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: TGPTNDR who wrote (73762)	3/6/2002 6:45:34 PM
From: wanna_bmw	Read Replies (1) \| Respond to of 275872

TGPTNDR, I agree with you 100% on this one. The only question will be whether those multiples of x86-64 based machines are really running 64-bit applications, or not. wbmw

To: TGPTNDR who wrote (73762)	3/6/2002 8:20:00 PM
From: pgerassi	Read Replies (1) \| Respond to of 275872

Dear Tgptndr: Plan A is failing now and will continue to fail. It is currently, underperforms, overpriced and unwanted. It has the same attributes as RDRAM and even less to recommend it. It will quickly sink into oblivion joining Rambus as just another money losing wrong turn by Intel. X86 is here to stay. Too much momentum to turn aside and way too many applications and systems to ignore. X86-64 just adds a number of improvements to x86, 64 bit addressing, double the registers both GPR and FPU, doubling size of GPR registers, while keeping compatability with all existing applications. Within the first year or two of Hammer release, more x86-64 CPUs and systems will be in the market than all other high performance (workstation and server) 64 bit RISC and VLIW (IA-64) CPUs and systems combined. Any 64 bit application will be able to be run on x86-64. The only way for those other 64 bit CPUs to make it in the market is to have far higher performance than any x86-64 CPU as they will be far more expensive. When it cannot sustain that performance advantage, it will be superceeded by x86-64. When any program or application runs on x86 now that does not need more than 32 bit addressing, almost all servers now run on x86s rather than 64 bit RISC or VLIW. When the 64 bit addressing barrier falls, there will not be anywhere for VLIW or RISC to hide. There is no doubt that IA-64 currently does have a performance disadvantage over x86 in general apps. That is why it is being ignored by the market. McKinley will have the same problem. Thus IA-64 days are numbered. Pete