Pratik Nayak

No, I mean building Ginkgo with the Kokkos dependency always enabled.

Yes, that is what is now. But if I understand correctly, what @upsj is suggesting is that you remove the option to disable it, thereby always building Ginkgo with Kokkos...

@upsj, This Kokkos layer header would still be a part of `ginkgo.hpp`, right ? Wouldn't the applications then necessarily be compiling with Kokkos (if available), without a way to awitch...

Okay, I see. Then I think I agree with @upsj that if the users are explicitly including the header, then having a CMake option is not necessary, and we are...

Do we push to have this in 1.6.0 ?

@greole , Yes, but a coarse generation algorithm ( that is distributed capable) is necessary. Meaning we need to have the equivalent of AMGX which generates the triplet (R, A_c,...

@MarcelKoch, yes, I dont intend to merge this yet. I just wanted to show what changes could be necessary. At present we do not need the partition or the matrix_data.

@greole, yes, #1403 would need to be merged as well. @yhmtsai , please feel to merge this when you are ready. If you need me to merge it, let me...

@upsj, After a bit of thought, I think this class should not represent Geometric/Structured coarsening. Uniform coarsening is just a cheap coarsening method that just uniformly discards rows and columns...

In a similar fashion to PGM, the prolongation matrix will be a transpose of the restriction matrix. I think maybe I have given a wrong impression that this would be...