1. Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

Computing Experts Unveil Superefficient ‘Inexact’ Chip

Discussion in 'News' started by btarunr, May 17, 2012.

  1. Vinska

    Vinska

    Joined:
    Jul 23, 2011
    Messages:
    1,540 (0.81/day)
    Thanks Received:
    1,451
    Location:
    Kaunas, Lithuania
    differece:

    flawed CPU
    vs.
    intentionally flawed CPU in a controlled and specific way
     
  2. AphexDreamer

    AphexDreamer

    Joined:
    Jun 17, 2007
    Messages:
    7,319 (2.16/day)
    Thanks Received:
    997
    Location:
    C:\Program Files (x86)\Aphexdreamer\
    Oh and uh, doesn't crash as a result or freak out!
     
  3. Perra

    Joined:
    Feb 9, 2009
    Messages:
    147 (0.05/day)
    Thanks Received:
    22
    Location:
    Örebro, Sweden
    Very cool stuff! Guess it wouldnt work too good in a pacemaker or a nuclear power plant though :p
     
    hellrazor says thanks.
  4. Depth

    Joined:
    Aug 7, 2009
    Messages:
    605 (0.23/day)
    Thanks Received:
    139
    This is reminding me more and more of the Improbability Drive from The Hitchhikers Guide To The Galaxy...

    How does one program and accomodate for 8% failures in the CPU? How does the kernel not self destruct? After 1,000,000 binary strings 80,000 of them will be wrong, how does an OS support that?
     
    sergionography and hellrazor say thanks.
  5. xBruce88x

    xBruce88x

    Joined:
    Oct 29, 2009
    Messages:
    2,517 (1.00/day)
    Thanks Received:
    756
    what happens if it decides it can devide by zero?
     
  6. Maban

    Maban

    Joined:
    Mar 6, 2008
    Messages:
    2,723 (0.87/day)
    Thanks Received:
    1,333
    Location:
    Minnesota
    Perhaps it will find that it's actually possible.
     
  7. Vinska

    Vinska

    Joined:
    Jul 23, 2011
    Messages:
    1,540 (0.81/day)
    Thanks Received:
    1,451
    Location:
    Kaunas, Lithuania
    Looking through OP again, I should say:

    NOT a CPU with x% error rate,
    But a DSP with x% error rate.

    Read: DSPs. ^^^^^
     
    Depth says thanks.
  8. qubit

    qubit Overclocked quantum bit

    Joined:
    Dec 6, 2007
    Messages:
    12,713 (3.95/day)
    Thanks Received:
    6,098
    Location:
    Quantum Well (UK)
    That's just soo cynical. Love it. :laugh:
     
  9. Vinska

    Vinska

    Joined:
    Jul 23, 2011
    Messages:
    1,540 (0.81/day)
    Thanks Received:
    1,451
    Location:
    Kaunas, Lithuania
    Actually, in mathematics, dividing by zero is impossible in most cases. Yet there are special cases where dividing by zero is acceptable. So to say, it is actually possible.
    There, Your joke's been ruined by me. Ain't I'm a stinker?
     
  10. brandonwh64

    brandonwh64 Addicted to Bacon and StarCrunches!!!

    Joined:
    Sep 6, 2009
    Messages:
    19,305 (7.48/day)
    Thanks Received:
    6,761
    Location:
    Chatsworth, GA
    Nice avatar ;)
     
    Crunching for Team TPU
  11. Darkrealms

    Joined:
    Feb 26, 2007
    Messages:
    852 (0.24/day)
    Thanks Received:
    23
    Location:
    USA
    Thanks : )
     
  12. SteveJK

    SteveJK New Member

    Joined:
    Jun 18, 2009
    Messages:
    33 (0.01/day)
    Thanks Received:
    0
    Ia m weriting this so fast i cnat write good, i thing you can understand my english but... wht the heck is that?

    Do you imagine a world with dudes talking/writing like that? Creating CPUs with Inexact chips, for me, it's an involution.
     
  13. Frick

    Frick Fishfaced Nincompoop

    Joined:
    Feb 27, 2006
    Messages:
    13,524 (3.50/day)
    Thanks Received:
    4,416
    As said in the article, it depends entirely on application. Video and voice are perfect examples as they don't have to be perfect.
     
    10 Year Member at TPU
  14. AphexDreamer

    AphexDreamer

    Joined:
    Jun 17, 2007
    Messages:
    7,319 (2.16/day)
    Thanks Received:
    997
    Location:
    C:\Program Files (x86)\Aphexdreamer\
    Yeah when we talk on the phone bits are getting lost, but enough get through we don't even notice this missing bits.

    We aren't computers and that is why we can read this.

    Fi yuo cna raed tihs, yuo hvae a sgtrane mnid too. Cna yuo raed tihs? Olny smoe plepoe can. I cdnuolt blveiee taht I cluod aulclty uesdnatnrd waht I was rdanieg.

    So yes its safe to have computers mess up at half the energy cost and twice the speed. It seems like a good idea in certain applications. Btw anyone with a normal IQ should be able to read that.
     
    Last edited: May 18, 2012
  15. Vinska

    Vinska

    Joined:
    Jul 23, 2011
    Messages:
    1,540 (0.81/day)
    Thanks Received:
    1,451
    Location:
    Kaunas, Lithuania
    Not to mention, most of the data those chips are targeted to be used on, is in one way or another in analog form at least once before even reaching the said chip. In other words: the data it is targeted to gets distorted at least a little before even reaching the chip.
    Inevitably, there is some amount of distortion in such processing, no matter if one uses such a chip, or not. So, there always must be some level of distortion threshold, where it is still "good enough". So, if the total data distortion with such a chip is below such threshold, then why the heck nawt?
     
    robn says thanks.
  16. Jizzler

    Jizzler

    Joined:
    Aug 10, 2007
    Messages:
    3,836 (1.15/day)
    Thanks Received:
    865
    Location:
    Geneva, FL, USA
    If it's good enough, then have at it :D

    However, I've already lived through the early 90's once, don't care relive "modem-friendly media" again (although I do play Winnie the Poo Worhips Satan every now and then... such a classic).
     
  17. brandonwh64

    brandonwh64 Addicted to Bacon and StarCrunches!!!

    Joined:
    Sep 6, 2009
    Messages:
    19,305 (7.48/day)
    Thanks Received:
    6,761
    Location:
    Chatsworth, GA
    You are right frick videos and voice do not have to be perfect


    I am an infantry man too ;)
     
    Crunching for Team TPU
  18. Fourstaff

    Fourstaff Moderator Staff Member

    Joined:
    Nov 29, 2009
    Messages:
    9,333 (3.74/day)
    Thanks Received:
    2,075
    Location:
    Home
    I can almost hear it: "My iPhone 10 has a better video quality than your shitty Samsung Galaxy S9"
     
    hellrazor says thanks.
  19. Vinska

    Vinska

    Joined:
    Jul 23, 2011
    Messages:
    1,540 (0.81/day)
    Thanks Received:
    1,451
    Location:
    Kaunas, Lithuania
    And I can hear myself mumbling: "Why would anyone watch videos on a phone instead of using a computer with a good player, capable of properly decoding bad-ass encodes, on big-ass monitor, is beyond me."
     
  20. hellrazor

    hellrazor

    Joined:
    Feb 18, 2010
    Messages:
    1,667 (0.69/day)
    Thanks Received:
    340
    It's like JPG for computations.
     
    Jizzler says thanks.
  21. Vinska

    Vinska

    Joined:
    Jul 23, 2011
    Messages:
    1,540 (0.81/day)
    Thanks Received:
    1,451
    Location:
    Kaunas, Lithuania
    If You put it that way, now it makes me worry a little.
    Jpeg is a good thing when used correctly. Yet, I see jpeg being painfully misused & abused way too often. So when You compare this to jpeg, I start to think what would be, if this technology gets (mis|ab)used at least as half as jpeg - that makes me shiver.
     
    hellrazor says thanks.
  22. sergionography

    Joined:
    Feb 13, 2012
    Messages:
    311 (0.18/day)
    Thanks Received:
    49
    well i doubt this will be for a general purpose cpu, it could be a feature to enable better performance or so, it makes sense on graphic cards im my opinion but not for cpu calculations or appls



    or for THIS^

    well it might assume 0 is 0.000975 or something, and then its possible, but i think this is more like if a cpu miscalculates something it simply doesnt bother to leave it in the cache queue and return it to be reprocessed and simply just passes it, so you end up with much lower latencies hence better efficiency, so its pretty unpredictable what it will calculate
     
  23. Kreij

    Kreij Senior Monkey Moderator Staff Member

    Joined:
    Feb 6, 2007
    Messages:
    13,881 (3.94/day)
    Thanks Received:
    5,632
    Location:
    Cheeseland (Wisconsin, USA)
    I'm all for it as long as the processors are unlocked.
    Would be fun seeing if you could get that 0.25% error rate up by a factor of 10 or so.
     
  24. FordGT90Concept

    FordGT90Concept "I go fast!1!11!1!"

    Joined:
    Oct 13, 2008
    Messages:
    18,496 (6.36/day)
    Thanks Received:
    7,807
    Location:
    IA, USA
    I don't think this can work in a CPU, it would have to be part of a GPU design. If the CPU so much as hits the wrong memory address, everything crashes and burns. GPU, on the other hand, rarely has to be accurate.
     
    Crunching for Team TPU
  25. Fourstaff

    Fourstaff Moderator Staff Member

    Joined:
    Nov 29, 2009
    Messages:
    9,333 (3.74/day)
    Thanks Received:
    2,075
    Location:
    Home
    That is the whole point of this processor: to hit all as many wrong buttons as they possibly can, without crashing the system.
     

Currently Active Users Viewing This Thread: 1 (0 members and 1 guest)