Slurm Core Training 6-8 February 2023

Slurm is critical to help you manage supercomputing resources. This course is targeted at new HPC users, who have beginning to intermediate Slurm knowledge. The training is a combination of presentation slides, live demo, Q&A and hands-on.

The training is offered virtual/online only. It is a 3-day event, 3 hours per day (from 9am – 12noon (AWST)). There are a limited number of seats available, so register only if you plan to attend.  

The following Overview topics are refreshers / target core knowledge. Attendees must have general computer literacy; no prior HPC experience is required.

1. How Slurm works
2. How Slurm schedules jobs
3. How long to wait
4. Slurm priorities
5. Learn how to play the game (best practices)
6. Hands-on / Your turn!

The following topics build on the previous module, targeting Resource Management. Attendees must have:

• A basic idea of code development
• Familiarity with Linux command line
• Experience with command-line editors (i.e. vi, nano, emacs)
• Experience with compilers

Topics:

1. Key Features and Resource Management
2. Hands-on with:
   1. Running a job/step allocation
   2.  Serial
   3.  OpenMP
   4.  MPI
   5.  GPU
   6. Hybrid

Register here:

Presenter: Jordi Blasco

Jordi Blasco is the Co-founder and Chief Technology Office of HPCNow! He has degrees in physics with specialization in computational physics from the University of Barcelona (Spain). Jordi has +17 years experience in High Performance Computing (HPC) in industry and academic environments, +12 years experience in solutions architect on mission-critical environments, and +12 years experience in leadership & coordination of cutting-edge HPC projects.

Jordi has a solid background in parallel programming, performance analysis, application tuning, and HPC system administration. Jordi is a very active contributor to several open-source projects dealing with High Performance Computing and he has worked as an independent advisor for several companies and research centers.