Tpetra: Isolate sparse matrix-matrix multiply local kernel
Created by: mhoemmen
@trilinos/tpetra @mndevec @srajama1 @csiefer2
In Tpetra, we need to isolate the "local" part of the sparse matrix-matrix multiply kernel from the "global" (MPI communication) part. This will facilitate thread parallelization and the use of third-party libraries' implementations of the local kernel.