pressmaster -

Australia to upgrade supercomputer in HPC boost

The Gadi supercomputer at the Australian National University will run 10 times faster than its predecessor, giving researchers access to high performance computing resources to solve the toughest research problems

Australia is bolstering its high performance computing (HPC) chops with a supercomputer that boasts a 10-fold increase in speed over its predecessor, giving researchers access to computing resources needed to solve complex research problems.

Dubbed Gadi, which means “to search for” in the language of the Ngunnawal, the first inhabitants of the Canberra region, the supercomputer will be housed at the Australian National University (ANU) in Canberra and operated by the National Computational Infrastructure (NCI).

When ready by November 2019, Gadi, which cost the Australian government A$70m under its National Collaborative Research Infrastructure Strategy, will replace the NCI’s current supercomputer that has been in use since 2012. Both machines are supplied by Japanese IT giant Fujitsu.

The new supercomputer will comprise 3,200 nodes. Its users are expected to hail from government research bodies such as the Commonwealth Scientific and Research Organisation (CSIRO), Geosciences Australia and the Bureau of Meteorology.

ANU vice-chancellor Brian Schmidt said the upgrade will power some of Australia’s most vital research, noting that the NCI plays a pivotal role in the national research landscape.

“This new machine will keep Australian research and the 5,000 researchers who use it at the cutting-edge. It will help us get smarter with our big data. It will add even more brawn to the considerable brains already tapping into NCI,” Schmidt said.

Gadi is expected be fitted with high-end components from Fujitsu as well as that of Lenovo, Intel, Nvidia, NetApp, Mellanox and Schneider Electric, among others. To keep things cool, it will also use liquid cooling technologies with warm water, allowing for high-density computing.

While Australia’s top HPC facilities are on the Top 500 list of the world’s most powerful computers, their positions are slipping. In its 2016 national research infrastructure roadmap, the Australian government had called for an immediate need to refresh Australia’s national HPC infrastructure.

In April 2018, the government earmarked A$70m to fund replacements for the flagship supercomputer, Magnus, as well as the real-time supercomputer, Galaxy, at the Pawsey Supercomputing Centre in Perth. Both systems were said to be close to the end of their operational lives.

Magnus, a Cray XC40 considered as one of the most advanced supercomputers in the southern hemisphere, currently supports the operational requirements of several Australian radio telescopes such as the Australian Square Kilometre Array Pathfinder and the Murchison Widefield Array.

In 2017, CSIRO also upgraded its Bragg supercomputer with Bracewell – effectively doubling its total aggregate performance – to keep pace with global research.

With a similar footprint to Bragg, Bracewell sports over 114 nodes in the form of Dell PowerEdge C4130 servers that are decked out with Nvidia GPUs and Intel Xeon CPUs.

Read more about high-performance computing in APAC

Read more on Clustering for high availability and HPC

Data Center
Data Management