[all-commits] [llvm/llvm-project] cc8dc5: [OpenMP][AMDGPU] Switch host-device memory copy to...

[carlobertolli via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: cc8dc5e28be84099ef4802157984a3522c503e02
      https://github.com/llvm/llvm-project/commit/cc8dc5e28be84099ef4802157984a3522c503e02
  Author: Carlo Bertolli <carlo.bertolli at amd.com>
  Date:   2021-12-08 (Wed, 08 Dec 2021)

  Changed paths:
    M openmp/libomptarget/plugins/amdgpu/dynamic_hsa/hsa.cpp
    M openmp/libomptarget/plugins/amdgpu/dynamic_hsa/hsa_ext_amd.h
    M openmp/libomptarget/plugins/amdgpu/impl/impl.cpp
    M openmp/libomptarget/plugins/amdgpu/impl/impl_runtime.h
    M openmp/libomptarget/plugins/amdgpu/src/rtl.cpp

  Log Message:
  -----------
  [OpenMP][AMDGPU] Switch host-device memory copy to asynchronous version

Prepare amdgpu plugin for asynchronous implementation. This patch switches to using HSA API for asynchronous memory copy.
Moving away from hsa_memory_copy means that plugin is responsible for locking/unlocking host memory pointers.

Reviewed By: JonChesterfield

Differential Revision: https://reviews.llvm.org/D115279