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

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.

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: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.

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).

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: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.