In-place NCCL reduce-scatter is not in-place

[ndryden]

The NCCL backend's in-place reduce-scatter uses sendbuf = recvbuf here. But per NCCL documentation, the in-place reduce-scatter should actually have recvbuf be the appropriate offset into the recvbuf (see here). This appears appears to differ from the usual MPI semantics. Our current version works, but I'm not sure whether using overlapping buffers without telling NCCL that we are is safe. We may also be missing some performance benefits.