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: Elmer who wrote (74014)10/5/1999 12:57:00 PM
From: Steve Porter  Read Replies (1) of 1572295
 
Elmer,

I expect Intel will do this at some point, however if that was the only way Intel could lead on any benchmark I would consider it bogus. Let me turn the question around, if Intel leads in SpecInt95, would you consider it to have the fastest chip, regardless of SpecFP?

Actually that would mean (in my mind) the 2 were essentailly tied. If Intel leads by a couple of % in SpecInt, then Coppermine is a better server chip (with the on die L2 coppermine SHOULD come within +/- 3% of Athlon anyway). With Athlon winning SpecFC, Athlon would be the better workstation CPU.

Notice how both of these market segments are very profitable. Also note how an Athlon with on die L2 would like take back the integer lead, at least until Williamette (or however you spell that name).

Another interesting aspect to the 'who is faster' arguement, is should we (in considering which CHIP is faster) only take benchmarks with the same speed memory type. I mean since who is faster is purely an academic argument when the difference is only a couple of % anyway.

For the record, I expect Coppermine will be at the least 'competitive' with Athlon in Int. I really don't expect too much from TRUE Fpu (of course Coppermine using SIMD vs. Athlon FPU would allow Coppermine to be competitive again).

Regards,

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