MPI_Neighbor_xxxxx Optimizations?

[drmichaelt7777]

I was wondering if the MPI_Neighbor_xxxxx calls have received any special design and optimizations in OpenMPI 4.1.x+ for these patterns of communication.

Is UCX or UCC/HCOLL doing anything special in a more "intelligent" way to provide optimized neighborhood collectives? For instance, these could benefit from proximity awareness and intra- vs inter-node communications. However, even single node communications have hierarchical structure due to the increased number of num-domains, larger L3 caches and so on.

thanks
Michael