Skip to content

Conversation

@brownbaerchen
Copy link
Contributor

In this PR

  • synchronisation is skipped for some MPI operations that are used in mpi4py-fft, such as Is_inter,
  • synchronisation is skipped if allreduce and reduce (lower case) are used with data that is not on GPU,
  • Barrier now synchronises the device to cause a barrier on device as well, rather than just on the host.

These changes are rather small and are still not captured by any test. There is some unrelated issue that causes some Allen-Cahn tests to fail. I haven't looked into why yet, but they also fail on the master branch.

@pancetta pancetta merged commit b81b47b into Parallel-in-Time:master Nov 14, 2024
79 of 86 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants