Aurora Supercomputer Targets 2 Quintillion Ops per Second

Aurora, built by Intel and Hewlett Packard Enterprise, is the latest supercomputer to come online at the Department of Energy’s Argonne National Laboratory outside of Chicago and is among a new breed of exascale supercomputers that draws on artificial intelligence. When fully operational in 2024, Aurora is expected to be the first such computer that will be able to achieve two quintillion operations per second. Brain analytics and the design of batteries that last longer and charge faster are among the vast potential uses of exascale machines.

“Aurora is the size of two tennis courts and weighs 600 tons,” according to The Wall Street Journal. It “is slowly being turned on, rack by rack” as technicians spend months looking for flaws “like mechanics testing a Formula One car before a race.”

The Top500 global ranking of supercomputers said that as of this week the partially functional Aurora — currently performing about one quintillion ops per second — is already the world’s second-most-powerful supercomputer, exceeded only by the Oak Ridge National Laboratory’s Frontier.

Aurora is powered by more than 60,000 GPUs, giving it approximately 70 percent more memory than Frontier, which has nearly 40,000 GPUs, reports Fast Company.

“The extra memory will allow the computer to ‘tackle problems that no other machine can approach,’” Intel’s Olivier Franza, Aurora’s chief architect, told WSJ, which writes that the machine can “screen 22 billion drug molecules an hour, accelerating potential drug discovery.”

“The extra memory will also give Aurora the ability to handle the biggest large language model — a predictive AI system similar to ChatGPT — ever deployed, Franza said” via WSJ, which adds that “another potential task is mapping connections in the brain,” an undertaking of such extreme complication “it could take Aurora a full day to process a tiny sliver of the brain.”

Elon Musk’s Tesla is building Dojo, a $1 billion exascale supercomputer, and the Lawrence Livermore National Laboratory in California is switching on El Capitan, a $600 million exascale supercomputer “expected to be deployed next year” that “could eventually exceed Aurora’s computational firepower,” according to WSJ.

As AI makes its effects felt on computing, many more of these powerful machines are coming online worldwide. The UK has also been busy booting up exascale supercomputers, with three in the works.

It is well known within the high-performance compute world that “China has these computers, and they have been operating for a while, but they have not run the benchmarks,” HPCwire reports, sourcing Oak Ridge HPC pioneer Jack Dongarra.

No Comments Yet

You can be the first to comment!

Leave a comment

You must be logged in to post a comment.