this might be old news to mosta you... {8^D spike
IBM To Build Largest Academic Research Supercomputer
SOMERS, N.Y. (Reuters) - IBM said it had been selected by the National Partnership for Advanced Computational Infrastructure (NPACI), a leading U.S. academic computer consortium, to supply the first supercomputer capable of handling more than one trillion calculations per second.
The supercomputer, to be installed at the San Diego Supercomputer Center (SDSC), will help researchers tackle massive computer calculations that are currently impossible to calculate.
The NPACI, which is backed by the U.S. government's National Science Foundation, links together 46 prominent universities and research institutions. The computer system is available for use by researchers throughout the world.
The new supercomputer system, an IBM RS/6000 SP computer, is scheduled to begin operation in the second half of 1999.
The machine initially will be built to handle a quarter- teraflop of data, or 250 billion calculations a second, before it eventually is upgraded to full teraflop, or one trillion calculations per second, capacity.
When complete, the system will have simultaneously operate more than 1,000 IBM Power3 microprocessors.
Financial terms were not disclosed, but a similar computer sold commercially would carry a list price of around $50 million, an IBM spokesman said.
While there are supercomputers under construction at several U.S. government research labs with the capacity to handle up to 4 trillion calculations, the new San Diego system will represent the world's largest supercomputer available for general academic research, the SDSC and IBM spokesmen said.
In conjunction with the deal announced Wednesday, SDSC and IBM
have expanded their partnership, which now involves data storage and
digital library systems, to include parallel programming software and
``transparent supercomputing.''
Transparent supercomputing will enable users from around the world to access the computer over the Internet using a simple Web browser.
SDSC and IBM are already working jointly on a system for storing and retrieving massive amounts of data. The system can handle up to 80 terabytes, but capacity is expected to grow to a petabyte, or one quadrillion bytes, in the next few years.