Intel Discusses Future Plans

heeeraldo writes "Tom's Hardware (unfortunately known for their one-page-stretched-into-nine articles, and endless ads) attended an Intel presentation about their future processor plans. The unsurprising bit: the endless march of additional cores. The surprising part: they're already focusing on 45nm processes." From the article: "Last week, Intel held a series of presentations at its Ronler Acres campus in Hillsboro, Oregon, whose facilities represent the main pillar of product design and manufacturing. These presentations included a short tour to the top-notch 65 nm production facility Fab D1D whose specifics Intel is currently replicating to other locations. The primary purpose of this show obviously was to convince around 80 analysts and journalists of the substantial health of Intel's 65 nm fabrication leadership, which is outputting new processors in high volume for launching new Pentium 4 6x1, Pentium D 900 and Core branded (known as Yonah) processors in early 2006."

Comments

apple

[eobanb]

FTFA.

they're already focusing on 45nm processes

substantial health of Intel's 65 nm fabrication leadership, which is outputting new processors in high volume for launching new Pentium 4 6x1, Pentium D 900

Now I think we all know why Apple did what they did.

Re:apple

[darkmeridian]

Intel is also showcasing technology that allows for lower voltage leakages. Lower voltage leakages in their chips mean less power having to be pumped into the core, which means lower heat dissipation requirements. The heat savings are huge on laptop because excess heat requires fans, which need power and create noise. On desktops, Apple can use their water-cooling system, but on laptops, not so much.

Re:apple

[timeOday]

Now I think we all know why Apple did what they did.

I don't. Which of the revelations are surprising?

Surprising how?

[Ziviyr]

The surprising part: they're already focusing on 45nm processes.

Thats the only way to dodge their inefficiency problems. Outside of like, designing better chips.

Re:Surprising how?

[Anonymous Coward]

Pentium M is not inefficient.

Re:Surprising how?

[ciroknight]

Well I hate to burst your bubble, but the next generation Yonah and the "Core" technology is gearing up to be more effecient than anything AMD has ever produced.

You see, effeciency isn't a measure of raw speed, it's a measure of power verses the thermal production and power needed to run the chip. In this case, Intel wins flat out. While AMD's chips may be faster, Intel's Pentium M platform has been growing in the background. When Yonah is released, we will not only see speeds slowly being ramped back up to the previous heights, but you'll also see a very small jump in heat production. I remember from an article a few days back: "While the Yonah is slightly behind the Athlon X2 in performance, it outputs less heat under load than the Athlon X2 does when idling."

And yes, while Yonah is a laptop chip, the desktop version of it isn't going to be far above that; the whole platform was designed to tweak for effecienty.

So please, stop spilling your FUD. The 45nm process is the next logical step, and it shows that Intel hasn't been operating in a vacuum this last year when it comes to the Pentium 4. It also proves they have an exit strategy to get away from the Pentium 4 and the whole Pentium name and legacy (however tarnished it might have become due to the Pentium 4's inadequacies), and it shows that not only do they have the *entire* next generation of chips taped out, that they're moving on to the generation after the next.

If you'd have read the article, you would have been impressed. Even though it seems AMD still has the upper hand (especially if they'd hurry up and move to 300mm wafers and drop down to 65nm production ASAP), Intel's coming back into the game with a vengence. It almost seems they've taken a leaf out of the IBM playbook; Release a very expensive, mainstream platform to derive technologies for the next generation (think Power -> G5, Power -> [game consoles]). The most interesting part to me; Intel made a new logo for the Itanium, which means we might be seeing a smaller wavelength Itanium update, which a lot of the high end cluster machines might enjoy. Next year's looking to be a very good one in Microprocessing.

Re:Surprising how?

[Anarke_Incarnate]

So you are comparing existing technology with engineering samples. That works so well in a vacuum, however when both sides get to shift into dynamic design mode, that doesn't always hold true.

By the way, how much of a difference in speed for how much of a difference in power savings is there between those chips?

Re:Surprising how?

[default luser]

I remember from an article a few days back: "While the Yonah is slightly behind the Athlon X2 in performance, it outputs less heat under load than the Athlon X2 does when idling."

That preview from Anandtech failed to mention some key aspects necessary for comparison, such as: was Cool 'n Quiet enabled on the Athlon 64 processor?

But there was also no conjecture that took into account the comparison between a desktop and laptop chip. The Yonah, like Dothan and Turion will be binned based on a lower full-load operating voltage. The X2 desktop dual-core runs at 2.0 GHz with 1.35v, and idles at 1GHz at 1.1v. The Turion MT line, on the other hand, is much more aggressive: 1.2v full-speed, full-load, 1.0v at 800 MHz idle. The difference in power consumption is huge.

The fact that Anandtech didn't elaborate on the reality of the situation just speaks of their sensationalist writing style. When AMD releases their X2 Turion MT next year, it will be competitive.

And yes, while Yonah is a laptop chip, the desktop version of it isn't going to be far above that; the whole platform was designed to tweak for effecienty.

I expect Merom will use significantly more power than Yonah, and be in the same realm as desktop A64 processors. Do expect it to use a higher full-load voltage than Yonah. Do expect it to not turn off the second core when not loaded. Do expect the power-saving cache design to be deactivated as well, so the chips can be competitive in performance.

Yonah turns off the second core when not in use, thus negating one of the really nice features of dual-core (zippy responsiveness, even under load). If you want that benefit, Yonah uses twice as much power at idle. Otherwise, you have to wait for the monitoring software to pick up on the increased load and wake up the second core. No doubt, AMD will do the same thing with their Turion X2 offering...this is just intended to highlight the power consumption perspective between the deaktop and mobile versions.

Re:Surprising how?

[LWATCDR]

Yes everything you say is true but we haven't seen these new chips yet in the real world. After the chain of missteps Intel has made ,Rambus , Pentium 4, Itanium, I could go on but frankly Intel has a long history of failures in the CPU market with one HUGE success the X86 line. While the X86 turned out to be a success the likes of which no cpu has ever seen Intel's other CPUs have largely been okay CPUs or failures. And yes the Itanium is a failure. It was supposed to replace the X86 line every where. I think at this point in time Intel has too be looked at with a good bit of wait and see. Having AMD beat it silly may be the best thing that ever happened to Intel.

Re:Yes but

[Anonymous Coward]

"but it's much more important to know what the technology leader is doing. Quad core CPU's next year, I understand, from AMD."

Meanwhile Sun Microsystems came out with 8 cores _this_ year.

Quantity better than Quality

[obender]

If this proves to be more than vapourware Intel could beat up AMD again just by volume. I have been trying to buy a cheap dual core Opteron 165 and no shop seems to stock it. I will not preorder as I know this involves a price premium plus if things go wrong it will take even longer to get it replaced.

If Intel starts mass producing these then people will just buy what's avalable.

Re:Quantity better than Quality

[ZenShadow]

Try QSOL. They've been good about getting Opterons out for us so far. We usually order 2xx's, though...

--S

Re:Quantity better than Quality

[Lonewolf666]

AMD is getting close to starting its second fab in Dresden, Germany. Some time in 2006, it should reach full capacity. So I don't expect a shortage of AMD processors.

Re:Quantity better than Quality

[foobarra]

tigerdirect has them in stock for $329.99.

The PR War

[yerdaddie]

I couldn't help but think that this is just the newest assult as part of a press-release war between Intel and AMD. Recently, it seems AMD has been taunting Intel about the performance of its dual core technology. So it appears Intel's reponse is to say "your manufacturing process couldn't lithograph its way out of a paper bag."

Re:The PR War

[Malor]

Wow, you know Intel is hurting right now if they're using that argument. This is exactly equivalent to,

AMD: "Your car sucks! Ours is faster, more comfortable, safer, and gets better mileage."
Intel: "Oh yeah? Well our factories are better! Your factories suck!"

If Intel has pulled its head out of its butt and put the engineers in charge again, instead of the marketroids, it could easily come back and eat AMD's lunch once again. They execute better than anybody in the tech business. They are a fearsome competitor. They've marketed themselves into a significant bind, but if anyone can dig themselves out of that jam, it's Intel. 80% market share gives you some leeway for mistakes, even big ones.

However, that said, I don't think 2006 is looking too good for them. If AMD can simplify their lines a little and keep executing as well as they have, they could take a good chunk of marketshare next year. By 2007, I figure Intel is going to be back in the game, and I'm looking forward to whatever they come up with.

This competition is GREAT for us. When Intel isn't challenged, prices stagnate and chips go nowhere. And with the competition this intense, it will be harder for either company to push involuntary DRM hardware.

Re:The PR War

[darkmeridian]

The analogy you propose is inaccurate. Intel is saying, "Look, AMD factories are going to be unable to make the next generation of cars." Intel is telling the investors (stock analysts) that the Intel future is great because AMD cannot match the 45 or 65 nm process in large quantities with sufficient yield. Chip designs obsolete quickly, but fab facilities are relatively long-term. Whenever Intel decides to stick a dual-core Pentium-M based design onto the desktop, with or without 64 bit extensions, is the day it takes over the marketshare. Let's not forget that smaller circuits mean more cache on-die.

Re:The PR War

[thebdj]

Let's not forget that smaller circuits mean more cache on-die.

Let's not forget that smaller circuits also mean more errors per wafer. The key here is to make sure your processes are still good enough that when you shrink the die size the extra dies per wafer outpaces the errors per wafer. To be honest, Intel can be confident that their processes will work fine, but they will not really know for sure until they actually begin mass producing at 45 nm.

Re:The PR War

[Kjella]

AMD: "Your car sucks! Ours is faster, more comfortable, safer, and gets better mileage."
Intel: "Oh yeah? Well our factories are better! Your factories suck!"

Don't forget that an important part of better process tech is more dies/wafer, meaning lower marginal cost. Basicly, that tells the investors that margins will stay good, and that they can be cut if the competition forces them to.

When Intel isn't challenged, prices stagnate and chips go nowhere. And with the competition this intense, it will be harder for either company to push involuntary DRM hardware.

Pardon me, but doesn't both all the newer Intels and everything since Athlon 64 support TCPA, if the motherboard has the appropriate TCPA chip and BIOS? Basicly Microsoft made some hints about Vista and TCPA, and they both jumped to comply.

Kjella

Re:The PR War

[ciroknight]

I disagree; with this next wave of promotion (and the fact they've been holding off so long on it), it indicates Intel is very confident and is preparing to repair confidences in their company in this upcoming year. To sweeten the deal, they threw in all of the upcoming information about *easily* a year and a half's worth of new core details, many of which have already been taped out and are simply waiting for all of the manufacturing plants to come onboard.

It also seems that Intel has adopted a very Applish attitude about releasing details; waiting until the very last minute, and it also seems to be evidence that the engineers are back in charge at Intel. True dual core technology with shared L2 cache. SSE+SSE2 Micro-op fusion (WHAT TOOK YOU SO LONG INTEL). And x86-64 on its way (even if it's highly downplayed).

But you are right, any competition in the desktop sector is great for all of us. Apple jumping onboard with Intel seems to have adjusted attitudes within both companies (Intel becoming more design oriented and secretive, Apple becoming more mainstream and [according to rumors] cutting a few more corners to try to drive down costs). But it is definitely going to be an interesting year in microprocessing. Cheers to the new year.

It is mostly wrong

[Groo Wanderer]

The article is full of problems. Whitefield was canceled a couple of months ago:
http://www.theinquirer.net/?article=27192
There is a lot wrong with the 45nm code names, and in general, it is lacking a lot of info.

If Intel gave him this info, it is blurring the lines for PR purposes, and somewhat flat out wrong. As of Friday, Whitefield was still dead, and the roadmap didn't match up with Intel's internal ones.

There is a bit of right there, but few if anything that can't be found at the usual places.

                  -Charlie

Re:It is mostly wrong

[Ravadill]

As much as Tom's seems to always come across as a fanboy site, The Inq is probably the single mose unreliable tech/business rumour site on the internet, especially with their lack of any solid refrences to 90% of the things they post.

Re:It is mostly wrong

[Groo Wanderer]

I guess I must guess well then.
http://www.theinquirer.net/?article=11588
http://www.theinquirer.net/?article=11668
http://www.theinquirer.net/?article=25591
There is a ton more, but that is all I feel like looking up for now.

            -Charlie

P.S. You are not that stupid for real, are you?

Re:It is mostly wrong

[Hack Jandy]

Don't bother replying to him, he writes for the Inq. He is just going to cite a bunch of cases when he was right, but he won't cite the ones where he was wrong.

HJ

Re:It is mostly wrong

[Matimus]

Even if the inquirer did manage to accurately report the status of Whitefield, Intel re-uses code names on purpose for the sake of ambiguity. So Whitefield a couple of months ago may not be the same chip as Whitefield today. Why throw away perfectly good code names?

Re:It is mostly wrong

[Groo Wanderer]

"Even if the inquirer did manage to accurately report the status of Whitefield, Intel re-uses code names on purpose for the sake of ambiguity. So Whitefield a couple of months ago may not be the same chip as Whitefield today. Why throw away perfectly good code names?"

In this case, it isn't an issue, the article on Tom's is flat out wrong there, I checked.

              -Charlie

the real question is

[radicalnerd]

how is intel planning on confusing customers with their new naming schemes?

Re:the real question is

[nmb3000]

Confusing? Not this time around! Intel marketing has learned it's lesson. These new processors will all have distinct and different names, including:

Pentium I
Pentium Ì
Pentium Í
Pentium Ï
Pentium Î

The new line features the standard, grave, acute, diaeresis, and circumflex models. Very different from one another!

Each processor will serve it's own special purpose and will have the exact same socket configuration. Unfortunately the processors are incompatible from a power standpoint and the mismatching of a processor and motherboard will result in the loss of both.

Intel finally catching up ?

[tuxpert]

From TFA - "The introduction of the Merom design will be a turning point in Intel's product policy, because it will be the backbone for all processor families that go into the desktop, the mobile or the enterprise space. In contrast, the desktop and enterprise markets are provided with Pentium 4 and Pentium D NetBurst architecture processors while the mobility CPUs are derived from the more efficient Pentium M design"

Merom being the sucessor to the forthcoming Yonah. Based on the recent AnandTech benchmarks of Yonah against desktop chips , it seems like Intel may not have to play 'catch up' for much longer. Of course, we don't know what else AMD has up their sleeve :)

Re:Intel finally catching up ?

[edxwelch]

Also interesting that they are bringing out a server version of Yonah for blades, especially considering in that benchmark you linked to the Yonah nearly performed as well as the AMD dual core and ran a lot cooler. The only catch is that Yonah is 32bit... not good for a server chip.

But it will be about 3 months before Intel release the Yonah and a few months more before they become available in the shops... in that time AMD can gain a lot more marketshare

Re:How Intel Told Off The DCMA

[Groo Wanderer]

Your dates are a tad out of la-la land, but your heart is in the right place.
http://www.theinquirer.net/?article=24638
It was linked here, but I can't find it.

The short story is that Intel's new VIIV boxes are crushingly DRM infested, and can load more. There is remote key revocation and all the things MS wanted, they are playing AMD off of Intel. Don't look to AMD to be any better, they are being screwed too.

I predict massive failure and egg on Intel's face here.

                  -Charlie

watts, heat ... ahhh no infertility

[ericcantona]

the next generation merom will, apparently, operatate at wattages of ~0.5 watts. Maybe now they will be a bit more cool. And, maybe, now I can buy a laptop that wont heat to the point of causing infertility. Kool. This better happen soon or there will be no "geeks, the next generation"(TM)!

Re:watts, heat ... ahhh no infertility

[tktk]

This better happen soon or there will be no "geeks, the next generation"(TM)!

But first Intel or AMD will have to design a CPU that will get a geek laid.

Re:watts, heat ... ahhh no infertility

[ericcantona]

which is ironic really, given they are such technophilies you would have thought they'd find it easier to open source their own source code...

Re:watts, heat ... ahhh no infertility

[vertinox]

But first Intel or AMD will have to design a CPU that will get a geek laid.

I don't know when that will be, but I suspect it will involve AI and a real doll.

Focus / Schmocus

[Chordonblue]

Who CARES what process tech they are using. At one time, the Northwood at .13 looked like it was going to KICK ASS on paper. It turned out to be an underperformer - to say the least. Let's not talk 'process', let's talk about IPC and how it's going to kick AMD's butt.

Re:Focus / Schmocus

[Darren Winsper]

Err...the Northwood kept Intel ahead of AMD for most of its existence.

Pentium 5?

[ScottCooperDotNet]

When is Intel going to move to Pentium 5 chips instead of a billion models of Pentium 4s? Sure it may seem redundant (pent = 5) but it was at least easy to keep some of this stuff straight when the chips matched to their socket sizes and years somewhat well. P4s go back at least to 2001, when is Intel going to help the everyone sell new hardware?

And while we're at it, could AMD explain their CPU lines better (esp. to consumers)?

Re:Pentium 5?

[mobby_6kl]

From what I heard, they are not going to use the Pentium brand any more after they kill off NetBurst.

Re:Pentium 5?

[chrish]

"Pentium 5" should be named "Tentium" for marketing purposes.

Re:Pentium 5?

[chrish]

But seriously... I suspect they won't give up "Pentium"; they've spent Brazilions of dollars marketing that into a household name.

Re:Thanks for the corrections

[Hack Jandy]

Odd that he couldn't find the link. He wrote the damn thing.

HJ

Argh.. naming...

[Oestergaard]

Who dreamt up the "Core" brand?

It's like when MS picked "SQL server" for their SQL server product.
A: What SQL server are you guys running?
B: Oh, we're using SQL server.
A: Yes, but *which* SQL server? Oracle? Sybase?
B: No, SQL server!
A: Yes but.... doh!

Now that everyone else have been selling multi-core processors for some time, Intel chose to brand their new processor geenration, of all things, "Core".
A: What multi-core processors are you guys using?
B: Oh, we're using multiple Core processors
A: Yes, but *which* multi-core processors?
B: We're using multiple Core processors!
*doh*

Oh dear oh dear...

Re:Argh.. naming...

[ceeam]

Yeah, this on a site eych-tee-tee-pea-colon-slash-slash-slash-dot-dot-o rg, right.

Re:Hmmm... Shady Intel.com Business

[vistic]

That seems an ok basic description of what a wireless LAN is to me... what's shady here?

Suspicious article title...

[dtjohnson]

I'd be a little suspicious of any article that is titled "Top Secret Intel Processor Plans Uncovered" even if it wasn't from a long-time Intel fan-boy site. It's hardly surprising that Intel is moving to more cores with 65 and 45 nm. AMD started doing that two years ago and just opened their newest fab to facilitate quad-core and octa-core future cpus on much larger dies. Right now, AMD has at least a one-year lead over Intel in this technology and there's no sign that Intel is doing anything that will leapfrog AMD. The entire article could be entitled 'Intel says 'me too.' It would be much more impressive if there was some meaty info about the performance of actual products rather than a lot of stuff about 'xx will do this' and 'yy will do that.' As it is, it just reads like an expanded description of a roadmap which can quickly change with future developments or non-developments.

Re:Suspicious article title...

[Kjella]

It's hardly surprising that Intel is moving to more cores with 65 and 45 nm. AMD started doing that two years ago and just opened their newest fab to facilitate quad-core and octa-core future cpus on much larger dies. Right now, AMD has at least a one-year lead over Intel in this technology and there's no sign that Intel is doing anything that will leapfrog AMD.

If by "this technology" you are referring to process technology, you are wrong. Intel has a lead on AMD in processing technology, they were first on 90nm, first on 65nm, first on 300mm wafers, and I'm quite sure they'll be first on 45nm technology. AMD has a lead on Intel in multi-core technology, but you were talking as if it was the fab that was ahead of Intel. It's not, it is the chips that have a smarter design. If you could have AMD's chips on Intel's processing tech, they'd be superior to anything currently on the market.

Re:Suspicious article title...

[dr.badass]

It's hardly surprising that Intel is moving to more cores with 65 and 45 nm. AMD started doing that two years ago.

The point is that Intel is actually producing 65nm chips in quantity right now. AMD is not: even Fab 36 is still 90nm. Your statement that AMD has "at least a one-year lead" is outright false.

Re:Suspicious article title...

[darkmeridian]

It depends on what you think is important. According to Anandtech, Intel has a one-year lead on shipping 65 nm processor parts because it has working Yonah parts now while AMD is not expected to have a 65 nm part until late next year. The smaller die size allows, according to that same article, for Intel to make a dual-core chip at the same die-size and cost as a regular single-core processor. Same price, higher performance, higher profit margins for Intel. AMD has always bettered Intel in chip design while Intel has always sat on its huge fab capacity and manufacturing process advantage. It will be fun to see how things shake out.

Re:Suspicious article title...

[CPUGuy]

Meanwhile, THG has been accused outrightly of being biased to AMD.

I guess it just depends on who YOU are biased to.

Re:Suspicious article title...

[dtjohnson]

The significant AMD technology leads over Intel for multi-core products right now are their dual-stress liner technology, their silicon-on-insulator (SOI) manufacturing process, their implementation of hypertransport, and their use of an on-die memory controller. These technologies have allowed AMD to develop multi-core cpus that outperform Intel products while operating at a cooler temperature with lower power consumption. Intel OTOH has been relying on clock speed, and more lately, process shrinks, to achieve performance that is somewhat competitive with AMD. AMD will also use those but those aren't the biggest tools in the AMD performance toolbox, as they are for Intel.

Re:Suspicious article title...

[dtjohnson]

AMD has significant leads in both manunfacturing technology and cpu design. The specific AMD technology leads over Intel right now are their dual-stress liner technology, SOI, their use of hypertransport, and their implementation of the on-die memory controller. These are the areas that AMD has a 1-2 year lead in. The newest AMD Fab was built for 65 nm and can later move to 45 nm. AMD leads in other areas have allowed them to place less reliance on clock speed increases and process shrinks to achieve performance goals, in contrast to Intel for which clock speed and process shrink seem to be its primary performance tools. Clock speed topped out for Intel so now they have only process shrinks left. There is a lower limit on process shrinks as well due to physical limits so Intel is probably also scrambling desperately to catch up in the areas where AMD has surpassed them. Unfortunately for Intel, there are likely to be no quick paths to implementing the things that AMD has spent years developing.

Re:Suspicious article title...

[WhiteWolf666]

Intel will turn around their architectural decisions too, or else they will loose.

Why?

You can't just keep making things smaller/cooler forever. You hit physical limitations.

As-is, AMD is happy to lag behind Intel interms of fabrication technology, as long as they win everywhere else. Intel will change this, however; Intel is a rich, powerful, well-staffed company, they can turn it around.

Re:Suspicious article title...

[WuphonsReach]

Intel will change this, however; Intel is a rich, powerful, well-staffed company, they can turn it around.

Your blind faith in corporate ability is astounding. After all, this is the same Intel that came out with Itanium and the NetBurst architecture (5Ghz or bust!).

They've shoveled a lot of money down the Pentium 4 / NetBurst hole. How long did it take them to admit that the NetBurst architecture was not living up to expecations and that they were going to go back to the Pentium M designs? (Or an improvement based on the Pentium M?)

Being a rich, powerful, well-staffed company doesn't automatically mean you can turn a situation around. In fact, being a large company can work against you (inertia, fiefdoms, contracts). Or you run into issues where a new product might damage another product line (Sony electronics vs the content-creation side of the business). Or because you're large and rich, there's more leeway for poor business plans to not get corrected right away.

Now, I'm not saying that Intel can't turn the situation around and get back on top of the performance list. But it won't be as simple as "hey! we're rich, powerful and well-staffed so we can turn this around.".

Re:Suspicious article title...

[dr.badass]

The specific AMD technology leads over Intel right now are.... ...not what was implied by your previous post.

The newest AMD Fab was built for 65 nm and can later move to 45 nm.

That doesn't change the fact that it is 90nm today, and will be until at least late next year.

I'm not going to bother mentioning out all of the things you're overlooking, because I don't really care one way or another about Intel or AMD, but I will point out that for someone apparently concerned about fanboyism, you sound a lot like a fanboy.

Re:Suspicious article title...

[loose_cannon_gamer]

I don't really know about SOI or hypertransporting, but I am pretty confident in claiming that Intel never wanted to put in an on-die memory controller -- they preferred giving customers the flexibility to use their processors with all kinds of memory.

I understand your point, but I don't think you can claim AMD is beating Intel in a race that Intel isn't running in. I don't know if this same point applies to SOI and hypertransport or not.

You could equally claim that Intel has a several years' edge on AMD in hyperthreading, but it is rather meaningless, because AMD doesn't do care to do hyperthreading, as far as I can tell.

Re:Suspicious article title...

[WhiteWolf666]

Honestly, I'm an AMD fan, but I try to overweigh by arguments in the other direction to cut off the trolls at the knees. :)

Sorry, I probably overdid it.

Re:Suspicious article title...

[jp10558]

Well, it's a little different though - as a layman, it seems like AMD was dual core as a response to Hyperthreading - something that AFAIK is better than hyperthreading.

This instance is rather an orthagonal competition. Intel is betting that (so far anyway) flexibility is more important to customers than performance, whereas AMD is betting on the better performance they get from having the memory controller on die being the important thing for customers.

Re:Suspicious article title...

[darkwhite]

What you neglect to mention is that Intel's 90 nm process suffers from very high leakage and thus thermal problems, while AMD has managed to decrease overall TDP dramatically on their 90 nm designs compared to 130 nm. 65 nm will probably be different, but as the processes in current production stand, AMD's 90nm kicks Intel's ass.

Nope.

[Groo Wanderer]

http://www.theinquirer.net/?article=13153
This one was wrong.

http://www.theinquirer.net/?article=13171
Here is the correction.

That is the one I can think of, if you got more, I'd be glad to post them for you. You seem utterly incapable of finding them on your own, so that kind of disproves your point.

              -Charlie

Re:Nope.

[Hack Jandy]

Usually I don't feed the trolls, but what the hell... Let's start with just ATI stuff. Fuck, let's just pick ONE card and see if you can bat 0.500

The Inquirer on R520 Pipelines
http://www.theinquirer.net/?article=22202 ("ATI placed 32 pipelines inside, but there is a chance that it will enable just 24 for a start.")
http://www.theinquirer.net/?article=22345 ("IT'S STILL NOT crystal clear what ATI implemented in its 24 to 32 pipelines, 300 millions+ transistor beast")
http://www.theinquirer.net/?article=23648 (R520 has 32 pipelines, 24 workin)
http://www.theinquirer.net/?article=24423 (It's either 24 or 32, but we ain't telling!)
http://www.theinquirer.net/?article=25730 (16)
http://www.theinquirer.net/?article=25730 (Ok ok, really it was 16 pipes, we lied)
http://www.theinquirer.net/?article=26618 (16 again!)

The Inquirer on R520 Clock Speeds
http://www.theinquirer.net/?article=22486 (1400MHz is really close to 1500MHz, good for running 24 or 32 pipelines)
http://www.theinquirer.net/?article=24423 (Nice estimate of the clock speed there -- so close)
http://www.theinquirer.net/?article=24698 (Er wait,.. )
http://www.theinquirer.net/?article=25898 (I would have thought by now you'd get the clock right....)
http://www.theinquirer.net/?article=26010 (Still can't get that clockspeed right...)
http://www.theinquirer.net/?article=26378 (Let me get this straight, ATI TOLD you the clock speeds and you still got it wrong?)

The Inquirer on R520 Launch date
http://www.theinquirer.net/?article=20896 (May, October, close enough right?)
http://www.theinquirer.net/?article=23097 (Getting warmer! Just one month away from the actual date!)
http://www.theinquirer.net/?article=24203 (Oops that was one of your gems, Charlie. And I quote "mid-August for the lucky partners, and September for the real shipments." Nice pipeline estimates there too I might add)

The Inquirer on R520 Memory Controller
http://www.theinquirer.net/?article=26168 (Oh, remember this one before it was editted? 512bit addressing!!! Even after the edit it's still nonesense ... "I believe that you don't have enough interconnections on the PCB to take the full advantage of 512 bit memory controller.")

Other Various Inquirer Thoughts
http://www.theinquirer.net/?article=22894 ("At least, in 2005 you will get R520 in an AGP version as well")
http://www.theinquirer.net/?article=21413 (You can always count on the Inq to even get the fucking name wrong)
http://www.theinquirer.net/?article=21699 (..."We don't know many details about it yet, but we are almost certain that ATI plans to bridge the R520 chip with its Rialto bridge chip"...)
http://www.theinquirer.net/?article=26543 (How do you cancel a chip that nev

Re:Nope.

[default luser]

As an Inq reader since 2001, there are some simple truths:

1. Fuad is fun to read, but never to be believed.

2. In the big rivalries (ATI v Nvidia, Intel v AMD), the one that is down will always make as much noise as possible. That is why Faud reported so much inaccurate information about R520, even with insider information it's hard to see through the noise.

But even Faud gets it right some times: your R520 AGP card in 2005, as requested. You can even buy it online now.

Re:Nope.

[theantipop]

Except the X1300 isn't an R520 it's an R515.

Re:Nope.

[augustz]

Most of the articles were by Fuad Abazovic I beleive. He's one of theinquirer reports that doesn't do a lot of inquiring. Everytime I see a company like ATI promising everything and making a ton of noise, while their competition eats their lunch, I take the hype of the stuff with a grain of salt.

Aren't there some crossfire articles as well. Crossfires been launched and re-launched for ages now, and got lots of coverage.

Re:Thanks for the corrections

[Groo Wanderer]

Gee, you have a serious axe to grind, but as I said earlier, you are dead wrong, factually, and probebly on other levels.

I DID post a link ot the one I wrote, or maybe you missed the off-colored underlined text in my post. What I could not find is the Slashdot article on the subject, if anything there seacrh is worse than ours.

I DID NOT write the slashdot one.

Go back to your hole little troll. If you mother catches you up this late, you might lose your allowance for the week.

              -Charlie

Easy one to answer

[Groo Wanderer]

http://www.theinquirer.net/?article=27957

Yup, not a problem. The last two are by far the best.

          -Charlie

the edison symdrome

[lop367]

Still Amd has been light years ahead yet it isn't seen on a tv ad. The number of users that have amd on one form or another keep growing. Can intel keep up the heat, even though challenged by to start a camp fire with one of the new procesors... ohh no wait does that say intell?. 0nly time will tell...

Re:the edison symdrome

[CPUGuy]

I've seen a couple of AMD commercials.....

They suck... big time.
I'm glad they don't do the whole commercial thing.

Re:the edison symdrome

[mario_grgic]

Of course Intel can "keep up the heat"! That's what they are famour for.

My personal ad campaign

[LaughingCoder]

In the past year and a half I converted all my home machines (12) over to AMD. Then I put a sticker on my front door - "Intel Outside".

Re:My personal ad campaign

[GreyWolf3000]

That sticker likely has the unintended side effect of also keeping the "gurls" outside as well.

Re:My personal ad campaign

[LaughingCoder]

That's a good thing because I have 3 teenage boys and I don't want them dating Intel bigots. ;-)

Future Plans?

[Bazman]

Whats the difference between Current Plans and Future Plans? Surely if you've made them they are Current Plans, and if you haven't made them yet then they don't exist, and even when you start thinking about making them they become 'Current Plans'....

Hey, its a fairly quiet thread!

Re:Future Plans?

[WuphonsReach]

Personally, I'd categorize them as:

Current plans: In the process of being implemented. Resources have been set aside, contracts are in-progress, maybe there's concrete and steel being laid already. Funds are being spent.

Future plans: Anything that still exists only on paper.

No idea if those are common definitions.

Re:How Intel Told Off The DCMA

[21chrisp]

You would think they'd have learned from the xbox...

Re:Yes but

[mmkkbb]

But those are SPARCs.

Imagine that Cray decides to make a personal computer. It contains 16 * 800MHz processors executing in parallel, has 800Gb of RAM, 1000Gb of disc storage, 4096 * 4096 pixel screen resolution, does 48-bit 3D graphics in realtime, relies entirely on thought recognition for input, fits in your shirt pocket and costs $250. What is the first question the computer community asks ?

"It is PC - compatible ?"

advert in article annoying

[cinnamon colbert]

am i the only one who finds highlighted words = ads revolting ?

There is only one way to stop this horrid thing: boycott toms hardware rev and the advertisers

Re:advert in article annoying

[Anonymous Coward]

If you're using Firefox + AdBlock, those stupid things can be banished by adding *.intellitxt.* to the filter.

Re:Yes but

[laffer1]

I don't think so. They may ask if its intel compatible or ia32 compatible. A PC does not imply intel based, just that its a PERSONAL COMPUTER. A Mac is a PC. Granted next year the distinction is gone. Besides sun makes workstations, not pcs.

Apple is shipping a dual dual core now. Its not 4 on one die, but its 4 processors on a computer the masses can buy. I think AMD is on the right track. I'd like to see a dual core in a laptop personally.

Sparcs are good processors for servers. You'd be suprised. Desktops are toys anyway. Sun's been shipping 64bit cpus for how many years now? AMD was playing catch up in the server realm. Even intel had the itanium pos out. It all depends on your perspective. If you wish to think on a desktop scale, Intel is the big dog and AMD has a better product (after years of lousy ones). The server world is a bit different. Companies are shifting back to buying larger servers and not just filling a room with pcs like they did 5 years ago. Intel can't deliver in this market. On the up side, AMD's 4 core chips will be nice additions to Sun's low end opteron lineup.

Re:Yes but

[Peter La Casse]

I don't think so. They may ask if its intel compatible or ia32 compatible. A PC does not imply intel based, just that its a PERSONAL COMPUTER.

You know that, and I know that, but the "computer community" is not so well-informed. It sees "PC" as the opposite of "Mac", as in: "is that computer a PC or a Mac?" Other kinds of computers aren't even on the radar.

Cyrix

[illuminix]

What ever happened to cyrix? :) I owned one or two of those, back in the day. Maybe they've got a new super-secret mega processor in the works that will jump out and take the CPU market by storm!

Or, maybe not.

Re:Cyrix

[CPUGuy]

VIA bought Cyrix and is basically just doing low-power stuff with them.
Putting them in micro and nano ATX boards, etc...

Writing Quality

[necro81]

Perhaps it is secondary to the point of the article itself, but did anyone else find the quality of the writing, particularly the final page, to be atrocious? There were a number of spelling errors that would have been flagged by even the most basic of spell-checkers, and the style of the concluding paragraphs was glib to say the least.

Today, it is all about squeezing the current manufacturing advantage in order to conquer middle earth and lock down brave AMD into its current 90 nm shire - although it is blossoming and as green as it can possibly be....

Yet we don't believe that Intel is going to drop the elfish Pentium brand with the next generation micro architecture.

I love Tolkien as much as any geek, but I find this analogy to be way over the top.

Intel is going to focus on its reorientation towards a platform company, but it won't be able to change the simple fact that performance decides over victory of defeat - whether you simply refer to processing speed by parallelism or clock speed, or you go for the increasingly important performance per Watt benchmark. One thing is for sure, though: The upcoming years will be all but boring.

What does "performance decides over victory of defeat" mean? And I especially love the final sentence - it is like something from the old Batman TV series. "Will our heros meet a fiery doom at the hands of the Riddler? Can Batman overcome once again and save Gotham? Tune in next week for another exciting episode!" [cue the music and credits].

This rant is now over.

Re:In the meantime, despite your positive spin

[Lonewolf666]

On both sides. The new processors Intel has promised are also not available yet. I guess AMD will get its new fab going before Yonah is available in significant quantity.

Re:Yes but

[lemaymd]

However, that advancement is very important to its intended community. Sun and Cray target very specific communities (which overlap only slightly I might add) with a lot of cash and specific needs. That community would certainly be happy to hear about more cores, or any other advancement, in a Cray, Power, SPARC, or IA64 processor. You might also note that Cray uses AMD processors in some of its offerings, so in a way comparing SPARC and AMD isn't too far off the mark.

Re:How Intel Told Off The DCMA

[ciroknight]

Do you work for the inquirer? Because it certainly seems like it; it's the only source you seem to be able to site for your "superior" knowledge about a product that hasn't been released yet.

I think I'll wait to get actual evidence over a news journal that publishes every microprocessing rumor or grumble that runs across them [not that this Tom's article is much better, though].

Re:Yes but

[Trelane]

You know that, and I know that, but the "computer community" is not so well-informed. It sees "PC" as the opposite of "Mac", as in: "is that computer a PC or a Mac?" Other kinds of computers aren't even on the radar.

Or, to adapt a certain Blues Brothers quote, "We support both operating systems: PC and Mac!"

Re:How Intel Told Off The DCMA

[Groo Wanderer]

Yeah, I do, and I am only linking my articles where I have first hand knowledge. It saves me from having to type it all in again, and tends to be a more complete answer than a shorter one here.

            -Charlie

Re:Yes but

[Anarke_Incarnate]

So it has 100GB of RAM and 125GB of storage, decent, but nothing "noteworthy" except for the size. Too many people would fubar it up by trying to use thought recognition. It requires THOUGHT; something entirely lacking in today's society. Besides, how many applications do you expect to make use of 100GB of RAM for a personal machine?

Missing Optimum

[4of12]

Is it just me, or is the Big Picture non optimal?

You know, Intel's wonderful state-of-art 65 nm fab line producing dual core Opteron's would be nice:)

Re:Thanks for the corrections

[Kjella]

Gee, you have a serious axe to grind, but as I said earlier, you are dead wrong, factually and probably on other levels.

I DID post a link to the one I wrote, or maybe you missed the off-colored underlined text in my post. What I could not find is the Slashdot article on the subject, if anything their search is worse than ours.

Five typos in two sentences, not bad for an Inquirer author. About EF, I think it will only accelerate piracy to the point of no longer being enforcable. The police already don't give a shit, the legal system just isn't willing to deal with massive lawsuits and bandwidth and software is constantly improving. DRM isn't putting the brakes on. DRM is making the pirated product superior, how can you win by that?

No power data is revealed...

[foobarra]

Being in the Enterprise server business, it is difficult to gauge a manufacturer's press hype without seeing "real" data - power consumption is a major concern to businesses running more than a few servers. This type of usable data is typically only released by the manufacturer very near consumer release date, and sometimes real-world use data can only be gathered in real-world testing, regardless of what the manufacture states in press releases and white papers.

AMD far surpasses Intel, so far, in perfomance and scale per power power consumption. Our recent power testing shows that for similar spec Opteron vs. Xeon servers from big-name hardware manufacturers, the same power use would give us either 1000 Xeon servers to rack, or 1600 Opteron servers using the same amount of power. This is a no-brainer.

A recent WSJ article hit this on the head - posted in full here, since WSJ requires login (and the article appears to now be archived...).

---

Power-Hungry Computers Put Data Centers in Bind

Newer Hardware Guzzles Electricity and Spews Heat, Requiring Costly Alterations

By DON CLARK
Staff Reporter of THE WALL STREET JOURNAL
November 14, 2005; Page A1

The University at Buffalo installed a $2.3 million Dell Inc. supercomputer last summer, hoping to bolster its image as a research institution. Instead, the big machine came to symbolize an increasingly vexing problem for data centers world-wide.

Once the machine was delivered, university officials discovered they had only enough electrical power to switch on two-thirds of the system. They have temporarily responded by throttling back use of an older supercomputer, but a $20,000 electrical-system upgrade will be needed to run both systems at full capacity.

"The calculations that were done fell slightly short," says Bruce Holm, a senior vice provost at the school, which is part of the State University of New York. "The bottom line was that they missed."

More such misses are likely. That's because, in its long-running race to boost performance, the computer industry has hit a major hurdle: The newest hardware -- particularly the servers that run most business programs and Web sites -- draws too much electricity and generates too much heat.

The power-hungry machines, along with rising energy prices, are generating enormous utility bills and forcing changes on Silicon Valley technology suppliers that are akin to Detroit's struggle to improve gas mileage. (See related article1.) Though more-energy-efficient computers are on the way, it could be years before companies replace the systems they have already purchased.

In the meantime, bringing in more electricity and cooling is expensive and difficult in some data-center buildings. Organizations face unpleasant choices that include building new facilities, putting off server purchases or leaving costly space in computer rooms unoccupied to avoid overwhelming their air-conditioning systems.

Facilities planners at the University at Buffalo, for example, originally erred because they thought an older supercomputer would no longer be needed by the time their new machine arrived, Mr. Holm says. The need for both systems caused the university to consider spending as much as $150,000 to upgrade the current data center's air conditioning, just as the university was on the verge of moving the systems to a more modern computer room. "It's that kind of juggling act," Mr. Holm says.

If planners miscalculate, servers overheat, damaging circuitry or causing shutdowns that disrupt operations. The Uptime Institute, an organization that represents data-center managers, predicts that power-related problems this year will cause four of the 20 major failures typically experienced by members annually, up from two of 20 last year. "We are headed into a territory where there is no precedent," says Kenneth Brill, the group's executive director.

For years, no one worried much about power consumption.

Re:Thanks for the corrections

[Groo Wanderer]

"Five typos in two sentences, not bad for an Inquirer author. About EF, I think it will only accelerate piracy to the point of no longer being enforcable. The police already don't give a shit, the legal system just isn't willing to deal with massive lawsuits and bandwidth and software is constantly improving. DRM isn't putting the brakes on. DRM is making the pirated product superior, how can you win by that?"

Good points, it is basically what I am arguing to the people in charge of various projects. It is an unwinable war that only alienates the consumer. One of the big problems is that every time Intel tries to stand up, MS just says 'AMD will do what we want, and we will go to them if you say no'. Intel immediately buckles.

The hardware manufacturers have no voice here because none of them will stand up and try. It is fairly sad.

            -Charlie

Re:How does this affect Mac users?

[Khakionion]

> It seems that the G5 outperforms the Intel lineup on the desktop right now, for Mac users at least.

You're telling me; I bought Tiger from the Apple Store and tried putting it on my P4 Inspiron, and it didn't even boot up.

Maybe those G5 zealots are right, after all.

I expect the OS...

[Belial6]

I expect the OS to use all 100GB. Although it would be better with another 30GB of ram. I would expect the OS to boot up, and then start caching the entire HD to ram in the background. Obiously the most often used files first. That way I can keep working, and every second my chances of having lightning fast "disk access" becomes better and better. If I leave my computer running (As many of us do) I would definitly get a massive speed boost.

How to program for multiple cores

[doc modulo]

There are three ways to implement concurrency in a programming language:
- Shared-state concurrency
- Message-passing concurrency
- Declarative concurrency (synchronization on logic variables)

A post from this mailing list: Lambda the Ultimate

Peter Van Roy - Concurrency-oriented programming blueArrow
10/21/2003; 5:06:42 AM (reads: 1765, responses: 20)
Concurrency-oriented programming is a phrase invented by Joe Armstrong, the main designer of Erlang. Basically, we would like to write applications where the concurrency follows the concurrency of the problem. This should be easy (language support) and cheap (implementation support). As far as I know, there are only two languages that support COP: Oz and Erlang (I would love to be proven wrong here--please give me evidence for others, if they exist! I mean good implementations, not paper designs.)

The majority of existing languages are sequential; concurrency was added as an afterthought. This makes concurrent programming difficult for them. A typical example is Java: it has monitors (shared-state concurrency) and expensive threads. Two years ago, when I told the head of our department I wanted to teach concurrent programming in a second-year course, he exploded "That's impossible!".

The reaction of our department head is understandable: shared-state concurrency, the kind that Java has, is the hardest to program in. There are two other kinds of concurrency that are just as practical, but much easier to program: message-passing concurrency (asynchronous messages between sequential objects) and declarative concurrency (threads and dataflow synchronization added to functional programming).

The easiest is declarative concurrency (see chapter 4 of CTM). This seems to have been forgotten by almost everybody. Yet it is not new: the first article on it I found was by Gilles Kahn in 1974.

Declarative concurrency is so nice that I believe it should be the baseline execution model for functional programming. (Not strict or lazy evaluation, which are both sequential.) This leads to many good things, for example here are two. (1) All the usual functional building blocks become concurrency patterns. For example, Map is a broadcast that collects results, and FoldL is the heart of a concurrent object with internal state (it accumulates an internal state from a stream of messages). (2) I/O becomes very simple: program input is a stream and program output is a stream. This is a perfectly good solution to the problem of declarative I/O.


When you compare the three ways of concurrency programming, shared-state is the worst and declarative concurrency is the best. Declarative concurrency prevents the most bugs and makes you waste the least amount of thought effort on concurrency. There are implementations of the different kinds of concurrency:

- Message-passing concurrency:

• Erlang Developed by Ericsson for their realtime telephone servers. Is mature and has concurrent communications and database libraries among other things.
• Oz was made as an implementation of the ideas in the book: "Peter van Roy (2004). Concepts, Techniques, and Models of Computer Programming. MIT Press" Where the idea was that different kinds of programming (concurrency, OO, Logic) could be implemented and cooperate in the same language. Not as mature as Erlang.

- Declarative concurrency (synchronization on logical variables):

• Curry is a extension of the language Haskell and, like Oz, combines different kinds of programming in one language. Unlike Oz, Curry uses declarative concurrecy. Curry is in an even earlier stage of development than Oz.
  
  All these languages are open source and free but they are functional programming languages. The difference betwee

Re:Yes but

[IntergalacticWalrus]

"Meanwhile Sun Microsystems came out with 8 cores _this_ year."

And meanwhile, no one gives a shit about Sun's new overpriced hardware.

Speeds conspicuously absent

[tji]

Did I just miss it, or were they absolutely no references to the clock speeds of any CPUs in the article?

The cpu speeds have hit a plateau for the last couple years. (Yes, I know about the P4->PM core changes, but even considering that, clock speeds have been stagnant).

Will the changes to 65nm and later 45nm enable 4GHz++ clock speeds? Or, is all this multi-core talk implying that Intel will be "building out rather than building up"?

Re:193 Immersion or EUV?

[level_headed_midwest]

Whoa, whoa, whoa. This is SLASHDOT- we are supposed to just make facts up, not actually know real ones!

Re:Yes but

[laffer1]

I suppose you are correct. I just wish more computer people would point out the distinction. Not just mac vs pc, but that pcs can run something besides windows (linux, bsd, solaris, etc). I think it would be a huge step forward for open source. My mother asked me recently what kind of computer can run linux. When i told her that her crappy hp might run it, she seemed very confused. I offered to install it, but when she learned that itunes wouldn't work she said forget it. I don't have enough exerpience with wine to make that kind of promise. Anything would be better than her unpatched, pirated copy of xp.

Out of curiosity...

[dimension6]

...what do you use your 12 machines for?

Re:I guess it's not worth reading the fine article

[aminorex]

Ooooh, touched a sensitive nerve there, did I? Got too close to the revenue stream and the political support base then?