[Openmp-commits] [PATCH] D98832: [libomptarget] Tune the number of teams and threads for kernel launch.

[Jon Chesterfield via Phabricator via Openmp-commits]

JonChesterfield added a comment.

This is really interesting. The idea seems to be to choose the dispatch parameters based on the kernel metadata and the limits of the machine.

What's the underlying heuristic? Break across N CU's in chunks that match the occupancy limits of each CU?

If so we probably want to compare LDS usage as well to avoid partitioning poorly for that.

Maybe others - there might be a performance cliff on amount of private memory too.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D98832/new/

https://reviews.llvm.org/D98832