Great Lakes is a campus-wide HPC cluster designed to meet the diverse needs of researchers across the university. It supports a variety of applications, including simulation, modeling, machine learning, data science, genomics, and more. The platform offers a well-balanced mix of computing power, I/O performance, storage capability, and GPUs. It utilizes Slurm as its workload manager, enabling users to work interactively or submit batch jobs.
To access this cluster, you must have a login and a Slurm account to submit jobs. Many researchers can use the U-M Research Comuputing Package to obtain a Slurm account for no cost, which provides 80,000 CPU hours of high-performance computing that can be allocated between the Great Lakes and/or Armis clusters.
There are three ways to interact with this cluster:
- Open On Demand — a web-based portal designed primarily for interactive work, with applications for Jupyter Notebooks, R Studio, Matlab, and more
- Command Line — Linux-based login nodes, where you can manage your files, submit and monitor your jobs
- Globus transfer — a high speed file transfer and management service
- Slurm User Guide - a guide to how the cluster manages jobs