Slashdot Mirror

← Back to Stories (view on slashdot.org)

'Approximate Computing' Saves Energy

Posted by Soulskill on from the 1+1=3-for-sufficiently-large-values-of-1 dept.

hessian writes "According to a news release from Purdue University, 'Researchers are developing computers capable of "approximate computing" to perform calculations good enough for certain tasks that don't require perfect accuracy, potentially doubling efficiency and reducing energy consumption. "The need for approximate computing is driven by two factors: a fundamental shift in the nature of computing workloads, and the need for new sources of efficiency," said Anand Raghunathan, a Purdue Professor of Electrical and Computer Engineering, who has been working in the field for about five years. "Computers were first designed to be precise calculators that solved problems where they were expected to produce an exact numerical value. However, the demand for computing today is driven by very different applications. Mobile and embedded devices need to process richer media, and are getting smarter – understanding us, being more context-aware and having more natural user interfaces. ... The nature of these computations is different from the traditional computations where you need a precise answer."' What's interesting here is that this is how our brains work."

27 of 154 comments (clear)

  1. meanwhile... by i+kan+reed · · Score: 3

    The majority of CPU cycles in data centers is going to be looking up and filtering specific records in database(or maybe parsing files if you're into that). They can possibly save energy on a few specific kinds of scientific computing.

    1. Re:meanwhile... by ron_ivi · · Score: 4, Informative

      The majority of CPU cycles in data centers is going to be looking up and filtering specific records in database

      Approximate Computing is especially interesting in databases. One of the coolest projects in this space is Berkeley AMPLab's BlinkDB. Their cannonical example

      SELECT avg(sessionTime) FROM Table WHERE city='San Francisco' ERROR 0.1 CONFIDENCE 95%

      should give you a good idea of how/why it's useful.

      Their bencmarks show that Approximate Computing to 1% error is about 100X faster than Hive on Hadoop.

    2. Re:meanwhile... by lgw · · Score: 5, Funny

      Currently Slashdot is displaying ads for me along with the "disable ads" checkbox checked. Perhaps "approximate computing" is farther along than I imagined!

      --
      Socialism: a lie told by totalitarians and believed by fools.
    3. Re:meanwhile... by ron_ivi · · Score: 4, Informative
      Better - more technical link/paper that explains it in more detail: http://www.cs.berkeley.edu/~sameerag/blinkdb_eurosys13.pdf

      DB: Queries with Bounded Errors and Bounded Response Times on Very Large Data

    4. Re:meanwhile... by formfeed · · Score: 5, Funny

      Currently Slashdot is displaying ads for me along with the "disable ads" checkbox checked. Perhaps "approximate computing" is farther along than I imagined!

      Sorry, that was my fault. I didn't have my ad-block disabled. They must have sent them to you instead.
      Just send them to me and I will look at it.

  2. Analog by Nerdfest · · Score: 5, Interesting

    This is also how analog computers work. They're extremely fast and efficient, but imprecise. It had a bit of traction in the old days, but interest seems to have died off.

    1. Re:Analog by wavedeform · · Score: 2

      This was my immediate reaction, as well. Analog computers do some things extremely well, and faster than could be done digitally. Absolute accuracy may not be possible, but plenty-good-enough accuracy is achievable for a lot of different types of problems. Back in the 1970s I worked for a small company as their chief digital/software guy. The owner of the company was wizard at analog electronics, and instilled in me a solid respect about what can be done with analog computing.

    2. Re:Analog by bobbied · · Score: 3, Informative

      This is also how analog computers work. They're extremely fast and efficient, but imprecise. It had a bit of traction in the old days, but interest seems to have died off.

      Analog is not imprecise. Analog computing can be very precise and very fast for complex transfer functions. The problem with Analog is that it is hard to change the output function easily and it is subject to changes in the derived output caused from things like temperature changes or induced noise. So the issue is not about precision.

      --
      "File to fit, pound to insert, paint to match" - Aircraft Maintenance 101
  3. Accuracy isn't important anymore by EmagGeek · · Score: 4, Insightful

    We're teaching our kids that 2+2 equals whatever they feel it is equal to, as long as they are happy. What do we need with accuracy anymore?

    1. Re:Accuracy isn't important anymore by Anonymous Coward · · Score: 2, Insightful

      Where the hell did you get that from? Oh yeah, its the talking points about the common core approach. Too bad that is nothing like what the common core says. Find a single place where any proponent of the common core said something like that and I'll show you a quote mine where they really said "it is understanding the process that is important, of which the final answer is just a small part because computation errors can be corrected."

    2. Re:Accuracy isn't important anymore by Em+Adespoton · · Score: 2

      3/9 is 0.3* in decimal, which is an infinitely repeating 3. Add 3 of those together, you get an infinitely repeating 9, which, while it approaches 1 using concrete values, is not precisely 1, for the standard definition of 1. However, using approximate computing or general notation, they're the same for all intents and purposes.

      This gets even more interesting when you use a different base such as binary, that doesn't have the same issues with notational conversion as base 10. Base 12 is also useful here.

      In my original comment, I was pointing out that we're already teaching partial answers, and we're also already doing approximate computing. Doing both intentionally though is a different matter altogether.

      Time for a few mathematicians to completely refute what I said; it's mostly a thought experiment after all -- hence the "do we care?"

  4. Numerical computation is pervasive by l2718 · · Score: 4, Informative

    This is not about data centers and databases. This is about scientific computation -- video and audio playback, physics simulation, and the like.

    The idea of doing a computation approximately first, and then refining the results only in the parts where more accuracy is useful is an old idea; one manifestation are multigrid algorithms.

    1. Re:Numerical computation is pervasive by DutchUncle · · Score: 2

      Isn't Newton-Raphson an "approximation"?

    2. Re:Numerical computation is pervasive by raddan · · Score: 5, Interesting

      Not to mention floating-point computation, numerical analysis, anytime algorithms, and classic randomized algorithms like Monte Carlo algorithms. Approximate computing has been around for ages. The typical scenario is to save computation, nowadays expressed in terms of asymptotic complexity ("Big O"). Sometimes (as is the case with floating point), this tradeoff is necessary to make the problem tractable (e.g., numerical integration is much cheaper than symbolic integration).

      The only new idea here is using approximate computing specifically in trading high precision for lower power. The research has less to do with new algorithms and more to do with new applications of classic algorithms.

    3. Re:Numerical computation is pervasive by mrbluze · · Score: 2

      Welcome to half assed computing.

      Which half?

      --
      Do it yourself, because no one else will do it yourself. [beta blockade 10-17 Feb]
    4. Re:Numerical computation is pervasive by indeterminator · · Score: 2

      More significant half, I would expect.

  5. Re:It's a nice thought by K.+S.+Kyosuke · · Score: 3, Funny

    Actually, computers are already capable of computing with arbitrary precision - they're just incapable of computing with infinite precision.

    --
    Ezekiel 23:20
  6. Cue the hoary old Intel Pentium jokes in 3...2...1 by thatseattleguy · · Score: 2
    Q: What do you call a series of FDIV instructions on a Pentium?
    A1: Successive approximations.
    A2: A random number generator

    .

    Hey, folks, I can keep this up all day.
    http://www.netjeff.com/humor/item.cgi?file=PentiumJokes

  7. Been there by frovingslosh · · Score: 4, Funny

    I remember Intel doing something like this back in the days of the 386, except without the energy savings.

    --
    I'm an American. I love this country and the freedoms that we used to have.
    1. Re:Been there by Dogtanian · · Score: 3, Funny

      I remember Intel doing something like this back in the days of the 386, except without the energy savings.

      Actually it was Pentium [wikipedia.org] which was a precursor for these processors.

      Near enough... he was saving mental energy by settling for the approximately correct answer.

      --
      "Slashdot - News and Chat Sites Deviant". (Click "homepage" link above for details).
  8. Fuzzy Logic anyone? by kbdd · · Score: 4, Informative
    Fuzzy logic was also supposed to save energy (in the form of requiring less advanced processors) by replacing computation intensive closed loop systems with table driven approximate logic.

    While the concept was interesting, it did not really catch up. Progress of silicon devices made it simply unnecessary. It ended up being used as a buzz word for a few years and quietly died away.

    I wonder if this is going to follow the same trend.

  9. Re:Finally some better 'Ai' by Diss+Champ · · Score: 3, Funny

    It's just another example of the 'Approximate Spelling' technique. The parent poster is illustrating significant savings in mental energy.

  10. Half-precision by michaelmalak · · Score: 3, Interesting

    GPUs have already introduced half-precision -- 16-bit floats. An earlier 2011 paper by the same author as the one in this Slashdot summary cites a power savings of 60% for a "an approximate computing" adder, which isn't that much better than just going with 16-bit floats. I suppose both could be combined for even greater power savings, but my gut feeling is that I would have expected even more power savings once the severe constraint of exact results is discarded.

  11. Computation is not the big energy drain by Ottibus · · Score: 4, Interesting

    The problem with this approach is that the energy used for computation is a relatively small part of the whole. Much more energy is spent on fetching instructions, decoding instructions, fetching data, predicting branches, managing caches and many other processes. And the addition of approximate arithmetic increases the area and leakage of the processor which increases engergy consumption for all programs.

    Approximate computation is already widely used in media and numerical applications, but it is far from clear that it is a good idea to put approximate arithmetic circuits in a standard processor.

  12. Approximately once a month.. by DigitAl56K · · Score: 2

    .. this story or a slight variant gets reposted to Slashdot in one form or another.

  13. Clive SInclair did this in 1974. by hamster_nz · · Score: 4, Informative

    Due to ROM and cost limitations the original Sinclair Scientific calulator only produced approximate answers, maybe to 3 or four digits.
    This was far more accurate than the answers given by a slide rule....

    For more info have a look at this page Reversing Sinclair's amazing 1974 calculator hack - half the ROM of the HP-35

  14. Re:It's a nice thought by russbutton · · Score: 2

    Slide rule. Good to three places. Good enough to design moon rockets, the SR-71, B-52, the Golden Gate Bridge, Hoover Dam...