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: Alan Aronoff who wrote (14374)	2/17/1998 10:40:00 AM
From: Nimbus	Read Replies (1) \| Respond to of 29386

I wouldn't worry about superHIPPI. Yes it is a valid technology, yes there is an ANSI spec, and yes it is critical to Supercomputer clustering ..... but ....... I can count on one hand the number of CRAY supercomputers delivered each year .... Besides, the cables are huge, the distances are short, and the costs are in the stratoshere. Let's move on ....

To: Alan Aronoff who wrote (14374)	2/17/1998 11:04:00 AM
From: Trish	Read Replies (1) \| Respond to of 29386

Cray and SGI platforms are differently technically and still, to a degree, culturally. SGI's high end Origin Server line is based on FCAL. Today they offer full fibre from Server to the disk subsystem. I don't think they yet offer a hub or switch. It would most likely be a FCAL solution.

To: Alan Aronoff who wrote (14374)	2/17/1998 11:06:00 AM
From: Craig Stevenson	Read Replies (1) \| Respond to of 29386

Alan, Have you noticed that there are suddenly a lot of new names here on the ANCR thread? <g> Craig

To: Alan Aronoff who wrote (14374)	2/17/1998 2:56:00 PM
From: Pigboy	Respond to of 29386

Alan, << Also, maybe I'm wrong in thinking this way, but I consider Cray and SGI to be somewhat distinct entities while recognizing they share many of the same resources. I assume Cray's scalable supercomputers will at times be based on different protocols/architectures than SGI's product lines. >> Good point. I do not know how different storage and clustering are for set ups with Fibre Channel. It would be interesting to compare clustering with FC and Hippi. I assumed FC goes very well with clustering too, bc I assume that Tandem's ServerNet/Wolfpack meant clustering and that this could work with Fibre Channel. I think I got that feeling after reading an interview with the CEO from SQNT last year in which he said that they may go with/license ServerNet from Tandem for Numa-Q (they had already made a commitment with FC, so I assume they can work together). My assumptions may be out of whack though. As a SAN gets bigger, does it then eventually need/use clustering or are they two different gorillas completely? Anyone? all imho pigboy