We have now moved into a purpose-built £40M new building at Upper Mountjoy in Durham, which is indicative of the major investment the University is making in Computer Science. The building will also include colleagues from Mathematical Sciences and will mean we can further develop joint teaching and research strategies.
The building has academic offices, offices for research staff and students, open-plan space for undergraduate students to work, breakout spaces to collaborate, labs, computer rooms and, of course, a café.
An innovative feature of the new building is the Hazan Venture Lab which is run by Careers and Enterprise and will be the first space in the University dedicated to developing student enterprise and entrepreneurship.
We are fortunate to have the following hardware available – several local and regional supercomputers for High-Performance Computing (HPC), a GPGPU-driven supercomputer primarily used for data analysis and machine learning, several visualisation and data postprocessing labs, and so forth. On top of this, we host additional local kit which we use to give students and researchers a safe environment to prototype solutions, to explore novel technologies before they hit the market, or to actually design new solutions.
Durham hosts its own local supercomputers (the Hamilton family) and the DiRAC Cosma machine. In Computer Science, we furthermore have our own Dine installation which we drive in collaboration with DiRAC. Dine is a small 16-node general purpose supercomputer. Its outstanding feature is that it hosts SmartNICs – network devices which are themselves equipped with processors that can hijack and reroute messages in the network, alter message content, or run computations on messages while they travel through the supercomputer network. This allows our researchers to investigate novel data transportation concepts, to simulate different supercomputer topologies, or to work on novel security concepts.
Further details about High Performance Computing Cluster.
Our NVIDIA CUDA Centre (NCC) GPGPU system is a multi-node / multi-GPU server that we use primarily to prototype machine learning (ML) algorithms and codes before they hit the University's "big" system Bede. The local system features the latest ML software stack mainly focusing around PyTorch and TensorFlow, and consists at the moment of four different subservers with different GPU generations.
Further details about Machine Learning Cluster.
The purpose is insight, not numbers. Based on Richard Hamming's famous quote, Durham's Computer Science hosts its own visualisation lab equipped with a set of freely movable large 3d screens, 3d autostereoscopic monitors that do not require glasses, and plenty of smaller kit. The lab allows us to visualise the large data we obtain from various machines and to interactively navigate through big result sets. It also allows us to play around with novel visualisation concepts – both from a software and a hardware perspective – and to prototype software that later runs in big visualisation centres.