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: Elmer who wrote (41940)	11/19/1998 11:54:00 PM
From: RDM	Respond to of 1573116

The Silicon Graphcis MIPS workstation is twice as fast at the same clock rate for double precision floating point than the Pentium II using the Benchmarks in Matlab, at scientific modeling language. I am shown my Geek side, but this is an impressive difference that the K7 might be able to close with the MIPS chip archictectures. I think that there is not so much that can be done for Pentium II integer performance, but if graphics and floats were doubled by the K7s nine execution units, it would great for workstations. Workstation have to be more annual units than servers IMHO.

To: Elmer who wrote (41940)	11/20/1998 9:14:00 AM
From: Jim McMannis	Read Replies (1) \| Respond to of 1573116

Elmer, I know you want to see benchmarks for the K6-3 and K-7 but isn't it customary to wait until the chips are released? Especially in light of the Klamath debacle a few years ago when Tom Pabst got a hold of a pre-production version of the Pentium II and it didn't bench nearly as well as the production version. Let's assume that the K7 and K6-3s shown at comdex are as fast as the production versions will be. Why in the world would AMD want to release benchmarks so the Elmers of the world could scrutinize pre-production versions? The demo of the K6-3-400 easily beating a Pentium II-450 (at what I don't know) was just to prove the point that clock for clock the K6-3 is faster. I repeat, (over and over) that we won't see the K6-3 until the K6-2 yields at 450...which will likely mean the K6-3 is yielding at 450. Jim