SI
SI
discoversearch

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 : PMC-Sierra (PMCS) -- Ignore unavailable to you. Want to Upgrade?


To: Trader Dave who wrote (2672)8/24/1999 8:08:00 PM
From: Bulldozer  Read Replies (3) | Respond to of 3818
 
Will discuss more tomorrow, but looks like a fantastic addition. Reading the background and research of Nick McKeown (CTO, Co-Founder and Stanford Asst. Prof) and his group at Stanford, makes me pretty comfortable about the quality of these guys.
There is a LOT of high-end algorithmic details in their papers and talks (which is beyond me), but the bottom line seems to be a very, very efficient architecture to switch terabits of data at the OC-48 and 192 level. They outline the difference between attacking the complexity at the Input vs. Output Queue. HOL(Head of Line Blocking), the use of queue occupancy vs port occupancy as the request weight (which one gets relieved first of their backlog) are addressed, as well as many other factors.

I like the fact that the technology is adaptable to virtually every core element (IP Router, ATM Switch, DCC). Thats the kind of versatility that makes PMC currently so attractive.

The Venture guys behind Abrizio are among the most prominent in the world and probably receive 100 proposals for every one deal - so you have to think they did a LOT of DD and liked what they saw. Between them, Sequoia and Benchmark financed Cisco, Juniper, Oracle, 3COM, Vitesse, AMCC, Yahoo, Rambus, etc. Not a bad list. I also think Sequoia was involved with PMC to some extent.

More tomorrow after reading a few white papers!

Bulldozer