-
Technology
Entertainment
-
Music
-
Creative
Sport & Auto
- About Future
- Jobs
- News
- Advertising
- Digital Future
- Privacy Policy
- Cookies Policy
- Terms & Conditions
- Shop
- Investor Relations
- Contact Future
© Future US, Inc. 4000 Shoreline Court, Suite 400, South San Francisco, California, 94080. All Rights Reserved.







John Carmack may not want anything to do with Nvidia after the whole Rage debacle, but the driver issues that caused the programmer to call the game’s PC launch “a clusterf*ck” don’t bother governments nearly as much. Last year, China stuffed a bunch of Nvidia’s GPU’s into its Tianhe-1A supercomputer to make it the second fastest supercomputer in the world. That bumped the Cray-built Jaguar rig out at Oak Ridge National Laboratory down to the third slot. Now, the US Department of Energy’s looking to return the favor by – you guessed it – shoving a bunch of Nvidia GPUs into Jaguar to boost its performance and create a “Titan.”
The Texas Advanced Computing Center (TACC) at the University of Texas at Austin is building a world-class supercomputer called "Stampede." It's scheduled to power on in 2013 and will solicit 20 percent of its performance from Intel's Xeon E5 series processors, and the other 80 percent from Intel's "Knights Corner" co-processors based on Intel's Many Integrated Core (MIC) architecture.
Ken Jennings and Brad Rutter, two of Jeopardy's greatest winners of all-time, might consider unplugging their TV sets from September 12-14, 2011, the three days in which Jeopardy will broadcast an encore presentation of its first-ever man vs. machine competition featuring IBM's Watson supercomputer. If you happened to miss it the first time around -- or want to study Watson for signs of weakness just in case machines decide to rise against their makers -- clear your schedule or set your DVR.
Quick, someone assemble an eight-man band like the one that played during the Titanic's final moments above water. The National Center for Supercomputing Applications' Blue Waters project is sinking fast now that IBM has abandoned ship, leaving NCSA on its own to build a sustained petascale supercomputer. IBM and NCSA didn't have any kind of falling out, it just turned out to be more expensive than either side anticipated.
No matter what side of the Google-China shouting match you fall on, you can't help but admire the country's drive towards bigger and badder processing power. China's Tianhe-1A, capable of 2.57 petaflops per second, held the crown as the most powerful supercomputer in the world until Japan's "K Computer" blew away the competition with 8.16 petaflops last month. China's newest supercomputer is the Tianhe-1A's baby brother, creatively named the Tianhe-1.
We suspect that with a little bit of tweaking, Japan's "K Computer" wouldn't break a sweat running Crysis, but where this supercomputer really struts its stuff is in the LINKPACK benchmark. Equipped with 68,544 processors, Fujitsu's half-build system cranked out 8.162 petaflops (quadrillion floating-point operations per second) in LINKPACK, short of the company's goal of 10 petaflops by 2012 but still enough to take first place on the 37th Top 500 list.
With the Cold War a thing of the past, Russian scientists are free to concentrate their efforts on projects other than the space race and building a stockpile of nuclear arms. These days Russian scientists are studying computationally heavy topics like global climate change, ocean modeling, post-genomic medicine, and galaxy formation, and they're tapping into Nvidia's Tesla GPUs to do the heavy lifting.
Petaflops. Something about the word brings a smile to our faces – maybe because it sounds like a vaguely dirty word? But the term refers to processing power rather than a part of the human anatomy. A petaflop computer performs 1,000 trillion operations per second, and the new XK6 supercomputer announced today by Cray promises to scale up to 50 petaflops. Now, math isn't one of our strong points, but we're pretty sure we'd be able to rock a pretty awesome game of Dwarf Fortress on one of those puppies.









