NSF awards $53 million supercomputing bid. Linux shines :)

Super-clusters have always been a Linux strong point, don't you agree?
How important is clustering software in the information age?

[link|http://news.cnet.com/news/0-1003-200-6829412.html?tag=mn_hd|
NSF awards $53 million supercomputing bid ]
By Stephen Shankland
August 9, 2001, 1:50 p.m. PT

The National Science Foundation has awarded contracts worth $53 million to build a grid that connects supercomputer clusters across the country into a single large computing resource called the Distributed Terascale Facility.

The main part of the work will be handled by the National Center for Supercomputing Applications (NCSA) and the San Diego Supercomputer Center, said NCSA Director Dan Reed.

But a big winner will be IBM, which will build four Linux supercomputer clusters and take home tens of millions of dollars, said Mike Nelson, director of Internet technology and strategy at IBM. The NCSA's cluster will be able to perform 6.1 trillion calculations per second (teraflops), and SDSC's will handle 4 teraflops, Nelson said. Argonne National Laboratory will have a 1 teraflop machine and the California Institute of Technology a 0.4 teraflop machine.

This is a huge win for Linux, IBM and Intel. Does it surprise anyone that the grid software is open-source? Nah, I doubt it. (:
[link|http://dailynews.yahoo.com/h/nm/20010809/tc/tech_supercomputer_dc_1.html|
National Science Foundation to Fund Supercomputer]
By Duncan Martell

SAN FRANCISCO (Reuters) - The National Science Foundation (news - web sites) said it will spend $53 million to build a massive computing grid that will be the most powerful of its kind ever completed and could lead to ground-breaking research that would have otherwise taken years, if not decades, to complete.

Called the Distributed Terascale Facility, or DTF, it will be used by four U.S. research centers for research in areas including molecular modeling for detecting diseases, cures and drug discovery, research on alternative energy sources, climate and atmospheric simulations, among others.

The current grid, which is the latest example of distributed computing that is becoming increasing popular, will be able to process 13.6 trillion calculations per second and will boast some 600 terabytes of data storage, the equivalent of 146 million full-length novels. To put that computational power in perspective, it would take one person with a calculator about 10 million years to tabulate the number of calculations the proposed grid could in a single second.
....
The DTF, which will be connected using Qwest Communications International Inc.'s (NYSE:Q - news) 40-gigabit-per-second network, will be built by International Business Machines Corp.(NYSE:IBM - news), using Intel Corp.'s (Nasdaq:INTC - news) Itanium microprocessors and the Linux (news - web sites) operating system. More than a thousand IBM servers and 3,300 next-generation Itanium McKinley chips will comprise the DTF.
....
Unlike traditional supercomputers, which are typically housed at a single location, grids allow for pools of computing resources by connecting multiple supercomputers that are often in different locations via the Internet using open-source protocols from Globus. Globus is an organization seeking to set standards for grid computing similar to the standards that were set up to run the World Wide Web.

Welcome to IWETHEY!