Pratik Nayak

Hm, they dont seem to have a GPU version. I think that is the actual last update, but I am not sure. the user guide says 2001. :|

Naming it `Coarsening` is a good idea. How about `SimpleCoarsening` ? Because you have the ability to specify an array for the coarsening indices, `Uniform` might not be the best...

Yes, we could technically put them in two separate classes. I guess at some point we will have a lot of separate classes. But I guess that might be okay...

Yes, I think generation of the restriction and prolongation matrices can be de-coupled from the coarsening strategy itself in some cases. I don't have a clear solution for that now...

@fritzgoebel, I think it might make sense to add this to an updated version of this branch, `mpi-base-dist-mat`, which also runs CI for MPI ? @tcojean , 1. Yes, I...

@upsj, Thank you for the review and the comments. I will try to update it soon.

@tcojean, thanks. I will look into GPU timers and see if it extensible from within googlebenchmark. I agree with your other suggestions.

I think with the value semantics PR update this might need to be rebased and adapted.

Do you mean an additive identity ?

:+1: I think `host` is a good name. This would be interface breaking, so I guess we add the new function name, deprecate `get_master()` and remove it in the next...