Catch up on stories from the past week (and beyond) at the Slashdot story archive

 


Forgot your password?
Close
typodupeerror
×
Data Storage Science

'Racetrack' Memory Could Replace Hard Drives? 149

Posted by CmdrTaco from the sure-why-not dept.
Galactic_grub writes "An experimental new type of memory that uses nanosecond pulses of electric current to push magnetic regions along a wire could dramatically boost the capacity, speed and reliability of storage devices. Magnetic domains are moved along a wire by pulses of polarized current, and their location is read by fixed sensors arranged along the wire. Previous experiments have been disappointing, but now researchers have found that super-fast pulses of electricity prevent the domains from being obstructed by imperfections in the crystal."
This discussion has been archived. No new comments can be posted.

'Racetrack' Memory Could Replace Hard Drives? More

'Racetrack' Memory Could Replace Hard Drives?

Comments Filter:

  • Sounds like... (Score:2, Interesting)

    by Anonymous Coward
    ...they've updated coil memory.

    • Re: (Score:3, Interesting)

      by AltGrendel ( 175092 )
      I think you mean core memory [wikipedia.org].

      • No, core memory... (Score:5, Interesting)

        by msauve ( 701917 ) on Wednesday May 16, 2007 @07:55AM (#19143825)
        stores 1 bit per "core." The article is about a form of memory which continually cycles multiple bits stored as magnetic regions through a single physical ring. The OP is correct in that this is similar to cycling photons through an optical ring.

        Looking back, this is all very similar to shift register memory, one of the earliest forms of solid state memory.
      • Magnetic domain -- bubble memory -- this is old, as in late 70's early 80's old. I think Intel had a 1MB chip before it was dropped. Clock speed may be different, but pushing magnetic domains along a wire isn't.

    • Re:Sounds like... (Score:4, Informative)

      by Hal_Porter ( 817932 ) on Wednesday May 16, 2007 @07:52AM (#19143795)
      Actually, it's more like Bubble Memory
      http://en.wikipedia.org/wiki/Bubble_memory [wikipedia.org]

      • Re: (Score:2)

        by vadim_t ( 324782 )
        It sounds more like Delay line memory [wikipedia.org] to me.

        • Re: (Score:3, Informative)

          by Intron ( 870560 )
          Bubble memory was like delay-line memory, but retained the data when the power was off. Not clear from the article whether racetrack can be non-volatile, but it needs that to compete with disk.
          • I would hope if it was volitile, that nobdy would be stupid enough to publish an article suggesting it for use by hard drives. Odds are strong that it is non-volitile. This is especially true if the quote from IBM is acurate: "According to IBM, this type of magnetic memory could vastly simplify computers, and eventually replace all hard-disk drives."

            On the other hand, more idiotic things have been done in the past.

      • Re: (Score:2)

        by Gilmoure ( 18428 )
        Bubble mammary, holographic mammary, Where the hell's my flying car? Why are we still using these Victorian mechanical storage devices. Feel like I'm stuck in Difference Engine World. Now, if it was Girl Genius World, that would be something.
        • Bubble mammary, holographic mammary, Where the hell's my flying car? Why are we still using these Victorian mechanical storage devices. Feel like I'm stuck in Difference Engine World. Now, if it was Girl Genius World, that would be something. Not quite sure where mammaries came into the picture.... ...mind you, not like that's a bad thing. I just don't quite know how much storage your average mammary would have, or whether it would be volatile, or how it might replace a 'hard drive'....

    • Re: (Score:2)

      by morie ( 227571 )
      I think you mean "Audio like..."

      What a nice game, this "guess what he means". I wonder how many more replies there (their/they're/there're) will be.
    • It reminded me of Delay Line Memory [wikipedia.org]

      I remember tearing apart a small one as a kid - out of a 100 lb 80 x 25 monochrome CRT. A bunch of wire in a foot square metal box.

    • Re: (Score:2)

      by kjs3 ( 601225 )
      Bubble memory, rope memory, mercury delay lines, etc., etc. Oh, yeah...new and innovative stuff, pushing bits around a medium...

    • Re: (Score:2, Funny)

      by grangerfx ( 998424 )
      I remember taking apart an old CRT terminal decades ago to see how it worked. It contained a sealed flat metal case. When I opened it, I was shocked to discover a simple coil of wire with a precision set screw on the end. The function of the device was obvious. The contents of the display buffer were shunted into the coil where the bits were cycled endlessly. When a new character needed to be added the oldest was dropped off the end.

  • I've seen it in fibre before... (Score:3, Interesting)

    by simm1701 ( 835424 ) on Wednesday May 16, 2007 @07:44AM (#19143717)
    I remember reading some research a couple of years ago that somethign similar was done using 100km of optical fibre and a router programmed to keep sending the same stuff around the loop, or it could read it/write it as it came around.

    In some ways being slower is definitely an advantage, even with 100km at 10Gb/s you don't have much storage when the bits are moving at the speed of light.

    • Re:I've seen it in fibre before... (Score:5, Informative)

      by kaszeta ( 322161 ) <rich@kaszeta.org> on Wednesday May 16, 2007 @07:55AM (#19143829) Homepage
      I remember reading some research a couple of years ago that somethign similar was done using 100km of optical fibre and a router programmed to keep sending the same stuff around the loop, or it could read it/write it as it came around.

      The basic technique is even older than that. Google "Mercury Delay Line" for early examples: they'd make a long thin tube of mercury with transponders at each ender. It was around 5 ft per K, IIRC.

      • Cool :) thanks for that.

        Mod parent up interesting/informative :)

      • Re:I've seen it in fibre before... (Score:5, Interesting)

        by Anonymous Coward on Wednesday May 16, 2007 @08:38AM (#19144343)
        Mercury delay lines were the cause of a bizarre
        computer architecture. The normal form of instructions
        had an "address of next instruction" field.

        After getting the program to "work", i.e get the correct
        answer, the "optimization" stage consisted of working out how
        long each instruction would take, and then positioning the "logically next"
        instruction at the location just about to appear out of the delay line.

        There was no advantage to inner loops that were faster than the
        delay round the mercury loop. Unless you could unroll and fit two
        repetitions into one trip round.

        Of course, all of this was done by hand.

        • Plus one addressing (Score:5, Informative)

          by A nonymous Coward ( 7548 ) * on Wednesday May 16, 2007 @08:53AM (#19144559)
          Generally known as n + 1 addressing, where n was how many operands had addresses in the instruction. Also used with drum memory, which was in the physical shape of a cylinder ion the one drum machine I used, but was mainly a head per track disk, so no seeking required. Some drums had multiple heads per track for some tracks to reduce latency further.

          The optimization was great fun, my favorite part. You could make programs scream if you paid attention.

          • Re:Plus one addressing (Score:4, Funny)

            by Rorschach1 ( 174480 ) on Wednesday May 16, 2007 @10:06AM (#19145593) Homepage
            Mel [pbm.com]? Is that you?

            • Re: (Score:3, Interesting)

              by A nonymous Coward ( 7548 ) *
              I wish! I understand Mel *exactly*. Squeezing the last bit of performance and efficiency is heaven. It is an almost useless skill nowadays, and I don't do it any more on that level, but I sure wish ....

              • Re: (Score:3, Interesting)

                by Rorschach1 ( 174480 )
                I understand completely. My thing is 8-bit MCUs, and there's nothing like the satisfaction of coming up with some elegant, tight construct where not a byte or cycle is wasted. And there's a real economic incentive for that sort of optimization, too - I'm running my code on chips that cost $1.68 each, and doing things that my competitors might use a $6 ARM chip or $20 Java module for.

              • Re: (Score:2)

                by jd ( 1658 )
                Oh, I dunno about that. In this day and age, those kinds of skills are actually quite valuable. If you're looking in the right sectors. Look at the contortions ATLAS has to go through to optimize itself to different architectures and cache sizes. This couldn't be done at all if the maintainer wasn't in the borderlands of genius at hand-optimizing, as the optimized versions don't write themselves. The same is arguably true of compiler optimizations - you can't tell a computer how to do something you don't kn
                • I find the most useful remnant of that skill is simply having a picture in my head of all the contortions it takes to get something done. I literally imagine bits flowing between programs and interrupts triggering other programs when I think of a web page loading. I know of far too many programmers who have no concept of what is involved in doing something and think that one line of code is just as fast (or slow) as another. The best they can do is understand that calls to their own subroutines do invoke
          • >The optimization was great fun, my favorite part. You could make programs scream if you paid attention.

            How can you be so cruel to the poor poor programs? Sadist.

    • Re: (Score:3, Funny)

      by Anonymous Coward
      if I had a dollar for every time they've said "this new XYZ technology could replace hard drives," I could buy a lot of hard drives

      • Re: (Score:3, Insightful)

        by simm1701 ( 835424 )
        Sounds like an idea for a slashdot poll:

        Which is your favorite vapourware "hard disk replacement"? :)

    • Re: (Score:2)

      by Ant P. ( 974313 )
      Straight from google's built-in calculator:
      10 Gbps / c * 100 km = 437.209131 kilobytes

      • Re: (Score:3, Informative)

        by simm1701 ( 835424 )
        Not really...

        10Gbps = 1.25GB/s
        c = 300,000Km/s (2sf)

        Does 100km in 1/3s

        1.25GB/s * 1/3 s = 0.416GB

        I think your answer is off by a factor of 1000 (or maybe 1024) :)
        • "c = 300,000Km/s (2sf)

          Does 100km in 1/3s"

          Nope, 100km takes 1/3 of a millisecond or 3x10^-4 seconds

        • Re: (Score:2)

          by Intron ( 870560 )
          Speed of light depends on the material. Fiber cable is usually about 1.5, so you will get 50% more storage capacity than light in a vacuum.
    • Really? I actually had that idea about 30 years ago.

      It's a good thing I didn't have a lab at my disposal. I was just a lowly undergrad.

  • This sounds.... (Score:3, Informative)

    by Dogtanian ( 588974 ) on Wednesday May 16, 2007 @07:47AM (#19143751) Homepage
    ...vaguely reminiscent of "Bubble Memory" 25 years ago. And everyone was saying *that* was going to replace hard drives too.

    • Re: (Score:2, Informative)

      by MakerPharoah ( 1102947 )
      Yes, reminds me of both bubble and "Twistor" type memories from the 70s (yes this is an actual thing).
    • it also sounds like mercury delay line memory from the 1940's and used in the earliest computers.

      Plus ca change

    • I had *exactly* the same reaction.

      Geez. Every 30 years, or so, everything old is new again. I'm getting tired of this constant repetition in life.

      I mean, I was praying *never* to see bell-bottoms ever again, as long as I lived. Shudder.
      • Ironically, I'm wearing a pair of bell-bottom jeans right now.

        Thankfully, you can't see them. :)

      • Every 30 years, or so, everything old is new again

        And vice versa. The first time I heard about commercially-available SSDs (solid-state disks), they were being used to replace the aging HDs on industrial PDP-11 systems. The SSDs were more reliable than the RK05/RP07s they replaced and used less power, but it just seemed so wrong to have these SOTA[0] drives hooked up to these ancient machines. Nothing against PDP-11s, they're great, but why does a machine with a cycle time measured in milliseconds need a disk with a couple hundred MB/sec of bandwidth?

        • When I was working on the development of DEC's DHU-11 at their Acre Rd., Reading, UK plant, we had this real comedian on staff.

          One day, when the first protoype of the DHU-11 (we're talking wire-wrap here) was to be demoed, he rigged up a little plastic pipe that ran from the backplane of the PDP 11/24 holding the prototype to a place just out of sight of the various higher-up mucky-mucks who were receiving the demo.

          Right after the machine was fired up, he took a big drag on his cigarette and blew into the p
    • lol, bubble WRAP plastic memory would be the shit! Just break the bubbles for all zeros, for each memory update just replace the sheet of bubble wrap and break all the appropriate bubbles again :D

      • lol, bubble WRAP plastic memory would be the shit! Just break the bubbles for all zeros, for each memory update just replace the sheet of bubble wrap and break all the appropriate bubbles again :D

        I don't think that you've thought your clever plan all the way through; is there anyone strong-willed enough to resist popping bubble wrap? Imagine a student getting back to their dorm only to find that their roommate has popped all the bubbles on their final dissertation...

  • Anything (Score:4, Funny)

    by eldavojohn ( 898314 ) * <eldavojohn@gm a i l . com> on Wednesday May 16, 2007 @07:48AM (#19143759) Journal
    Anything would be better than the current way my hard drive works. Spinning discs on a platter?! A thousand moving parts?! What is this, the Stone Age?!

    • Re:Anything (Score:5, Insightful)

      by Silver Sloth ( 770927 ) on Wednesday May 16, 2007 @07:57AM (#19143857)

      Anything would be better than the current way my hard drive works
      You mean a technology that is
      • cheap
      • reliable - OK, hard drive errors do exist but I wish my car, for example, was as reliable
      • standardized - OK, there are a number of standards but not that many
      Yes, in the long term I don't see the hard drive as the best method of data storage but the altenatives have a long way to go before they replace it.

      • Hard disks vs Cars (Score:3, Insightful)

        by giafly ( 926567 )

        ok hard drive errors do exist but I wish my car, for example, was as reliable
        If I drove a car that was as as unreliable as my hard drives, I'd be dead. Three crashes in the last 4 years, all contents lost.

        • Re: (Score:2)

          by ivan256 ( 17499 )
          Something tells me that you have either heat, vibration, or power issues.

          Either that or you're incredibly unlucky.
    • Anything would be better than the current way my hard drive works. Spinning discs on a platter?! A thousand moving parts?! What is this, the Stone Age?!


      Hey, it works and is for the most part reliable. BTW- why does everyone assume that there won't be a need or desire for mechanical systems in the next century? Mechanical engineering and design is far from passe, and will find applications in new fields like space travel in the future.


      -b.

    • Re:Anything (Score:4, Informative)

      by pla ( 258480 ) on Wednesday May 16, 2007 @08:07AM (#19143957) Journal
      Spinning discs on a platter?! A thousand moving parts?! What is this, the Stone Age?!

      I know you meant that as a joke, but...

      You should take a HDD apart some time. Though manufactured to incredibly small tolerances, they only really have two moving parts - the platters, and the head assembly (which despite having a lot of sub-parts, moves as a single unit).

      And aside from them, you don't even have that much else that goes into a HDD - usually two air filters (one for keeping internal air clean, and one that balances external air pressure changes); the body itself (just a big aluminum block with an airtight lid); A magnet assembly for moving the heads; and the electronics on the visible external board. Sometimes you have one more small mechanical bit that doesn't seem to do anything (perhaps it parks the heads for shipping?); And that about covers it.

      • Re: (Score:2, Informative)

        by dotfile ( 536191 )
        That extra little mechanical bit is a head lock - keeps them from flopping around while the drive's powered down.

        • Re: (Score:3, Interesting)

          by Dogtanian ( 588974 )
          That reminds me of something I'd almost forgotten; the first Amstrad PC clones (*) that my Dad had at work required you to run a utility to "manually" park the heads on the hard drive before you powered down. Or maybe I'm remembering it wrong.

          (*) Amstrad is a British company who (amongst other things) sold the first *really* successful PC clones on the UK market.

          • That reminds me of something I'd almost forgotten; the first Amstrad PC clones (*) that my Dad had at work required you to run a utility to "manually" park the heads on the hard drive before you powered down. Or maybe I'm remembering it wrong.

            Every ST-506 interface drive I've ever owned (MFM, RLL, maybe ESDI? I never had any ESDI) required manual parking of the heads. park.com was a required utility back in the DOS days. You only really need to park heads before moving the computer, though.

      • Re: (Score:3, Interesting)

        by dargaud ( 518470 )
        I understand the need for air to keep the head flying off the surface of the platter. What I don't understand is the need to have a hole to exchange the air with the outside. Can't they just fill it with neutral gas at the optimum pressure and seal the damn thing ? I say that because I've used hard drive at high altitude and they FAIL often. I mean, if they can do it with salad, why can't they do it to HDs ?

        • Re:Anything (Score:4, Informative)

          by Nimey ( 114278 ) on Wednesday May 16, 2007 @09:36AM (#19145147) Homepage Journal
          They're not sealed because air pressure is a powerful thing. If you take a laptop with a sealed hd on an airplane, the pressure changes in flight could throw various parts out of true. There'd also be metal fatigue just from normal air-pressure changes due to weather.

          In other words, the guys who've been designing hard drives for the past few decades aren't stupid.

          • Re: (Score:2)

            by dargaud ( 518470 )
            I never said they are stupid, I just didn't know the reason. But I'm still surprised that my plastic watch can withstand 4 bars (~30m depth) when a much easier to harden HD cannot... Why should there be metal fatigue on a static enclosure ?!?

            • Re: (Score:2)

              by Nimey ( 114278 )
              Your watch isn't a precision instrument, while the drive is. The watch's internal works can sustain more damage before the watch's operation is affected. Plus, nobody stores information, important or otherwise, on a watch.
          • Why can't they just throw a silicone diaphragm in there in place of the filter? It would outlast the device and eliminate the pressurization problem without involving exchange with outside air (which I agree is stupid - but then, the last drive I saw without such a feature was a dead conner drive.)

          • Re: (Score:2)

            by HiThere ( 15173 )
            Why should you need to totally seal it? Just have a very small hole blocked by a very tight filter. This would effectively seal the case, while allowing pressure changes to equalize slowly. (Is that what they do? It used to be that air circulation / exchange with the outside was used to cool the drive. And driven by a fan.)

      • Re: (Score:2)

        by suggsjc ( 726146 )

        they only really have two moving parts
        I'm not saying that flash memory is the answer, but it has zero moving parts.
        The last time I checked two is an infinitely larger number than zero.

        So I'm not knocking HDDs as the R&D, and precision engineering involved is noting to scoff at, but I think we can all agree that it isn't the ideal medium for storage.

    • A thousand moving parts?! What is this, the Stone Age?!
      Yes, but when they fail you have some cool magnets to play with!
    • Bah, in my day, the REAL Stone Age, we had to etch hash marks into a nearby rock to save our data. You damn kids and your fancy, rewritable magnetic storage media.

    • Re: (Score:3, Funny)

      by comradeeroid ( 1048432 )
      Anything would be better than the current way my hard drive works. Spinning discs on a platter?! A thousand moving parts?! What is this, the Stone Age?!

      Well, actually it's worse than the stone age. Back then we had "Monoliths" which (apart from glacial shift and other geological "features" - or "bugs" as anyone outside sales management called them) had no moving (of movable even) parts at all.

      When the storage space on a monolith wasn't enough you could expand to a "Circle".
      Still, the space on a full c

      • Re: (Score:2, Funny)

        by BrewedInTexas ( 971325 )
        That was a quick trip to Godwin's.
        • Can we shut up about the Godwins already? Godwin posts have become even more annoying than the Nazi references they referred to.

          Also, anti-Godwin posts are getting pretty tired, too.

    • Re: (Score:2)

      by AlecC ( 512609 )
      Almost as bad as the engine of my car. Lumps of metal hurling themselves up and down hundreds of times a second, accelerating and braking over and over again. Tolerances of a hair thickness running at hundreds of degrees and expecting tom be kept oiled without burning the oil. Fires meing lit ans extinguished ijn millisecond. Camshafts? Valves? Timing chains? All expected to keep in exact step? It'll never work, I tell you. And if it does, it will only run for minutes before something in the whole haywire m
    • William Gibson had made a remark about computers and the hard drive, and he was fascinated to learn that the hard drives had a moving platter. He then likened them to Victorian age record players.

  • Who needs nylon? (Score:3, Funny)

    by Andy_R ( 114137 ) on Wednesday May 16, 2007 @07:59AM (#19143867) Homepage Journal
    I just ping foreign servers a lot
  • "The question is can we fabricate media that are perfect or control the imperfections,"
  • How racetrack-like are we talking about? Does it smell like spilled booze and horse puckey? Can I gamble away the kids' college money on it?

    • Does it smell like spilled booze and horse puckey?
      That's a rather zen-like question: what do the vapours of vapourware smell like if they don't exist?

      Can I gamble away the kids' college money on it?
      I'm sure there will be an overambitious start-up somewhere looking to leverage this, and bring in some gullible venture capitalists, so in that sense your wish may yet be granted.

  • there != their (Score:4, Informative)

    by niceone ( 992278 ) * on Wednesday May 16, 2007 @08:07AM (#19143943) Journal
    their location.

    I will stop now before I make a simple grammatical error myself.

    (yes, I know you're looking, hmm, hmm, must be one here somewhere)

    • Re: (Score:1, Offtopic)

      by Aladrin ( 926209 )
      Ah, too bad. 'their' is plural, so it'd be 'their locations'. It's okay, though, since the original summary had the same problem. To have 'their location' read, they'd all have to be in exactly the same place... And that'd be pointless in this situation. So 'their locations are read'.

      I'm going to completely ignore the lack of a capital letter and period on that last sentence.

      I'm terribly annoyed by the constant inability of people to use the correct word, too, but in the end, none of us are perfect. I

    • Re: (Score:2)

      by Phleg ( 523632 )

      I will stop now before I make a simple grammatical error myself.

      Unless you're really replacing yourself with a simple grammatical error, I think you meant, "I will stop now before I make a simple grammatical error, myself."

  • Sweeeeeeeet! Bubble memory is back.
    • Upside of everything old being new: Lifelong employment will come back.
      Downside of everything old being new: Wham! will come back.

      I'm pretty sure I prefer to live in the future, not the past...
  • Magnetic memory went the way of the dodo a good 35 years ago.

  • The more things change, (Score:3, Informative)

    by gillbates ( 106458 ) on Wednesday May 16, 2007 @08:33AM (#19144275) Homepage Journal

    The more they stay the same.

    For those who don't know, delay line memories [wikipedia.org] have been around for at least 50 years...

    Kind of interesting that they are using an old concept with new technologies.

  • However, there are still problems that need to be overcome before the technique could be used more widely. In particular, small crystal imperfections in the wire impede progress, slowing down some domain walls and stopping others altogether.

    Maybe it's obvious, but wouldn't carbon nanotubes be a prime suspect, here?
  • It's Shigawire! [wikipedia.org]

    This will bring us one step closer to the Dune Universe. I call dibs on the first load of Spice!
  • If you have a million monkeys tatooing a million geeks, you could achieve, ah, roughly 50k letters per second?

    Of course, there is the poo factor....
  • Am I the only one reminded of Acoustic Delay Line Memory [wikipedia.org] by this?
  • "Polarized current?" I simply can't stop laughing.
  • IANAN (neurologist), so if any are here, please answer me this: is this sort of keep-sending-signals-around-in-loops method at all like how human memory works? I've often pondered what sort of physical mechanism human memory operates under, as (AFAICT) there's nothing like a hard disk platter or RAM chip or any other sort of fixed array of bits (or other units of data) in the brain; it's just a bunch of neurons firing.

    If there is such a similarity between this new technology and human memory, that might exp

  • Racetrack? (Score:3, Interesting)

    by PPH ( 736903 ) on Wednesday May 16, 2007 @03:21PM (#19150683)
    Are we talking Gand Prix, Baja 1000 or stock car?

    At least it'll make a crash a lot more fun to watch.

  • Old news (Score:2, Funny)

    by bughouse26 ( 975570 )
    What's scary is the story appeared in the Economist a week and a half before it appeared on slashdot.

Slashdot Top Deals

"Out of register space (ugh)" -- vi

Close