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 (105775)	11/14/2003 4:47:06 AM
From: Gopher Broke	Read Replies (1) \| Respond to of 275872

I'm apparently the only person on the planet that thinks this is a possibility Not at all, I agree with you. My reasoning is different. - To make Prescott a full 64 bit CPU Intel would have had to start work on it three years ago. - They would have to be discussing the instruction set with compiler writers a couple of years ago. - Initial samples to OEMs a year ago. It would be impossible to keep all that completely quiet. So whatever they have done in Prescott has to be a lot smaller development effort and requiring less testing. If I were Intel I would have come up with the smallest possible change to Prescott that could be labelled as "64-bit" and then let my formidable marketing team go to work.

To: Petz who wrote (105775)	11/14/2003 5:46:25 AM
From: Joe NYC	Read Replies (1) \| Respond to of 275872

Petz, On 64 bit extension: In terms of SSE(x) to do 64 bit integer arithmetics, it is a little kludgy. SSE resides in FPU, and has no communication with normal registers. It communicates only with 64 or 128 bit MMX registers or memory. You can't do branching based on it, and in general the operations on MMX registers are limited. Generally, an architecture is considered say 32 or 64 bit based on the size of the normal integer register. So the SSE is a non-starter on many fronts. So you really need to redo the ALU and switch to 64 bit integer registers - which may brake a lot of code, and without 64 bit addressing, it is still not a full 64 bit architecture, and in general, if Intel is going to bite the bullet and do an x86 extension, I don't see any reason to do an half assed job, that you are suggesting they will do. The reason is that to this day, Intel is not sure about Itanium. It is plan A, and there is no plan B. A half assed 64 bit extended x86 is still no plan B. So if plan A fails, Intel doesn't have a plan B, and would still need to come up with a completely new plan B to be a longer term solution. Joe

To: Petz who wrote (105775)	11/14/2003 8:38:21 AM
From: kapkan4u	Read Replies (1) \| Respond to of 275872

<First, if Intel was implementing AMD64, he could have just said, "Intel will do the same thing in 2004" or "Intel will implement AMD64." End of story.> Have you heard of NDAs? Why are you so afraid of AMD64 in Prescott? Wouldn't it be great for AMD? Imagine the headlines. Kap

To: Petz who wrote (105775)	11/14/2003 12:02:57 PM
From: mozek	Respond to of 275872

I'm apparently the only person on the planet that thinks this is a possibility, so take it with a grain of salt. Message 19409630 Message 19412934 Not necessarily the only one :-) Mike

To: Petz who wrote (105775)	11/14/2003 12:08:44 PM
From: dougSF30	Respond to of 275872

Petz, I don't think you can draw those conclusions from that quote from a Sun rep in one interview. He may not know that it is AMD64, or if he does know, he may not be allowed to say. Also, Intel may well change plans regarding which Prescott-family chip first sports the "extensions". (Given the delays, maybe delay a little more and launch with it?) And finally, that language "64-bit extensions" is EXACTLY what Microsoft seems to be rebranding the version of Windows that will support AMD64. So it is very far from clear that Intel's extension is not AMD64. Personally, I feel it's about 80-85% likely to be AMD64-compatible (perhaps a superset) at this point. Just my opinion. Doug