Barry Smith <[email protected]> writes:

I think we should start porting the PetscFE infrastructure, numerical integrations, vector and matrix assembly to GPUs soon. It is dog slow on CPUs and should be able to deliver higher performance on GPUs.

IMO, this comes via interfaces to libCEED, not rolling yet another way to invoke quadrature routines on GPUs. DMPlex setup and distribution could conceivably be ported to GPUs, but it would be a monumental task and that stuff is usually done once and intermediate structures don't necessarily fit in device memory even when they fit comfortably in DRAM. Way too big of a task for one hackathon.