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 (97281)	6/13/2003 1:47:39 PM
From: Dan3	Read Replies (1) \| Respond to of 275872

Re: improving Itanium's 32 bit performance with an integrated chip rather than emulation Think how much fun they'll have modifying the cache controller to work with the Itanic core.... concurrently.

To: Petz who wrote (97281)	6/13/2003 3:02:49 PM
From: PerryA	Respond to of 275872

Anyone know the status of the 64-bit (Opteron) betas of Windows XP & Server due "middle of 2003" (per MSFT press release April 9th)? "At Microsoft Tech-Ed 2003 AMD will showcase the new AMD Opteron processor for servers and workstations ..." microsoft.com I believe this event is June 30th. Thanks, PerryA

To: Petz who wrote (97281)	6/13/2003 3:38:11 PM
From: Joe NYC	Respond to of 275872

Petz, Centrino core must be tiny, if you remove L2, bus interface. As Dan pointed out, having both cores access the same L2 may be a challange. But maybe they can overcome it by each core having its own 256K L2 and a shared L3 of several MB (on 90nm and 65). I think that's what Itanium already has. Also, Centrino core is not a power hog that P4 is, so adding it to Itanium core would not add too much power. And, the power consumption of Itanium will certainly go down. Also, achieving high clock rates of this combination core may be challenging. The whole thing seems like a challenging project from implementation point of view, but it makes ultimate sense marketing-wise. It would offer gradual move to Itanium instruction set. If Windows supported it, you could run side by side applications that are IA32 as well as IA64, matching what AMD is offering. Intel needs to do something radical, because the current path will lead to AMD64 CPU installed base vs. IA64 installed base in a ballpark of 100:1, and guess where the development resources for 64 bit development would go. I don't think Intel can allow this to happen without a significant challenge. Joe