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

Vaporware

[EggMan2000]

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. Codenamed Antares, the chip will be delivered - likely in sample form - to Apple later this summer.

News article here

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).

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.

Nothing to see here.

[njfuzzy]

This article is pure speculation. Yeah, well I doubt the reporter was at the show... I mean, he *could* just be saying he was there.

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

[Em Ellel]

Umm....2 Chips on a Single die is dual core. So an overglorified dual cpu system on a single chip is a dual core chip. What else do you think a dual core chip is? Besides the Advantages of what you call shared cache are none. If essentially 2 (different) cores/chips share a single cache the performance could possibly be less than optimal. The only benefit of 2 cores sharing a single cache is to save on die size

I think the implication is that this was Dual die - single package rather than "Single die"

I think people often confuse the packaging of a chip and the "chip" itself (silicon) thinking that the plastic they see is the chip itself

-Em

Re:Or maybe it was a dual core

[philipgar]

Uh, actually there are significant advantages to having a shared cache depending on the application. While it may not be too obvious, and its not true in all cases (ie 2 single core processors with 1MB L2 cache each will be a dual core with 1MB L2 in most all situations). In general however they will give the dual core chip a larger L2 cache to make up for the fight between the two processors to use (often including heuristics to ensure that one processor doesn't kick out all the other processors data from cache).

Where then do performance gains over simple dual core operation come from then? Well in many multithreaded applications there is a significant ammount of shared data. When processing this shared data only one copy needs to exist in the L2 cache. On top of that if one core is using the data (or used it recently) and the second processor needs to use it, the data exists in the first processors L1 cache (generally dual cores won't share L1 cache due to the necessity to locate L1 cache near the core of the processor for speed reasons. When this happens the 2nd processor must wait longer then normal for the first processor to update the L2 cache (cache coherence protocols and the fact that L1 cache is duplicated in L2 cache), but this is still an order of magnitude faster then a standard dual processor setup.

So there you have it, the advantages of a shared cache.

Phil

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.

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?

[phalse phace]

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

Must I remind you of the first rule of /.? You *never* RTFA.

Rather Fishy

[cloudscout]

Dan Rather has uncovered 8th-generation photocopies of some internal Intel memos confirming that the actual dual-core processor was AWOL during the Devloper Forum.

Re:Rather Fishy

[EvilTwinSkippy]

The Swift-Server Veterens for Truth meanwhile has posted a story from Steve Job's cousin's roomate claiming that the Apple IIe did not in fact exist.

Re:If I may flaunt my ignorance...

[zoobaby]

It is two processors on a single die. It would be like having a dual processor system, but only needing a single socket to support it. Now add in Hyperthreading and it would appear to be a 4-way system. Many people are really excited about this, and it is definately a cool engineering feat.

From the article

[Max Threshold]

"Designing a unique motherboard is clearly less expensive and takes less time than creating a multi-chip package, and the resulting system would come close to replicating the performance of the eventual dual-core product."

So... why don't they just do that?

Re:From the article

[dirty]

Oracle doubles in price with a dual core chip too. I'm pretty certain Oracle has stated that for licensing purposes, a single chip with hyper threading counts as two chips. A dual core chip definately counts as two in that case.

Yes, They Would

[00Monkey]

I was at a Microsoft OEM System Builder conference for the release of Windows XP and Intel just happened to be showing off the Pentium 4. They did a video encoding benchmark, the pentium 4 2ghz vs the Pentium III 1ghz. They had *1* stopwatch, started the Pentium 4 and then 15 seconds later started the Pentium III. Then when the Pentium 4 only made out twice as fast as the Pentium III, they started saying how great it was that it was 2x the performance. They never accounted for the 15 second head start that the Pentium 4 had... meaning it wasn't even twice as fast.

Regardless of whether the P4 is good or not, that was a pretty crappy thing to do and when about 20% of the crowd commented on it, the Intel guys merely say "that didn't happen".

Why not show it?

[hirschma]

AMD did a dual core demo the week before. They opened the boxes, passed around sample chips, showed enlargements of the cores, etc.

Intel did their demo with a closed box, presumably in response to AMD. Only when asked if it was really dual core did they say it contained "real silicon".

I'd say that there was some vapor in that closed box, too.

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.

Running scared

[IGnatius T Foobar]

Intel has been caught off guard. They definitely have a lot of products in the R&D pipeline, but they spent so many years focusing on the Itanium future that they're really starting to hurt from the fact that nobody wants Itaniums.

Fortunately, even Intel's second-string is big and fast enough to keep pace with the rest of the industry, but things like this show that they really are having to make a huge effort to do so. I'm sure the dual-core demo was genuine, but as with so many demos of this type, it must have been very carefully scripted to avoid an embarassing crash.

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.

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.

hehe, wow

[ak3ldama]

i just read on thg their review of the idf held recently, and those intel fan boys didn't even say anything about why the chip wasn't physically displayed ... there is even a funny picture of a staffer hauling the case out of the presentation right away ( here )

N64 demo was better.

[Kenja]

I recall a demo of the Nintendo 64 that had an SGI reality engine system under the table.

Re:If I may flaunt my ignorance...

[Malor]

Just a single CPU die with two CPUs on it. If the board can support it, it's like plugging two CPUs into one socket.

This is quite easy for AMD because of how bus logic works. The Athlon 64 series use an integrated memory controller, and normally, a second CPU uses the same connection to the system RAM that the first one does. (ie, one Hypertransport connection is shared, by design, between two CPUs.) So a dual-core CPU is trivially easy for them to implement, relatively speaking: they have space and heat issues, but all the architectural design work is done already.

Intel, on the other hand, hasn't designed this way. Instead, for years now, they have been totally focused around more and more clock speed. This has left AMD scrambling, becaus their chip designs get more work done per clock tick, so a 1600mhz AthlonXP will keep up quite nicely with a much higher-clocked P4. But consumers, thanks to Intel mostly, don't understand that, and so AMD came up with their numbering system instead. (they were lucky this worked, because at least one prior attempts at this, by Cyrix, failed utterly.)

Well, the worm is turning. Intel's aproach, that of "more megahertz, dammit!" is very rapidly running out of steam. They have been selling people for years on megahertz, and suddenly they're in the position where they can't increase megahertz easily anymore. This is a BIG deal for them; all those billions spent 'educating' consumers on something that wasn't true is coming back to bite them.

A dual-core Prescott will not be an easy thing, and will require substantial motherboard and chipset changes. And they have a fundamental bandwidth problem; P4s need very high memory bandwidth to really get good. The P4 didn't truly hit its stride until it went to a quad-pumped 200mhz bus... 800mhz effective RAM speed. At that point, the P4 architecture finally sits up and really starts singing. But doing a dual-core chip means that both CPUs have to share bandwidth, so to maintain performance, they'll have to go to a 1600mhz bus. That's not likely in the near future.

AMD is doing the exact same thing, but the A64 design is much less clockspeed- and bandwidth-intensive. It gets more work done per clock tick, doesn't hit the RAM as hard, and runs cooler. So it's a natural for dual-core. Forcing the P4 into that same mold, on the other hand, is a move of desperation by Intel. It won't work very well, but their crank-the-megahertz strategy suddenly isn't working AT ALL.

From what I can see, Intel is in trouble.

Any Sufficiently Advanced Technology

[Anonymous Coward]

is indistinguishable from a rigged demo. Apologies to Asimov.

Re:If I may flaunt my ignorance..Intel's other cpu

[Nom du Keyboard]

A dual-core Prescott will not be an easy thing...they have a fundamental bandwidth problem...Forcing the P4 into that same mold, on the other hand, is a move of desperation by Intel

Remember, Intel has a second P4 compatable CPU. The Pentium-M is much closer to AMD in instructions per clock (e.g. a Pentium-M at 1.5GHz performs close to a P4 at 2.5GHz). And it uses less power to accompolish this feat. Perhaps Intel will use their more efficient processor for dual core applications.

Re:If I may flaunt my ignorance...

[temojen]

So the difference between this and a chip having double the transisitors is?

The more transisters you put in a processor, the farther the signals have to travel, which reduces clock speed. Using 2 cores on one die improves locality of reference, which lets you use a higher clock speed.

Also, dual processor system (whether on the same die or not) perform better for multi-task applications (with both lightweight (threads) and heavyweight (no shared memory) tasks). UNIX like systems tend to see more benefit from this than VMS or Windows NT/2000/XP based systems, because they tend to have more processes.

Designing a more complex CPU is a harder task than simply joining two pre-existing designs, especially if your design has a built-in memory controller (as the Opteron does).

It's all in the typing

[Nom du Keyboard]

Of course the demo was fake. If you look closely at the chip surface you'll see that where it said:

Pentium 4 Dual Core Prescott

That was actually typed using a 1974 IBM Correcting Selectric II typewriter on loan from CBS.

Google the authors name

[Anonymous Coward]

Google the authors name, the very first result is a link to AMD's website becasue Nathan Brookwood gave a keynote speech for AMD.

http://www.amd.com/us-en/Weblets/0,,7832_8366_78 23 _8721%5E7827,00.html

Faked Demo? Happens all the time.

[Anonymous Coward]

I used to work at what is now a major telecomm company ( hint: now owned by a French telecomm giant ).

We were at a show once pitching a new router that simply Did Not Work. To make matters worse, the case for our engineering sample was damaged just before the show.

Truth: We got a block of wood. Painted in black. Attached some LED's with wires on it that blinked randomly. Put it inside a rack with a smoked glass door.

"Demoed" the crap out of it for 16 hours over three days. I had new respect for the ability of our sales people to talk bullshit for so long without opening that freaking rack door.