Menu
Aussie supercomputer centre taps IBM Power

Aussie supercomputer centre taps IBM Power

NCI takes on four new IBM Power System servers

NCI's large-scale peak Fujitsu Primergy cluster system, Raijin. (NCI)

NCI's large-scale peak Fujitsu Primergy cluster system, Raijin. (NCI)

Australia’s national research computing facility, National Computational Infrastructure (NCI), has purchased four new IBM Power System servers for High Performance Computing (HPC) in a bid to drive its artificial intelligence, deep learning, and advanced analytics capabilities.

At the same time, NCI has become the first Australian organisation to join the OpenPOWER Foundation, a global open technical community enabling collaborative development and industry growth.

This means that the facility will introduce an open architecture solution and IBM Power Systems for HPC technology into its data centre for the first time, in the hopes of providing increased flexibility, optimisation, efficiency, and a bespoke solution to support its needs.

The computing power provided by NCI, based at Canberra’s Australian National University (ANU), is leveraged by researchers, industry, and government. The facility boasts a large-scale peak Fujitsu Primergy cluster system named Raijin, and a small specialized Fujitsu PrimeHPC FX10 system, Fujin.

A wide range of applications are run on NCI’s hardware to support national research projects, including climate and weather modelling, satellite data for environmental monitoring, and genomics research.

NCI’s purchase of the new IBM hardware and its membership of the OpenPOWER Foundation follow a collaborative development process with the IBM Australia Development Laboratory (ADL) and its Linux and Open Technology team, based in Canberra.

“To be the first ever Australian organisation to join the OpenPOWER Foundation provides recognition of NCI’s standing, and represents a step toward a more heterogeneous architecture,” NCI associate director, Allan Williams, said.

According to NCI, the ADL provides OpenPOWER development capability, and locally develops IBM's Power System firmware. NCI's decision to purchase the new IBM Power System servers was prompted by its direct access to the local IBM Power Systems development team.

“Having the local IBM Power development team at our fingertips in Australia, and being able to work with them in a truly collaborative fashion was critical to our decision to purchase the new IBM Power System S822LC for HPC servers. The new Power architecture provides the ideal infrastructure for GPU-based workloads," Williams said.

NCI said it plans to use the initial four IBM Power Systems HPC servers to run its top five graphics processing unit (GPU) based workloads to assess their performance.

“NCI plays a critical role in supporting some of Australia’s largest research projects, and this new system and architecture will be key for it to achieve higher levels of performance and greater computing efficiency,” said IBM Australia development laboratory director, Mike Schulze.

NCI’s IBM purchase comes almost two years after the facility inked a $2 million deal with NetApp that saw the software, systems, and services company work with Fujitsu to supply and install its NetApp FAS, E-series, and EF all-flash storage arrays with a raw storage capacity of 11 petabytes.

Subscribe here for up-to-date channel news

Follow Us

Join the ARN newsletter!

Error: Please check your email address.

Tags NCIAllan WilliamsIBMNational Computational InfrastructureMike SchulzeSupercomputer

Show Comments