GPU Computing

Graphics Processing Units (GPUs) were, as the name suggests, originally designed for the efficient processing of graphics. Over time, they were developed into systems that were capable of performing general purpose computing which is why some people refer to modern GPUs as GP-GPUs (General Purpose Graphical Processing Units).

Graphics processing typically involves relatively simple computations that need to applied to millions of on-screen pixels in parallel. As such, GPUs tend to be very quick and efficient at computing certain types of parallel workloads.

Access to GPU resources

Public GPU nodes are available to use in Stanage and Bessemer. These can be be used without acquiring extra permissions.

Research groups also have an option to purchase extra resources/priority in the cluster. To make use of these extra resources (e.g. GPU nodes (Computer Science)) / this extra priority access researchers need to be approved by the academic/researcher who made that purchase.

Using GPUs on the different clusters

Hardware, software and ways to access GPUs differ between the clusters. Instructions specific to each cluster can be found below:

• Using GPUs on Stanage

• Using GPUs on Bessemer