Tpetra: Measure thread scaling of solver kernels, with MPI (multiple nodes)
Created by: mhoemmen
@trilinos/tpetra Epic: #820 (@jjellio, I can't assign you yet because you're not part of the Trilinos organization. See #819 (closed). After that's done, I'll assign you too :-) .)
This is like #824 (closed), but for multiple nodes. A modest number of nodes suffices; large node counts is a different epic. The point is to increase communication costs, exercise MPI's interaction with the network interface, and make sure this all plays nicely with threads.