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 : Intel Corporation (INTC) -- Ignore unavailable to you. Want to Upgrade?

To: Charles Gryba who wrote (155123)	1/12/2002 11:26:22 PM
From: wanna_bmw	Read Replies (2) \| Respond to of 186894

Constantine, Re: "when the P4 gets more bandwidth its memory subsystem (i850) can provide enough data to it. When the athlon fsb is overclocked its single channel memory subsystem cannot do the same." I was under the impression that the memory bus increases at the same speed as the front side bus. Would this not give extra bandwidth to both areas, and eliminate the bottleneck you are describing? Re: "Did you notice the jump in performance the athlon got when better chipsets came along? For example, going from kt266->sis735->kt266a etc? They actually allowed the Athlon to beat the P4 in some benchmarks it was losing previously. So the CPU alone does not provide an accurate enough picture of system performance." I completely agree with you here. There is much optimization that can be done inside the chipset. But why bring that up? Are you expecting future chipsets to be even more optimized? Re: "The question remains, will AMD pump up the athlon fsb to 200 and are the chipsets ready to support that? From what you are saying, AMD has no plans to do so and my opinion is that it would be very foolish not to do so unless hammer is around the corner which does not seem to be the case. If I were in charge now, I would be pushing for the 200fsb as a backup plan ( and I would also be looking for a partner to come up with a dual channel chipset )." Any resources you put onto a project like this, you would be subtracting from Hammer development. If you ran AMD, you would be pushing out Hammer schedule even farther, just to compete with Intel at the front side bus. But let me ask you: once you pull people from the Hammer team to create a chipset with a 200MHz Athlon bus, would you pull more people to improve the memory bandwidth, and more people to do a reference design, and more people to handle electrical issues, and more people for validation, etc? Oh, and also, if you start now, you might be able to get such a project out by 2004. Yes, it does take that long to start a project like that from scratch. Unless you are trying to prove that in 2000, AMD previously anticipated that Intel will have caught up to them, and they pushed for a chipset with 200MHz Athlon bus at that time? I am just wondering, Constantine, because your theories don't seem to add up. wbmw