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: Charles R who wrote (69628)	8/23/1999 5:13:00 PM
From: Scumbria	Read Replies (2) \| Respond to of 1572657

Chuck, what kind of speed improvements are likely on Athlon as they go from 0.25 to 0.18 given that the transistors are already at 0.18. We missed your expertise on how transistor delays, interconnect delays, and clock skew contribute for this class of designs. Any comments? I'm certainly not a process expert, but I don't expect to see a very large transistor speedup from 0.18u. Copper will however make a significant impact on wire delays. I wouldn't be surprised to see >20% clock speed improvement out of the 0.18u copper process (relative to current production.) Clock skew is a very serious problem for large designs like K7. Depending on the floor planning and layout, it may steal >10% of the cycle time. I expect that a K7 cycle times will increase dramatically over the next 6 months, just due to speed work. Once the design became stable, I suspect that AMD shifted a lot of resources into speedpath debug. Sorry about my "disappearance", but I've been very busy at the new job, and rather bored by the lack of substantive Intel/AMD news. Scumbria