We have recently worked with two universities, Queen Mary University of London (QMUL) and Newcastle University, to bring greater processing power to their existing HPC infrastructures. QMUL’s researchers were undertaking more and more research involving Artificial Intelligence (AI), deep learning and analytics. While Newcastle University had researchers from the mathematics, statistics and physics departments who were all in need of greater power to complete their computational physics projects successfully.
For QMUL, we designed, integrated and configured two IBM Accelerated Compute Servers (AC922) powered by POWER9 CPUs, Volta GPUs and NVLink 2.0 interconnects. Both universities were the first to use the POWER9 system.
The AC922 leverages IBM’s new POWER9 processor with a myriad of modern connectivity capabilities – which improves data movement by up to 5.6x over the PCIe Gen 3 buses found in x86 servers. IBM Power Systems deliver the only architecture enabling NVLink between CPUs and GPUs, unlocking new potential for accelerated computing.
In our recent work with QMUL, Professor Sean Gong who is Head of the Computer Vision Research Group told us that after previous test trials on IBM Minsky POWER8 servers, he was expecting to see significant benefit from the new POWER9 servers for deep learning on big video data.
The team at Newcastle University were in the same mind. In trial runs, researchers got a ‘speed up factor’ in the order of 10x magnitude. Carlo Barenghi, who is Co-Director of the Joint Quantum Centre at Newcastle University said that traditionally they face major difficulties because their calculations are non-linear, time-dependent and three-dimensional – generally, solving them is out of reach with pencil and paper, and the numerical computation requires large memory and fast speed. He said he was humbled from the start of the project by the speed gains on offer with the new system.
In such a highly competitive field as academic research, providing superior HPC services to compute large quantities of data quickly can help to attract world-class researchers, as well as grants and funding providing another example of how OCF is helping UK academia reach its goals. If you’d like to hear more about our work with IBM POWER9, please get in touch with us here.