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: Tenchusatsu who wrote (112028)	10/1/2000 9:33:40 PM
From: Joe NYC	Respond to of 186894

Tench, Now, take that table, chop off Legacy Mode, and keep only the two Long Modes. That's IA-64. The two things IA-64 loses will be lack of legacy OS support, and slower performance in Compatibility Mode compared to 32-bit processors. Good point. What's going for SledgeHammer is that it that the in Compatibility Long mode it will be able to run at full speed, and be able to take advantage of all the resources. It will be a legitimate mode for the customer to use the CPU in (for a 64bit OS user) The performance of Merced in the compatibility mode may or may not outperform a Celeron, so if an organization has something important that needs to run on the server that is a 32-bit app, Merced will not be a preferred choice. The advantage of having the Legacy mode from the point of view of AMD is that the first target of SledgeHammer will be the IA-32 server market. This market happens to be vast and revenue rich. If AMD gains a substantial portion of this market and even if not a single x86-64-only CPU is sold, AMD will be hugely successful. But IA-64 performance in 64-bit Mode is expected to be even better than that of x86-64. (Maybe not with Merced, but by the time Sledgehammer is out, McKinley will also be here, so the real comparison is with McKinley.) It's possible, but your guess is as good as mine, since none of the 3 CPUs have been released. Intel is banking on the hope that IA-32 compatibility is enough for IA-64 customers, and that existing IA-32 applications that really need the performance will be the first ones to be recompiled for IA-64. AMD is banking on the hope that customers of 64-bit platforms not only value 32-bit compatibility, but also 32-bit performance. Of course, they'll sacrifice potential 64-bit performance relative to the competition. Nevertheless, AMD sees an opportunity that Intel isn't taking. Intel already has a CPU in that market (P3 and P4 Xeon), so concentrating on 64bit performance mmay have been the right choice. Adding better performing 32bit compatibility mode to already a huge a hot CPU could possibly push it over the cliff. So Itanium will live (and possibly die) on it's own merit, on the the applicability of EPIC instruction architecture to real world problems. It has no life support that kept 386 alive while there was no native 386 software. Joe