roystgnr
roystgnr
## Background information ### What version of Open MPI are you using? (e.g., v3.0.5, v4.0.2, git branch name and hash, etc.) `v4.1.2`, and the bug is still present for me...
This replaces #3188 - it starts with that branch, but adds data output as well. I still have more testing to do before merging, but I'm again at a stage...
We don't actually need an ordering here, and count/insert/etc operations in O(1) instead of O(log(N)) might be nice. @friedmud, try this on the case from #1859 and see if it...
OpenMPI has a fix for their regression currently posted at https://github.com/open-mpi/ompi/pull/10527, and MPICH seems to already have their git head working again, but in the meantime, not being able to...
I noticed some time ago that there was a regression in periodic boundary conditions on distributed mesh on some weird corner case (I could run libMesh "make check" on up...
Hopefully not send/receiving with every single other processor will help with the scalability issues in #1817, and this will automatically suck in any subsequent parallel_sync re-optimization too.
Otherwise we create inconsistent coarsening flags on adaptively h-refined meshes! This should fix #1832 @bboutkov, could you try it out too?
Declaring a `std::map vals` and then trying to perform a parallel `set_union(vals)` is enough to demonstrate the problem. `set_union` correctly detects that we need to turn the `map::value_type` into a...
@friedmud points out that MOOSE currently supports array variables as a bit of a hack; we could put this support down at the libMesh level and use less memory+CPU+code. It...
Much discussion on Slack with @lindsayad and @jwpeterson seems to boil down to: 1. In the short term, we need --enable-cxx14 and --enable-cxx14-required arguments, working the way their cxx11 equivalents...