The Longleaf cluster is a Linux-based computing system available to researchers across the campus free of charge. With nearly 6500 conventional compute cores delivering 13,000 threads (hyperthreading is enabled) and a large, fast scratch disk space, it provides an environment that is optimized for memory and I/O intensive, loosely coupled workloads with an emphasis on aggregate job throughput over individual job performance. In particular, workloads consisting of a large number of jobs each requiring a single compute host are best suited to Longleaf. The Longleaf cluster is targeted for data science and statistical computing workloads, very large memory jobs, and GPU computing. Resources are managed through a fair-share algorithm using SLURM as the resource manager/job scheduler.
Get an account on Longleaf and learn more:
Sign up for the next “Using Longleaf” Research Computing Training Course:
Research Computing Course Calendar.
Review Research Computing Course Materials:
How to Order/Buy a Reserved, Dedicated Compute Node on Longleaf:
Cluster Patron Node