Big Blue Mining MIPS with Grid Computing Initiative
- By John K. Waters
- August 6, 2001
IBM Corp. has announced it is amping up its efforts to develop and exploit a technology known as "grid computing," which organizes linked PCs and servers for the purpose of sharing computing cycles. Through its Grid Computing Initiative, the company is contracting with remote customers, who will be allowed to harvest the computing power of a group of comparatively centralized servers.
IBM announced last week that it has already won contracts with two national grid projects in Europeone in Britain and another in The Netherlands.
Grid computing (also called "distributed computing") harnesses the dormant processing power in idle desktop PCs and servers. Computers running software from companies like San Diego-based Entropia utilize idle computer time drawn from a network of PCs to solve large, computational problems. Working in the background, these programs take on small workloads that have been divided and distributed to various devices across the Internetessentially borrowing processing power from other computers on the network.
"Through the use of these resources, your computing device can be both a consumer and a producer on what becomes a universal platform," explained Scott Kurowski, Entropia's founder. "In as little as five years, we fully expect end users to be running applications that invisibly tap into huge amounts of computing capacity on the back end."
One of the best-known examples of the distributed computing model is the [email protected] project. Under the auspices of the SETI organization (the Search for Extraterrestrial Intelligence), [email protected] marshals unused computing cycles from a global network of volunteer PC owners to search for radio signals from an extraterrestrial intelligence. Based at the University of California at Berkeley, [email protected] allows anyone with a computer and an Internet connection to take part in the search. To date, the project has attracted more than 2 million participants.
Researchers at the University of Wisconsin estimate that most companies use less than 25% of their computing and storage capacity. By some estimates, 90% of America's computer capacity is idle at some point during the day, especially when people turn off their machine and go home for the evening. Grid computing seeks to "rescue" these wasted computing cycles.
The technology behind distributed computing is not new. Scientists have linked supercomputers this way for years. Companies have distributed computing software on internal networks to get extra work done at night and on weekends.
"This is a good way not to have to buy a lot of servers to get massive amounts of computing resources," said Entropia's Kurowski.
Grid or distributed computing has been lumped together with Napster-style file-sharing technologies under the "peer-to-peer" rubric. But the two concepts are quite different.
"The trade press has blurred the distinction between a peer-to-peer computing architecture, and peer-to-peer products that enable direct interaction between desktop machines," said Scott Davis, chief technology officer at Mangosoft. "They are very different things, and we're seeing the metaphors getting mixed." Based in Westborough, Mass., Mangosoft has developed a patented technology it calls "pooling," which is a clustered caching technology that utilizes the network and resources on PCs and workstations to deliver software services normally associated with servers.
Nevertheless, distributed computing companies make up a significant membership in Intel's Peer-to-Peer Working Group, which was formed earlier this year; Entropia was a founding member.
For more E-Business, go to: http://www.adtmag.com/.
John K. Waters is a freelance writer based in Silicon Valley. He can be reached
at [email protected].