Distributed setup calls _make_cross_face_batches once per face

[inducer]

Here. It definitely shouldn't. As the name possibly suggests, _make_cross_face_batches is supposed to be a batched routine. (called once per rank pair) @MTCam spotted this when doing some parallel runs.

This is actually pretty bad, since it creates lots of small interpolation batches rather than one big one.

[inducer]

@majosm, would you be willing to take a look at this?

[inducer]

This is actually pretty bad, since it creates lots of small interpolation batches rather than one big one.

The impact of that is that MPI buffer packing is essentially a Python loop over elements/faces. (and it obviously shouldn't be)

[MTCam]

Doesn't this issue also affect wave-eager examples?

[inducer]

It does.