Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
×
Data Storage Hardware

Inventor of GMR Bids To Shake Up Storage, Again 220

Nrbelex writes "Stuart S. P. Parkin, an I.B.M. research fellow largely unknown outside a small fraternity of physicists, thinks he is poised to bring about a breakthrough that could increase the amount of data stored on a chip or a hard drive by a factor of a hundred. This is the man who pioneered exploiting the giant magnetoresistance effect in the 90s, causing disk storage to jump ahead of the Moore's Law curve. If he proves successful in developing 'racetrack memory,' he will create a universal computer memory, one that can potentially replace DRAM and flash memory chips, and make a 'disk drive on a chip' possible. It could begin to replace flash memory in three to five years, scientists say."
This discussion has been archived. No new comments can be posted.

Inventor of GMR Bids To Shake Up Storage, Again

Comments Filter:
  • Finally... (Score:3, Funny)

    by Anonymous Coward on Tuesday September 11, 2007 @03:25PM (#20560843)
    Enough space for all the porn in the internet... at least for now.
    • by XenoPhage ( 242134 ) on Tuesday September 11, 2007 @03:30PM (#20560919) Homepage

      Enough space for all the porn in the internet... at least for now.
      I disagree.. I don't think the Internet has enough space for porn, it seems to keep spilling over into my browser...
      • I don't think the Internet has enough space for porn, it seems to keep spilling over into my browser...

        Please... don't use the words porn, spill, and browser in the same sentence...

  • by morgan_greywolf ( 835522 ) on Tuesday September 11, 2007 @03:33PM (#20560971) Homepage Journal
    What? All of you? You're all using this man's technology right now. Accusations of this product being vaporware do not account for the man's track record (no pun intended). You should all give this man a little credit, okay?
  • I made the mistake of RTFA, ensuring this wasn't the Frost Pist (tm), but what the article describes sounds like an interesting technology. The medium involves coiled wire on a silicon chip and "sliding" magnetic ones and zeros down "notches" in the wire.
    • The medium involves coiled wire on a silicon chip and "sliding" magnetic ones and zeros down "notches" in the wire.
      From the article's description, it sounds like it isn't "sliding" magnetic data in a metaphorical sense, but actually physically sliding magnets around. This sounds kinda like the nanomechanical computers the hard-code nanotech people (Drexler, etc.) talk about, although I'm not clear if it's quite down to that scale, yet.

      It could be very cool, but I do wonder about the shock resistance of suc
      • Re: (Score:3, Informative)

        by harrkev ( 623093 )

        From the article's description, it sounds like it isn't "sliding" magnetic data in a metaphorical sense, but actually physically sliding magnets around.
        TFA is far from clear on this point. If it IS mechanical, I would have serious doubts about its reliability. If there are no moving parts, then he has just re-invented Bubble Memory [wikipedia.org]
        • Re: (Score:3, Informative)

          This New Scientist article [newscientist.com] from centuries ago is slightly clearer.

          • by MBCook ( 132727 )

            You're right, that is better, but I'm a bit unclear still. This really sounds like a microscopic and magnetic version of delay line [science.uva.nl] memory. Is that really what this is?

            I'm still amazed that delay line memories were ever used in consumer products (like calculators).

        • Yep, it's very similar to bubble memory, only the loops the magnetic domains travel on are now vertical, giving much higher density and speed.
    • It sounds for all the world like some kind of tiny electromagnetic abacus.
    • The medium involves coiled wire on a silicon chip and "sliding" magnetic ones and zeros down "notches" in the wire.

      Yep. It sounds like a nanotech abacus, with one bead on each wire. Relevant quote (for people who haven't R'd TFA):

      His research group is able to slide the tiny magnets along notched nanowires at speeds greater than 100 meters a second. Since the tiny magnetic domains have to travel only submolecular distances, it is possible to read and write magnetic regions with different polarization as quickly as a single nanosecond -- far faster than existing storage technologies.

      One poster mentioned wear problems with nanomachines. I'm fairly sure that well-designed nanotech can work without friction damage. Take DMD displays [wikipedia.org] for example. DLP projector bulbs wear out as normal, but I've never heard of the DMD chips themselves failing.

  • Awesome! (Score:5, Funny)

    by illegibledotorg ( 1123239 ) on Tuesday September 11, 2007 @03:38PM (#20561075)
    If it means my computer gets to look like that thing from TFA [nytimes.com], then I'm SO in!
  • by Per Wigren ( 5315 ) on Tuesday September 11, 2007 @03:43PM (#20561147) Homepage

    allow every consumer to carry data equivalent to a college library on small portable devices
    Now, I'm confused. How many College Libraries are there in a Library of Congress?
    • A better way of measuring vast amounts of storage in manner relevant to the iPod generation would be the "RIAA". The actual value of this unit would continuously increase depending upon the total number of musical tracks in existence at any given point in time. This would allow it to scale nicely with advances in storage technology. For example, "My MP3 player has one RIAA of storage". That's all you would ever need.
  • by snooo53 ( 663796 ) * on Tuesday September 11, 2007 @03:44PM (#20561165) Journal
    When I skimmed TFA, it states that this development will take microelectronics into the 3rd dimension, but doesn't really state how these magnetic loops translate into 3 dimensions... does anyone have a better reference for the technology? Also what kind of heat issues will arise (since packing they will be packing more transistors which presumably means more heat) and how can those be dealt with beyond the current ways of using massive cooling systems and shrinking the wire size?

    The article talks about how great and fast this is going to be, but doesn't go into how one fabricates wire loops on a semiconductor die, or how one would stack them in 3 dimensions
    • by Spy Hunter ( 317220 ) on Tuesday September 11, 2007 @04:24PM (#20561951) Journal
      Here's the concept, with a nice animated gif: http://www.almaden.ibm.com/spinaps/research/sd/?racetrack [ibm.com]

      The genius of the design is that the bits can be moved along the nanowires, allowing tens to hundreds of bits or maybe more to be accessed by only one reader. The readers can be fabricated in an array on a chip, and the wires can be hung from above, storing the data vertically. AFAIK they haven't yet gotten to the point of figuring out fabrication issues for the nanowire parts, like making a vertically oriented array and aligning them to readers. So far they have been working on getting the racetrack part working. That is, they have been working on using an electric current to shift magnetic domains longitudinally along a nanowire, and reading/writing the domains. And actually, the article seems to suggest that they are ignoring the 3-dimensional nanowire fabrication issues for now, and are going to make prototypes with the wires fabricated traditionally, 2-dimensionally, on a chip surface, which may still be competitive with Flash.

      As for heat issues, Hopefully the amount of current necessary will be small and thus the wires themselves will generate little heat. I would imagine that this design would have fewer transistors than, say, a DRAM, since the transistors will not be storing the data themselves. The transistors remain 2-dimensional, only on the chip surface. The wires are the only 3-dimensional part.
  • Whats the point... (Score:5, Insightful)

    by damburger ( 981828 ) on Tuesday September 11, 2007 @03:45PM (#20561197)

    If every 4mb of music you buy have costs $2 [slashdot.org], then your 16 Terrabyte Ipod would cost $4 million to fill up.

    Extra capacity is useless if the cost of data is artificially inflated

    • by merreborn ( 853723 ) on Tuesday September 11, 2007 @04:39PM (#20562207) Journal
      Bah, you can get 30 GB of blu-ray/HD-DVD for $15. It'd only cost $8,200 to fill a 16 TB iPod with full-quality movies at that price.

      As storage grows, so does the bit rate and fidelity of file formats, and the way we use storage itself. I don't know about you, but back in 1994, I had maybe 20 meg of low-bitrate WAV files on my 250 megabyte harddrive. 10 years later, I had 20 gigabytes of MP3 files on my 250 gigabyte harddrive. In another 10 years, I fully expect to have 20 terrabytes of audio/video on my 250 terrabyte drive.
      • And hell, if you hit the HD-DVD bargain bin at wal-mart in 5 years, you could probably load your 16 TB iPod up with B-movies for $2k...
    • Re: (Score:3, Insightful)

      by suv4x4 ( 956391 )
      Extra capacity is useless if the cost of data is artificially inflated

      If your measure of data cost is size, then I have an uncompressed bridge to sell you.
  • In the early 1960's Bell labs was researching bubble memory. By the early 80's, TI or Bell commercialized it but it was too slow and bulky except for limited use, like static telephone messages. Guess shrinking the wires/tube and magnetic domains sped it up quite a bit.
  • Thus again proving (Score:3, Insightful)

    by suv4x4 ( 956391 ) on Tuesday September 11, 2007 @03:57PM (#20561445)
    Even evolution happens in jumps, not gradually.
  • by Nom du Keyboard ( 633989 ) on Tuesday September 11, 2007 @04:03PM (#20561569)

    begin to replace flash memory in three to five years

    Five years! It's always Five Years!

    By 2012 I expect to have, this super memory technology, solar cells with efficiency above 70% for pennies per watt, flying cars, paper thin televisions the size of my wall, fuel cell powered hybrid cars, batteries replaced by power cells that store more power, cost less, are infinitely rechargeable, and charge/discharge like capacitors -- plus several other things from the last few months of Slashdot.

    Also the Mayan calendar will have expired, and the entire West Coast in to the Sierra Nevada mountains will be flooded, so I don't know how useful this all will be to me.

    • It could begin to replace flash memory in three to five years, scientists say
      Who cares what the scientists say? What does accounting, marketing and production say?!?!

      -Rick
      • Who cares what the scientists say? What does accounting, marketing and production say?!?!
        Marketing says 2 and half years if your pre-order.
        Production says 10 years if don't screw up the prototypes again.
        And accounting says in 1 year it won't matter because you're all being laid off.
    • By 2012 I expect to have, this super memory technology, solar cells with efficiency above 70% for pennies per watt, flying cars, paper thin televisions the size of my wall, fuel cell powered hybrid cars, batteries replaced by power cells that store more power, cost less, are infinitely rechargeable, and charge/discharge like capacitors -- plus several other things from the last few months of Slashdot.

      I like your future better than mine, where I am running from grey goo, hiding from flesh-eating robots, all
    • In five years, you will have:

      16 cores
      10GB Ram
      300 GB HVDs, burnable
      5-10 TB disks
      Aforementioned disks will be 90% full or pron
      Carpal tunnel syndrome

      Be happy with that.
  • Storage leaps (Score:5, Interesting)

    by CopaceticOpus ( 965603 ) on Tuesday September 11, 2007 @04:06PM (#20561621)
    Imagine the social implications of the $50 5TB thumb drive...

    "I was over at Jimmy's house yesterday and asked him to put some good stuff on my thumb drive. He gave me HD copies of the top 80 movies released in the past two years, plus 2000 of his favorite albums.

    Meanwhile, a second thumb drive I keep clipped to my belt has been keeping an audio/video recording of the last 17 months of my life, nonstop."
    • by rhakka ( 224319 )
      I think the ramifications and implications of the "I can record my entire life on a wearable device" alone makes for a major revolution. You never have to forget ANYTHING, EVER AGAIN.

      Combined with wireless internet, and you are also a one person, non stop, possible reporter, eye on the scene.

      How far from there to Hive Mind?
      • by nuzak ( 959558 )
        > I think the ramifications and implications of the "I can record my entire life on a wearable device" alone makes for a major revolution.

        You can do that now, for at least several years worth of your life at a time. The rest is a matter of getting the video connection back to wherever you've stashed your archives. Or hell, you could just stream it there directly.

        Thing is, most people don't want to do that, and they don't want you to do so either, at least when they're involved. Revolutions happen when
      • by hoggoth ( 414195 )
        > I think the ramifications and implications of the "I can record my entire life on a wearable device" alone makes for a major revolution. You never have to forget ANYTHING, EVER AGAIN.

        Wonderful. It will take approximately ONE LIFETIME to review the recording.
        Maybe 50% of a lifetime with compression and high speed review.
  • by Badge 17 ( 613974 ) on Tuesday September 11, 2007 @04:10PM (#20561691)
    Read what the article actually says - "Mr. Parkin puttered for two years in a lab in the early 1990s, trying to find a way to commercialize an odd magnetic effect of quantum mechanics he had observed at supercold temperatures." Though he may have been absolutely critical to making GMR hard drives (I don't know the history) credit for discovery of GMR goes to Peter Grunberg and Albert Fert [wikipedia.org]. You might be able to call Parkin the inventor of GMR hard drives, though.
  • by www.sorehands.com ( 142825 ) on Tuesday September 11, 2007 @04:20PM (#20561865) Homepage
    Now comes the MPAA and RIAA asking for damages and injunctive relief.

    This speed and storage capacity and can only be used for downloading and pirating illegal copies of movies and music.

    Therefore this must not be permitted to happen.

  • At Long Last! (Score:5, Insightful)

    by BlackGriffen ( 521856 ) on Tuesday September 11, 2007 @04:24PM (#20561949)
    They have finally perfected the abacus!

    FTFA:
    "His idea is to stand billions of ultrafine wire loops around the edge of a silicon chip -- hence the name racetrack -- and use electric current to slide infinitesimally small magnets up and down along each of the wires to be read and written as digital ones and zeros.

    His research group is able to slide the tiny magnets along notched nanowires at speeds greater than 100 meters a second. Since the tiny magnetic domains have to travel only submolecular distances, it is possible to read and write magnetic regions with different polarization as quickly as a single nanosecond -- far faster than existing storage technologies."

    What is really really old is new again, eh?

    I can see it now - to erase your iPod, turn it on its side and shake - just like an Etch-a-Sketch!
    • by Splab ( 574204 )

      I can see it now - to erase your iPod, turn it on its side and shake - just like an Etch-a-Sketch!


      Thats just great, so every time I go running (It could happen!!!) I'm going to erase my iPod?
  • Quite old. (Score:2, Informative)

    New Scientist [newscientist.com] covered this a lifetime ago.

  • by 3ryon ( 415000 ) on Tuesday September 11, 2007 @04:48PM (#20562349)
    This is the man who pioneered exploiting the giant magnetoresistance effect in the 90s, causing disk storage to jump ahead of the Moore's Law curve.

    I didn't realize that the amount of data stored on a disk was related to the number of transistors on an integrated circuit. This sentence doesn't even make sense if you misinterpret Moore's law the way it's usually misinterpreted...doubling of speed of CPUs.

    Moore's Law [wikipedia.org]
  • by sehlat ( 180760 ) on Tuesday September 11, 2007 @04:53PM (#20562449)
    I have a truly marvelous proof of this proposition which this 50TB hard drive is too small to contain.
  • Damn, I wish I were smart enough to invent my own effects in the realm of physics... It sure woulda made physics classes a lot more fun and easy!
  • by greywire ( 78262 ) on Tuesday September 11, 2007 @05:59PM (#20563335) Homepage
    What makes this, and some other potential memory technologies, so interesting is that it would have the mass storage and non volatility of harddrives, the solid state of flash, and the speed of DRAM, or even exceeding that of current techs.

    This is interesting not because its "more, better, faster" but because it can completely change the way computers work. Imagine simply not needing all the storage tiers we currently have... disks, harddrive, flash, DRAM, cache... imagine something big enough and fast enough to cover it all. A CPU and this memory, and nothing else. It could mean big changes to your operating system. Imagine just not needing to load and save things anymore. Imagine not needing elaborate schemes like virtual memory paging, harddrive caching, file systems, or even needing to compress things as often. There's all kinds of overhead and mechanisms in our OS's that are currently needed to deal with all the different storage hardware and their limitations.

    If this memory can work fast enough, it could even change the way CPU's are designed. It could change almost everything.
    • Now you're thinking!
    • Re: (Score:3, Interesting)

      by Just Some Guy ( 3352 )

      Imagine not needing elaborate schemes like virtual memory paging, harddrive caching, file systems, or even needing to compress things as often.

      Virtual memory is A Good Thing (tm), and once you have a working VM system, paging can be a relatively easy add-on. Stripping out paging but keeping VM won't be all that much simpler, I don't think.

      HD caching, I'll give you.

      File systems? You'll still need to find all that data and mete out access to it. Since I don't know what latencies would be like in this storage, it's possible that current filesystems that are optimized for high latency and high throughput might still be reasonable.

      Finally, a

    • Re: (Score:3, Insightful)

      by the_ed_dawg ( 596318 )

      Imagine not needing elaborate schemes like virtual memory paging

      The ability to use a full 4GB virtual address space (i386) is only one of the major features of virtual memory. An equally important goal of virtual memory is process isolation. That is, the illusion that a process has exclusive access to the full memory. Prior to virtual memory, programs had to know what other programs were running and stay out of their physical address spaces. Virtual memory drastically simplifies the lives of million

MS-DOS must die!

Working...