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


To: Dan3 who wrote (111885)9/29/2000 10:19:21 PM
From: Tenchusatsu  Respond to of 186894
 
Dan, <AMD's use of local interconnect makes it easier for them to fit big caches on chips. I think the wait is almost over.>

Give me a break. AMD had local interconnect for a long time, yet the most cache they ever squeezed on the die is 256K.

Intel is able to put 1.5M of cache on a PA-RISC chip at 0.25u. Intel is also able to put 2M of cache on a P3 Xeon. All this without local interconnect.

<I don't think SUN is worried about AMD entering the server chip business, they might even partner with AMD.>

Just like AMD was going to partner with IBM for external fab space. Just like AMD was going to partner with Motorola, but now gets rewarded with a lawsuit. Just like AMD was going to partner with Microsoft on XBox.

Tenchusatsu



To: Dan3 who wrote (111885)9/30/2000 6:25:29 PM
From: Paul Engel  Read Replies (2) | Respond to of 186894
 
Lewinsky-Dan - Re: "AMD's use of local interconnect makes it easier for them to fit big caches on chips. "

Why is AMD's ThumperTurd 33% LARGER that Intel's Coppermine - 120 sq.mm vs. 90 sq. mm?

They both have 256K L2 cache, although the Thumpy has 128K L1 vs. 32K for the Coppermine.

Whatever advantage AMD had with local interconnect, Intel has surpassed them at the 0.18 micron level in density - WITHOUT the added complexity of local interconnect.

Paul