ff071d6165
Scalar reduction variables in `do concurrent reduce(...)` were being mapped with `implicit ByCopy` when offloaded to device, because `genMapInfoOpForLiveIn` treated all trivial types uniformly. This caused the reduction result to be silently dropped — the device-side reduction would compute the correct value but never write it back to the host. Fix by detecting reduction variables and forcing `implicit tofrom ByRef` mapping, matching the behavior of explicit `!$omp target teams distribute parallel do reduction(...)`. Co-authored-by: ergawy <kareem.ergawy@amd.com> Co-authored-by: Claude <noreply@anthropic.com> Made-with: Cursor Fixes: https://github.com/ROCm/llvm-project/issues/1844 Co-authored-by: Claude <noreply@anthropic.com>
The LLVM/Offload Subproject
The Offload subproject aims at providing tooling, runtimes, and APIs that allow users to execute code on accelerators or other "co-processors" that may or may not match the architecture of their "host". In the long run, all kinds of targets are in scope of this effort, including but not limited to: CPUs, GPUs, FPGAs, AI/ML accelerators, distributed resources, etc.
For OpenMP offload users, the project is ready and fully usable. The final API design is still under development. More content will show up here and on our webpage soon. In the meantime, people are encouraged to participate in our meetings (see below) and check our development board as well as the discussions on Discourse.
Meetings
Every second Wednesday, 7:00 - 8:00am PT, starting Jan 24, 2024. Alternates with the OpenMP in LLVM meeting. invite.ics Meeting Minutes and Agenda