Slurm (Simple Linux Utility for Resource Management) is a powerful system for managing and scheduling computing jobs that is very popular at large-scale research computing centers. The SSCC is in the process of greatly expanding the size of our Slurm cluster, and we encourage all SSCC researchers who run even moderately big research computing jobs to learn now how to use Slurm so you can take advantage of the computing power we'll soon available. It's actually very easy.
In this workshop we'll introduce the core concepts of Slurm and show you how to use it. You'll learn how to submit Linux jobs to Slurm, specify your jobs' requirements, and figure out what those requirements are. Ideally you'll come to the workshops with one or more Linux jobs to run, and by the end of the workshop you'll have them running in Slurm. Everything we'll learn applies in the Silo environment as well.
This workshop is taught in conjunction with the "Running Big Research Computing at the SSCC" workshop immediately before it. That workshop will teach you about the SSCC's computing resources, how to run interactive jobs on Linstat, and the little bit of Linux you need to know in order to do so. If you are already comfortable running jobs on Linstat and just want to learn about Slurm, you only need to attend this workshop.
You must be a member of the Social Science Computing Cooperative to use the SSCC's Slurm cluster. SSCC accounts meant for class work do not have access to Slurm; if you have a Z: drive (Linux home directory) when you log into Winstat you are a member of the Cooperative with an account meant for research.
Instructor: Dimond
Room: 3218 Sewell Social Sciences Building
Date: 9/6
Time: 11:15 - 12:00
Semester: summer22