Python on HPC Clusters
About the Tutorials
This tutorial series covers topics on using Python on HPC clusters. The specific steps are based on the HOPPER cluster at George Mason University in Fairfax, VA. They should be implementable on most HPC clusters that have the SLURM scheduler installed, the Environment Modules system for managing packages and Open onDemand for a web-based GUI to access the cluster resources.
Tutorial Pages
| Name | Description |
|---|---|
| Running python Natively with a Module | Covers the steps on how to run python with SLURM using python modules on HPC clusters. |
| Running python with python virtual environments | Covers managing python packages and running python scripts on HPC clusters with python virtual environments. |
| Running python with conda-environments | Covers managing python packages and running python scripts on HPC clusters with conda environments. |
| Running python from a Notebook | Covers managing python packages and running python on HPC clusters from a GUI while using either conda environments or python virtual environments. |
| Example with Pytorch | A hands-on demo with a pytorch example. |
Tutorial videos and Slides
Links to recorded sessions and slides:
| Title | Presentation Date | Links |
|---|---|---|
| Managing Python Packages on HPC | 11/02/2023, 11:00AM | Slides |
| Recording |
Upcoming Sessions
| Title | Date |
|---|---|
| Profiling Multi-GPU Jobs on a Cluster, Examples with Pytorch DDP | TBD |
Check in for more tutorials and other demos related to Python and other packages on HPC Clusters.