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.

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?

[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?

[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: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

[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.

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

[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

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

[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?

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: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

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.

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.

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...

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...

[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...

[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.

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: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: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 ?"

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...

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.