Skip to content

Welcome to the Office of Research Computing WIKI

Argo_blades.png

Original Dell C8000 Argo Nodes

The Office of Research Computing administers two high-performance computing clusters called ARGO and HOPPER, available to all GMU faculty and faculty-sponsored students.

ARGO is a 1500+ CPU core batch-processing cluster based on the condo model. Contributors buying nodes for the ARGO clusters are provided higher priority access to the whole cluster and temporary exclusive access to the funded nodes by arrangement.

HOPPER is a more powerful cluster with over 10,000+ cores, including 24 A100 80GB GPUs, 2 DGX A100 40GB GPUs, and 20 A40s for OpenStack. It is based on the condo model, but contributors buying nodes for the HOPPER clusters are provided preemptive access to funded nodes.

This wiki provides login information and various HOWTO's as a guide to ORC users. The articles cover a wide range of topics, including cluster specifications, getting an account, logging in, uploading data, avoiding quota issues, getting started with SLURM, environment modules, installing user packages, running parallel jobs, running machine learning workloads, creating checkpoints, using Globus, and more.

To get started with our documentation, refer to any of the following pages:

About the ORC Clusters Getting Started Frequently Viewed Pages
About ARGO Getting an ORC Cluster Account Getting Started with SLURM
About HOPPER Logging into HOPPER Python Virtual Environment
ORC Main WebPage Getting Started with SLURM Data Transfer Using Globus
Contact the ORC for Assistance Open OnDemand on HOPPER HOPPER DGX_A100_User_Guide