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.

Technology Stocks : Intel Corporation (INTC) -- Ignore unavailable to you. Want to Upgrade?

To: Paul Engel who wrote (67229)	10/23/1998 3:07:00 AM
From: Joseph Pareti	Read Replies (3) \| Respond to of 186894

Paul, why is L2 limited to 2 MB ? Cost reasons ? For performance reasons we see a great improvement from large caches (e.g. 8MB on 21164), although this may benefit primarily floating point-intensive apps.

To: Paul Engel who wrote (67229)	10/23/1998 3:09:00 AM
From: Joseph Pareti	Read Replies (1) \| Respond to of 186894

Paul, can you explain the difference between coppermine and cascades. As far as I understood they will both employ 0.18micron technology and have KNI. Thanks /j

To: Paul Engel who wrote (67229)	10/23/1998 3:28:00 AM
From: Tenchusatsu	Read Replies (3) \| Respond to of 186894

<It also implies that the AMD K-7 with its slower speed L2 cache may not be much of a competitor to the XEON and newer versions (Cascades) when the K-7 finally does arrive.> First of all, I think that the AMD K7 is initially going to be targeted at high-end desktops. If you recall Intel's own difficulty with the now-slain Xeon bugs, it's likely that AMD will run into similar problems when running the K7 in multiprocessor configurations. And second, AMD hinted that the K7's L2 cache may be accelerated to faster speeds in the future. How AMD is going to do that is beyond me. Intel makes its own CSRAM for the Xeon, and AMD really can't afford to sacrifice capacity to make its own full-speed CSRAM. Perhaps AMD will resort to huge on-die caches, but that will have to wait until they get the 0.18 micron process rolling, and that won't be for a while. Finally, it's no secret that the current Deschutes Xeon with the large full-speed L2 caches are excellent for server applications. It's also no secret that Intel processors are somewhat anemic when it comes to graphics workstation applications, thanks to the weak FPU. It's too bad that the L2 cache has less of an impact in this area. That makes the Tanner release all the more critical, since the KNI in Tanner should be able to accelerate graphics workstation apps. Tenchusatsu