[all-commits] [llvm/llvm-project] 78f92c: [openmp][amdgpu] Initial gfx10 offloading implemen...

[Jon Chesterfield via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 78f92c38101fd1f6788500b3362d3c9c28213bc0
      https://github.com/llvm/llvm-project/commit/78f92c38101fd1f6788500b3362d3c9c28213bc0
  Author: Jon Chesterfield <jonathanchesterfield at gmail.com>
  Date:   2021-08-27 (Fri, 27 Aug 2021)

  Changed paths:
    M clang/lib/Basic/Targets/AMDGPU.h
    M llvm/include/llvm/Frontend/OpenMP/OMPGridValues.h
    M openmp/libomptarget/deviceRTLs/amdgcn/CMakeLists.txt
    M openmp/libomptarget/deviceRTLs/amdgcn/src/target_impl.h
    M openmp/libomptarget/plugins/amdgpu/src/rtl.cpp

  Log Message:
  -----------
  [openmp][amdgpu] Initial gfx10 offloading implementation

Lets wavefront size be 32 for amdgpu openmp, as well as 64.

Fixes up as little as possible to pass that through the libraries. This change
is end to end, as opposed to updating clang/devicertl/plugin separately. It can
be broken up for review/commit if preferred. Posting as-is so that others with
a gfx10 can try it out. It works roughly as well as gfx9 for me, but there are
probably bugs remaining as well as the todo: for letting grid values vary more.

Reviewed By: ronlieb

Differential Revision: https://reviews.llvm.org/D108708