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.

Technology Stocks : Advanced Micro Devices - Moderated (AMD) -- Ignore unavailable to you. Want to Upgrade?

To: Petz who wrote (40814)	5/21/2001 9:02:54 PM
From: Bill Jackson	Read Replies (2) \| Respond to of 275872

Petz, I did not realize it was such a severe problem that would make the p-4 totally unsuitable for workstation use. The use of a liquid inside the package would help as it would act as an added heat dissipation path from the die. Probably have to be a high boiler, silicon fluid would be inert enough. A sealing nuisance that will lead to leakers in some cases. Still, even with that any peak would set it to 50% speed and time to reboot. What bunch of baboons at intel let this one slip through? Bill

To: Petz who wrote (40814)	5/21/2001 10:52:10 PM
From: Jim McMannis	Read Replies (2) \| Respond to of 275872

RE:"the tests by Bert McComas showed that the only way to get the P4 out of half speed mode was to reboot. Considering that this has been shown to happen running commercially available engineering applications like Matlab, and considering that 3/4 of the workstations used by engineers are rebooted only once or twice a week, the P4 is unsuitable for engineers until this problem is fixed" The Willy gets more "Rube Goldberg" by the minute. One amazing chip. Maybe they should have just made it run without all the gadgetry. <G> What Engineers dream was this thing? Jim

To: Petz who wrote (40814)	5/22/2001 12:00:53 AM
From: Ali Chen	Read Replies (3) \| Respond to of 275872

Petz, "Bert McComas showed that the only way to get the P4 out of half speed mode was to reboot" I think the effect has nothing to do with thermal throttling. The throttling is easy to monitor by looking at the PROCHOT# signal, instead of bold speculations. This pin is easy accessible from the back of mainboard. The effect of performance deterioration may have another, simpler explanation - it may be related to randomization of memory pages under Window's memory management, and for some reason the P4 does not like it much. The reboot forces a system to start with a fresh memory layout. The whole issue with P4 thermal throttling is largely overblown. This is a good protective feature, and I wish AMD to implement something similar, and as soon as possible. - Ali