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.
Politics : Formerly About Advanced Micro Devices

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: kash johal who wrote (63499)6/26/1999 7:48:00 PM
From: fyo  Read Replies (2) of 1580161
 
Kash - Re: It will be interesting to compare with SPEC numbers for the workstation K7's with 8MB full speed caches running DDRDRAM at 266Mhz.

If they get these clocking in the 700-800Mhz range I suspect it will smoke the current top dog.


I seriously hope you don't think that. If you do, maybe you should take a look at SPEC.org numbers:

HP9000/N4000 (440MHz PA-RISC 8500)

SPECfp : 48.7 / 51.4
SPECint: 30.8 / 34.0

OUCH! Let's take a look at some speculative, approximate K7 numbers and then let's mess it up completely by doing some totally unwarranted linear extrapolation (from 550MHz --> 800MHz):

SPECfp : 23 --> 33.5
SPECint: 25 --> 36.4

As you can see, the K7 (err.. Athlon) may get close in integer, but it won't get ANYWHERE near the PA-RISC in floating point. And I certainly wouldn't call this 'smoking the current top dog'...

Ok, ok, so this isn't the K7 with PC266 DDRDRAM and 8MB full-speed cache (which may be DDRDRAM), but I still don't see how you are going to make up the HUGE gap in floating point performance.

--fyodor
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext