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: Yousef who wrote (43392)	12/14/1998 11:17:00 PM
From: Elmer	Read Replies (1) \| Respond to of 1572629

Re: "On business applications, the K6-2 400/100 can't even keep up with a PII 350/100 ?" Well clearly you're right Yousef. The Katmai blows away the K6 but so does the PII. The Quake scores will change dramatically when the KNI instructions are employed. EP

To: Yousef who wrote (43392)	12/14/1998 11:25:00 PM
From: Cirruslvr	Read Replies (2) \| Respond to of 1572629

Yousef - RE: "Appears that the "KNI" instructions make a big difference ... and ... 3DNOW is "craps"." You must be an outstanding reader. I didn't see 3D NOW! being mentioned in the paragraph that discussed the lighting & transformations. RE: "On business applications, the K6-2 400/100 can't even keep up with a PII 350/100 ??" Notice that that benchmark was run under NT 4.0? It is understood that the K6 family of processors don't run NT very well compared to Intel processors. This was known OVER 18 months ago. Keep up the deep thoughts! I noticed you didn't want to comment on that fact that in the Business benchmarks, the Katmai with extra L1 cache had a less than minimal gain on the PII. Waiting for a reply.... In what applications will the extra L1 cache be noticeable? Waiting.... How much wasted die space does the extra L1 cache take up? Waiting.... Hey, now I know how OEM's feel like when waiting longer than expected on the next BIG thing from Intel- Merced. Seems like Intel tried to take a page out of AMD's book (with the 64K L1 cache) for a change, but it didn't take good notes. Waiting....