Intel Ramps Up 45nm Chip Production, Announces 'Atom' Line

Multiple readers have written to tell us of the latest developments out of Intel. Earlier this week, Intel announced the Atom brand of low cost, low power consumption processors. The CPUs, measuring only 25 square millimeters, are the result of the Silverthorne and Diamondville projects. The announcement has caused this CNet columnist to question whether Intel can "spur innovation in ultrasmall devices the way it has in the PC and server industry." Concurrently, Intel has increased its production of 45nm processors to a rate of roughly 100,000 chips per day. As TG Daily notes, the massive investments Intel has made into chip production will make it difficult for AMD to catch up.

Comments

Isaiah

[Clay Pigeon -TPF-VS-]

By the looks of things Isaiah will wipe the floor with Atom if intel doesnt bury Via with branding power. Isaiah's out of order execution will offer much better performance than Atom's in-order execution.

Re:Isaiah

[CajunArson]

That's like saying that a Phenom will bury Atom in performance... of course it will, but then you are missing the entire point of what Atom is about. Atom is about devices smaller than notebooks where Isaiah cannot go (look at the TDP's, Atom running full-tilt is in a much lower power envelope than Isaiah). The next generation after the current Menlow platform will even work at the cellphone level, but right now Intel is targeting MIDs (Mobile Internet Devices) which predominantly run Linux BTW. The Atom/Menlowe platform could be the single biggest market for consumer-grade Linux for the foreseeable future.

Re:Isaiah

[Unoti]

Cmon, get with the program. The next version of office is going to near a dozen cores just for the ribbon bar alone, plus a handful of cores for the new Clippy.

Laughably high power consumption for handheld

[pslam]

The Atom architecture is intended to give Intel a foothold in handheld devices that have traditionally been the sole domain of very low-power RISC processors. The chip itself is tiny at less than 25mm square, and, according to Santa Clara, has a TDP of 0.6W - 2.5W, as compared to a 35W TDP for a "typical" Core 2 Duo.

Sigh. They do this every year or two - Intel announces a new core that will get them into more handhelds. They're still an order of magnitude short. Typical "very low-power RISC processors" you see in a device such as a mobile phone or MP3/video player are more like 0.01W - 0.25W, or even less. They're way more efficient clock-for-clock (and MIP-for-MIP) than any x86 core Intel has ever churned out.

Unless they have a funny definition of hand-held device we don't normally use, of course.

Re:Laughably high power consumption for handheld

[CajunArson]

These chips aren't designed to go into cellphones, and Intel frankly says they are not going into cellphones. They are instead designed for MIDs that will predominantly run Linux. Think of these things as smaller & lighter than your notebook with customized interfaces (not just mini-desktops) that are also easier to use than cellphones for accessing the Internet. Considering that Atom chips are roughly equivalent in processing power to first-gen Centrino chips, these devices should be extremely capable with the right software. The next generation of Atom at 32nm will have the proper power envelope to run your cellphone BTW.

Re:Laughably high power consumption for handheld

[pslam]

These chips aren't designed to go into cellphones, and Intel frankly says they are not going into cellphones. They are instead designed for MIDs that will predominantly run Linux.

That's funny, because according to the link, MIDs are a class of hand-held device invented by Intel. So I'm right - they have a different definition of hand-held to everyone else.

The next generation of Atom at 32nm will have the proper power envelope to run your cellphone BTW.

They will be 10 times more power efficient than their 45nm version? Extremely unlikely. Also consider that the real lower power processor market isn't standing still either - they're managing about a 25%-50% power efficiency improvement per year. Also consider that the current high-end low-power CPUs you find in mobiles are comparable in performance to the first-Gen Centrino chips.

The kind of "hand-held" devices Intel are talking about have big batteries and are held with two hands. 1 Watt is not a lower power device in this market. The real hand-held device chip market measures their power in milliwatts not watts. They idle at a single milliwatt and average a 20-50mW in use. Intel is still running orders of magnitude higher than that.

Re:Laughably high power consumption for handheld

[pslam]

I was under the impression that most of these had extremely lousy performance, and relied on dedicated decoding chips specificly designed for the task they do.

It's a common impression but it's wrong. For example, most of the CPUs you find powering MP3 players do decoding entirely in software. Even many CPUs powering hand-held video players do decoding entirely in software, but to be honest you'll find most of the high-end video players use hardware decode because a) it's faster and b) it's more power efficient.

The performance of the CPUs you find in a most high-end hand-held devices these days is surprisingly good. Well, it's surprising to people who haven't worked in the field, at least. We're constantly somewhat annoyed that the rest of the world hasn't worked it out yet. A high end ARM11 (common in high-end mobile phones) is actually quite competitive to the performance of a Via C3, for example.

Re:Laughably high power consumption for handheld

[bhima]

From Linux Devices: http://www.linuxdevices.com/news/NS5492118276.html

ARM vs. Atom

There's much to like about the Intel Atom, writes Williston in EETimes. Yet, he suggests, the media and its readers may have been overwhelmed by the hype machine. Williston offers the following responses to typical arguments from the atomic power lobbyists, at times quoting analysts such as Forward Concepts's Will Strauss to back him up:
Atom will beat ARM because it can run Vista. -- No it can't, says Williston. Atom can run Windows CE and Linux, but ARM can do the same.

Only Atom offers a "real" Internet experience with Flash video, YouTube, etc. -- "Wrong," writes Williston, pointing to ARM Flash players from BSquare, and an ARM-based YouTube decoder from On2. He might also have noted that Nokia's ARM- and Linux-based Internet tablets use a Mozilla-based browser, with plugins for Flash, Windows Media files, and even Microsoft's Flash-like Silverlight technology.

Intel dominates every market it enters. Here, the writer refers the reader to the history books, especially two years ago when Intel sold its PXA line of embedded processors to Marvell after failing to dominate the market for ARM-based SoCs.

Atom will win because ARM is proprietary technology. Nope, he writes. ARM chips are available from a number of semiconductor vendors.

Intel will win on cost. Not likely, he writes. Using a 65nm process, the Cortex-A8 occupies less than 3mm x 3mm, he notes, while the Atom core probably takes up about 9mm x 9mm of Atom's 25mm x 25mm die size, despite its smaller 45nm process. "With such a huge area disadvantage, it's hard to see how Intel will win on cost," he writes.

Intel will win on power. Once again, not likely, he argues. Intel quotes a thermal design power (TDP) of 0.6W to 2W for Atom, he writes, but doesn't specify clock speeds. ARM offers only "typical" power measurements, making comparison difficult. But at best, he suggests, Intel matches ARM on power usage, while "in most scenarios, Atom burns more power."

Intel will win because it has the most advanced fabs. Perhaps, he writes, but who cares? "Consumers focus on cost, power and speed," he writes.

Re:Laughably high power consumption for handheld

[hattig]

The next generation of Atom at 32nm will have the proper power envelope to run your cellphone BTW.

No it won't.

It won't be small enough, nor will it be integrated enough. Sure, Intel will move the GPU and Northbridge into the CPU, but that's still nowhere near as integrated as the ARM based competition.

Also it seems that people think that ARM will stay where they are now, and just happily let Intel slowly get to their power consumption over the next five years. What utter tosh. ARM have multi-core Cortex cores ready now, and on 65nm they'll make Atom and its successors irrelevant, never mind 45nm. Intel's 32nm may be what they need to get power consumption down, but that's 2011.

Intel may get into some bulky mobile phones in 2011 and 2012, but they won't be ready for slimline phones until 2015. Of course, with 20 billion ARM cores sold by then, and 20 years of extensive ARM experience and software ... who'd want to use it.

Re:Laughably high power consumption for handheld

[SlashWombat]

Sorry, if you RTFA carefully, the Atom chip size is 25 square mm. This means its about 5mm by 5mm.

While intel did sell its PXA line of ARM uP's, it still makes a fairly large range of ARM processors, most of which clock at fairly impressive speeds. (Faster than most of the competitors ARM uP's) Easy to check, just go to the Intel site.

Even ARM processors start requiring a fair bit of power when the clock rate gets high.

ARM IS proprietary. The fact that every semi vendor appears to have ARM in its lineup just means they have licensed the arm core.
The ARM's that draw milliwatts from the supply are NOT the ARMs used in mobile phones ... They are the "embedded" arms, running at less than 80 MHz. (they are still very nice chips, but, no go in a phone. These slower ARM's simply don't have enough grunt to perform the relevant speech compression algorithms. Most of these slower ARM's are ARM7 devices which do not have MMU's, making multi threaded apps significantly slower.
If Intel offer these new chips at a low enough price point, they probably will eventually drive ARM out of the market, but only if the ARM is denied access to 45/32/smaller geometries. This is not really likely. BUT, the development tools for the X86 architecture are MUCH better than dev tools for the ARM. This in its own right will ensure future development for many apps will use low power x86 devices.

AMD doesn't HAVE to compete in this market.

[Vellmont]

This isn't a new market, it's a well established one. Intel already has serious competition in this market, as evidenced in the article:

The Atom architecture is intended to give Intel a foothold in handheld devices that have traditionally been the sole domain of very low-power RISC processors.


I'm not sure that anyone really cares about what the instruction set for a handheld device is, since the operating systems for handheld devices has been relatively chip-agnostic.

Re:AMD doesn't HAVE to compete in this market.

[ocirs]

That statement isn't made towards atom, rather Intel's ability to mass produce 45nm which costs less, performs better and generates less heat. AMD is just starting 45nm production and by the time we see it hit full production, you can expect Intel to be transitioning 32nm.

Re:AMD doesn't HAVE to compete in this market.

[Lord Ender]

The Microchip PIC is an example of a "very low power RISC proc" but it doesn't even have an OS. With no OS, the instruction set matters.

The Ars Performance Judgement

[gnutoo]

Atom's performance in shipping hardware isn't something we've been able to test, yet, but given the architecture's simple, in-order nature, you shouldn't expect Atom to match even a Pentium M in raw performance.

AMD is supposed to feel threatened by that?

Re:The Ars Performance Judgement

[billcopc]

If Atom is cheaper than the AMD's lowest offering, then yes, they should feel threatened. We've reached a point where even the most basic processor has more power than the common person needs. Combine that with the mindless eco-babble that has tainted every aspect of North American life in the last few years, and you've got a market that's perfect for a power-miser medium-performance processor that will be at the heart of numerous little PC-like gadgets.

Via's line doesn't get much traction outside of the tinkerer circles, because they're still tied to clumsy legacy chipsets and the costs are ridiculous, considering their extremely limited performance. If Intel can release a slightly better processor for less money, that can be paired with an inexpensive chipset and tiny power supply, they could take a bite out of the microcontroller segment and ARM's small but tenacious market share.

Re:The Ars Performance Judgement

[Metasquares]

I'm not too sure about that. Software scales to make use of available resources, which can result in the same task requiring more processing power over time. There's a vast difference between using, say, Vista and Word 2007 to do word processing vs. something like Windows 95 and Word 6.0 - even though you're using the two packages for the same purpose.

Re:The Ars Performance Judgement

[TheRaven64]

ARM's small but tenacious market share Last figures I read (from early 2007, admittedly) showed that ARM was the most widely deployed CPU architecture in the world. Considering that mobile phones (which outnumber PCs by about 3:1) and set top boxes almost all use ARM cores, I think calling ARM's market share 'small' is quite funny.

Re:The Ars Performance Judgement

[Nullav]

Vista and Word 2007 to do word processing vs. something like Windows 95 and Word 6.0 - even though you're using the two packages for the same purpose.

How about Windows XP/2k and Word 2000? Not much difference there, save for resources and a few superfluous features hanging off of 2k7. I've rarely needed more than a 700MHz P3 for 'everyday work'. If those chips are anywhere near that in performance, I'm sure it'll find a niche in cheap school/office computers.

Re:The Ars Performance Judgement

[pslam]

Not at all. Are you aware of how many embedded Intel chips there are? I am counting the older generation parts, of course. Aren't you also doing so with ARM?

Are you aware of how many embedded ARM chips there are?

Do you know how many mobile phones are sold every year? DSL modems? Cable modems? WiFi routers? MP3 players?

Are you aware that every PC with an Intel chip in it has 1 or more ARM chips in it? Every recent hard disk I've seen has at least 1 (or more) ARM cores driving it. Monitors have them. The interface controller on flash cards sometimes have ARM cores.

That's right - for every Intel CPU sold, they enabled the sale of 1 or more ARM cores because Intel doesn't make a part suitable for some peripheral device. Intel's a minnow and they just don't make the right sort of cores - even with Atom - to beat the existing players.

Re:The Ars Performance Judgement

[billcopc]

Being conscious of our environment is a good thing. Throwing around random buzzwords is not.

I'm all for conserving energy, and I abuse my Kill-A-Watt meter on a daily basis. What irritates me, and this also applies to health fads, is the use of pseudo-science in marketing. Gadgets are being branded as "low power" when they were never high power in the first place, and sold at a premium. Other things are remade into low power variants, sold at a premium but consume more power during fabrication than the savings incurred by the user.

Let's face it: it's common sense that using less of a limited resource will result in that resource lasting longer and/or serving more people. The fact that this conservation fad has become a daily brainwash is no accident. Just like the health food fads of the 90's, it is now profitable to market "green" products, thanks to some very lax regulations on advertising. Whether these products actually result in net savings is dubious, but they do result in net profits for the manufacturers.

Ultrasmall devices?

[jhoger]

"Ultrasmall" is fine if you don't need a display and keyboard.

I think the utility for these new processors is reducing power consumption on devices that are the same size we normally expect.

Is anybody really satisfied with ~3 hours of battery life on a laptop? Considering this is the 25th anniversary of the Model 100, which sold 6 million units, has 20 hours battery life, lighter than most laptops today and was easier to use, instant-on, off, people should know we can do better.

-- John.

Re:Ultrasmall devices?

[Vellmont]

Is anybody really satisfied with ~3 hours of battery life on a laptop?

Given that laptop sales are at an all-time high, I'd say the answer is "yes". Do people want more? Sure, but they're willing to settle for 3 hours.

Part of them problem is laptops are just an extension of desktops, and desktops are driven by more and more resource usage (and thus more power). I'm sure someone could come out with a laptop with a 12 hour battery life, but:

It'd run modern desktop software slowly.
It'd have a smaller storage space (20 gigs of flash ram?) (this isn't so bad really)
The screen wouldn't be quite as "nice" as the 3 hour laptop. The maker would likely have to compromise on the screen technology to reduce power consumption.

low-power devices like this exist, of course. They're just identified in a different class of device because of the above compromises.

subsidies anyone?

[buddyglass]

This reminds me of an economics lecture I attended once, which dealt with the topic of government subsidies. In general, the professor was extremely against subsidies, since they pervert free market dynamics and generally leads to lower overall efficiency, higher prices, etc. However, the one situation where he supported them was for industries where the cost of doing business is so high that the world market can only support a monopoly. In that case, he argued that subsidies were vital in that they enable the existence of two entities in a given space, thus creating competition and spurring innovation.

His main example was the commercial aviation industry, where the two big players are Boeing and Airbus. According to him, without large subsidies from the U.S. and E.U., one of those two would "win" and the other would cease to exist, leaving us with a single global manufacturer of commercial airplanes. I wonder if this argument now applies to Intel?

Re:subsidies anyone?

[Albanach]

Hmm, I'm not sure if it'd apply to Intel or not. Surely though it'd apply to operating systems since MS is a convicted monopolist. The solution is therefore for the government to subsidize linux.

Seriously, Intel is huge, but there have been other, better, chip makers before and likely will be again. If intel's competition declines, their designs will begin to stagnate as they try to increase profit and deliver 'shareholder value'. Then another AMD/ARM/IBM etc etc will come up with something different and the arms race will start again.

Re:subsidies anyone?

[theskipper]

An interesting aside wrt AMD. Apparently AMD's license for the x86 instruction set has a massive "catch":

http://www.overclockers.com/tips01276/

what clause 6.2 appears to say is that if AMD gets taken over or goes bankrupt, Intel has the right to end AMD's right to use Intel's patents and copyrights after sixty days notice. This would seem to mean AMD couldn't make x86 processors anymore.

The direct findlaw doc link:
http://contracts.corporate.findlaw.com/agreements/amd/intel.license.2001.01.01.html

So the arms race isn't so cut-and-dry because x86 is so pervasive. Any competitor would likely find themselves in the same situation as AMD because Intel holds the licensing trump card. Imagine being the startup trying to negotiate a fair arrangement under those conditions (i.e. where they could be truly competitive with Intel down the road).

Re:subsidies anyone?

[Reality Master 101]

Hmm, I'm not sure if it'd apply to Intel or not. Surely though it'd apply to operating systems since MS is a convicted monopolist. The solution is therefore for the government to subsidize linux.

The difference is that it takes billions of dollars just to start to compete with Intel. Someone could make a Windows clone and compete with Microsoft for, say, a couple tens of millions. That nobody does it is the stupidity of most of the industry, who don't understand the power of compatability. They just see the (relative) failures of MacOS, Linux, BeOS, etc, etc, and don't understand why they failed. But that's a different rant. :)

That a ragtag bunch of volunteers can get within some functional distance of this supposedly impossible task proves it can be done (not to mention the Wine project).

Re:subsidies anyone?

[that this is not und]

People need to remember that AMD is only in the x86 business at all because they got their foot in the door as a second-source producer of Intel chips decades back. Without those old agreements, they wouldn't be making an x86 processor at all.

Re:25 square mm, not 25 mm square

[Your.Master]

I'm from a place that properly uses SI units, untainted by imperial natures. I went to University and picked up an engineering degree. I have never, ever heard of 25 mm square necessarily meaning (25 mm)^2 instead of 25 mm^2. I would always assume the latter, and that's how my peers and professors talked to.

Eee/Cloudbook/OLPC class sub-lappies...

[MsGeek]

Now that Intel has seen people go bonkers for the Eee and similar devices, I wonder if they will put out a consumer version of the Classmate with Atom inside? A little Atom-powered mini lappie with a 1.8" HD ala the Cloudbook and a decent amount of RAM would own. Another suggestion would be to put an IBM/Lenovo/Toshiba style pointing stick "eraserhead" as the pointing device. The Cloudbook's miniature trackpad on the left and clicking buttons on the right suck ass. And the full-size trackpad on the Eee is wasteful of space which could be freed up with a pointing stick and a set of clicking buttons beneath the keyboard.

Gimme one of those, with a REAL Linux inside (Debian Lenny would be perfect, or Kubuntu) and I'd be sold.

AMD can go fabless

[cyfer2000]

The advantage of AMD is design. AMD has never bested Intel in fabrication. It looks that the design team of AMD has been dragged by its fabrication capability. To solve this problem, AMD can out source the fabrication to companies like TMSC or Chartered Semiconductor.

Re:AMD can go fabless

[Manatra]

One small problem, AMD's contract with Intel states that they can't outsource more than 20% of their chip production.

Cheap internet appliances for the whole world

[rbrander]

Sounds like the new big market is "ultra-mobile" mini-laptops, from those links to "MID" and "UMPC" in the Wikipedia.

My purchase of an Eee PC got me to do up a presentation for the engineers at work,

"Poor Man's Computer: Cheap Internet Appliances for the Whole World"

http://www.cuug.ab.ca/branderr/pmc

on the topic. Short version: as predicted by Dan & Jerry Hutcheson in Scientific American about 1997, the market is turning from "endlessly bigger and faster at the same price point" to "smaller and way cheaper if not as fast". We're taking our "Moore's Law gains" in the form of money rather than than speed, thanks very much.

And this price drop into $300 and $200 laptops (and under in the case of the XO) is colliding with the surge in global population that make $10/day or more in the developing world. Sales in the billions beckon. 100,000 per day? Hah. If they make the right product, they'll have to ramp up to many hundreds of millions per year.

Re:Cheap internet appliances for the whole world

[jhoger]

I dunno. Aside from the current blog buzz, the only thing that will continue to excite folks in the developed world about the EEE, CloudBook, et al are if they add more utility. That utility needs to come as:

all day battery life
light-weight
instant on/off (like a PDA)
full-screen window manager (like a PDA)
de-bloated software
but with a full sized keyboard and display

The point for me is not a low-cost cheapie computer. The point is more utility, usability, portability when moving from the kitchen to the conference room to the park to my couch. No plugging in. It's a laptop but the opposite of a "desktop replacement."

None of this requires the fastest speeds and feeds or the worlds best LCD.

It does require a reset of the software to make it appropriate for a truly portable laptop. It does require lower power CPUs and displays and better hardware for power management and software+OS that cooperates to make that power management really work.

Re:I don't think it does

[mechsoph]

That's what I'm talking about, not code recompilation. That's fine and all, but don't confuse it with transparent portability.

You're right that languages like Java and Python are much easier to port than C, but porting is the developer's problem, not the user's. When the software is open source, it is highly likely that, for major applications, some developer has already ported it to whatever architecture you may be interested in using. Debian runs on 11 architectures. When I used gentoo (perhaps not the best example of user-friendliness though) on a PPC, there was no difference using the open source packages compared to x86. It was the same case when I used Debian -- a little more friendly -- on a couple of sparcs. Now you can download Ubuntu for x86, amd64 and SPARC (and previously PPC), and I don't think you'll find anything much friendlier than that.

I don't think there's any question that higher level runtimes make porting easier, but to say that, for the past ten or more years, it hasn't been possible and easy for a user to drop Debian or BSD on whatever hardware he would care to use is just wrong

If they do something like cast pointers in to a 32-bit integer (which for some reason some people do) you are screwed, barring doing some rewriting.

I was under the impression that you could compile sparc apps to run in 32bit mode and that this was commonplace for performance reasons due to shorter pointer lengths.

Re:I don't think it does

[TheRaven64]

It's not the high-level runtimes that are making x86 obsolete, it's the low-level ones. Emulator technology has come a long way in the last few years. Rosetta (which Apple licensed from a little start up from Manchester University in the UK, by the way), has really shown how unimportant the ISA is. I run a few PowerPC apps on my MacBook Pro and don't even notice that they aren't native.