Forgot your password?
typodupeerror
Intel Upgrades Hardware

The Mile Markers of Moore's Law Are Meaningless 156

Posted by timothy
from the we-call-this-one-petite dept.
szotz writes "Keeping up the pace of Moore's Law is hard, but you wouldn't know it from the way chipmakers name their technology. The semiconductor industry's names for chip generations (Intel's 22nm, TSMC's 28nm, etc) have very little to do with actual physical sizes, says IEEE Spectrum. And the disconnect is only getting bigger. For the first time, the "pay us to make your chip" foundries are offering a new process (with a smaller-sounding name) that will produce chips that are no denser than their forbears. The move is not a popular one."
This discussion has been archived. No new comments can be posted.

The Mile Markers of Moore's Law Are Meaningless

Comments Filter:
  • Is that some archaic form of measurement used by a backwards nation somewhere?

    • Several backward nations: Am. Samoa, Bahamas, Belize, British Virgin Islands, Cayman Islands, Dominica, Falkland Islands, Grenada, Guam, Myanmar, The N. Mariana Islands, Samoa, St. Lucia, St. Vincent & The Grenadines, St. Helena, St. Kitts & Nevis, the Turks & Caicos Islands, USA, UK and the U.S. Virgin Islands.

    • Re:What's a mile? (Score:5, Informative)

      by msauve (701917) on Thursday October 31, 2013 @07:11PM (#45295545)
      It's one thousand (mille) paces of a Roman soldier, as modified through history. That seems to be as reasonable a basis for a unit of length as the meter, which is 1/10000000th the distance between the poles and the equator, as modified through history. Mileposts were markers placed by Roman roadbuilders as reference points.

      Why do you ask - do you live in some backwards nation without a good educational system?
      • Re: (Score:2, Insightful)

        Those romans must have had really long legs. A 1m pace is already pretty uncomfortable.

        • by Anonymous Coward

          A pace is two steps. It's not so bad.

        • Re:What's a mile? (Score:5, Informative)

          by Livius (318358) on Thursday October 31, 2013 @07:40PM (#45295843)

          The Romans were counting the right and left steps as one pace.

          • Oh, come on. Stupid romans. That definition is even more ridiculous than the weird leaps, stretches and assorted silly walks I was imagining.

            • Pacing (Score:2, Insightful)

              by Anonymous Coward

              If you've ever actually had to do precision pacing and measured it out, you'd know why a pace is 2 steps. It equalizes the difference between left and right. 1% accuracy in pace length over a moderately long distance (50-500 m) isn't unusual.

        • by khallow (566160)
          As he noted, it's two steps. For example, my stride is roughly 9 paces in 50 feet (1 2/3 meters per pace roughly) which is 5500-5600 feet per 1000 paces.
      • by KiloByte (825081)

        Then why in so many countries the mile was around 7.5 kilometers? Basically, everywhere north or east of Germany, although there's a few 11km miles as well.

      • Oh, the romans used all kinds of impractical systems, and I don't think anybody can ever disagree with that... Just look at their numbers.

        After them, our tech advanced a bit, we started using those things called arabic algarisms, positional notation and decimal base numbers. And on the context of a civ that uses that tech, yes, the meter is a more reasonable measurement unit than the mile.

        • No, there's no inherent advantage to the meter as opposed to the mile. There is an inherent advantage in using kilometers, meters, and centimeters in daily use as opposed to miles, feet, and inches. There is an inherent advantage in having scalable units of measure rather than either making units up (the Angstrom), or using fractions of the smallest available unit (the inch). There is a scientific advantage in having a unit of mass (the gram) rather than a unit of force (the pound). The virtues of the

          • There was once an inherent advantage to the meter (a defined fration of the Earth's curve) to the mile (a badly define multiple of step sizes). That advantage did go away once we defined the mile as a multiple of the meter, but it lasted for long enough to assure that anybody that cared about it used the metric system.

    • Sure. Where people still measure weight in "stone" the ENGLISH system must seem very archaic.
      • by jabuzz (182671)

        Really the people who actually live in English look at the system of units in use in the USA and wonder why they are still using a system of units that they depreciated while the USA was still a colony. Further they wonder why they call them English units because they are not.

        • by msauve (701917)

          the people who actually live in English look at the system of units in use in the USA and wonder why they are still using a system of units that they depreciated while the USA was still a colony.

          That's not hard to figure out - they lost to not only the colonies, but to the French. But I'm being facetious. They're "imperial units," not "English units." They're based on the British Weights and Measures Act of 1824, which postdates your claim that they deprecated such measures in colonial times. Britain didn't

  • by bobbied (2522392) on Thursday October 31, 2013 @06:19PM (#45295111)

    And thirdly, More's law is more what you'd call "guidelines" than actual rules.

    • Just like all the other laws. Scientific or otherwise.

    • And thirdly, More's law is more what you'd call "guidelines" than actual rules.

      Yeah; but that's what got Sir Thomas into trouble in the first place....

    • by Xyrus (755017)

      Welcome to the IC market, Ms. Turner.

  • Moore's Law isn't even a law... it's a prediction. Didn't we already agree that predictions are only useful to talking heads, pundits and hucksters?

    • Re:Not a law (Score:5, Insightful)

      by crgrace (220738) on Thursday October 31, 2013 @06:27PM (#45295177)

      I don't know about that. It's been a damn useful prediction in that it gave a pretty ambitious roadmap for engineers to follow. They've been quite successful and meeting the challenge up until quite recently.

      A wise proverb that is apropos: If you don't know where you're going, you'll never get there.

      • I don't know about that.

        I do. Its been a fairly accurate prediction, yet a prediction none the less. The "law" part is just an anecdotal, off-the-cuff addendum. You want to support your theory that its in fact an actual law, here's room for your proof right here:

        • by crgrace (220738)

          I wrote:

          It's been a damn useful prediction

          You replied:

          You want to support your theory that its in fact an actual law, here's room for your proof right here:

          I didn't claim it was a law. No one even slightly knowledgeable about semiconductors thinks its a law. Did you read my post? The original post stated that "Didn't we already agree that predictions are only useful to talking heads, pundits and hucksters?".

          My response was that this was in fact a very useful prediction for engineers and scientists actually doing the work.

          So when I said "I don't know about that", it was pretty clear I meant that I didn't agree that predictions are only us

      • Well, Murphy's Law is actually more of a prediction too, a pretty useful one at that.

        Indeed, TFS is simply Murphy's Law applied to Moore's.

    • by jbengt (874751)
      Moore's law is an observation, assumed to be true until observations contradict it, which is exactly what a scientific law is.
      Also, correct me if if I'm wrong, but wasn't Moore's law about the number of transistors in an integrated circuit, rather than the (closely related) size of features?
      • Re:Not a law (Score:4, Insightful)

        by ChrisMaple (607946) on Thursday October 31, 2013 @11:37PM (#45297219)
        Most scientific laws are orders of magnitude more precise than Moore's "law", and are quite stable over time. Moore himself varied the period for doubling from 12 to 24 months over the course of just a few years. That's better than a meteorologist but not as good as an economist, and economic "laws" are mostly poor approximations even on good days.
    • by gman003 (1693318)

      A self-fulfilling prediction. Once it was accurate for a few iterations, it moved from being a prediction to being a target, and engineers at every major foundry have worked to meet or even exceed it.

    • "Moore's Law isn't even a law... it's a prediction."

      A prediction, and an observation... just like any other scientific law.

    • Moore's Law isn't even a law... it's a prediction.

      If you were doing more than thinking in tiresome categories you might have called it a self-fulfilling projection which is pretty much exactly what it became.

      To refine this even more precisely, it's an ex post self-fulfilling projection, where "ex post" modifies "self-fulfilling".

      But wait, there's more! It's a virtuous ex post self-fulfilling projection, where "virtuous" modifies "self-fulfilling projection".

      We're now deep into The Remains of the Day. I m

    • by necro81 (917438)

      Moore's Law isn't even a law... it's a prediction

      No, it's not even a prediction... it's an empirical observation on historical data. It tends to be self-fulfilling, but there's no reason that it must continue to any arbitrary horizon. Using historical trends can be useful tools for predicting the future, except when they're not [xkcd.com].

    • All scientific laws are predictions. Or at least abstractions over prediction. "If you drop a ball from a height h, it will accelerate at 9.8 m/s and have a velocity v."

      If anything, your point supports the validity of treating Moore's law as testable science instead of delineating between science and non-science.

  • by Anonymous Coward

    Anyone who actually works in the semiconductor industry could've told you this. (Ever notice how the GHz stopped growing a while ago? The move to multi-core happened around the same time and even that's stopped growing.) Yes, it's still possible to shrink transistors further but the speed and power reduction gains are diminishing and the costs of further shrinking are moving from merely eye-popping to astronomical.

    Intel can afford to stay ahead of everyone else a bit (this is one of the primary reasons A

    • Clock maxed out. Multicore will take you only so far before you run out of space and hit problems with coherency.

      I expect the future is going to involve a lot more specialised silicon. Scientific number-crunching will move onto GPUs or things like the Phi designed just for that type of workload. Mobile processors will start featuring even more single-task accelerators like those already used for video decoding. While general-purpose processors of today become the things that tie all the other parts together

    • I work quite closely with various parts of the semiconductor industry, but I've not heard anyone say that Moore's law is dead. Transistors are still shrinking, the problem is not that the number of transistors you can stick on an IC is not changing, but that the number you can have powered at once is not dropping much. Each new generation in process technology reduces the size (or, at least, increases yields or reduces costs), but it only has a small impact on the power consumption per transistor. That i
  • all are antiquated.
    • Marketing is all about not getting caught lying.

      Except in the entertainment industry, where lying is also included in the marketing tools.

      And don't call me Shirley.

  • by Anonymous Coward on Thursday October 31, 2013 @06:34PM (#45295227)

    That way, you'd have the option of scrolling back to less dense chip designs.

  • by Nyder (754090) on Thursday October 31, 2013 @06:36PM (#45295247) Journal

    Changing the names to make something sound better has been a strat for decades, if not longer.

    So why is this a surprise that the semiconductors are using it now to sell stuff.

  • These line widths of 22 nm or 28 nm etc are some 50 times narrower than the wavelength of visible light. Making the lines thinner is difficult and it is approaching quanum mechanics limit. Unless people start immersing the entire etching machines in water or some such medium, we cant make the lines thinner.

    Even if we did, there are not enough electrons in these lines to make the "law of large numbers" work. So this time we are bumping against a real barrier.

    Anyway, there are not any mass market killer

    • by crgrace (220738)

      All sub-65nm and most 65nm processes are lithographically exposed in water current for the reason you stated. The next step is extreme UV or even e-beam lithography but it's expensive and very, very difficult.

      You're quite right that this is an economic/mass-market issue more than a pure technical issue.

    • As somebody who works in Lithography, I can let you know that they have not been using visible light for a long time. All fine resolution lithography is designed around as close to a monochromatic light source as possible. Having a significant spread in the light spectrum was just not consistent to do much below the 1.0 um feature size. This is because of the diffraction spread is very dependent on the wavelength and the fact that the photons have different energies thus reacting differently (or not at all)

    • The ultimate limit is the placement of individual atoms. It's already been done, but the process is agonizingly slow.
  • http://electronicdesign.com/digital-ics/tiny-transistors-giant-molecules-moore-s-law-crashes-laws-physics [electronicdesign.com]

    Give this a read.

    Moore's law extrapolations are hitting the limitations of physics.

    As for shrinking transistors?
    Pretty meaningless, silicon hit the limitations of the interconnects a while back.

    Parasitic capacitance has been the brick wall that people can not get past.

    • It seems to me that the next thing to really boost computer performance is optical interconnect.

      With optical interconnect, parasitic capacitance and RC delays are just gone, and associated power consumption radically reduced.

      I know that there are various parties working on optical interconnect and even optical transistor equivalents.

      I don't mean to imply that achieving optical interconnect (or optical transistor equivalents) will be easy, I'm just saying that it has promise to remove many of the current per

      • by TeknoHog (164938)

        I don't mean to imply that achieving optical interconnect (or optical transistor equivalents) will be easy, I'm just saying that it has promise to remove many of the current performance limits.

        I see what you did there.

      • Already been done between boards, for sure. Limitations of copper connections on PCB is at roughly 20GB/s - although there are arguments above or below that, that is what I have been able to get up to with some heroic measures.
        http://en.wikipedia.org/wiki/Titan_(supercomputer) [wikipedia.org]

        Optical connections across boards has been done some but its generally not seriously explored due to the overhead associated with getting in-out of optical medium, people tend to just use copper and put more parallel paths in.

        Optical i

  • by Ukab the Great (87152) on Friday November 01, 2013 @12:45AM (#45297447)

    Battling for the title of who has the smallest one.

  • Moore's law has been superseded by Koomey's law [wikipedia.org]:
    the number of computations per joule of energy dissipated has been doubling approximately every 1.6 years.
    Koomey's law seems to hold well.

Never test for an error condition you don't know how to handle. -- Steinbach

Working...