Author: Shilei Tian Date: 2021-02-03T14:24:51-08:00 New Revision: 4d0874c72a0a3f53eb3084a1ea3ee4456ab6e004
URL: https://github.com/llvm/llvm-project/commit/4d0874c72a0a3f53eb3084a1ea3ee4456ab6e004 DIFF: https://github.com/llvm/llvm-project/commit/4d0874c72a0a3f53eb3084a1ea3ee4456ab6e004.diff LOG: [OpenMP][NVPTX] Added the missing -O1 when building NVPTX bitcode libraries In the past `-O1` was used when building NVPTX bitcode libraries. After we switched to OpenMP, `-O1` was missing by mistake, leading to a huge performance regression. Reviewed By: JonChesterfield Differential Revision: https://reviews.llvm.org/D95545 (cherry picked from commit 5a64794bbad4010778406dfee7748e6080258dbf) Added: Modified: openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt Removed: ################################################################################ diff --git a/openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt b/openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt index 23efbba29d66..eeda137ef120 100644 --- a/openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt +++ b/openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt @@ -126,14 +126,14 @@ set(cuda_src_files ) # Set flags for LLVM Bitcode compilation. -set(bc_flags -S -x c++ - -target nvptx64 - -Xclang -emit-llvm-bc - -Xclang -aux-triple -Xclang ${aux_triple} - -fopenmp -fopenmp-cuda-mode -Xclang -fopenmp-is-device - -D__CUDACC__ - -I${devicertl_base_directory} - -I${devicertl_nvptx_directory}/src) +set(bc_flags -S -x c++ -O1 -std=c++14 + -target nvptx64 + -Xclang -emit-llvm-bc + -Xclang -aux-triple -Xclang ${aux_triple} + -fopenmp -fopenmp-cuda-mode -Xclang -fopenmp-is-device + -D__CUDACC__ + -I${devicertl_base_directory} + -I${devicertl_nvptx_directory}/src) if(${LIBOMPTARGET_NVPTX_DEBUG}) list(APPEND bc_flags -DOMPTARGET_NVPTX_DEBUG=-1) _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
