Stories
Slash Boxes
Comments

SoylentNews is people

posted by janrinok on Monday June 23 2014, @03:56PM   Printer-friendly
from the faster-and-cooler dept.

California-based semiconductor product company, AMD, has announced goals for very ambitious efficiency gains in its products over the rest of the decade. AMD has already made headway in improving the energy efficiency of its products by more than tenfold during the last six years (2008 to 2014). Now, in a Thursday announcement, AMD revealed the new intent which involves a "25X20" target, namely AMD intends to realize a 25x improvement for their processors over the next six years. "Through APU architectural enhancements and intelligent power efficient techniques, our customers can expect to see us dramatically improve the energy efficiency of our processors during the next several years. Setting a goal to improve the energy efficiency of our processors 25 times by 2020 is a measure of our commitment and confidence in our approach."

APUs refer to Accelerated Processing Units; AMD combines CPU and GPU compute cores and special purpose accelerators such as digital signal processors and video encoders on the same chip in the form of APUs. This innovation from AMD saves energy, said the company, by eliminating connections between discrete chips, reduces computing cycles by treating the CPU and GPU as peers, and enables the seamless shift of computing workloads to the optimal processing component.

This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 1) by Alfred on Monday June 23 2014, @04:11PM

    by Alfred (4006) on Monday June 23 2014, @04:11PM (#59054) Journal

    I hope that AMD has some cool rabbit out of a hat tricks coming. I hope they pull it off and give intel a run for their very large pile of money.

    I cheered for the surface when it was announced but Microsoft let me down and failed. I hope AMD does better.

  • (Score: -1, Flamebait) by Anonymous Coward on Monday June 23 2014, @04:21PM

    by Anonymous Coward on Monday June 23 2014, @04:21PM (#59058)

    We can't make our CPUs faster, so let's concentrate on portability and power consumption.
    Oh yeah, let's kill off desktop computers at the same time and lock people into two year
    consumable devices at the same time.

    • (Score: 1, Funny) by Anonymous Coward on Monday June 23 2014, @04:54PM

      by Anonymous Coward on Monday June 23 2014, @04:54PM (#59071)

      Not to mention JavaScript breakthroughs. Not that I have nothing against blank white web pages...

    • (Score: 3, Interesting) by Anonymous Coward on Monday June 23 2014, @04:59PM

      by Anonymous Coward on Monday June 23 2014, @04:59PM (#59072)

      > We can't make our CPUs faster, so let's concentrate on portability and power consumption.

      Performance per watt [hpcwire.com] has been a driving metric for many years now.

  • (Score: 5, Insightful) by Thexalon on Monday June 23 2014, @04:35PM

    by Thexalon (636) on Monday June 23 2014, @04:35PM (#59066)

    What's hard is not setting a goal, but actually making that goal a reality. For example, take this goal set by John F Kennedy:
    "I believe that this nation should commit itself to achieving the goal, before this decade is out, of landing a man on the moon and returning him safely to the earth."

    Contrast it with this goal set by George W Bush:
    "Our second goal is to develop and test a new spacecraft, the Crew Exploration Vehicle, by 2008, and to conduct the first manned mission no later than 2014."

    One of these goals actually happened (barely). The other does not look like it will. The difference has nothing to do with the feasibility of the goal, and everything to do with the capabilities of NASA and the willingness to put the necessary funds into it in the 1960's versus the 2000's.

    Anyone can say that we'll have flying cars in 15 years, but that doesn't mean you have a flying car. Best of luck to AMD's engineering team, they'll need it.

    --
    The only thing that stops a bad guy with a compiler is a good guy with a compiler.
    • (Score: 2, Informative) by Hairyfeet on Monday June 23 2014, @08:46PM

      by Hairyfeet (75) <bassbeast1968NO@SPAMgmail.com> on Monday June 23 2014, @08:46PM (#59132) Journal

      Well AMD is getting plenty of experience (and money) by being the main chips in 2 out of the 3 major consoles and from the looks of it the Jaguar is a pretty good ULV chip. What worries me is we don't see anything that isn't an APU on the future roadmap from either AMD or Intel. APUs are fine for certain tasks but are pointless for others. I mean what good is an APU gonna do me when I already have a discrete with much faster memory than any APU can access?

      I just hope AMD doesn't forget the ones that kept buying even when they weren't on top, AM3+ chips have been big sellers for AMD this entire time yet we have no replacement for AM3+ on the roadmap, no replacement for the hexacore and octocores on the roadmap (quad core APUs only), it just seems like AMD is ignoring their most loyal customers to court the low mainstream market and there is zero loyalty there as too much of the mainstream market is driven by price alone. Its just not a good place to be and while lowering power usage is commendable lets not forget the first gen Atom chips used practically nothing....and were so slow as to be worthless for pretty much any mainstream tasks. Lower power is only half the equation and if they can't deliver the other half? Well nobody wants another Atom dragging everything down.

      --
      ACs are never seen so don't bother. Always ready to show SJWs for the racists they are.
      • (Score: 2) by tibman on Tuesday June 24 2014, @01:25AM

        by tibman (134) Subscriber Badge on Tuesday June 24 2014, @01:25AM (#59194)

        I buy AMD only but haven't been able to find a new AM3+ microATX mobo. I'd like to put an FX-8350 into a tiny build for work. Looks like a great processor. You're right though that APUs seem to be their focus right now : / Makes for great little gaming machines but most gamers still prefer a discrete card because of ease to upgrade. APUs seem to be for pre-built machines or someone specifically building a very tiny box (media pc).

        --
        SN won't survive on lurkers alone. Write comments.
      • (Score: 3, Interesting) by carguy on Tuesday June 24 2014, @01:53AM

        by carguy (568) Subscriber Badge on Tuesday June 24 2014, @01:53AM (#59208)

        Maybe these new processors will be used in the next generation(s) of cable TV "set top" boxes? I went to my local Time-Warner office a few weeks ago and looked at the ratings printed on the back -- three different basic units were available from 15 watts up to 60w. For something that is left on 24/7 (no standby mode), any of these options are pretty wasteful. By comparison, a recent Samsung TV is less than a watt when on standby.

        • (Score: 0) by Anonymous Coward on Tuesday June 24 2014, @03:39PM

          by Anonymous Coward on Tuesday June 24 2014, @03:39PM (#59454)

          Wait ... you cannot even put those boxes into standby? That alone would be a reason for me not to buy them.

        • (Score: 3, Insightful) by VLM on Tuesday June 24 2014, @05:52PM

          by VLM (445) on Tuesday June 24 2014, @05:52PM (#59503)

          You have to be realistic here, when a watt-year is about a buck, but cable is about $150/month, that means one year of electricity costs about as much as 3 days of service. If you assume a TV is $500 and its value engineered to fail within five years for maximum mfgr profit, that still means you're paying more for wear and tear on the TV than for the electricity.

          The cable plant and headends are not exactly run off unicorn rainbows either, WRT greenwashing.

    • (Score: 3, Interesting) by LoRdTAW on Monday June 23 2014, @09:38PM

      by LoRdTAW (3755) on Monday June 23 2014, @09:38PM (#59149) Journal

      To be fair we were in a pissing match with Russia. So the space race was very important and winning it would prove which country was more technically advanced. They already beat us to satellites and manned orbital flights. We had to one up in a major way.

      We no longer have that superpower boogie man to compete with. But if you ask me I bet a country looking to prove itself would undertake such a mission. And I bet that nation would be China. The west has grown fat and lazy and don't care enough to go to Mars. But I bet China is willing to prove they are a first world economic and technological super power. Though, I really would prefer it be an international effort of all major space players.

      Either way I hope someone goes to Mars in my lifetime. That would be spectacular to see.