The US Again Has the Worlds Most Powerful Supercomputer

Plenty of people around the world get new gadgets Friday, but one in Eastern Tennessee stands out. Summit, a new supercomputer unveiled at Oak Ridge National Lab is, unofficially for now, the most powerful calculating machine on the planet. It was designed in part to scale up the artificial intelligence techniques that power some of the recent tricks in your smartphone.

America hasn’t possessed the world’s most powerful supercomputer since June 2013, when a Chinese machine first claimed the title. Summit is expected to end that run when the official ranking of supercomputers, from an organization called Top5 00, is updated later this month.

Supercomputers have lost some of their allure in the era of cloud computing and humongous data centers. But many thorny computational problems involve the giant machines. A US government report last year said the nation should invest more in supercomputing, to keep pace with China on defense projects such as nuclear weapons and hypersonic aircraft, and commercial inventions in aerospace, petroleum discovery, and pharmaceuticals.

Summit, built by IBM, occupies floor space equivalent to two tennis courts, and slurps 4,000 gallons of water a minute around a circulatory system to cool its 37,000 processors. Oak Ridge says its new newborn can deliver a peak performance of 200 quadrillion computations per second( that’s 200 followed by 15 zeros) employing a standard measure used to rate supercomputers, or 200 petaflops. That’s about a million times faster than a typical laptop, and nearly twice the peak performance of China’s top-ranking Sunway TaihuLight.

The view inside one of the Summit supercomputer’s 4,608 servers.

Oak Ridge National Laboratory

During early testing, researchers at Oak Ridge employed Summit to perform more than a quintillion computations per second in a project analyzing variation between human genome sequences. They claim that’s the first time a scientific calculation has reached that computational scale.

America’s new best computer is significant for more than only the geopolitics of computational brawn. It’s designed to be more suited than previous supercomputers to running the machine learning techniques popular with tech companies such as Google and Apple.

One reason computers have lately got much better at recognizing our voices and beating us at board games is that researchers discovered that graphics chips could set more power behind an old machine learning technique known as deep neural networks. Facebook recently disclosed that a single AI experiment use billions of Instagram photos occupied hundreds of graphics chips for almost a month.

Summit has nearly 28,000 graphics processors made by Nvidia, alongside more than 9,000 conventional processors from IBM. Such heavy use of graphic chips is unusual for a supercomputer, and it should enable breakthroughs in deploying machine learning on tough scientific problems, says Thomas Zacharia, director of Oak Ridge National Lab. “We set out to build the world’s most powerful supercomputer, ” he says, “but it’s also the world’s smartest supercomputer.”

Summit’s thousands of servers could fill two tennis courts.

Carlos Jones/ Oak Ridge National Laboratory

Eliu Huerta, a researcher at the National Center for Supercomputing Applications, at the University of Illinois at Urbana-Champaign, describes Summit’s giant GPU pool as “like a dreamland.” Huerta previously used machine learning on a supercomputer called Blue Water to see signs of gravitational waves in data from the LIGO observatory that won its founders the 2017 Nobel Prize in physics. He hopes Summit’s might will help analyze the roughly 15 terabytes of imagery expected to arrive each night from the Large Synoptic Survey Telescope, due to switch on in 2019.

Summit will also be used to apply deep learn to problems in chemistry and biology. Zacharia says it could contribute to an Energy Department project use medical records from 22 million veterans, about a quarter-million of which include full genome sequences.

Some people worried about US competitiveness in oversized calculating machines hope that the hoopla around Summit will inspire more interest in build its successors.

The US, China, Japan, and the European Union have all declared the first “exascale” computer–with more than 1,000 petaflops of calculating power–as the next big milestone in large-scale computing. China claims it will achieve that milestone by 2020, says Stephen Ezell, vice president for global invention policy at the Information Technology and Innovation Foundation. The US may get there in 2021 if Summit’s successor, known as Aurora, is completed on schedule, but the program has already been had delays.

The Trump administration’s budget this spring asked for $376 million in extra funding to help meet the 2021 target. It’s now up to the nation’s legislators to approve it. “High-performance computing is absolutely essential for a country’s national security, economic competitiveness, and ability to take on scientific challenges, ” Ezell says.

More Great WIRED Stories

How WIRED lost $100,000 in bitcoin Four rules for learning how to talk to each other again Your next glass of wine might be a fake–and you’ll love it Maybe DNA can’t answer all our questions about heredity Xbox is losing the console war–but that’s a good thing Appearing for more? Sign up for our daily newsletter and never miss our latest and greatest stories

Leave a Reply