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: Douglas Nordgren who wrote (25782)	1/25/2000 9:24:00 AM
From: KJ. Moy	Read Replies (1) \| Respond to of 29386

<<(Don't they own a patent on their FC cross-connect architecture?)>> I believe the patent(s) were on aggregation techniques. IMO that's part of the reason why Ancor has a better scalability platform, not necessarily Class 1-centric. Viangio has a good point in comparing VIA and Class 1 process. There are similarities between the two, but IMO they are not inclusive. In other words, Brocade can do VIA also without having Class 1 experience. I believe that the adoption of FC switching came as somewhat a surprise to many, therefore only two serious competitors so far. Going forward with IB, the success of IB switching is fairly apparent. There will no doubt be more competitions IMO. Don't be surprised some may come from overseas, such as Israel. The transport layer probably will borrow a chapter from FC. But, I think that's where the similarity end. Current FC switch makers may have an advantage because of working experience. By no means Ancor and Brocade may have the IB switching market lockup. Not even close IMHO.

To: Douglas Nordgren who wrote (25782)	1/25/2000 1:54:00 PM
From: George Dawson	Read Replies (1) \| Respond to of 29386

Don't want to rain on anybody's parade: But my recall of the events of the past three to four years, show some potential problems with designing the IB switch from an FC perspective. These potential problems are based on current public knowledge of FC applications. I have no knowledge of what is currently being worked on in labs. Latency - many of the cross connects mentioned as candidates for IB type architectures have latencies in the tens of nanoseconds range. Ancor's current product line has a latency that is 10x greater than this range. In my last correspondence with an FC scientist, I was advised the lowest theoretical latency for a point to point FC connection was about 40-50 ns. FC alliance groups have suggested that latencies are a limiting factor in terms of using FC as a viable processor clustering technology. Class 1 - don't know what the advantage of this is other than broader engineering expertise. The important protocols discussed are not class dependent and it seems no more likely to me that class 1 would be more important in an IB switch than a standard FC switch. If there are people at Intel and Agilent with cross connect architecture experience on the cluster side-I see it as a very tight race. I do not believe Ancor's existing patent is on their cross connect architecture, but encourage everyone to read it themselves. There are several crossconnect technologies that have been around for awhile. George D.