I have reviewed the MapD docs on distributed configuration (https://www.mapd.com/docs/latest/mapd-core-guide/distributed/).
But what if I have a single node with multiple GPUs? Does MapD core discover and use all GPUs automatically? Or do I need to deploy this as a cluster? In that case, would I have a separate entry in the Cluster.conf file for each GPU?
Thanks for developing and open sourcing this fabulous resource!