Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : The New QLogic (ANCR) -- Ignore unavailable to you. Want to Upgrade?

To: J Fieb who wrote (27462)	7/11/2000 9:07:05 AM
From: J Fieb	Respond to of 29386

OT? Supercomputers?? SAN here isn't the usual SAN... The first networks used as SANs were based on technology developed for local-area networks including Ethernet, Fast Ethernet and asynchronous transfer mode (ATM). They provided bandwidth on the order of 100 Mbits/s with a latency of between 100 and 200 microseconds. More recently developed Gigabit Ethernet has a peak bandwidth of 1 Gbit/s and latency of approximately 100 microseconds, and Myrinet (developed by Chuck Sites, a researcher at California Institute of Technology in Pasadena) delivers a slightly greater bandwidth with latency as low as 20 microseconds. The new VIA standard and the emerging Infiniband standard remove much of the software from the critical path, eliminating multiple copies required by earlier network protocols, increasing the bandwidth to a few gigabits a second and bringing the latency to about 5 microseconds. To overcome the basic problems mentioned above, Beowulf-class systems as well as other COTS-based massively parallel processors routinely organize data and task allocation statically to avoid latency and overhead as well as to provide load balancing. techweb.com