HPC Administrators Handbook

• Insert some image as the logo

Why put this together?

During the last several years leading and managing a HPC organization with a diverse array of clients, I have found that there were many educational resources lacking in the HPC operational space. There are multiple resources for scientists and researchers to get started with developing scientific software including youtube videos, conference courses, and The Art of HPC. There are many fantastic lectures, video series, and slide presentations I have found through SC, LCI, and various LCF publications. I have yet to find a book which distills HPC Operations into a single book

Audience

This documentation is not aimed at the experienced HPC engineer with 20 years of experience, or who works at a leadership class compute facility with large support from HPC Vendors. This has been written with the intent to train new HPC engineers at my company who have either come straight out of college, or are switching from an enterprise IT career. I also hope this will benefit those graduate students or professors who need to run a small cluster at their university but don't know where to start, even if they are provided a turnkey solution.

That being said, I hope

The Goal

My ultimate goal in writing this is to get our hands dirty spinning up a local HPC cluster and various components.:wa