Slashdot Mirror
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.""
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
what? what I thought we were in the trust tree in the nest, were we not?
"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.
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.
My Photography - http://ian-x.com
The Deathlings (comic) - http://thedeathlings.com
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.
Feed the need: Digitaladdiction.net
At last week's Developer Forum, Intel demonstrated how its Digital Office vision might enable three workers in different locations to collaborate to solve a complicated problem. One of the workers ("Jason") had to juggle several compute-intensive tasks on his system, but the work flowed easily without the sorts of fits and starts that would plague many contemporary systems.
Ah, a flawless network connection! Proof!
pay attention to the man behind the curtain.
A feeling of having made the same mistake before: Deja Foobar
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.
What exactly is a dual-core microprocessor? The article didn't really elaborate.
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.
I am unamerican, and proud of it!
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.
unlike MSFT which likes to do exactly the opposite
Bill Gates dies in a car accident. He finds himself in purgatory, being sized up by St. Peter. "Well, Bill, I`m really confused on this call; I`m not sure whether to send you to Heaven or Hell. After all, you enormously helped society by putting a computer in almost every home, yet you also created that ghastly Windows `95. I`m going to do something I`ve never done before in your case; I`m going to let you decide where you want to go." Bill replied, "well, what`s the difference between the two?" St. Peter said, "I`m willing to let you visit both places briefly, if it will help your decision." "Fine, but where should I go first?" "I`ll leave that up to you." "Okay then," said Bill, "Let`s try Hell first." So Bill went to Hell. It was a beautiful, clean, sandy beach with clear waters and lots of bikini-clad women running around, playing in the water, laughing and frolicking about. The sun was shining; the temperature perfect. He was very pleased. "This is great!" he told St. Peter. "If this is hell, I really want to see heaven!" "Fine," said St. Peter, and off they went. Heaven was a place high in the clouds, with angels drifting about, playing harps and singing. It was nice, but not as enticing as Hell.
Bill thought for a quick minute, and rendered his decision. "Hmmm. I think I`d prefer Hell," he told St. Peter. "Fine," retorted St. Peter, "as you desire." So Bill Gates went to Hell. Two weeks later, St. Peter decided to check on the late billionaire to see how he was doing in Hell. When he got there, he found Bill, shackled to a wall, screaming amongst hot flames in dark caves, being burned and tortured by demons. "How`s everything going?" he asked Bill. Bill responded, with his voice filled with anguish and disappointment, "this is awful! This is nothing like the Hell I visited two weeks ago! I can`t believe this is happening! What happened to that other place, with the beautiful beaches, the scantily-clad women playing in the water?!??? "That was a demo," replied St. Peter.
Analyst Doubts Intel's Dual-Core Demonstration
Insight 64 Asks Whether Intel Has Desktop Dual-Core x86 Chip
by Anton Shilov
09/15/2004 | 01:55 PM
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 64'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.
At last week's Developer Forum, Intel demonstrated how its Digital Office vision might enable three workers in different locations to collaborate to solve a complicated problem. One of the workers ("Jason") had to juggle several compute-intensive tasks on his system, but the work flowed easily without the sorts of fits and starts that would plague many contemporary systems. At the conclusion of the demo, Bill Siu, the General Manager of Intel's Desktop Platforms Group, casually noted that "Jason was using a dual-core system on a 915 [i.e., Grantsdale] platform." When asked about it later during a Q&A session, Siu smiled coyly, and added only that the system used "an engineering prototype" of a dual core processor with "real silicon." This begs the question of what was really inside the box.
Nathan Brookwood, the principal analyst for Insight 64 believes there are three options of what Intel might demonstrate.
"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.
"It is a bit more likely that Intel crammed two of its current Pentium chips into a single package that could be plugged into the socket of a 915 motherboard. (This is known as a multi-chip package (MCP), and has been used for years in certain applications.) The standard P4 package measures about 30mm on a side, and could conceivably hold many discrete processors that only measure about 11mm on a side. Intel wouldn't do this just for an IDF demo, but the resulting MCP might be useful for evaluating dual-core platforms, especially if the initial dual-core design follows the scheme we outlined above. The system would certainly be consistent with Siu's claims of "dual core," "915," and "real silicon," Mr. Brookwood claims.
"It is even more likely that Intel merely designed a dual-processor motherboard around its 915 chipset. The 915 is normally used only in uniprocessor designs, but there is no reason why engineers inside Intel could not circumvent the restrictions that prevent Intel's customers from using the 915 in DP configurations. 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. Like the MCP scenario, this system would fit with Siu's claims of "dual core," "915," and "real silicon," Insight's 64 principal analyst concludes, leaving the readers to decide what exactly did Intel showcase.
The analyst notes that typical Intel-based SMP systems, such as those fuelled by Intel Xeon processors, have processor system bus bottleneck, as all the chips have to share one PSB, be it a 400MHz QPB for 4-way systems or 800MHz PSB for 2-way systems. It is believed that dual-core processors will also have to share the same bus, which may limit their performance, even though by the time dual-core desktop chips are available, Intel will also present 1066MHz infrastructure for such microprocessors.
Intel and AMD both showcased
So... why don't they just do that?
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".
And it was actually just a VCR or BetaMAX or whatever hooked up to the screen? yeah, that was pretty funny, but I don't think that's what we are seeing here. Intel isn't under the same kind of pressure NeXT was, and would have no real reason to atempt such a stunt.
The "Insert Quote Here" line is almost as predictable as inserting an actual quote.
Or Intel will bitch slap him into the stone age for attempting to discredit them. I dont really hold out much hope for him given his article is based purely on conjecture.
Do not try to read the dupe, thats impossible. Instead, only try to realize the truth
What truth?
There is no dupe
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.
"Capricornian One" sounded pretty fishy to me too, but they did boil several kettles of tea during the demo, so who knows?
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...
"Freedom means freedom for everybody" -- Dick Cheney
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.
Tired of FB/Google censorship? Visit UNCENSORED!
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.
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.
A feeling of having made the same mistake before: Deja Foobar
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 )
"but money is the God of Algiers & Mahomet their prophet." - Rich. O'Bryen June 8th 1786
I recall a demo of the Nintendo 64 that had an SGI reality engine system under the table.
"Have you ever thought about just turning off the TV, sitting down with your kids, and hitting them?"
Ya, I remember seeing that memo a few years ago. They said we were going to adopt that policy and use 'sister' companies for policing it. I think, if I recall right, oursister company at the time (Intel) was Enron. ;)
The place must be full of dual head computers, dual processor computers, multiple core processors, and multiple personality math heads.
I can see someone starting to lose track of what is what where is what what is who and who is who.
Likely someone forget the medicine, that's all.
Build your own energy sources from scratch. http://otherpower.com/
Is that like getting head from two guys at once?
More seriously though, none of this stuff is worth getting all that excited about, until you can actually buy it yourself -- and it works!
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
However, there was a desktop "engineering prototype" that was kind of quiet. No picture was shown. It sounds like they made a multichip module from 2 die to test things. If they had a dual-core Xeon, they would have said so clearly and not just mentioned after a demo that the machine was using an engineering prototype dual-core.
is indistinguishable from a rigged demo. Apologies to Asimov.
Caches may make a minor difference, but AMD and Intel run the same instructions. To run them, they both have to fetch them, all of them. Because of this, AMD doesn't get more work done per memory access.
This appears to be some kind of sour graping about AMD being behind Intel on memory bandwidth for a long time.
The large your dataset is, the more bandwidth you need to process it at a given speed. Intel is just keeping up with the increasing size of datasets (programs+associated data). AMD needs to also.
AMDs chips are fine, Intels are also. Both do well on speed, power usage, etc. (I measure power usage on my PCs at the wall with a Kill-A-Watt). AMD is cheaper, that's nice. AMD also does 64-bit, that's nice. Intel will have to rectify the latter to remain competitive. But to say Intel is in trouble when P4 performs as well as AMD on 32-bit code, and they have P-M as a power-saving processor seems just like fanboyism to me.
It could have been a dual core or not. It doesn't matter, especially to the Marketing folks. Heck, I've made demos that my Marketing department has tried to pass off as real products- they like to call them "capabilities." Never mind that the manufacturing capability hadn't been worked out yet. I hate it when they say, "hmmm... maybe Mark can make 10k of them a month." :)
At least in Intel's case, there's the real possibility of actually having the part available when they say it will.
That said, I have an acquaintance (Hi, John!) who will never work for Intel again because fifteen+ years ago their Marketing department had done exactly that. At one conference they had a pretty little box on the table with a card that they said did something, while under the table they had the his, cobbled-together breadboard actually doing the work ("Ignore the man behind the curtain").
That's marketing. No big deal. That's why you wait for an actual released product. Anything else is vaporware.
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.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Because Intel had to revamp roadmap, and has no product.
Their Pentium4 with NetBurst Architecture has smashed into a brick wall.
Their IA-64, meant to destroy the Clones, never caught on very well, and any plans to penetrate the lower-end (but not low-end) have been cut off at the knees by X86-64.
The Pentium-M is a success, but was apparently meant to be a niche product. Suddenly it's being called on to become mainstream, and they're not ready for that.
They've got to show something to make them worthy of the future. They've reacted and revamped their roadmap, but their hand TODAY is rather weak. They've got to show that they're executing their new roadmap, and will deliver what customers want/need.
I suspect that to uncover the truth, you have to find out *exactly* what Intel said at the demo, and offered for publication. Then you have to analyze that for what they *didn't* say. I suspect that Intel didn't lie, but I also suspect that they were careful to omit some details. Neither of those can be gleaned from the article.
The living have better things to do than to continue hating the dead.
That was actually typed using a 1974 IBM Correcting Selectric II typewriter on loan from CBS.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
In functionality, that is - isn't intel using their same old lousy technology to do multiple cores in a system? Would there really be substantially different performance from a system with totally separate packages on a board as compared to two dies in the same package, or two cores on one die? I know on-chip interconnects are faster than off-chip, of course, but my understanding was that the limiting factor was the cross-connect architecture, not the traces.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
Ok, but I think one of the grandparent's points still stands: people educated by Intell about the Mhx/Ghz will have hard time understanding why they have to go to slower rates (even if it will mean that dual core will be faster due to better instruction handling and hyperthreading.)\
You can't handle the truth.
Google the authors name, the very first result is a link to AMD's website becasue Nathan Brookwood gave a keynote speech for AMD.
8 23 _8721%5E7827,00.html
http://www.amd.com/us-en/Weblets/0,,7832_8366_7
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.
Hm. Lots of apostrophes there.
The Pentium-M is an incredibly good design, probably the single best piece of technology out of Intel since the original Pentium. And their numbering schemes would lend some plausibility to that; Pentium-Ms are 700-series, and P4s are 400-series. Bigger is obviously better. :-)
It's weird that you can't find Pentium-M motherboards. I looked a whole bunch, not too long ago... I wanted to set up a nearly silent PC in the front room, and figured a Pentium-M was the perfect choice. I only found one, and it was like $450, and impossible to order in singles. It's weird that so few manufacturers make motherboards for this chip... it's exceptionally powerful, and would be just about the best choice for a silent PC I can imagine. The Via Edens are good, but the Pentium-M is far more powerful and only dissipates a little bit more heat.
Definitely a good choice for a multicore CPU, but the marketroids have been in charge of Intel for a long time, and I'm not sure how the Pentium-M, as good as it is, fits into their 'message'.
Well assume they really only put two processors onto one chip.
That would not be that great, since you'd have to replace the entire CPU if one processor turns bad in or after production.
What would really interest me, does the dual processor already benefit from a shared cache ? Or is there enough benefit from a shared bus access management ?
Of course even if not it is a step into the multiprozessors-on-a-chip direction, but as long as there are less than say 8 prozessors are on it, I dunno whether there is enough pay-off already.
I'm still trying to figure out what people mean by 'social skills' here.
http://shit.slashdot.org/article.pl?sid=04/09/16/1 645205
Like many others here, I'm a little skeptical of this "analyst's" line of reasoning and ultimate conclusions.
I think it's important to remember that this was a freakin' dog & pony show. Everyone knows multi-core is the future. Everyone knows that having a multi-core CPU shipping in some critical timeframe is important.
Does Intel actually have working prototypes? Who cares.
Will Intel ever have working multi-core 64-bit CPUs. They will, or they will no longer be significant.
-- clvrmnky
Nah. It's easy to fool the consumers: all they have to do is add together the Ghz from BOTH cores to get the higher number. So if they run a dual core 2Ghz Pentium M style processor they can call it a 4Ghz machine.
Sometimes my arms bend back.
The i5's have dual/quad/eight way cores.
The new OpenPower Linux boxes will/do have multicore processors available.
IBM has been selling dual cores for around a year now.
In truth the "Apple IIe" did not exist, the II and II+ did, and then came the Apple //e.
Which is exactly why Intel is now going to model numbers to distinguish processors, instead of just referring to them by their clock rates, as they used to do. They are as strongly deemphasizing clock rates now as they once promoted them. They too know that the clock rate wars are over.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
"Any sufficiently advanced technology is indistinguishable
from a rigged demo".
Since Opterons have ondie memory controllers, every CPU has access to its own independent bank of memory.
In truth the "Apple IIe" did not exist, the II and II+ did, and then came the Apple //e.
There were the "apple //e" computer (beige case), the "enhanced apple //e" computer, and then the "Apple IIe Platinum" (gray case). Like the //c, the enhanced //e had a 65c02 processor, which had a few more instructions than the original 6502, a more robust BASIC interpreter, and a better built-in debugger. The IIe added a numeric keypad to the enhanced //e.
You know, it really made me wonder when they chose Dan Rather to report about it ...
Global warming is neither science, nor politics. It is a religion.
Quick, sick HardOCP on them!
The real truth, if you look at Pentium Ms, is that they have a processor that is quite up there with AMD in every respect. For now, they are selling Prescotts and their 3.x GHz number, once they get "car model"-numbering worked in, they can replace it with a desktop version of the Pentium M, running at A64-class clock speeds.
AMD is not "taking over the world" any time soon. They have been improving because Intel has been too busy competing against their last round of processors by increasing GHz numbers. Their engineers are on par with AMD from what I can tell.
Kjella
Live today, because you never know what tomorrow brings
There's actually a third possibility... CBS is showing fabricated evidence, but the fabrication reflects the truth.
But it's all a distraction from the issues.
The living have better things to do than to continue hating the dead.