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: Kevin K. Spurway who wrote (48713)2/5/1999 11:12:00 AM
From: Scumbria  Respond to of 1583823
 
Kevin,

Is it because with 64k of L1, you need to have 4x as much L2 to really see a performance improvement?

That is correct. The memory hierarchy from L1-L2-L3 has to show an steep increase in size at each stage to be of any benefit.

Mendocino showed a large performance improvement because it went from 32K L1/0K L2 to 32K L1/128K L2. In contrast, K6-2 systems typically have 1MB (slow) L2 on them already.

Scumbria



To: Kevin K. Spurway who wrote (48713)2/5/1999 3:29:00 PM
From: Paul Engel  Respond to of 1583823
 
Kevin - Re: " But also keep in mind that the Sharptooth has
more transistors than your Dixon,"

The only significant difference is in the L1 cache size/transistors - 32K Bytes for DIXON and 64 K for the late-to-the-party Sharpy !

Re: " Maybe that's why it is appearing one month after
Dixon?"

Dixon has APPEARED INSIDE MANy, MANY NOTEBOOK COMPUTERS - ready for sale.

Sharpy will be launched this quarter - but how many companies will have Sharpy products ready for sale? One? Zero?

That's a HOLLOW launch !

Paul