Analyst Doubts Intel's Dual-Core Demo

bakeacake writes "At Xbitlabs they have a article on the possibility that Intel's Dual core Preview at the IDF was not real. Would Intel sink this low? "An analyst expressed doubts about demonstration of a 'real' dual-core microprocessor during an Intel's recent demonstration at Intel Developer Forum Fall 2004 in San Francisco, California. Insight's Nathan Brookwood believes that Intel was most likely to showcase a dual-processor system instead of a dual-core processor-based system during the show.""

Comments

Intel always has rocking tech in their R&D dep

[garcia]

"The least likely scenario is that the demo used the first silicon samples of the dual-core product planned for release next year. Intel did demo the first silicon for its dual-core Itanium, and AMD had just demonstrated the first silicon for its Opteron processor the week prior to IDF. We believe that if Intel actually had achieved this milestone, it would have trumpeted the news far more loudly and widely; their awesome PR machine would have made sure everyone on the planet was aware of this accomplishment. So we discount this theory completely," Nathan Brookwood writes.

Intel's R&D department routinely has processors way more advanced than its current offerings running at near production stability so I am confused as to why Mr. Brookwood believes something different. Intel rarely trumpets any news "loudly". They are much more likely to wait until they are confident that they can release the product on time (unlike MSFT which likes to do exactly the opposite).

Mr. Brookwood should be moderated -1 Troll. He's likely being paid off by another chip manufacturer to "trumpet this news loudly" and keep the public's attention away from other people's lack of success in the same arena.

Or maybe it was a dual core

[Jailbrekr]

When releasing "cutting edge" technology, sometimes they have to cut corners. What may have been a dual core processor could possibly be nothing more than an overglorified dual processor system in a single chip. Any advantages of a dual core chip (shared cache, faster interprocessor communications) would have been negated by the fact that they had to rely on older, proven technology to hobble together that dual core chip.

Re:Or maybe it was a dual core

[rhsanborn]

I think everyone is speculating without knowing a darn thing. I would like to see an Intel response. If they have the chip, I think they'll step out and show everyone. Or, it could be another Dan Rather event where they say, well it exists we just won't give you any evidence of it.

Right..

[Anonymous Coward]

Some random idiot questions something, and it's news? By the way, "analyst" _is_ synonymous with "random idiot".

The guy has no data whatsoever to back his crackpot opinion and just likes to hear himself talk and sound knowledgeable.

How ridiculous. I'm hoping Intel's lawyers send this guy a very pointed letter.

Re:Right..

[Anonymous Coward]

I'm hoping Intel's lawyers send this guy a very pointed letter.

Yeah, how dare he voice his (educated or not) opinion!

What are you on? Crack? If his opinion is silly, it should be easy to dispell it with, say, FACTS. And if not, gee, shouldn't that be heard loud and clear. In either case, lawyer scum should be kept out of the picture.

Tin-foil hat?

[Krach42]

What kind of weird conspiracy are these people trying to set up?

WHY would Intel lie about providing a dual-core processor?

WHY would Intel think it better to showcase a dual processor system and call it a dual-core?

WHY does this person think that Intel would be incapable of producing the demo?

Hm... maybe I should RTFA, and have a good laugh.

Re:Tin-foil hat?

[Anonymous Coward]

: WHY would Intel lie about providing a dual-core processor?

Because the processor business is highly competetive and AMD has already proven that they can produce these chips.

: WHY would Intel think it better to showcase a dual processor system and call it a dual-core?

Because Intel has no interest in providing technical samples of this product yet want to retain the perception that Intel is *the* chip-maker.

: WHY does this person think that Intel would be incapable of producing the demo?

Not "incapable of producing a demo" but rather "not completely confident in the status of their development."

Or to sum it up for you simply. Competetive Advantage and Mind Share.

I doubt the analyst

[El]

Intel has a "don't cheat" mentality for precisely this reason - getting caught misrepresenting a demo would seriously damage their credibility. Intel also has a lot of stuff available in-house that is several years away from production. So I don't think an engineer would lie about this, even though Intel marketing does lie every time they claim the latest Pentium will make the Internet much faster...

Re:I doubt the analyst

[twfry]

Thats why they called it an "engineering prototype". That can be anything, even two separate processors slapped together in the same package. You can be sure that if they had real silicon they would be showing pictures and doing a _LOT_ more PR.

does it matter?

[21chrisp]

After reading the article I fail to see what difference it makes. So Intel used something "similar" to a dual core to demonstrate how a dual core CPU would perform. What's the big deal? It doesn't seem like it's worth the time to write an article over something like this. I'm sure the "real" dual core processors will show up soon enough. It's not like they're selling whatever is in that computer.

Re:does it matter?

[l3v1]

So Intel used something "similar" to a dual core [...] I'm sure the "real" dual core processors will show up soon

Well in case you mean like two zebras are "similar" to one two-headed zebra which is the "real" thing, than you are absolutely right :P

In case you would understand the difference between dual processor systems and a dual-core cpu architecture, you wouldn't say things like you did (no matter what Intel has or has not shown).

Re:does it matter?

[drinkypoo]

Depending on how intel is doing the dual-core part there might or might not be a significant difference in performance between the two. Any difference would make the real thing faster so at least intel is not misrepresenting the processor's performance.

If the new architecture is similar to the old one, with a separate piece of logic handling the SMP, then I suspect this will not substantially change performance. In the classic intel SMP model, only one processor can access main memory at a time.

However, if the two cores share store and load paths then the dual-core processor would likely be substantially faster than a classic intel SMP configuration - and even more so if they shared cache, although that's likely to be skipped in the first instantiation of their multi-core technology.

Harsh

[ackthpt]

Mr. Brookwood should be moderated -1 Troll. He's likely being paid off by another chip manufacturer to "trumpet this news loudly" and keep the public's attention away from other people's lack of success in the same arena.

That's a bit harsh. Yes, Intel is going to have stuff in R&D that would make your eyes pop and have you salivating and the thought of being posessed of such technology (a friend, back in 1980, was working on CPUs for the DoD clocked at 100 MHz, while we dinked around with sub 10 MHz stuff) but you would probably find it in such a state that it couldn't be housed in a standard cabinet or the motherboard is fairly jury-rigged to support it, and that says nothing about actually having a compiled O/S to run on the thing and take full advantage of it.

Re:Remember when NeXT Had Video?

[EvilTwinSkippy]

Lack of reason has certainly not kept people from doing stupid things in the past. Hell Nixon had the 1972 election in the bag, but his staff still pressed on with the Watergate Burglaries.

Re:Vaporware

[binaryDigit]

What Intel and Vaporware? Never! They have to compete with the likes of IBM: In other news: IBM is preparing a dual-core version of its 90nm PowerPC 970FX processor - aka the G5

Hardly an apples/apples comparison (no pun intended). IBM has been shipping dual core Power4 processors now for a couple of years. Wouldn't be that much of a stretch to believe that they would have a dual core G5 out in that timeframe. After all, if you read the article and applied the three scenarios, you'd see that the dual core G5 actually meets there first one (it really was a dual core).

Re:Nothing to see here.

[Barryke]

I tried to moderate this, when
I realized we realy need a new
moderation category 'paranoid'.

Seriously, i do believe that the
'maybe intel didnt demo a real
dualcore cpu but said they did'
article is near 100% speculation.
Any facts here? Didnt saw them.

Re:This guy better be right

[pclminion]

He posited three theories and gave his assessment of their relative likelihoods. The worst that could possibly happen to him is that his assessment was wrong.

At no point did he state "Intel lied about this."

I think you're overly paranoid.

Re:Google the authors name

[Anonymous Coward]

Thank ghod SOMEBODY is researching these things before presenting them as fact...

AC's DO provide a service!

Re:From the article

[snuf23]

So then a dual-core chip with hyperthreading counts as four cpus for licensing?
Now that would be retarded. In fact requiring a two cpu license for a hyperthreading chip is also extremely stupid.