HPCwire: Fujtisu Plans Worldwide Supercomputing Comeback

Since 1986 - Covering the Fastest Computers
in the World and the People Who Run Them

Translation Disclaimer

Subscribe | Sign In

Visit additional Tabor Communication Publications

Leading HPC
Solution Providers

January 05, 2011

Fujtisu Plans Worldwide Supercomputing Comeback

Tiffany Trader, Associate Editor

Fujitsu is planning its return to the worldwide supercomputing market after a 10-year hiatus, reports Timothy Prickett Morgan, intrepid Reg reporter. The supercomputer maker is looking to export its ultrafast Sparc64-based technology to markets outside Japan. This is the same technology used in the Project K machine, which Fujitsu is currently building for Japan's Riken Research Institute. 'K' is a reference to the Japanese word 'Kei,' or 10 to the 16th power -- a figure that can also be expressed as 10 petaflops.

Morgan cites a report in the Japanese Business Daily, Yomiuri Shimbun, which reveals Fujitsu's intentions to export the technology sometime this year.

Says Morgan:

The obvious place for Fujitsu to start exports is in Europe, where it has a strong presence of its own (thanks to its long server partnership with and then acquisition of the Siemens IT unit), but given that the K machine can run either Solaris or Linux, there is no reason why the Sparc64-based clusters cannot be sold in the United States and China.

This may be a case of history eating its own tail. Over a decade ago, Fujitsu (and NEC) were the targets of high tariffs pushed by lobbyists from homegrown supercomputer-maker Cray. The practice of dumping, selling machines for less than cost, then led to further trade sanctions, which effectively pushed the companies out of the US market.

Due to the expensive nature of manufacturing the petascale-level Sparc64-VIIIfx-based machines, it makes sense for Fujitsu to spread the development costs over more than one account. Specifically, Fujitsu, according to the Yomiuri Shimbun article, is aiming its initial K export efforts at ITER, an international fusion project based in the south of France.

The K super will have over 80,000 CPUs, each possessing 8 cores using the Sparc64-VIIIfx processor running at 2.2GHz. The machine's 640,000 cores will be interconnected by Fujitsu's Tofu interconnect, which uses a propriatary six-dimensional mesh-torus topology. All told, the system is expected to wield 10-petaflops of processing power. Fujistu began shipping the K supercomputer in late September 2010, but it won't be fully operational until fall 2012.

Full story at The Register

Share Options

Subscribe

Subscribe to HPCwire

Discussion

There are 0 discussion items posted.

Join the Discussion

Become a Registered User Today!

Registered Users Log in join the Discussion

RSS Feeds

Feeds by Topic

Feeds by Industry

Feeds by Content Type

Subscribe to All Content

All

May 23, 2012

May 22, 2012

May 21, 2012

May 18, 2012

May 17, 2012

May 16, 2012

May 15, 2012

May 14, 2012

Feature Articles

NVIDIA Works On CPU Co-Dependency Issues with Kepler GPU

NVIDIA is telling everyone that the GK110, its new Kepler GPU aimed at supercomputing, is all about improving performance per watt. But the other driving theme behind the new architecture is reducing the GPU's reliance on its CPU host. How well it accomplishes both these goals areas could determine the success of the new chip in high performance computing.
Read more...

OpenACC Starts to Gather Developer Mindshare

PGI, Cray, and CAPS enterprise are moving quickly to get their new OpenACC-supported compilers into the hands of GPGPU developers. At NVIDIA's GPU Technology Conference this week, there was plenty of discussion around the new HPC accelerator framework, and all three OpenACC compiler makers, as well as NVIDIA, were talking up the technology.
Read more...

NVIDIA Launches Kepler Into HPC

NVIDIA has introduced its first Kepler-generation GPU product for high performance computing, and revealed some of the inner working of the new architecture. The announcement took place at the kickoff of the company's GPU Technology Conference taking place this week in San Jose, California.
Read more...