[all-commits] [llvm/llvm-project] c41ae2: [OpenMP][Clang][NVPTX] Only build one bitcode libr...

[Shilei Tian via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c41ae246ac673e97ec1abdc2b9cbe1989f8682fe
      https://github.com/llvm/llvm-project/commit/c41ae246ac673e97ec1abdc2b9cbe1989f8682fe
  Author: Shilei Tian <tianshilei1992 at gmail.com>
  Date:   2021-03-08 (Mon, 08 Mar 2021)

  Changed paths:
    M clang/lib/Driver/ToolChains/Cuda.cpp
    R clang/test/Driver/Inputs/libomptarget/libomptarget-nvptx-cuda_102-sm_35.bc
    A clang/test/Driver/Inputs/libomptarget/libomptarget-nvptx-sm_35.bc
    M clang/test/Driver/openmp-offload-gpu.c
    M openmp/libomptarget/deviceRTLs/nvptx/CMakeLists.txt
    M openmp/libomptarget/deviceRTLs/nvptx/src/target_impl.cu

  Log Message:
  -----------
  [OpenMP][Clang][NVPTX] Only build one bitcode library for each SM

In D97003, CUDA 9.2 is the minimum requirement for OpenMP offloading on
NVPTX target. We don't need to have macros in source code to select right functions
based on CUDA version. we don't need to compile multiple bitcode libraries of
different CUDA versions for each SM. We don't need to worry about future
compatibility with newer CUDA version.

`-target-feature +ptx61` is used in this patch, which corresponds to the highest
PTX version that CUDA 9.2 can support.

Reviewed By: jdoerfert

Differential Revision: https://reviews.llvm.org/D97198