::Type *ArgTys[] = {QueueTy, Int32Ty, RangeTy, Int8PtrTy}; + llvm::FunctionType *FTy = llvm::FunctionType::get( + Int32Ty, llvm::ArrayRef(ArgTys, 4), false); + + llvm::Value *Block = + Builder.CreateBitCast(EmitScalarExpr(E->getArg(3)), Int8PtrTy); + + return RValue::get(Builder.CreateCall( + CGM.CreateRuntimeFunction(FTy, Name), {Queue, Flags, Range, Block})); + } + // Could have events and/or vaargs. + if (NumArgs >= 5) { + if (E->getArg(3)->getType().getTypePtr()->isBlockPointerType()) { + // No events passed, but has variadic arguments. + Name = "__enqueue_kernel_vaargs"; + llvm::Value *Block = + Builder.CreateBitCast(EmitScalarExpr(E->getArg(3)), Int8PtrTy); + // Create a vector of the arguments, as well as a constant value to + // express to the runtime the number of variadic arguments. + std::vector Args{Queue, Flags, Range, Block, + ConstantInt::get(IntTy, NumArgs - 4)}; + std::vector ArgTys = {QueueTy, IntTy, RangeTy, Int8PtrTy, + IntTy}; + + // Add the variadics. + for (unsigned i = 4; i < NumArgs; ++i) { + Args.push_back(EmitScalarExpr(E->getArg(i))); + } + + llvm::FunctionType *FTy = llvm::FunctionType::get( + Int32Ty, llvm::ArrayRef(ArgTys), true); + return RValue::get( + Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name), + llvm::ArrayRef(Args))); + } + // Any calls now have event arguments passed. + if (NumArgs >= 7) { + llvm::Type *EventTy = ConvertType(getContext().OCLClkEventTy); + unsigned AS4 = + E->getArg(4)->getType()->getPointeeType().getAddressSpace(); + llvm::Type *EventPtrAS4Ty = + EventTy->getPointerTo(CGM.getContext().getTargetAddressSpace(AS4)); + unsigned AS5 = + E->getArg(5)->getType()->getPointeeType().getAddressSpace(); + llvm::Type *EventPtrAS5Ty = + EventTy->getPointerTo(CGM.getContext().getTargetAddressSpace(AS5)); + + llvm::Value *NumEvents = EmitScalarExpr(E->getArg(3)); + llvm::Value *EventList = EmitScalarExpr(E->getArg(4)); + llvm::Value *ClkEvent = EmitScalarExpr(E->getArg(5)); + llvm::Value *Block = + Builder.CreateBitCast(EmitScalarExpr(E->getArg(6)), Int8PtrTy); + + std::vector ArgTys = { + QueueTy, Int32Ty, RangeTy, Int32Ty, + EventPtrAS4Ty, EventPtrAS5Ty, Int8PtrTy}; + std::vector Args{Queue, Flags, Range, NumEvents, + EventList, ClkEvent, Block}; + + if (NumArgs == 7) { + // Has events but no variadics. + Name = "__enqueue_kernel_basic_events"; + llvm::FunctionType *FTy = llvm::FunctionType::get( + Int32Ty, llvm::ArrayRef(ArgTys), false); + return RValue::get( + Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name), + llvm::ArrayRef(Args))); + } else { + // Has event info and variadics + + // Pass the number of variadics to the runtime function too. + Args.push_back(ConstantInt::get(Int32Ty, NumArgs - 7)); + ArgTys.push_back(Int32Ty); + Name = "__enqueue_kernel_events_vaargs"; + + // Add the variadics. + for (unsigned i = 7; i < NumArgs; ++i) { + Args.push_back(EmitScalarExpr(E->getArg(i))); + } + llvm::FunctionType *FTy = llvm::FunctionType::get( + Int32Ty, llvm::ArrayRef(ArgTys), true); + return RValue::get( + Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name), + llvm::ArrayRef(Args))); + } + } + } + llvm_unreachable("Unhandled enqueue_kernel signature"); + } + // OpenCL v2.0 s6.13.17.6 - Kernel query functions need bitcast of block + // parameter. + case Builtin::BIget_kernel_work_group_size: { + Value *Arg = EmitScalarExpr(E->getArg(0)); + Arg = Builder.CreateBitCast(Arg, Int8PtrTy); + return RValue::get( + Builder.CreateCall(CGM.CreateRuntimeFunction( + llvm::FunctionType::get(IntTy, Int8PtrTy, false), + "__get_kernel_work_group_size_impl"), + Arg)); + } + case Builtin::BIget_kernel_preferred_work_group_size_multiple: { + Value *Arg = EmitScalarExpr(E->getArg(0)); + Arg = Builder.CreateBitCast(Arg, Int8PtrTy); + return RValue::get(Builder.CreateCall( + CGM.CreateRuntimeFunction( + llvm::FunctionType::get(IntTy, Int8PtrTy, false), + "__get_kernel_preferred_work_group_multiple_impl"), + Arg)); + } case Builtin::BIprintf: if (getLangOpts().CUDA && getLangOpts().CUDAIsDevice) return EmitCUDADevicePrintfCallExpr(E, ReturnValue); Index: lib/Sema/SemaChecking.cpp =================================================================== --- lib/Sema/SemaChecking.cpp +++ lib/Sema/SemaChecking.cpp @@ -71,6 +71,240 @@ << call->getArg(1)->getSourceRange(); } +static inline bool isBlockPointer(Expr *Arg) { + return Arg->getType().getTypePtr()->isBlockPointerType(); +} + +/// OpenCL C v2.0, s6.13.17.2 - Checks that the block parameters are all local +/// void*, which is a requirement of device side enqueue. +static bool checkBlockArgs(Sema &S, Expr *BlockArg) { + const BlockPointerType *BPT = + cast(BlockArg->getType().getCanonicalType()); + ArrayRef Params = + BPT->getPointeeType()->getAs()->getParamTypes(); + bool IllegalParams = false; + unsigned ArgCounter = 0; + + // Iterate through the block parameters until either one is found that is not + // a local void*, or the block is valid. + for (ArrayRef::iterator I = Params.begin(), E = Params.end(); + I != E; ++I, ++ArgCounter) { + const Type *ParamType = I->getTypePtr(); + if (!ParamType->isPointerType()) { + IllegalParams = true; + break; + } + QualType PointeeType = cast(ParamType)->getPointeeType(); + if (!PointeeType.getTypePtr()->isVoidType()) { + IllegalParams = true; + break; + } + Qualifiers ArgQual = PointeeType.getQualifiers(); + if (ArgQual.getAddressSpace() != LangAS::opencl_local) { + IllegalParams = true; + break; + } + } + if (IllegalParams) { + // Get the location of the error. If a block literal has been passed + // (BlockExpr) then we can point straight to the offending argument, + // else we just point to the variable reference. + SourceLocation ErrorLoc; + if (isa(BlockArg)) { + BlockDecl *BD = cast(BlockArg)->getBlockDecl(); + ErrorLoc = BD->getParamDecl(ArgCounter)->getLocStart(); + } else if (isa(BlockArg)) { + ErrorLoc = cast(BlockArg)->getLocStart(); + } + S.Diag(ErrorLoc, + diag::err_opencl_enqueue_kernel_blocks_non_local_void_args); + } + + return IllegalParams; +} + +/// OpenCL C v2.0, s6.13.17.6 - Check the argument to the +/// get_kernel_work_group_size +/// and get_kernel_preferred_work_group_size_multiple builtin functions. +static bool SemaOpenCLBuiltinKernelWorkGroupSize(Sema &S, CallExpr *TheCall) { + if (checkArgCount(S, TheCall, 1)) + return true; + + Expr *BlockArg = TheCall->getArg(0); + if (!isBlockPointer(BlockArg)) { + S.Diag(BlockArg->getLocStart(), + diag::err_opencl_enqueue_kernel_expected_type) << "block"; + return true; + } else + return checkBlockArgs(S, BlockArg); +} + +static bool checkForLocalSizeArgs(Sema &S, CallExpr *TheCall, unsigned Start, + unsigned End) { + for (unsigned i = Start; i < End; ++i) + if (!TheCall->getArg(i)->getType().getTypePtr()->isIntegerType()) + return false; + return true; +} + +/// OpenCL v2.0, s6.13.17.1 - Check that sizes are provided for all +/// 'local void*' parameter of passed block. +static bool checkEnqueueVariadicArgs(Sema &S, CallExpr *TheCall, Expr *BlockArg, + unsigned NumNonVarArgs) { + const BlockPointerType *BPT = cast(BlockArg->getType()); + unsigned NumBlockParams = + BPT->getPointeeType()->getAs()->getNumParams(); + unsigned TotalNumArgs = TheCall->getNumArgs(); + + // For each argument passed to the block, a corresponding uint needs to + // be passed to describe the size of the local memory. + if (TotalNumArgs != NumBlockParams + NumNonVarArgs) { + S.Diag(TheCall->getLocStart(), + diag::err_opencl_enqueue_kernel_local_size_args); + return true; + } + + // Check that the sizes of the local memory are specified by integers. + if (!checkForLocalSizeArgs(S, TheCall, NumNonVarArgs, TotalNumArgs - 1)) { + S.Diag(TheCall->getArg(NumNonVarArgs)->getLocStart(), + diag::err_opencl_enqueue_kernel_invalid_local_size_type); + return true; + } + return false; +} + +/// OpenCL C v2.0, s6.13.17 - Enqueue kernel function contains four different +/// overload formats specified in Table 6.13.17.1. +/// int enqueue_kernel(queue_t queue, +/// kernel_enqueue_flags_t flags, +/// const ndrange_t ndrange, +/// void (^block)(void)) +/// int enqueue_kernel(queue_t queue, +/// kernel_enqueue_flags_t flags, +/// const ndrange_t ndrange, +/// uint num_events_in_wait_list, +/// clk_event_t *event_wait_list, +/// clk_event_t *event_ret, +/// void (^block)(void)) +/// int enqueue_kernel(queue_t queue, +/// kernel_enqueue_flags_t flags, +/// const ndrange_t ndrange, +/// void (^block)(local void*, ...), +/// uint size0, ...) +/// int enqueue_kernel(queue_t queue, +/// kernel_enqueue_flags_t flags, +/// const ndrange_t ndrange, +/// uint num_events_in_wait_list, +/// clk_event_t *event_wait_list, +/// clk_event_t *event_ret, +/// void (^block)(void*, ...), +/// uint size0, ...) +static bool SemaOpenCLBuiltinEnqueueKernel(Sema &S, CallExpr *TheCall) { + unsigned NumArgs = TheCall->getNumArgs(); + + if (NumArgs < 4) { + S.Diag(TheCall->getLocStart(), diag::err_typecheck_call_too_few_args); + return true; + } + + Expr *Arg0 = TheCall->getArg(0); + Expr *Arg1 = TheCall->getArg(1); + Expr *Arg2 = TheCall->getArg(2); + Expr *Arg3 = TheCall->getArg(3); + + // First argument always needs to be a queue_t type. + if (!Arg0->getType()->isQueueT()) { + S.Diag(TheCall->getArg(0)->getLocStart(), + diag::err_opencl_enqueue_kernel_expected_type) + << S.Context.OCLQueueTy; + return true; + } + + // Second argument always needs to be a kernel_enqueue_flags_t enum value. + if (!Arg1->getType().getTypePtr()->isIntegerType()) { + S.Diag(TheCall->getArg(1)->getLocStart(), + diag::err_opencl_enqueue_kernel_expected_type) + << "'kernel_enqueue_flags_t' (i.e. uint)"; + return true; + } + + // Third argument is always an ndrange_t type. + if (!Arg2->getType()->isNDRangeT()) { + S.Diag(TheCall->getArg(2)->getLocStart(), + diag::err_opencl_enqueue_kernel_expected_type) + << S.Context.OCLNDRangeTy; + return true; + } + + // With four arguments, there is only one form that the function could be + // called in: no events and no variable arguments. + if (NumArgs == 4) { + // check that the last argument is the right block type. + if (!isBlockPointer(Arg3)) { + S.Diag(Arg3->getLocStart(), + diag::err_opencl_enqueue_kernel_expected_type) << "block"; + return true; + } else + return checkBlockArgs(S, Arg3); + } else if (NumArgs >= 5) { + // we can have block + varargs. + if (isBlockPointer(Arg3)) + return (checkBlockArgs(S, Arg3) || + checkEnqueueVariadicArgs(S, TheCall, Arg3, 4)); + // last two cases with either exactly 7 args or 7 args and varargs. + if (NumArgs >= 7) { + // check common block argument. + Expr *Arg6 = TheCall->getArg(6); + if (!isBlockPointer(Arg6)) { + S.Diag(Arg6->getLocStart(), + diag::err_opencl_enqueue_kernel_expected_type) << "block"; + return true; + } + if (checkBlockArgs(S, Arg6)) + return true; + + // Forth argument has to be any integer type. + if (!Arg3->getType().getTypePtr()->isIntegerType()) { + S.Diag(TheCall->getArg(3)->getLocStart(), + diag::err_opencl_enqueue_kernel_expected_type) + << "integer"; + return true; + } + // check remaining common arguments. + Expr *Arg4 = TheCall->getArg(4); + Expr *Arg5 = TheCall->getArg(5); + + // Fith argument is always passed as pointers to clk_event_t. + if (!(Arg4->getType().getTypePtr()->isPointerType() && + Arg4->getType().getTypePtr()->getPointeeType()->isClkEventT())) { + S.Diag(TheCall->getArg(4)->getLocStart(), + diag::err_opencl_enqueue_kernel_expected_type) + << S.Context.getPointerType(S.Context.OCLClkEventTy); + return true; + } + + // Sixth argument is always passed as pointers to clk_event_t. + if (!(Arg5->getType().getTypePtr()->isPointerType() && + Arg5->getType().getTypePtr()->getPointeeType()->isClkEventT())) { + S.Diag(TheCall->getArg(5)->getLocStart(), + diag::err_opencl_enqueue_kernel_expected_type) + << S.Context.getPointerType(S.Context.OCLClkEventTy); + return true; + } + + if (NumArgs == 7) + return false; + else if (NumArgs >= 7) // check if varargs are correct types. + return checkEnqueueVariadicArgs(S, TheCall, Arg6, 7); + } + } + + // None of the specific case has been detected, give generic error + S.Diag(TheCall->getLocStart(), + diag::err_opencl_enqueue_kernel_incorrect_args); + return true; +} + /// Check that the first argument to __builtin_annotation is an integer /// and the second argument is a non-wide string literal. static bool SemaBuiltinAnnotation(Sema &S, CallExpr *TheCall) { @@ -454,7 +688,7 @@ return false; } - +// \brief OpenCL v2.0 s6.13.9 - Address space qualifier functions. // \brief Performs semantic analysis for the to_global/local/private call. // \param S Reference to the semantic analyzer. // \param BuiltinID ID of the builtin function. @@ -462,13 +696,6 @@ // \return True if a semantic error has been found, false otherwise. static bool SemaOpenCLBuiltinToAddr(Sema &S, unsigned BuiltinID, CallExpr *Call) { - // OpenCL v2.0 s6.13.9 - Address space qualifier functions. - if (S.getLangOpts().OpenCLVersion < 200) { - S.Diag(Call->getLocStart(), diag::err_opencl_builtin_requires_version) - << Call->getDirectCallee() << "2.0" << 1 << Call->getSourceRange(); - return true; - } - if (Call->getNumArgs() != 1) { S.Diag(Call->getLocStart(), diag::err_opencl_builtin_to_addr_arg_num) << Call->getDirectCallee() << Call->getSourceRange(); @@ -801,6 +1028,7 @@ TheCall->setType(Context.VoidPtrTy); break; + // OpenCL v2.0, s6.13.16 - Pipe functions case Builtin::BIread_pipe: case Builtin::BIwrite_pipe: // Since those two functions are declared with var args, we need a semantic @@ -841,6 +1069,15 @@ if (SemaOpenCLBuiltinToAddr(*this, BuiltinID, TheCall)) return ExprError(); break; + // OpenCL v2.0, s6.13.17 - Enqueue kernel functions. + case Builtin::BIenqueue_kernel: + if (SemaOpenCLBuiltinEnqueueKernel(*this, TheCall)) + return ExprError(); + break; + case Builtin::BIget_kernel_work_group_size: + case Builtin::BIget_kernel_preferred_work_group_size_multiple: + if (SemaOpenCLBuiltinKernelWorkGroupSize(*this, TheCall)) + return ExprError(); } // Since the target specific builtins for each arch overlap, only check those Index: test/CodeGenOpenCL/cl20-device-side-enqueue.cl =================================================================== --- /dev/null +++ test/CodeGenOpenCL/cl20-device-side-enqueue.cl @@ -0,0 +1,77 @@ +// RUN: %clang_cc1 %s -cl-std=CL2.0 -fblocks -ffake-address-space-map -O0 -emit-llvm -o - | FileCheck %s + +kernel void device_side_enqueue(global int *a, global int *b, int i) { + // CHECK: %default_queue = alloca %opencl.queue_t* + queue_t default_queue; + // CHECK: %flags = alloca i32 + unsigned flags = 0; + // CHECK: %ndrange = alloca %opencl.ndrange_t* + ndrange_t ndrange; + // CHECK: %event_wait_list = alloca %opencl.clk_event_t* + clk_event_t event_wait_list; + // CHECK: %clk_event = alloca %opencl.clk_event_t* + clk_event_t clk_event; + + // TODO: we shouldn't cast queue to i8* + // CHECK: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t*, %opencl.queue_t** %default_queue + // CHECK: [[FLAGS:%[0-9]+]] = load i32, i32* %flags + // CHECK: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange + // CHECK: [[BL:%[0-9]+]] = bitcast <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32{{.*}}, i32{{.*}}, i32{{.*}} }>* %block to void ()* + // CHECK: [[BL_I8:%[0-9]+]] = bitcast void ()* [[BL]] to i8* + // CHECK: call i32 @__enqueue_kernel_basic(%opencl.queue_t* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* [[BL_I8]]) + enqueue_kernel(default_queue, flags, ndrange, ^(void) { + a[i] = b[i]; + }); + + // CHECK: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t*, %opencl.queue_t** %default_queue + // CHECK: [[FLAGS:%[0-9]+]] = load i32, i32* %flags + // CHECK: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange + // CHECK: [[BL:%[0-9]+]] = bitcast <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32{{.*}}, i32{{.*}}, i32{{.*}} }>* %block3 to void ()* + // CHECK: [[BL_I8:%[0-9]+]] = bitcast void ()* [[BL]] to i8* + // CHECK: call i32 @__enqueue_kernel_basic_events(%opencl.queue_t* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i32 2, %opencl.clk_event_t** %event_wait_list, %opencl.clk_event_t** %clk_event, i8* [[BL_I8]]) + enqueue_kernel(default_queue, flags, ndrange, 2, &event_wait_list, &clk_event, ^(void) { + a[i] = b[i]; + }); + + // CHECK: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t*, %opencl.queue_t** %default_queue + // CHECK: [[FLAGS:%[0-9]+]] = load i32, i32* %flags + // CHECK: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange + // CHECK: call i32 (%opencl.queue_t*, i32, %opencl.ndrange_t*, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i32 256) + enqueue_kernel(default_queue, flags, ndrange, ^(local void *p) { + return; + }, + 256); + + // CHECK: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t*, %opencl.queue_t** %default_queue + // CHECK: [[FLAGS:%[0-9]+]] = load i32, i32* %flags + // CHECK: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange + // CHECK: call i32 (%opencl.queue_t*, i32, %opencl.ndrange_t*, i32, %opencl.clk_event_t**, %opencl.clk_event_t**, i8*, i32, ...) @__enqueue_kernel_events_vaargs(%opencl.queue_t* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i32 2, %opencl.clk_event_t** %event_wait_list, %opencl.clk_event_t** %clk_event, i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i32 256) + enqueue_kernel(default_queue, flags, ndrange, 2, &event_wait_list, &clk_event, ^(local void *p) { + return; + }, + 256); + + void (^const blockA)(void) = ^{ + return; + }; + void (^const blockB)(local void *) = ^(local void *a) { + return; + }; + + // CHECK: [[BL:%[0-9]+]] = load void ()*, void ()** %blockA + // CHECK: [[BL_I8:%[0-9]+]] = bitcast void ()* [[BL]] to i8* + // CHECK: call i32 @__get_kernel_work_group_size_impl(i8* [[BL_I8]]) + unsigned size = get_kernel_work_group_size(blockA); + // CHECK: [[BL:%[0-9]+]] = load void (i8 addrspace(2)*)*, void (i8 addrspace(2)*)** %blockB + // CHECK: [[BL_I8:%[0-9]+]] = bitcast void (i8 addrspace(2)*)* [[BL]] to i8* + // CHECK: call i32 @__get_kernel_work_group_size_impl(i8* [[BL_I8]]) + size = get_kernel_work_group_size(blockB); + // CHECK: [[BL:%[0-9]+]] = load void ()*, void ()** %blockA + // CHECK: [[BL_I8:%[0-9]+]] = bitcast void ()* [[BL]] to i8* + // CHECK: call i32 @__get_kernel_preferred_work_group_multiple_impl(i8* [[BL_I8]]) + size = get_kernel_preferred_work_group_size_multiple(blockA); + // CHECK: [[BL:%[0-9]+]] = load void (i8 addrspace(2)*)*, void (i8 addrspace(2)*)** %blockB + // CHECK: [[BL_I8:%[0-9]+]] = bitcast void (i8 addrspace(2)*)* [[BL]] to i8* + // CHECK: call i32 @__get_kernel_preferred_work_group_multiple_impl(i8* [[BL_I8]]) + size = get_kernel_preferred_work_group_size_multiple(blockB); +} Index: test/SemaOpenCL/cl20-device-side-enqueue.cl =================================================================== --- /dev/null +++ test/SemaOpenCL/cl20-device-side-enqueue.cl @@ -0,0 +1,141 @@ +// RUN: %clang_cc1 %s -cl-std=CL2.0 -fblocks -verify -pedantic -fsyntax-only + +typedef void (^bl_t)(local void *, local int *); + +const bl_t blockG = (bl_t) ^ (local void *a, local int *b) {}; + +// Diagnostic tests for different overloads of enqueue_kernel from Table 6.13.17.1 of OpenCL 2.0 Spec. +kernel void enqueue_kernel_tests() { + queue_t default_queue; + unsigned flags = 0; + ndrange_t ndrange; + clk_event_t event_wait_list; + clk_event_t evt; + void *vptr; + + // Testing the first overload type + enqueue_kernel(default_queue, flags, ndrange, ^(void) { + return 0; + }); + + enqueue_kernel(vptr, flags, ndrange, ^(void) { // expected-error{{illegal call to enqueue_kernel, expected 'queue_t' argument type}} + return 0; + }); + + enqueue_kernel(default_queue, vptr, ndrange, ^(void) { // expected-error{{illegal call to enqueue_kernel, expected 'kernel_enqueue_flags_t' (i.e. uint) argument type}} + return 0; + }); + + enqueue_kernel(default_queue, flags, vptr, ^(void) { // expected-error{{illegal call to enqueue_kernel, expected 'ndrange_t' argument type}} + return 0; + }); + + enqueue_kernel(default_queue, flags, ndrange, vptr); // expected-error{{illegal call to enqueue_kernel, expected block argument}} + + // Testing the second overload type + enqueue_kernel(default_queue, flags, ndrange, 1, &event_wait_list, &evt, ^(void) { + return 0; + }); + + enqueue_kernel(default_queue, flags, ndrange, 1, vptr, &evt, ^(void) // expected-error{{illegal call to enqueue_kernel, expected 'clk_event_t *' argument type}} + { + return 0; + }); + + enqueue_kernel(default_queue, flags, ndrange, 1, &event_wait_list, vptr, ^(void) // expected-error{{illegal call to enqueue_kernel, expected 'clk_event_t *' argument type}} + { + return 0; + }); + + enqueue_kernel(default_queue, flags, ndrange, 1, &event_wait_list, &evt, vptr); // expected-error{{illegal call to enqueue_kernel, expected block argument}} + + // Testing the third overload type + enqueue_kernel(default_queue, flags, ndrange, + ^(local void *a, local void *b) { + return 0; + }, + 1024, 1024); + + enqueue_kernel(default_queue, flags, ndrange, blockG, 1024, 1024); // expected-error{{blocks used in device side enqueue are expected to have parameters of type 'local void*'}} + + enqueue_kernel(default_queue, flags, ndrange, // expected-error{{mismatch in number of block parameters and local size arguments passed}} + ^(local void *a, local void *b) { + return 0; + }, + 1024); + + float illegal_mem_size = (float)0.5f; + enqueue_kernel(default_queue, flags, ndrange, + ^(local void *a, local void *b) { + return 0; + }, + illegal_mem_size, illegal_mem_size); // expected-error{{local memory sizes need to be specified as uint}} + + // Testing the forth overload type + enqueue_kernel(default_queue, flags, ndrange, 1, &event_wait_list, &evt, + ^(local void *a, local void *b) { + return 0; + }, + 1024, 1024); + + enqueue_kernel(default_queue, flags, ndrange, 1, &event_wait_list, &evt, // expected-error{{mismatch in number of block parameters and local size arguments passed}} + ^(local void *a, local void *b) { + return 0; + }, + 1024, 1024, 1024); + + // More random misc cases that can't be deduced + enqueue_kernel(default_queue, flags, ndrange, 1, &event_wait_list, &evt); // expected-error{{illegal call to enqueue_kernel, incorrect argument types}} + + enqueue_kernel(default_queue, flags, ndrange, 1, 1); // expected-error{{illegal call to enqueue_kernel, incorrect argument types}} +} + +// Diagnostic tests for get_kernel_work_group_size and allowed block parameter types in dynamic parallelism. +kernel void work_group_size_tests() { + void (^const blockA)(void) = ^{ + return; + }; + void (^const blockB)(int) = ^(int a) { + return; + }; + void (^const blockC)(local void *) = ^(local void *a) { + return; + }; + void (^const blockD)(local int *) = ^(local int *a) { + return; + }; + + unsigned size = get_kernel_work_group_size(blockA); + size = get_kernel_work_group_size(blockC); + size = get_kernel_work_group_size(^(local void *a) { + return; + }); + size = get_kernel_work_group_size(^(local int *a) { // expected-error {{blocks used in device side enqueue are expected to have parameters of type 'local void*'}} + return; + }); + size = get_kernel_work_group_size(blockB); // expected-error {{blocks used in device side enqueue are expected to have parameters of type 'local void*'}} + size = get_kernel_work_group_size(blockD); // expected-error {{blocks used in device side enqueue are expected to have parameters of type 'local void*'}} + size = get_kernel_work_group_size(^(int a) { // expected-error {{blocks used in device side enqueue are expected to have parameters of type 'local void*'}} + return; + }); + size = get_kernel_work_group_size(); // expected-error {{too few arguments to function call, expected 1, have 0}} + size = get_kernel_work_group_size(1); // expected-error{{expected block argument}} + size = get_kernel_work_group_size(blockA, 1); // expected-error{{too many arguments to function call, expected 1, have 2}} + + size = get_kernel_preferred_work_group_size_multiple(blockA); + size = get_kernel_preferred_work_group_size_multiple(blockC); + size = get_kernel_preferred_work_group_size_multiple(^(local void *a) { + return; + }); + size = get_kernel_preferred_work_group_size_multiple(^(local int *a) { // expected-error {{blocks used in device side enqueue are expected to have parameters of type 'local void*'}} + return; + }); + size = get_kernel_preferred_work_group_size_multiple(^(int a) { // expected-error {{blocks used in device side enqueue are expected to have parameters of type 'local void*'}} + return; + }); + size = get_kernel_preferred_work_group_size_multiple(blockB); // expected-error {{blocks used in device side enqueue are expected to have parameters of type 'local void*'}} + size = get_kernel_preferred_work_group_size_multiple(blockD); // expected-error {{blocks used in device side enqueue are expected to have parameters of type 'local void*'}} + size = get_kernel_preferred_work_group_size_multiple(); // expected-error {{too few arguments to function call, expected 1, have 0}} + size = get_kernel_preferred_work_group_size_multiple(1); // expected-error{{expected block argument}} + size = get_kernel_preferred_work_group_size_multiple(blockA, 1); // expected-error{{too many arguments to function call, expected 1, have 2}} +} Index: test/SemaOpenCL/clang-builtin-version.cl =================================================================== --- /dev/null +++ test/SemaOpenCL/clang-builtin-version.cl @@ -0,0 +1,44 @@ +// RUN: %clang_cc1 %s -fblocks -verify -pedantic -fsyntax-only -ferror-limit 100 + +// Confirm CL2.0 Clang builtins are not available in earlier versions + +kernel void dse_builtins() { + int tmp; + enqueue_kernel(tmp, tmp, tmp, ^(void) { // expected-warning{{implicit declaration of function 'enqueue_kernel' is invalid in C99}} + return; + }); + unsigned size = get_kernel_work_group_size(^(void) { // expected-warning{{implicit declaration of function 'get_kernel_work_group_size' is invalid in C99}} + return; + }); + size = get_kernel_preferred_work_group_size_multiple(^(void) { // expected-warning{{implicit declaration of function 'get_kernel_preferred_work_group_size_multiple' is invalid in C99}} + return; + }); +} + +void pipe_builtins() { + int tmp; + + read_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'read_pipe' is invalid in C99}} + write_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'write_pipe' is invalid in C99}} + + reserve_read_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'reserve_read_pipe' is invalid in C99}} + reserve_write_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'reserve_write_pipe' is invalid in C99}} + + work_group_reserve_read_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'work_group_reserve_read_pipe' is invalid in C99}} + work_group_reserve_write_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'work_group_reserve_write_pipe' is invalid in C99}} + + sub_group_reserve_write_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'sub_group_reserve_write_pipe' is invalid in C99}} + sub_group_reserve_read_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'sub_group_reserve_read_pipe' is invalid in C99}} + + commit_read_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'commit_read_pipe' is invalid in C99}} + commit_write_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'commit_write_pipe' is invalid in C99}} + + work_group_commit_read_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'work_group_commit_read_pipe' is invalid in C99}} + work_group_commit_write_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'work_group_commit_write_pipe' is invalid in C99}} + + sub_group_commit_write_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'sub_group_commit_write_pipe' is invalid in C99}} + sub_group_commit_read_pipe(tmp, tmp); // expected-warning{{implicit declaration of function 'sub_group_commit_read_pipe' is invalid in C99}} + + get_pipe_num_packets(tmp); // expected-warning{{implicit declaration of function 'get_pipe_num_packets' is invalid in C99}} + get_pipe_max_packets(tmp); // expected-warning{{implicit declaration of function 'get_pipe_max_packets' is invalid in C99}} +} Index: test/SemaOpenCL/to_addr_builtin.cl =================================================================== --- test/SemaOpenCL/to_addr_builtin.cl +++ test/SemaOpenCL/to_addr_builtin.cl @@ -10,43 +10,44 @@ glob = to_global(glob, loc); #if __OPENCL_C_VERSION__ < CL_VERSION_2_0 - // expected-error@-2{{'to_global' requires OpenCL version 2.0 or above}} + // expected-warning@-2{{implicit declaration of function 'to_global' is invalid in C99}} + // expected-warning@-3{{incompatible integer to pointer conversion assigning to '__global int *' from 'int'}} #else - // expected-error@-4{{invalid number of arguments to function: 'to_global'}} + // expected-error@-5{{invalid number of arguments to function: 'to_global'}} #endif int x; glob = to_global(x); #if __OPENCL_C_VERSION__ < CL_VERSION_2_0 - // expected-error@-2{{'to_global' requires OpenCL version 2.0 or above}} + // expected-warning@-2{{incompatible integer to pointer conversion assigning to '__global int *' from 'int'}} #else // expected-error@-4{{invalid argument x to function: 'to_global', expecting a generic pointer argument}} #endif glob = to_global(con); #if __OPENCL_C_VERSION__ < CL_VERSION_2_0 - // expected-error@-2{{'to_global' requires OpenCL version 2.0 or above}} + // expected-warning@-2{{incompatible integer to pointer conversion assigning to '__global int *' from 'int'}} #else // expected-error@-4{{invalid argument con to function: 'to_global', expecting a generic pointer argument}} #endif glob = to_global(con_typedef); #if __OPENCL_C_VERSION__ < CL_VERSION_2_0 - // expected-error@-2{{'to_global' requires OpenCL version 2.0 or above}} + // expected-warning@-2{{incompatible integer to pointer conversion assigning to '__global int *' from 'int'}} #else // expected-error@-4{{invalid argument con_typedef to function: 'to_global', expecting a generic pointer argument}} #endif loc = to_global(glob); #if __OPENCL_C_VERSION__ < CL_VERSION_2_0 - // expected-error@-2{{'to_global' requires OpenCL version 2.0 or above}} + // expected-warning@-2{{incompatible integer to pointer conversion assigning to '__local int *' from 'int'}} #else // expected-error@-4{{assigning '__global int *' to '__local int *' changes address space of pointer}} #endif global char *glob_c = to_global(loc); #if __OPENCL_C_VERSION__ < CL_VERSION_2_0 - // expected-error@-2{{'to_global' requires OpenCL version 2.0 or above}} + // expected-warning@-2{{incompatible integer to pointer conversion initializing '__global char *' with an expression of type 'int'}} #else // expected-warning@-4{{incompatible pointer types initializing '__global char *' with an expression of type '__global int *'}} #endif