Getting Started with High Performance Research Computing
What is the RIS Scientific Compute Platform?
The scientific compute platform provides research faculty access to computing resources and a “batch job scheduler” that runs large-scale, parallel computing tasks with access to many CPU and GPU cores, large amounts of RAM, high-speed networks, and high-performance storage systems.
What is the A&S Condo?
The A&S condo is a set of compute nodes that were purchased for the priority use of A&S research faculty. The condo offers more than 500 cores, 8TB of RAM and 8 GPU’s. All A&S research faculty requesting a new compute account at the RIS will be added to the A&S condo upon request.
Compute and Storage:
NOTE: A storage and compute account at the university research cluster (RIS) needs to be faculty sponsored. Any student, postdoc or staff member needing access to the RIS will need to have their account under a faculty sponsored member’s group. All faculty involved in research have access to 5TB of free active storage.
A&S will cover the cost for A&S faculty and lab members for use of the RIS general queue as well as the A&S condo. You will be asked to provide a cost center when setting up a new service or storage however you will not be charged for the general service or initial 5TB of storage.
Visit the FAQ for help on how to get started setting up a compute account and/or storage at the RIS.
Core Knowledge
It is recommended that you have some familiarity with how high-performance computing systems work. Knowledge of basic Linux commands is highly recommended before you begin working on the cluster. Additionally, the RIS uses Docker instead of the traditional HPC environment. Docker allows users to build their own software environments independently of anyone else. A Docker image is a lightweight, standalone, executable package of software that includes everything needed to run an application: code, runtime, system tools, system libraries and settings. To learn more about Docker visit the RIS Docker workshop. As an alternative to Docker the RIS offers Open on Demand (ODD) which is a web based interface that connects to compute resources. Visit our FAQ for more information.
Utilization Policy (RIS)
Data Storage User Policy: https://wustl.app.box.com/s/21vwnz7qc4d9bf7q2op90z2xiiuwiudx
Scientific Compute Platform User Agreement: https://wustl.app.box.com/s/6g9urv59fuesc02ygbmpb36sjfu2dkur