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: Joe NYC who wrote (101246)	3/31/2000 7:07:00 AM
From: Bill Jackson	Read Replies (1) \| Respond to of 1572910

Jozef, I disagree, they should put in the cache and work towards increasing the size later. SInce many command strings involve sequential data even a small cache like 32K will have an 80+% hit rate. 64K should be in the 85-90% hit area. Going to 128K will bring you up over 90% but you will not reach 100% until the cache is as large as main memory. This 64K will make a large improvement in performance. recall the small Celeron on board cache.....killed the P-II of the same speed. Bill

To: Joe NYC who wrote (101246)	3/31/2000 9:30:00 AM
From: Scumbria	Read Replies (1) \| Respond to of 1572910

Joe, Not if L2 is only 64K as was mentioned on some online hardware sites. If the L2 is only 64k, in my opinion, AMD should not bother putting it in. It would be interesting if L1 could be increased from 64/64 to 64/128K. It would be a lot better use of the additional 64KB worth of transistors. The L2 cache on Spitfire is a victim cache, which is a very efficient use of transistors. There is little overlap between the addresses in the L1 and L2. It is unlikely that any changes were made to the core layout, and particularly not to the L1. My opinion is that they did exactly the right thing with Spitfire. Scumbria