ORNL's Jaguar Shatters Petaflop Barrier

Print Friendly, PDF & Email

Oak Ridge National Lab has just announced that Jaguar, their Cray XT supercomputer, has just broken the Petaflop barrier.  After recent upgrades and enhancements, the system has achieved a 1.6 petaflop peak performance mark.  They have also sustained performance of up to 1.3 petaflops.  This sustained number falls just short of RoadRunner’s 1.375 petaflop peak, number one on the Top500.

Jaguar is one of science’s newest and most formidable tools for advancement in science and engineering,” said Dr. Raymond L. Orbach, DOE’s Under Secretary for Science. “It will enable researchers to simulate physical processes on a scale never seen before, and approach convergence for dynamical processes never thought possible. High end computation will become the critical third pillar for scientific discovery, along with experiment and theory.”

The project leading up to Jaguar’s impressive numbers began in 2004 when the DOE’s Office of Science launched an effort to perform major upgrades to unclassified compute capability within the labs.  I would certainly say they hit their mark with this one.

With the expansion of the leadership computing resources at Oak Ridge, the Department of Energy is continuing to deliver state-of-the-art computational platforms for open, high-impact scientific research,” said Michael Strayer, Associate Director of the DOE Office of Science for Advanced Scientific Computing Research. “The new petaflops machine will make it possible to address some of the most challenging scientific problems in areas such as climate modeling, renewable energy, materials science, fusion and combustion.”

Very cool!  Congrats to the Cray/ORNL team that spent long hours in rolling in the upgraded cabinets.  For more info on the achievement, read the full release here.

Trackbacks

  1. […] A petaflop here, a petaflop there, and soon we are talking about real performance […]

Comments

  1. Uh…that’s not actually what that release says. It says they ran “an unprecedented superconductivity calculation that achieved a sustained performance of more than 1.3 petaflops.”

    Now, that’s very cool. The app scales to that size, runs across both systems, gets great performance. But is it double or single precision? And what about the Linpack performance?

    The 1.6PF peak here, and the 1.3PF peak of Roadrunner are double precision. I’m very curious to see next week’s Top500 to see what the apples to apples (as much as possible) comparison is.