Reaching Others University at Buffalo - The State University of New York
Skip to Content

User Guide

User guide for running computations on the CCR cluster.   Topics include an introduction to cluster computing, basic UNIX, login, file transfer,compiling code, as well as submitting and monitoring jobs.

We have big plans in place for 2015!  Here's a list of the most important things you need to know after the recent downtime and storage migration.  As always, contact CCR Help if you have any questions or problems.
A brief introduction to help new users get started using the CCR cluster.
SLURM (Simple Linux Utility for Resourcce Management) is a workload manager that provides a framework for job queues, allocation of compute nodes, and the start and execution of jobs.
Short list of basic UNIX commands and the CCR reference card.
Description of how to login using secure shell and transfer files to and from the cluster login machine.
Certain software packages (Matlab, Paraview, etc) require an X11 display or OpenGl context even for non-interactive jobs. It is possible to provide a software only solution that does not require a graphics card. These solutions are only useful for fairly simple graphics needs, such as taking screen-shots of geometry. Operations such as volume rendering will be 2-3 orders of magnitude slower than on a dedicated graphics card and should not be attempted with this process.
User disk space at CCR is contained in a high-performance Network Attached Storage (NAS). CCR's NAS provides a total of 3 PB of disk storage to the general compute cluster and other servers at CCR.  Directories are available via the GPFS client on the cluster front end and all compute nodes.
Basic instructions on compiling codes on the compute cluster.
Jobs are submitted to CCR clusters using a batch queuing system. This provides the best means to insure an equitable distribution of CCR's computing resources among all users.
Detailed information on debugging, profiling, and checkpoint/restart among others.