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.

Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: Tenchusatsu who wrote (40348)	10/29/1998 8:00:00 PM
From: Scumbria	Respond to of 1573885

Tench, Compaq has measured its Alpha 21264 processor at 26.0 SPECint95 Well that stinks. It is only twice as fast as the fastest x86. Even in that leading edge 0.35u process the 21264 is currently being built in. ;^)) Here is Elmer's original statement which began the Brady Bunch episode: based on what is shipping today it is only a couple of percent ahead of Intel's Xeon in integer performance exchange2000.com Scumbria

To: Tenchusatsu who wrote (40348)	10/29/1998 8:31:00 PM
From: Elmer	Respond to of 1573885

Re: "So not only is the 21264 being released much later than Digital promised, it's also much slower than Digital promised. It's still the leader, but with prices set at $65,000 per CPU, I don't think Intel will be trembling." Not only will Intel not be trembling, they will be smiling. A Xeon workstation can be purchased for < $3000, which is less than 1/20th the cost you quoted for a 21264. If you had a group of 20 design engineers each doing logic simulation, which would you buy, 1 Alpha server and 20 dumb terminals (at additional cost), or 20 Xeon workstations, each with ~ 70% the integer performance of the yet to be released Alpha? EP PS the benchmark claiming 55% faster performance for the Alpha is simply wrong. A Xeon is better than 18 Specint95 vrs the 26.0 for the Alpha.