Forgot your password?
typodupeerror
Power Hardware Technology

Advance In PCM Memory Could Dramatically Reduce Power Consumption 74

Posted by Soulskill
from the freeing-up-electron-bandwidth dept.
Zothecula writes "Researchers from the Electrical and Computer Engineering Department of the University of Illinois have developed new low-power digital memory which uses much less power and is faster than other solutions currently available. The breakthrough could give future consumer devices like smartphones and laptops a much longer battery life, but might also benefit equipment used in telecommunications, science or by the military."
This discussion has been archived. No new comments can be posted.

Advance In PCM Memory Could Dramatically Reduce Power Consumption

Comments Filter:
  • Sheesh... (Score:2, Informative)

    by ibsteve2u (1184603)
    Five moderator points, and no comments worth reading.
  • by JoshuaZ (1134087) on Tuesday March 15, 2011 @12:49AM (#35488030) Homepage
    Two questions that hopefully more technically knowledgeable people can comment on. First, this system uses nanotubes- as I understand it, there's no good way of making high-quality naontubes in large batches. Is that still accurate? Second, for most devices isn't the CPU consuming a lot more energy than the memory? If that is the case, won't more efficient memory have only a small impact on overall power consumption?
    • by jamesh (87723)

      Second, for most devices isn't the CPU consuming a lot more energy than the memory? If that is the case, won't more efficient memory have only a small impact on overall power consumption?

      In standby mode where the CPU is more or less idle, maybe the amount of power required to keep the memory refreshed is significant in terms of total power use?

      • by GooberToo (74388)

        Remember, most low power designs specifically allow for cores to be shutdown when idle. This allows for substantial power savings. But, despite the CPU drawing very little power, the memory still requires full refresh cycles. This is, in part, why suspend exists as it allows memory contents to be flushed to disk, thusly removing the need to continued memory refresh cycles. Accordingly, if you can reduce the power required for memory refresh, you can greatly extend the "standby" life of many devices.

        • by drinkypoo (153816)

          This is, in part, why suspend exists as it allows memory contents to be flushed to disk,

          ITYM "hibernate", the memory is still refreshed in suspend mode. Some fancy RAM has a low-power mode though.

          • Sleep
            Suspend
            Standby
            Hibernate
            Shutdown

            Power state naming schemes are retarded.

            ON
            OFF (with or without a stored memory dump to resume from)
            All other states are simply power saving schemes per device. Display, video card, hard disk, speakers (girlfriend's new laptop will turn the speakers off after 10 seconds of silence), some of the CPU, more of the CPU, LAN port, USB ports, whatever.

            • by drinkypoo (153816)

              Power state naming schemes are retarded.

              No argument here. At least ACPI has discrete states which actually mean something... or are supposed to.

              ON
              OFF (with or without a stored memory dump to resume from)
              All other states are simply power saving schemes per device.

              I think it is reasonable for the user to distinguish between at least four states. Ideally your computer would only present three.

    • by Anonymous Coward

      Don't know on the nanotube front, but memory consumes more power than you probably think.

      http://www.interfacebus.com/Memory_Module_DDR3_DIMM.html
      A DDR DIMM needs 5.4 watts, a DDR2 DIMM needs 4.4 watts and a DDR2 FB-DIMM needs 10.4 watts. DDR3 provide a 30% reduction in power consumption.

      Of course this is in a standard PC, they use lower power memory in phones etc, but I bet they are still a decent part of the power budget.

    • by c0lo (1497653) on Tuesday March 15, 2011 @01:15AM (#35488140)
      TFA quotes

      uses much less power and is faster than other solutions currently available

      Haven't seen however any info on the speed.

      The researchers say that the low-power memory could even lead to previously elusive three-dimensional stacking of chips.

      This would be good indeed if achieved.
      Speaking of achievements, there's just this snag:

      The group has so far created and tested a few hundred bits

      On top of it:

      The device is also immune to accidental erasure from a passing scanner or magnet.

      This may well be, but... what range of temperatures is supported by the phase-change material? (i.e. what good is the low-power/high-speed memory if it melts when overclocking the CPU?)

      • by Anonymous Coward on Tuesday March 15, 2011 @01:58AM (#35488278)

        uses much less power and is faster than other solutions currently available

        Haven't seen however any info on the speed.

        Unless I'm reading it wrong -- and the wording is a bit ambiguous -- they seem to be claiming speeds higher than other PCM implementations, not DRAM. I would be very surprised if the write speed of phase-change memory could ever exceed that of DRAM, and I say write speed because phase-change devices can be read faster than they can be written.

        PCM is much more likely to be a SSD solution than a replacement for main memory, and even then, it's a long, long way from leaving the lab. All this announcement concerns is a proof-of-concept.

        • by mbessey (304651)

          > I would be very surprised if the write speed of phase-change memory could ever exceed that of DRAM

          You might very well be surprised. Individual memory cell write time is not all there is to write speed. There are addressing delays, amplifier settling time, etc. Depending on the design of the memory cells, some of these effects could be a lot lower for phase change memory.

          Intuitively, shuffling some electrons into and out of a capacitor seems like it would have to be faster than heating up a bit of cryst

    • Two questions that hopefully more technically knowledgeable people can comment on. First, this system uses nanotubes- as I understand it, there's no good way of making high-quality naontubes in large batches. Is that still accurate?

      These [swentnano.com] folks seem to have it worked out.

    • This is the worst /. article *summary* that I've read this week. TFA addresses phase-change materials (PCM)-based memory only. This is the self-same stuff used in writable DVDs, and has some very cool properties. In the above summary, "Faster than other solutions currently available" refers specifically to PCM-based memory. The durability of PCM memory is one big plus -- all those sci-fi plot twists from cosmic ray induced bit-flips in charge-dependent memory? Yeah, not a problem here.

      TFA itself is a
    • by EdIII (1114411)

      I was hoping to have somebody explain to me why the "digital" part is notable. As opposed to analog memory?

      • by drinkypoo (153816)

        DRAM is analog, SRAM is digital. SRAM is faster and no refreshes but it's more power hungry. DRAM has to be refreshed which means you can only read from it at certain times, which makes it slower. DRAM is designed to give digital answers when you ask it questions but it's analog internally (being made out of capacitors) which is why you have to refresh it. If you refresh it incorrectly then the answer will be wrong. Degradation of the silicon will affect correct answers coming out of DRAM before it will aff

    • if you are living in x86 land you may think a cpu needs to suck at least 10 watts and require a fan to do anything useful. embedded computing solved all that ages ago. you have tiny-process SOC with integrated controllers, peripherals, signal processing cores, etc... memory wastes energy. buses waste time. NOC NOC! that desktop you have is computing with some small percentage of its electricity usage, and dissapating heat with the other 99.99% of it. embedded devices can consume portions of a watt. there ar
    • as I understand it, there's no good way of making high-quality naontubes in large batches. Is that still accurate?

      It's a bit more complicated than that. Actually we now have a variety of very good procedures for making high-quality nanotubes in reasonably large quantities. You can buy carbon nanotubes quite easily now. The nanotubes are long, defect-free, and have low concentrations of impurities (e.g. catalyst). And one can make the nanotubes purely single-walled, or purely double-walled, or multi-walled. We have a high level of control. In these senses, you can certainly say that "high quality" tubes are a reality.

  • Noticeably muddier and harsher than DSD memory, though.

  • by Anonymous Coward

    Abstract

    Phase-change materials (PCMs) are promising candidates for nonvolatile data storage and reconfigurable electronics, but high programming currents have presented a challenge to realize low power operation. We controlled PCM bits with single-wall and small-diameter multi-wall carbon nanotubes. This configuration achieves programming currents as low as 0.5 A (SET) and 5 A (RESET), two orders of magnitude lower than state-of-the-art devices. Pulsed measurements enable memory switching with very low ener

  • by ackthpt (218170) on Tuesday March 15, 2011 @01:21AM (#35488162) Homepage Journal

    Were any Rambus people within earshot? Any patent applications suddenly filed by them?

  • How do clear bits? (Score:4, Informative)

    by Michael Woodhams (112247) on Tuesday March 15, 2011 @01:33AM (#35488194) Journal

    TFA explains how to set a bit (from 0 to 1), but not how to clear the bit.

    The actual paper in inaccessible to me (without $$$), even from a university, as it is pre-publication. (I think it will become available on the 17th.)

  • by Animats (122034) on Tuesday March 15, 2011 @02:24AM (#35488338) Homepage

    From the article:

    the solution needs to be upscaled. The group has so far created and tested a few hundred bits

    It's another one of those overhyped materials-science articles. Here's the hype part:

    Pop says that he envisions a point where a device could get its power needs from harvested thermal or mechanical energy or sourced purely from solar. Consumer devices won't be the only beneficiaries, however. "We're not just talking about lightening our pockets or purses," Pop said. "This is also important for anything that has to operate on a battery, such as satellites, telecommunications equipment in remote locations, or any number of scientific and military applications." Server farms or data centers could also benefit from lower energy costs by utilizing the solution. The researchers say that the low-power memory could even lead to previously elusive three-dimensional stacking of chips.

    Really. They've come up with yet another alternative to silicon-based memory devices. There are hundreds of such schemes, from Ovonics to silicon-on-sapphire. Many of them work, but each has something that makes it inferior to the mainstream technologies. Some (like this one, probably, since it's heating-based) have slow write times. Some are expensive to fab. Some won't scale up.

    The problem with the "elusive 3D stacking of chips" is not that it can't be done, but that it doesn't make systems cheaper. In the technologies developed to date, each new layer of devices costs about as much as making a separate part.

    • by dgatwood (11270)

      The problem with the "elusive 3D stacking of chips" is not that it can't be done, but that it doesn't make systems cheaper. In the technologies developed to date, each new layer of devices costs about as much as making a separate part.

      Until you factor in the cost of the board space and being able to fab three motherboards out of one copper-clad sheet instead of two or using one PCB instead of two inside the device. Once you reach that point, reducing the board space by stacking chips becomes a significant

  • by coldmist (154493) on Tuesday March 15, 2011 @03:17AM (#35488600) Homepage

    So, everyone said, if we switch to SSDs, longer battery life. Did it happen? No.

    Memory does not use up that much power, relative to the whole system. Even switching a laptop's screen to LEDs doesn't help that much.

    It's almost the same as the mythical new invention that will be out "in 5 years".

    Give it up people. Semiconductors improve year after year, These kinds of breakthroughs that drastically change everything just don't happen.

    The only thing I can think of that made that kind of a change in the last 30 years was going to an SSD drive for speed and responsiveness. Other than that, each year gets a bit better. Don't expect that to change any time soon.

    • Don't be such a pessimist.
      Together, all of the things you talk about have improved battery life. And turned that luggable portable PC we call a laptop from "useless on the road" into useful.
      We now have netbooks that on average last 5-6h (with an 8-10h battery)
      Quite a difference to the average battery time of older laptops 0.5-1.5h with the same kind of battery.

      LEDs instead of a HV fluorescent tube is natural progress, but why are they charging more for it, when it should be less?

      SSDs will start shining in e

    • by rahvin112 (446269)

      Battery life has been constantly improving. Even 5 years ago those most battery life you could expect on your top of the line low power laptop was 3 hours for the most expensive lightweight laptop available. With all the innovation in low power you can now routinely expect 5-10 hours. That's a 100% improvement in just a few years. Step back even further (before 2000) and the max was about 1.5 hours. Battery life and run times have dramatically improved. I'm simply amazed that my little 10" netbook can do mo

      • by gl4ss (559668)

        are you insane? have you not heard of psion? battery capacities have not improved too dramatically and computers used to need less power.

  • by pablo_max (626328) on Tuesday March 15, 2011 @04:28AM (#35488894)

    I, no doubt like most of you, enjoy reading about advancements in technologies. Especially those which can have a direct impact on computer performance!
    Lately though, it seems to me, that all of these headlines and articles are exactly the same article. Making some claim about a major breakthrough and how this will make my computer 100 times faster and use 100 times less power....maybe...in the future.
    It seems always to the case that in 10 years, "this" will enable us to use a lot less power and have much higher densities and so on and so on.
    Basically, why the techs are interesting, the articles are absolute crap. Sensationalizing everything where there is nothing worth do so about. Why can they not just explain the so-called break though, it's probable applications and realistically how long, if at all, until commercialization?

    • by ledow (319597)

      Which is why I have a rule.

      Unless I can buy it *today*, *this second*, from a supplier that I'm willing to buy from, it's not worth getting excited about except from a purely scientific standpoint (the same as someone claiming to have invented a new type of tile to use on the Space Shuttle - interesting but I will *never* hype the company that sells it, or end up using the product myself). Until it exists, is in a store I can order from, is in a standard format of some kind, and at a sensible price, I can'

  • make that a memristor sandwich and you would have my interest. in fact i've decided not to buy another pc until it features AMOLED and memristor memory. fuck these other "advances", they're just trying to stall the inevitable or grab some of the remaining market time. toshiba just got quaked and everybody's bitching about how memory's going to go up. someone is inevitably going to attempt to capitalize on that, but unless it's the *actual*, new, advance it's not really "advanced". so opt out of planned obso

  • While these folks may have made something 100x faster than something else, it's still useless.

    It's a phase-change -- that means HEAT, which means it takes time for the storage element to heat up, change phase, and then cool down. It's probably better than using punched cards, maybe even better than 1990 flash memory, but not a whole lot better.

    Memory technology today has to work on the nanosecond level-- phase-change is not going to get anywhere near that ballpark.

    You also need storage that

  • Why wouldn't this mythical device be applicable to medical devices? It seems there are a dozen other industries you left off your list, is it not potentially applicable to them either?

  • I was looking forward to new memory that might be more expensive, but has the best of all worlds.
    (simple hardware interface, durability and faster than dram write and read speed, ie. like sram but cheaper and only uses energy while active)
    The embedded world seriously needs new parts that allows designs and software to become simpler, at the expense of hardware cost.

If God is perfect, why did He create discontinuous functions?

Working...