In 2005 engineers at the U.S. Department of Energy's Oak Ridge National Laboratory unveiled Jaguar, a system that would later be upgraded into a world-beating supercomputer. By 2011 it had swelled to a room-size system that used seven megawatts of energy, ran nearly 225,000 processor cores and had a peak performance of 2.3 quadrillion calculations per second. Still, to keep up with ever more sophisticated problems in energy research, the engineers had to scale Jaguar's processing power 10-fold. Simply adding more CPUs would have required a ridiculous amount of power—enough for 60,000 homes. Brute force wasn't going to do the trick.
Oak Ridge engineers instead turned to video games—or more precisely, to the graphics processors used in Microsoft Xboxes, Nintendo Wiis and other video-game systems. In late October 2012 Jaguar became Titan, a supercomputer that leverages both CPU and GPU (graphics processing unit) accelerators to deliver 10 times the performance of Jaguar while consuming five times less power. It has become the world's most powerful supercomputer, beating the DOE's Sequoia, which had held the title since last June. Titan's performance comes at a price, however. Because Jaguar used only CPUs, its computer architecture was simpler, which made it easier to write its software. “The algorithmic complexity to write that code for a machine like Titan is momentous,” says Tom Evans, an Oak Ridge computational scientist.
Titan will initially support a handful of key projects at Oak Ridge, including Denovo, software that simulates the behavior of neutrons in a nuclear power reactor. Oak Ridge's engineers designed Denovo for Jaguar as a way to help extend the life of the U.S.'s aging nuclear power plants, which provide about a fifth of the country's electricity. Running Denovo, Titan will take 13 hours to model the complete state of a reactor core at a specified point in time, a job that took Jaguar 60 hours to perform. “The ability to burn nuclear fuel uniformly is very much dependent on knowing and being able to predict the distribution of neutrons in the core,” says Evans, who helped to create Denovo. The DOE will also make Titan available to researchers in academe, government and industry.