Pawsey Supercomputing Centre Western Australia award Hewlett Packard Enterprise (HPE) a A$48-million contract to build a new supercomputer as part of the government-funded Pawsey Capital Refresh Program.
Pawsey’s new system will be Australia’s most powerful supercomputer with 30 times more compute power and 10 times more energy efficiency to target complex modelling and simulation for accelerating research in areas such as astronomy, plant pathology, drug discovery and more.
The new system will have a speed performance of 50 petaflops, making it one of the largest supercomputers in the region. It will replace Pawsey’s Magnus and Galaxy systems, which are based on Cray technology.
HPE will build the new system using the HPE Cray EX supercomputer, touted as the world’s most advanced high-performance computing (HPC) architecture, to support higher performance, density, and efficiency needs.
Also, HPE will integrate the Cray ClusterStor E1000 system, which uses tailored software and hardware features to meet expanded high-performance storage needs, and feature a future-generation of AMD EPYC CPUs and AMD Instinct GPUs for significant compute power and targeted processors for AI and image-driven applications.
“Supercomputers like those at Pawsey are increasingly crucial to our ability to conduct world-class, high-impact research,” said Mark Stickells, executive director at Pawsey Supercomputing Centre. The upgrades we’re announcing are a critical move in strengthening Australia’s position in the global research environment and playing a part in major global research projects, from helping in the fight against COVID-19 to working with the precursor telescopes to the Square Kilometre Array.”
HPE, Cray and SGI, well before the companies merged with HPE, have had a 20 year-long history in powering Pawsey’s supercomputers. More than 1,600 researchers use these systems today to accelerate discovery and innovation.
Recent outcomes from Pawsey’s supercomputers include understanding grape vine viruses to preserve crop production, using AI to teach underwater robots to swim like fish, and detecting seven new galaxies which has been further studied using complex modelling and simulation as a step to understanding dark matter and the universe’s overall physical processes.