Mark,
Is there any chance the Chombo-Crunch team could cook up a portable good
sized example (but not too large), preferably with a run time parameter that
determines the problem size, example that anyone could use as a benchmark for
"adding OpenMP" to PETSc. This way we could have real numbers as we compare
different approaches; for example calling MKL vs putting in a few OpenMP
pragmas in the source code.
Thanks
Barry
For size I'm thinking of running on a handful of cores up to a few nodes of KNL.
