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: wanna_bmw who wrote (166647)	6/19/2002 7:51:09 PM
From: Elmer	Read Replies (1) \| Respond to of 186894

The test showed that the soon-to-be-announced HP 4-way Itanium 2 server logged results that were four times faster than the 8-way Sun Fire 3800 server... Let Dan3 put that in his pipe and smoke it! I love all the FUD he spread about Itanium 2 still being a dog on real world applications. Well, this is as real world as it gets, and Itanium 2 ROCKS. Dan's a liar and everybody knows it. Itanium2 can not be judged in the same terms as desktops because it's intended for an entirely different market. The things big iron does Itanium will do extremely well. EP

To: wanna_bmw who wrote (166647)	6/19/2002 11:25:45 PM
From: Dan3	Respond to of 186894

Re: The HP system ran the “Reuters Structured Negotiation Capability” software Someone re-wrote a one-off custom software app to fake a benchmark result. Use your head. Itanic has been a production system for over a calendar year. The only third party benchmarks, for which there exists a reasonable set of other systems for comparison, are the SAP benchmarks at: sap.com Intel's enforcers must be desperately trying to cram that particular egg back into the bird from which it dropped, but don't appear to have had any luck, so far. Itanic performance really stinks, it's absolutely horrible. Reverting to the technology of the early 80's by giving up the option for OOE was a fascinating theory, but it just didn't work out. There is the exception that Itanic looks suitable for a handful of very specialized floating point applications, that use a very limited number of lines of hand written assembler code, and that's all the code the system is ever expected to process. Maybe a dozen systems a year are needed for such uses, though they would be large, multiprocessor systems. Now, they may very well be able to fix it, by having the Alpha guys redesign it into something else, but that will take several years. At this point, for you to claim Itanic is performing well would be like me claiming AMD is having a great quarter - and AMD is most definitely not having a great quarter...