[all-commits] [llvm/llvm-project] 87e6b9: [OpenMP][libomptarget] Add AMDGPU NextGen plugin w...

[Kevin Sala Penadés via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 87e6b96b0009983996bfe0aa27d358008c1d1087
      https://github.com/llvm/llvm-project/commit/87e6b96b0009983996bfe0aa27d358008c1d1087
  Author: Kevin Sala <kevin.sala at bsc.es>
  Date:   2022-12-16 (Fri, 16 Dec 2022)

  Changed paths:
    M openmp/libomptarget/plugins-nextgen/CMakeLists.txt
    A openmp/libomptarget/plugins-nextgen/amdgpu/CMakeLists.txt
    A openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
    M openmp/libomptarget/plugins/amdgpu/dynamic_hsa/hsa.h

  Log Message:
  -----------
  [OpenMP][libomptarget] Add AMDGPU NextGen plugin with asynchronous behavior

This commit adds the AMDGPU NextGen plugin inheriting from PluginInterface's classes.
It also implements the asynchronous behavior in the plugin operations: kernel launches
and memory transfers. To this end, it implements the concept of streams of asynchronous
operations. The streams are implemented using the HSA signals to define input and output
dependencies between asynchronous operations.

Missing features:
  - Retrieve the maximum number of threads per group that a kernel can run. This requires
    reading the image.
  - Implement __tgt_rtl_sync_event, not used on the libomptarget side.

Differential Revision: https://reviews.llvm.org/D138389