Posted on 12/18/2004 8:28:03 AM PST by B Knotts
SAN JOSE, Calif. - Hewlett-Packard Co. and Intel Corp. have ended their partnership to co-develop the Itanium 64-bit processor line, according to a report from Reuters on Wednesday (Dec. 15).
The move follows disappointing sales for servers based on the processor, according to the report. Intel and HP developed the processor about 10 years, but the chip has been a flop due to delays, cost overruns and lackluster demand.
Under the terms with Intel, HP's Itanium development team, which includes several hundred engineers, will be acquired by Intel and remain in Ft. Collins, Colo., according to the report.
"HP will continue to use Itanium chips in its servers and will pledge $3 billion over the next three years in developing Itanium as a competitor in the $20 billion high-end server market," according to the report. "HP is winding down its other microprocessor architectures and getting out of that business entirely, having settled on using Intel's Itanium, Xeon, Pentium and Celeron processors, as well as Advanced Micro Devices Inc.'s Opteron, Athlon and Sempron chips."
Note the little blurb about HP using AMD chips.
I use Athlon 64 chips, and refuse to buy Intels garbage. Faster, cheaper, and 64 bit now.
I think Intel tried to push 64 bit processors too soon. They ensured Itanium would just be a niche processor when they did not build in compatibility with 32 bit software or at least not penalize the performance of 32 bit software. How can anyone afford the transition costs of switching all software to 64 bits all at once?
Your answer: Nobody can.
The AMD approach of building in 32 bit compatibility was a brilliant strategic move. It is amazing to me that Intel has, at least so far, failed to follow that path. I have been a lifelong Intel processor user - many computers since that first 8088 in my original IBM PC. It is guaranteed that my next machine will be based on an AMD single or, more likely, dual 64 bit Opteron running a 64 bit Microsoft operating system.
Intel: What are you thinking? Or are you thinking at all?
I think you're right about that, although another factor is the absolutely ridiculous pricing of the Itanic.
When you limit the market the way Intel did, you have to charge high prices to pay for the R&D. If they had designed a chip that had 32 bit compatibility, they would have had a much bigger market.
Intel, in their usual arrogance, was thinking that will all their resources they could dominate. They must think that none of us use AMD now. I was hesitant at first to switch to AMD, but I am much happier with their processors than I am with the Intel.
Oops..."With" not "will".
> The Itanic is beginning to take on water.
Not beginning. It never was floating well to begin with.
With respect to HP's involvement, the news this year has
included PTC de-certifying key applications on IA-64 in
June, and then HP cancelling their entire IA-64 workstation
line in Sept.
> I think Intel tried to push 64 bit processors too soon.
64bit has been standard on high-end workstations and
servers for a decade (Alpha, MIPS, PA, SPARC). It's
less a question of "when" than "how", and Intel blew "how".
> How can anyone afford the transition costs of
> switching all software to 64 bits all at once?
Bingo. IA-64 requires a software port. The economic
rationale for undertaking it is iffy at best.
> The AMD approach of building in 32 bit compatibility
> was a brilliant strategic move.
Bleedin' obvious, more like; and a clone of what Intel
itself did on the '286 to '386 transition.
> If they had designed a chip that had 32 bit ompatibility,
Intel did. The IA-64 chips have hardware emulation of
IA-32. It's just too slow to be useful.
Intel had likely expected to remain in command of the IA-32
market, and dole out performance increases of Pentiums
so that IA-64's emulation performance looked OK. IA-64
chips were supposed to arrive on schedule, and probably
with more (compelling) performance. Intel's gravitas was
supposed to cause all the software lemmings to line up
for ports. All of this, and more, didn't go according to plan.
AMD innovations and Intel bungling make a fatal combination.
Can you elaborate on this a bit more? I am just a user, not a geek or power user, if you'll pardon the expression.
How much is a dual AMD and motherboard cost? Other than a modest increase in speed, what is its advantage?
What are its heat problems? I have continuous problems with intel, which I suspect is a heat-related problem, no matter how many cooling fans I use.
Any help would be appreciated.
Not for AMD...
Seems to me that Intel and Microsoft both have a very similar death wish...
A dual processor can allow two independent processes to occur simultaneously. Users of large technical programs ofen initiate CPU intensive processes like rendering that can consume all of the time on a processor. Dual processors allow another processor to run software while one of the processors is engaged in serious number crunching. Eventually most CPUs will be equivalent to what today are separate dual CPUs. Unfortunately there aren't a lot of programs that are written to take full advantage of multiple processors. Windows XP has quite a few bottlenecks that prevent threads from being executed in parallel. Even on my dual Xeon machine at work, I still have to wait till a program finishes writing a plot file before I can do anything else with a program.
This FX-53 is by far the most impressive chip I've had in a home box: no matter what I feed it, I just can't bog the thing down. As an experiment, when I first built this box, I started rendering Battle Royale from .avi to .mpg and then played Doom3. I only dropped an average of 10 FPS.
I'm starting to think AMD's found a way to cast processor dies to cocaine instead of silicon.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.