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.
Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?


To: THE WATSONYOUTH who wrote (83767)12/21/1999 12:20:00 AM
From: Jim McMannis  Read Replies (1) | Respond to of 1572657
 
How will AMD deal with the heat dissapation of >1 GigHhz?
1. Copper
2. .13u front end

?



To: THE WATSONYOUTH who wrote (83767)12/21/1999 12:23:00 AM
From: kash johal  Read Replies (1) | Respond to of 1572657
 
The watsonyouth,

re:"AMD power consumption"

I suspect that the 0.18 micron parts will run up to 900Mhz from AMD using Al.

With dresden and cu process AMD has optimized the transisitors even further and also reduced RC paths by using copper allowing lower power.

My best guess for dresden/cu/new0.18 process will max out at maybe 1.2Ghz keeping power down rapidly.

Remember AMD AThlons currently use external Cache rams qhich are very power hungry - once they go on chip power gets reduced as well.

regards,

Kash



To: THE WATSONYOUTH who wrote (83767)12/21/1999 1:14:00 AM
From: Cirruslvr  Respond to of 1572657
 
TWY - RE: "Unless they lower gate and wiring capacitance considerably in their .18um process, the power will increase well beyond the max power they experienced at .25um and will approach 70W at 1 GHz or above."

According to the slides from AMD's Analyst Conference, Austin .18 has a gate length of ~120nm and Dresden will have a gate length of 100nm.

Does that fit what you say about the gate needing to be lowered?

The slides can be seen in the presentation by Dr. Seigle here - amd.com

Is it difficult to lower wiring capacitance?