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: Ali Chen who wrote (72676)	9/21/1999 12:11:00 PM
From: Process Boy	Read Replies (2) \| Respond to of 1575048

Ali - <I think you are misguided very much here.> Your talking one thing, the article is talking another. What I was implying was strictly related to large IT infrastructures and upgrade paths. The article clearly implies that at these processor speeds, the benefits of RAMBUS are suspect. Regardless, it will be interesting to see how Micron's business does relative to i820 houses. HP and Dell will be a couple of those. GTW too. These are Micron's competitors, are they not? Do you think customers will go flocking to Micron? Maybe, maybe not. I don't know. It will be interesting to see. PB

To: Ali Chen who wrote (72676)	9/21/1999 2:04:00 PM
From: Petz	Read Replies (3) \| Respond to of 1575048

VIA chipset K7 motherboards sooner rather than later? Some USENET posters in the UK claimed to have bought the Asus K7M motherboard which uses the VIA KX133 chipset and supports PC133 SDRAM. Their story seems to check out because here is the page which advertises the board: scan.co.uk Look near the bottom: A VERY Famous Name Top End K7 ATX Motherboard - We Cant Advertise 149.00 175.08 (w/VAT) Petz

To: Ali Chen who wrote (72676)	9/21/1999 3:50:00 PM
From: kapkan4u	Respond to of 1575048

<I think they are overestimating the value of prefetching techniques (this is the only thing I can think of for performance increases). Maybe Kap can comment on this?> Ali, I agree. It is hard for a compiler to choose the right combination of loop unrolling and prefetch latency compensation to hit the bandwidth "sweet spot". Just try prefetch optimizing some trivial loops burning through large arrays by hand. The bandwidth increases can mysteriously appear and disappear with slightest variations in prefetch parameters. Kap