[aspect-devel] Benchmark

[Timo Heister]

> attached figures. I am still wondering though, why I can't run the post
> processor in parallel. Do you happen to know that?

Yes. This is because integrate_difference() is a local operation. You
need to aggregate the results. For the L1 norm you need to do
  Utilities::MPI::sum(cellwise_errors_u.l1_norm(), MPI_COMM_WORLD)
and for the L2 norm:
    std::sqrt(Utilities::MPI::sum(cellwise_errors_pl2.norm_sqr(),
MPI_COMM_WORLD))

You can check if it is correct by checking that you get the same
errors with different number of processors.

-- 
Timo Heister
http://www.math.clemson.edu/~heister/