Valentin Churavy
Valentin Churavy
That look correct to me. I just noticed that we don't have mvapich in the test matrix. Would you be interested in adding that?
Or a `test/runtests.jl` file in MPIPreferences that uses different observed MPI_VERSION_STRINGs to check that identify_implementation_version_abi returns the right things?
In a multi-threaded environment Julia uses segmentation faults on special addresses for it's safepoint implementation. If the MPI implementation intercepts signals this will cause spurious aborts. UCX is a library...
If you can figure out how to tell Intel MPI not to intercept signals we can add that as a vendor specific workaround.
> However it seems though a more principled approach would be to tell Julia to use another signal for GC coordination, since it seems that in any situation where Julia...
Can you see which libfabric version the IntelMPI is using? There was a signal handler related bugfix that landed in v1.10.0rc1 (https://github.com/ofiwg/libfabric/pull/5613)
@simonbyrne the latest is `2021.8.0` maybe worth an update?
This could maybe be of inspiration https://github.com/cesmix-mit/LAMMPS.jl/tree/main/res
Should FFTW check for C_NULL and provide a better error?
Currently https://doi.org/10.5281/zenodo.7062685