Is Linux the future of supercomputing?

As the need for bigger, faster supercomputers increases at a rapid pace, IBM and the National Centre for Supercomputing Applications at the University of Illinois at Champaign are working together to create the world's fastest Linux supercomputer.

The NCSA said today it will install two Linux clusters, which include more than 600 IBM xSeries eServers running Linux and Myricom's Myrinet cluster interconnect network.

IBM Global Services will install the first cluster next month, which will be based on IBM eServer x330 thin servers, each with two 1GHz Intel Pentium III processors running Red Hat Linux.

The second cluster, which will run Turbolinux, will be installed this summer and will be one of the first to use Intel's next-generation 64-bit Itanium processor, IBM officials said.

NCSA is the leading-edge site for the National Computational Science Alliance, a partnership to prototype an advanced computational infrastructure for the 21st century. It includes more than 50 academic, government and industry research partners from across the United States.

Linux as the future
Dan Reed, director of the NCSA and the National Computational Science Alliance, said Linux clusters provide users with a single, easy-to-use computing environment that applies to single-user desktop workstations, small research clusters and the largest "tera-scale" systems.

"The explosion of the open-source community, the maturity of clustering software and the enthusiasm of the scientific community all tell us that Linux clusters are the future of high-performance computing," Reed said.

Dave Turek, vice president of Deep Computing at IBM, said the Linux clusters would allow scientists to focus more on the results of their research initiatives, freeing them from the burden of building their own clusters and writing code to support their heavy computational demands.

This is not Big Blue's first foray into supercomputing. Last year it put Linux on a 512-node cluster as part of the LosLobos supercomputer project at the University of New Mexico's Albuquerque High Performance Computing Center. LosLobos consists of 256 IBM Netfinity PC Servers.

That 733MHz Intel IA-32 processor-based system is expected to provide a peak theoretical performance of about 375 gigaflops. The Albuquerque High Performance Computing Center also recently made the top 500 supercomputer list, with LosLobos the highest-rated Linux cluster on that list.

Advertisement

Talkback 0 comments

Latest Videos

Sponsored content

Power Centre - Content from our premier sponsors

Blogs

  • Renai LeMay How reliable is IP telephony?
    Have you ever heard a weird kind of hissing, crackling or popping noise when calling someone on an IP telephony line? How rare is the phenomenon these days?
  • Array Forget the NBN, 100Mbps is already here
    Telstra and TransACT will shortly begin offering 100Mbps broadband to many customers. By moving early, the companies have not only raised the bar for Australia's broadband services, but thrown down a challenge to a government that now faces increased pressure to deliver the NBN as promised.
  • Array IT: Govt's cost-cutting bitch
    The government needs to stop looking at IT as a necessary evil or the place to remove costs when the Treasurer comes calling.
  • More blogs »

Tags

Back to top

Featured