Introduction

Grex

Grex is an UManitoba High Performance Computing (HPC) system, first put in production in early 2011 as part of Westgrid consortium.

The orihginal Grex was an SGI Altrix machine, with 312 compute nodes (Xeon 5560, 12 CPU cores ad 48 GB of RAM per node) and QDR 40 Gb/s Infiniband network. “Grex” is a Latin name for “herd” (or may be “flock”?). The names of the Grex login nodes (bison, tatanka, aurochs, yak) also refer to various kinds of bovine animals.

Since being defunded by Westgrid (on April 2, 2018), Grex is now available only to the users affiliated with University of Manitoba and their collaborators. The old Westgrid documentation, hosted on the Westgrid website became irrelevant after the Grex upgrade, so please visit Grex's New Documentation. Thus, if you are a user experienced in the previous “version” of Grex, you might benefit from reading this dociment: Description of Grex changes. If you are a new Grex user, proceed to the quick start guide and documentation right away.

It was primarily intended for applications that can take advantage of non-blocking low latency InfiniBand networks and (back then) larger memory per compute node.

In 2017, a new Seagate Storage Building Blocks based Lustre filesystem of 418 TB of useful space was added to Grex.

There are now several researcher-contributed nodes (CPU and GPU) to Grex.