The Princeton HPC clusters offer several machine learning (ML) software libraries. Some are straightforward to use while others need to be installed and are highly configurable. Additional complications arise when job scheduler scripts need to be written to take advantage of multi-threading and/or GPUs. This workshop will show participants how to get started with various ML libraries and use these libraries optimally on the HPC clusters. We will cover PyTorch, TensorFlow, Spark, NVIDIA Rapids, R, Julia and more. Note that the emphasis is entirely on the libraries with little discussion of ML theory.
Learning objectives: Attendees will learn which ML libraries are available and how to use these libraries optimally on the HPC clusters.
Knowledge prerequisites: Basic Linux and knowledge of machine learning theory
Hardware/software prerequisites: (1) Have an SSH client installed on your laptop. (2) Register for an account on Adroit(link is external). This is the cluster we will use for demonstration purposes. Make sure you can SSH to Adroit before the workshop by following this guide.
Workshop format: Demonstration and hands-on