Index: include/clang/Basic/DiagnosticDriverKinds.td =================================================================== --- include/clang/Basic/DiagnosticDriverKinds.td +++ include/clang/Basic/DiagnosticDriverKinds.td @@ -203,6 +203,9 @@ def warn_drv_omp_offload_target_duplicate : Warning< "The OpenMP offloading target '%0' is similar to target '%1' already specified - will be ignored.">, InGroup; +def warn_drv_omp_offload_target_missingbcruntime : Warning< + "No library '%0' found in the default clang lib directory or in LIBRARY_PATH. Expect degraded performance due to no inlining of runtime functions on target devices.">, + InGroup; def err_drv_bitcode_unsupported_on_toolchain : Error< "-fembed-bitcode is not supported on versions of iOS prior to 6.0">; Index: lib/Driver/ToolChains/Cuda.cpp =================================================================== --- lib/Driver/ToolChains/Cuda.cpp +++ lib/Driver/ToolChains/Cuda.cpp @@ -21,6 +21,7 @@ #include "llvm/Option/ArgList.h" #include "llvm/Support/FileSystem.h" #include "llvm/Support/Path.h" +#include "llvm/Support/Process.h" #include "llvm/Support/Program.h" #include @@ -580,6 +581,44 @@ CC1Args.push_back("-target-feature"); CC1Args.push_back("+ptx42"); } + + if (DeviceOffloadingKind == Action::OFK_OpenMP) { + SmallVector LibraryPaths; + // Add path to lib and/or lib64 folders. + SmallString<256> DefaultLibPath = + llvm::sys::path::parent_path(getDriver().Dir); + llvm::sys::path::append(DefaultLibPath, + Twine("lib") + CLANG_LIBDIR_SUFFIX); + LibraryPaths.emplace_back(DefaultLibPath.c_str()); + + // Add user defined library paths from LIBRARY_PATH. + llvm::Optional LibPath = + llvm::sys::Process::GetEnv("LIBRARY_PATH"); + if (LibPath) { + SmallVector Frags; + const char EnvPathSeparatorStr[] = {llvm::sys::EnvPathSeparator, '\0'}; + llvm::SplitString(*LibPath, Frags, EnvPathSeparatorStr); + for (StringRef Path : Frags) + LibraryPaths.emplace_back(Path.trim()); + } + + std::string LibOmpTargetName = + "libomptarget-nvptx-" + GpuArch.str() + ".bc"; + bool FoundBCLibrary = false; + for (StringRef LibraryPath : LibraryPaths) { + SmallString<128> LibOmpTargetFile(LibraryPath); + llvm::sys::path::append(LibOmpTargetFile, LibOmpTargetName); + if (llvm::sys::fs::exists(LibOmpTargetFile)) { + CC1Args.push_back("-mlink-cuda-bitcode"); + CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetFile)); + FoundBCLibrary = true; + break; + } + } + if (!FoundBCLibrary) + getDriver().Diag(diag::warn_drv_omp_offload_target_missingbcruntime) + << LibOmpTargetName; + } } void CudaToolChain::AddCudaIncludeArgs(const ArgList &DriverArgs, Index: test/Driver/openmp-offload-gpu.c =================================================================== --- test/Driver/openmp-offload-gpu.c +++ test/Driver/openmp-offload-gpu.c @@ -142,3 +142,23 @@ // RUN: | FileCheck -check-prefix=CHK-NOLIBDEVICE %s // CHK-NOLIBDEVICE-NOT: error:{{.*}}sm_60 + +/// ########################################################################### + +/// Check that the runtime bitcode library is part of the compile line. Create a bogus +/// bitcode library and add it to the LIBRARY_PATH. +// RUN: env LIBRARY_PATH=%S/Inputs/libomptarget %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \ +// RUN: -Xopenmp-target -march=sm_20 -fopenmp-relocatable-target -save-temps \ +// RUN: -no-canonical-prefixes %s 2>&1 | FileCheck -check-prefix=CHK-BCLIB %s + +// CHK-BCLIB: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-cuda-bitcode{{.*}}libomptarget-nvptx-sm_20.bc + +/// ########################################################################### + +/// Check that the warning is thrown when the libomptarget bitcode library is not found. +/// Libomptarget requires sm_35 or newer so an sm_20 bitcode library should never exist. +// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \ +// RUN: -Xopenmp-target -march=sm_20 -fopenmp-relocatable-target -save-temps \ +// RUN: -no-canonical-prefixes %s 2>&1 | FileCheck -check-prefix=CHK-BCLIB-WARN %s + +// CHK-BCLIB-WARN: No library 'libomptarget-nvptx-sm_20.bc' found in the default clang lib directory or in LIBRARY_PATH. Expect degraded performance due to no inlining of runtime functions on target devices.