EPCC, the supercomputing centre at the University of Edinburgh, is perhaps best known for being home to the UK's most powerful supercomputer, ARCHER2. Sitting alongside it, very soon, will be our first Graphcore IPU Pod. These two quite different machines perfectly illustrate the centre's mission: to accelerate the effective exploitation of novel computing throughout industry, academia and commerce. In Graphcore's Intelligence Processing Unit, we recognised a tool that will be of huge interest to our many partners, allowing them and the EPCC team to explore innovative applications of AI within their scientific and business challenges. The IPU's unique architecture is rooted in a deep understanding of the novel and idiosyncratic compute requirements of AI.

The world generates 2 billion tonnes of domestic solid waste annually but less than ten per cent is recycled because the current recycling process is extremely inefficient. We're working with a start-up that is developing a revolutionary robotic system to significantly increase recycling efficiency. Danu Robotics is an Edinburgh-based clean tech company that is looking to improve the efficiency of recycling through automation. Currently, most recycling centres and plants operate by having human pickers sort through recycled goods on conveyor belts – any recyclable of the wrong category (eg any soda can in the paper recycling) is manually removed from the conveyor belt and either sorted into the correct category or disposed of if not recyclable. This process has many disadvantages: sorting recycling is a thankless and repetitive task; sorters are prone to error (especially late in a shift); and, as sorting rates are determined by the number of people working the conveyor belt, sorting can quickly become a bottleneck in the recycling process.

The battle for HPC centers and national labs is underway among the leading AI chip startups in the high-end datacenter space (Graphcore, Cerebras, and SambaNova in particular). We talked last week about how Graphcore is stacking up in traditional supercomputing spaces at the University of Bristol, SambaNova has found inroads at Argonne and Lawrence Livermore (LLNL) labs in the U.S., and Cerebras has also become established at LLNL. In addition to those recent wins, Cerebras has crossed the Atlantic for its first European win at EPCC in Edinburgh. Despite this tit-for-tat in HPC site wins among the AI chip triumvirate, the jury is still out on what the favored architecture will be to meet the needs of deep learning in supercomputing. There are enough systems distributed around the globe now, however, that within a year we might start to have a sense, especially since EPCC will be evaluating the Cerebras experiments to its neighbors with Graphcore.