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: Kevin K. Spurway who wrote (38891)	10/9/1998 11:44:00 AM
From: Elmer	Read Replies (2) \| Respond to of 1577025

Re: "Whoever wrote that article was obviously an idiot. Anyone care to wager a case of beer that K7 will be faster than Katmai clock for clock on Winstone or Winbench or whatever it is?" But the K7 is supposed to be a highend server/workstation processor. Don't tell me AMD is going to rely on Win98 with 16bit code and "Mutant Alien Blaster" (tm EPhud '98) benchmarks to backup their claims? I don't think so. They'll need to show Spec and TpmC benchmarks. Also clock for clock won't cut it either. If the K7 is a 7th generation chip it will need both operations per clock and lots of clocks. EP

To: Kevin K. Spurway who wrote (38891)	10/9/1998 12:26:00 PM
From: Tenchusatsu	Respond to of 1577025

Anyone care to wager a case of beer that K7 will be faster than Katmai clock for clock on Winstone or Winbench or whatever it is? Kevin, nothing in the interview posted by Petz suggests that the K7 will have anything which is much better than Katmai. 3-way super-pipelining (like P6), deeper pipelines (like P6), extensions to 3D-Now which allow for 128-bit operands (like Katmai). The only thing that the interview suggested was that its floating point unit may be stronger than Pentium II. I would also guess that the extensions to 3D-Now would still be able to execute two 3D-Now instructions at once, giving K7 perhaps twice the FLOP-to-clock ratio of Katmai. I'm still wagering that K7 will probably be released less than a quarter ahead of Cascades and/or Coppermine. Those are the processors the K7 will be compared to if AMD wants the K7 to be a high-margin seller. If the K7 doesn't match up, AMD will once again have to price it at a level or two below the top. Tenchusatsu

To: Kevin K. Spurway who wrote (38891)	10/9/1998 12:40:00 PM
From: Tony Viola	Respond to of 1577025

Kevin, Re: "Anyone care to wager a case of beer that K7 will be faster than Katmai clock for clock on Winstone or Winbench or whatever it is?" or whatever it is? I sure hope you get better evidence/information than this before going out on a limb practicing the profession you display in your profile. Tony