Arm Throwing Elbows: LRZ to Deploy Arm-based HPE Cray CS500

Print Friendly, PDF & Email

It’s been a big week for Arm: the Fugaku supercomputer at Japan’s Riken research center was named no. 1 on the TOP500 listing of the world’s most powerful HPC systems, and today, the Leibniz Supercomputing Centre (LRZ) in Munich announced it will deploy HPE’s Cray CS500 with Fujitsu A64FX chips based on the Arm architecture – the same processor used in Fugaku (and then there’s Apple switching from x86 for new Arm chips).

LRZ, Munich (Credit: Michael Brenner – Own work, CC BY-SA 3.0)

LRZ said the HPE system is “a central asset for the LRZ test bed program” and its system, known as BEAST (Bavarian Energy, Architecture and Software Testbed), offering “pathways for traditional modelling and simulation tasks while being equally suitable for data analytics, machine learning and artificial intelligence workloads.”

The CS500 Cluster Supercomputer will be made available to core academic partners and select projects as well as HPC practitioners. It features the Cray Programming Environment, an integrated software suite designed to maximize programmer productivity and support the vectorised processor units.

The system’s A64FX processors will be equipped with 32GB of second-generation high bandwidth memory (HBM2), and the servers are connected by a Mellanox EDR-Infiniband network. The system comes with an Open-Source (GCC/LLVM) software stack.

“The Scalable Vector Extension (SVE) architecture, the high memory bandwidth with HBM2, and the Cray Compiler Environment and software stack are a few of the things we’re excited to explore and better understand in support of our users and their scientific work,” said Josef Weidendorfer, team lead Future Computing at LRZ.

“It is one of our core tasks to explore new and diverse architectures within our Future Computing Program,” said Dieter Kranzlmüller, LRZ director. “Together with our core partners, we look forward to exploring the capabilities of this technology and the benefit it brings to our users’ science – especially in the area of HPC and AI.”