Author: hahnfeld Date: Tue Oct 17 06:37:36 2017 New Revision: 315996 URL: http://llvm.org/viewvc/llvm-project?rev=315996&view=rev Log: [CMake][OpenMP] Customize default offloading arch
For the shuffle instructions in reductions we need at least sm_30 but the user may want to customize the default architecture. Differential Revision: https://reviews.llvm.org/D38883 Modified: cfe/trunk/CMakeLists.txt cfe/trunk/include/clang/Config/config.h.cmake cfe/trunk/lib/Driver/ToolChains/Cuda.cpp cfe/trunk/lib/Driver/ToolChains/Cuda.h Modified: cfe/trunk/CMakeLists.txt URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/CMakeLists.txt?rev=315996&r1=315995&r2=315996&view=diff ============================================================================== --- cfe/trunk/CMakeLists.txt (original) +++ cfe/trunk/CMakeLists.txt Tue Oct 17 06:37:36 2017 @@ -235,6 +235,17 @@ endif() set(CLANG_DEFAULT_OPENMP_RUNTIME "libomp" CACHE STRING "Default OpenMP runtime used by -fopenmp.") +# OpenMP offloading requires at least sm_30 because we use shuffle instructions +# to generate efficient code for reductions. +set(CLANG_OPENMP_NVPTX_DEFAULT_ARCH "sm_30" CACHE STRING + "Default architecture for OpenMP offloading to Nvidia GPUs.") +string(REGEX MATCH "^sm_([0-9]+)$" MATCHED_ARCH "${CLANG_OPENMP_NVPTX_DEFAULT_ARCH}") +if (NOT DEFINED MATCHED_ARCH OR "${CMAKE_MATCH_1}" LESS 30) + message(WARNING "Resetting default architecture for OpenMP offloading to Nvidia GPUs to sm_30") + set(CLANG_OPENMP_NVPTX_DEFAULT_ARCH "sm_30" CACHE STRING + "Default architecture for OpenMP offloading to Nvidia GPUs." FORCE) +endif() + set(CLANG_VENDOR ${PACKAGE_VENDOR} CACHE STRING "Vendor-specific text for showing with version information.") Modified: cfe/trunk/include/clang/Config/config.h.cmake URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/include/clang/Config/config.h.cmake?rev=315996&r1=315995&r2=315996&view=diff ============================================================================== --- cfe/trunk/include/clang/Config/config.h.cmake (original) +++ cfe/trunk/include/clang/Config/config.h.cmake Tue Oct 17 06:37:36 2017 @@ -20,6 +20,9 @@ /* Default OpenMP runtime used by -fopenmp. */ #define CLANG_DEFAULT_OPENMP_RUNTIME "${CLANG_DEFAULT_OPENMP_RUNTIME}" +/* Default architecture for OpenMP offloading to Nvidia GPUs. */ +#define CLANG_OPENMP_NVPTX_DEFAULT_ARCH "${CLANG_OPENMP_NVPTX_DEFAULT_ARCH}" + /* Multilib suffix for libdir. */ #define CLANG_LIBDIR_SUFFIX "${CLANG_LIBDIR_SUFFIX}" Modified: cfe/trunk/lib/Driver/ToolChains/Cuda.cpp URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Driver/ToolChains/Cuda.cpp?rev=315996&r1=315995&r2=315996&view=diff ============================================================================== --- cfe/trunk/lib/Driver/ToolChains/Cuda.cpp (original) +++ cfe/trunk/lib/Driver/ToolChains/Cuda.cpp Tue Oct 17 06:37:36 2017 @@ -542,9 +542,9 @@ CudaToolChain::TranslateArgs(const llvm: // flags are not duplicated. // Also append the compute capability. if (DeviceOffloadKind == Action::OFK_OpenMP) { - for (Arg *A : Args){ + for (Arg *A : Args) { bool IsDuplicate = false; - for (Arg *DALArg : *DAL){ + for (Arg *DALArg : *DAL) { if (A == DALArg) { IsDuplicate = true; break; @@ -555,14 +555,9 @@ CudaToolChain::TranslateArgs(const llvm: } StringRef Arch = DAL->getLastArgValue(options::OPT_march_EQ); - if (Arch.empty()) { - // Default compute capability for CUDA toolchain is the - // lowest compute capability supported by the installed - // CUDA version. - DAL->AddJoinedArg(nullptr, - Opts.getOption(options::OPT_march_EQ), - CudaInstallation.getLowestExistingArch()); - } + if (Arch.empty()) + DAL->AddJoinedArg(nullptr, Opts.getOption(options::OPT_march_EQ), + CLANG_OPENMP_NVPTX_DEFAULT_ARCH); return DAL; } Modified: cfe/trunk/lib/Driver/ToolChains/Cuda.h URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Driver/ToolChains/Cuda.h?rev=315996&r1=315995&r2=315996&view=diff ============================================================================== --- cfe/trunk/lib/Driver/ToolChains/Cuda.h (original) +++ cfe/trunk/lib/Driver/ToolChains/Cuda.h Tue Oct 17 06:37:36 2017 @@ -76,17 +76,6 @@ public: std::string getLibDeviceFile(StringRef Gpu) const { return LibDeviceMap.lookup(Gpu); } - /// \brief Get lowest available compute capability - /// for which a libdevice library exists. - std::string getLowestExistingArch() const { - std::string LibDeviceFile; - for (auto key : LibDeviceMap.keys()) { - LibDeviceFile = LibDeviceMap.lookup(key); - if (!LibDeviceFile.empty()) - return key; - } - return "sm_20"; - } }; namespace tools { _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
