PFLOPS in the NYT

From today’s NY Times, a story of RoadRunner’s PFLOPS milestone. This story actually does a good job of laying out the HPC landscape for a general reader.

An American military supercomputer, assembled from components originally designed for video game machines, has reached a long-sought-after computing milestone by processing more than 1.026 quadrillion calculations per second.

Oddly enough, classified as a “military supercomputer.” Ok, I guess the military is the ultimate customer of the stockpile stewardship mission. I would have thought this was a DOE supercomputer though.

These are the kinds of stats I use in my tours (albeit, you know, smaller)

To put the performance of the machine in perspective, Thomas P. D’Agostino, the administrator of the National Nuclear Security Administration, said that if all six billion people on earth used hand calculators and performed calculations 24 hours a day and seven days a week, it would take them 46 years to do what the Roadrunner can in one day.

Stats, in case you’re interested

The Roadrunner is based on a radical design that includes 12,960 chips that are an improved version of an I.B.M. Cell microprocessor, a parallel processing chip originally created for Sony’s PlayStation 3 video-game machine. The Sony chips are used as accelerators, or turbochargers, for portions of calculations.

…Roadrunner, which consumes roughly three megawatts of power, or about the power required by a large suburban shopping center, requires three separate programming tools because it has three types of processors. Programmers have to figure out how to keep all of the 116,640 processor cores in the machine occupied simultaneously in order for it to run effectively.

A picture of the future from Horst

“Roadrunner tells us about what will happen in the next decade,” said Horst Simon, associate laboratory director for computer science at the Lawrence Berkeley National Laboratory. “Technology is coming from the consumer electronics market and the innovation is happening first in terms of cellphones and embedded electronics.”

Warning: parallel computing hard

Solving that programming problem is important because in just a few years personal computers will have microprocessor chips with dozens or even hundreds of processor cores. The industry is now hunting for new techniques for making use of the new computing power. Some experts, however, are skeptical that the most powerful supercomputers will provide useful examples.

“If Chevy wins the Daytona 500, they try to convince you the Chevy Malibu you’re driving will benefit from this,” said Steve Wallach, a supercomputer designer who is chief scientist of Convey Computer, a start-up firm based in Richardson, Tex.

And a bonus: I didn’t know that Steve Wallach was doing a new startup. Cool. Last I knew he was at Chiaro Networks. He’s a fund advisor at CenterPoint Ventures, a venture capital fund, and Convey is a CenterPoint company (as was Chiaro; I had dinner with Steve a couple times when I was closely associated with SC…yes, I’ve just dropped name…and he is a really interesting, nice, regular guy who wouldn’t remember me from Adam).

One last reality check in the article before we head for the hills

“It’s a sign that we are maintaining our position,“ said Peter J. Ungaro, chief executive of Cray, a maker of supercomputers. He noted, however, that “the real competitiveness is based on the discoveries that are based on the machines.”

And now the hills, where the view is long, the air is thin, and the problems all seem solvable:

By breaking the petaflop barrier sooner than had been generally expected, the United States’ supercomputer industry has been able to sustain a pace of continuous performance increases, improving a thousandfold in processing power in 11 years. The next thousandfold goal is the exaflop, which is a quintillion calculations per second, followed by the zettaflop, the yottaflop and the xeraflop.

Ah, the xeraflop. I hadn’t actually heard of that one.

Comments

  1. Does anyone know if this was sustained or peak performance?

  2. Chris: The indications are that its an HPL number. Cross-correlate with this quote from Rick Stevens in a recent ComputerWorld article:

    “Roadrunner was built for Los Alamos National Laboratory by IBM, using 6,912 dual-core Opteron processors from Advanced Micro Devices Inc. and 12,960 of IBM’s Cell eDP accelerators. Early indications are that the machine’s Cell processors have reached a score of 1.33 PFLOPS, as measured by the Linpack benchmark, while the Opterons reached 49.8 TFLOPS, Stevens said.”

    URL: http://www.computerworld.com/action/article.do?command=viewArticleBasic&articleId=9093198

  3. Bah. Gimme a memristor-based processor, an analog processor, a normal CPU and a GPU on cube with shared memory between cores and a lone firewire port.