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: Petz who wrote (77145)	10/26/1999 2:19:00 PM
From: Yousef	Read Replies (1) \| Respond to of 1571204

John, Re: "Some people think the gate sizes will not be reduced much because they are already almost at 0.18." John, please explain why this is "good news" ... Looks like AMD will not be improving their performance dramatically soon ?? Make It So, Yousef

To: Petz who wrote (77145)	10/26/1999 2:31:00 PM
From: Saturn V	Read Replies (1) \| Respond to of 1571204

Ref-<Some people think the gate sizes will not be reduced much because they are already almost at 0.18.> If AMD is already at 0.18 micron gates, and the gates are not shrunk any further, the voltage does not have to be reduced. However the dramatic speed gain in a shrink is due to smaller and thinner gates. Thus if AMD has already shrunk the gate, there will be gains in speed and lower power, but these will not be dramatic. The shrink will reduce the capacitance of the interconnect, but will not speed up the transistor. My gut feel is that both AMD and Intel will continue to tweak the transistor length over the course of the coming year, and the performance will continue to inch up. So Intel AMD performance will be relatively equivalent, until the Intel 0.13 micron process or Willamette show up next year. The latest Microprocessor Design Report claims that the Coppermine is significantly superior to Athlon in performance. It claims that the 733 Coppermine outperforms all RISC processors [ Alpha included] on integer benchmarks.

To: Petz who wrote (77145)	11/1/1999 5:47:00 PM
From: Saturn V	Read Replies (1) \| Respond to of 1571204

Ref <Some people think the K-7 gate sizes will not be reduced much because they are already almost at 0.18 > If AMD does not shrink the gate size in the move to 0.18micron, the power consumption will drop significantly. the speed by a first order model will be unchanged. The cooler chip may cause the speed to improve by 50-100MHz at most. So how does AMd plan to go 1GHz and beyond ? Either AMD will shrink the poly gate significantly below 0.18micron or will have to change the K-7 design significantly by tweaking the speed paths. My guess is that they will do both, as they did on the 0.25micron technology on the K-62. Intel will most likely also tweak the Coppermine speed paths and the process to gain the most of the 0.18micron process. Any tweaks create the possibilities of fumbles and yield crashes.So it will be an interesting horse race for the next six months ! Once Willamette or the rumored 0.13micron process show up, Intel will have a more comfortable performance lead.