Single-node or multi-node run examples #52
Description
Hi! From what I can tell in the README, I need to compile a custom "deck" and then run the executable. Is that correct? Given that context, would this work just on a single node, or does it work with multiple nodes?
The build I currently have is here:
https://github.com/converged-computing/metrics-containers/blob/main/cabanaPIC/Dockerfile
And I just run cbnpic and that seems to run OK on a single node. What I'm interested in is a flux run example, if that is possible, across nodes.
And then after running, how do I assess the output? What is the FoM?
To give you some context for my questions, we are preparing a large set of proxy apps, benchmarks, and similar, and are running on cluster sizes 4-128 on a cloud, with a helm chart deployment that makes it one command. We could run this as a single node benchmark or across the scale, depending on what you think is best. Ideally there is a FoM or something we can plot to demonstrate the environment.
If you have other suggestions for similar apps, would love those too. Thanks for your help!