Lisandro Dalcin
Lisandro Dalcin
@hppritcha I believe the issues are not fully resolved yet. I'm running Fedora 33, with openmpi-4.0.5-1.fc33.x86_64. The following test run is with mpi4py/master. ``` $ mpiexec -n 1 python test/runtests.py...
Yes, I have a test that loops over datatypes and performs CompareAndSwap and FetchAndOp. Isn't that a reasonable test? IMHO, If an MPI implementation cannot support the operation for some...
> datatype=16 is 2-byte contig And datatype=128 is 16-byte contig, right?
@gpaulsen These are the current openmpi and ucx packages in my Fedora 33: ``` $ rpm -qa | egrep "(ucx|openmpi)" openmpi-4.0.5-1.fc33.x86_64 openmpi-devel-4.0.5-1.fc33.x86_64 ucx-1.9.0-1.fc33.x86_64 ```
@hjelmn mpi4py initializes MPI with THREAD_MULTIPLE. Perhaps that is affecting component selection?
mpi4py ABI build tests running: https://github.com/mpi4py/mpi4py-testing/actions/runs/9683326620/job/26718539505
@hzhou mpi4py still broken, same error.
New run just started: https://github.com/mpi4py/mpi4py-testing/actions/runs/9683326620/job/26721265683
Looks like your last commit fixed the mpi4py issue.
@raffenet Could you please approve this trivial PR such that the mpi4py ABI builds can get back to green?