The Future Of Supercomputing Is Now

With The HPE Apollo 80 With A64FX


If you want to get the benefits of accelerated computing and high bandwidth memory as well as be on the rise wave of Arm-based compute, you don’t have to wait and you don’t have to buy CPU-GPU systems and adopt a complex, hybrid programming model. All you need is an HPE Apollo 80 with the A64FX processor – the same processor used in the “Fugaku” system built by Fujitsu at the RIKEN Lab in Japan, which is the fastest supercomputer in the world – and you can get started today.

Hewlett Packard Enterprise has been on the bleeding edge of Arm compute for the past several years, particularly in supercomputing, and has extended the Apollo 80 system to bring the substantial benefits of the A64FX architecture to more general purpose HPC clusters. Many HPC applications have memory bandwidth constraints as well as intense computational requirements, and many existing CPU architectures make customers overprovision their memory to boost the bandwidth. The Apollo 80 with A64FX system brings the benefits of GPUs – massively parallel vector engines and high bandwidth memory – to CPUs, obviating the need for a hybrid architecture.

HPC centers in the United States and Europe have been testing the Apollo 80 with A64FX systems with their own codes and have also been sponsoring hackathons, and this panel discussion will dive into the HPC application porting efforts to date and the results that researchers have attained.

Join Simon McIntosh-Smith, professor in High Performance Computing and head of the Microelectronics Group at University of Bristol, Robert Harrison, professor in the Applied Mathematics and Statistics department and founding director of the Institute for Advanced Computational Science at Stony Brook University, Sharda Krishna, senior manager of HPC and AI supercomputing products at Hewlett Packard Enterprise, and Timothy Prickett Morgan, co-editor of The Next Platform, for a lively discussion about the issues of porting code to the A64FX architecture and the performance benefits that real users are seeing with this architecture, today.