diff options
| author | Carlo Bertolli <carlo.bertolli@amd.com> | 2021-12-07 23:04:50 +0000 |
|---|---|---|
| committer | Jon Chesterfield <jonathanchesterfield@gmail.com> | 2021-12-07 23:05:23 +0000 |
| commit | 6de698bf10996b532632bb9dfa9fd420c5af62af (patch) | |
| tree | cd0763b6658e3bea3df73c93f20426f5913fd69b /llvm/lib/IR/Module.cpp | |
| parent | c2acd4539396af2beb8f37e38e8da9e4a04565f5 (diff) | |
| download | llvm-6de698bf10996b532632bb9dfa9fd420c5af62af.zip llvm-6de698bf10996b532632bb9dfa9fd420c5af62af.tar.gz llvm-6de698bf10996b532632bb9dfa9fd420c5af62af.tar.bz2 | |
[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
Diffstat (limited to 'llvm/lib/IR/Module.cpp')
0 files changed, 0 insertions, 0 deletions