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

 


Forgot your password?
Close
typodupeerror
×

A Magnetic Memory Alternative to Hard Disk 258

Posted by Hemos from the read-from-the-magnets dept.
Dr Occult writes "Finally, a magnetic memory chip has been manufactured in volume and released by the U.S. company Freescale. Christened MRAM (magnetoresistive random-access memory),this chip will hold information even after power has been switched off. From the BBC news article: 'Unlike flash memory, which also can keep data without power, Mram has faster read and write speeds and does not degrade over time,' and 'MRAM chips could one day be used in PCs to store an operating system, allowing computers to start up faster when switched on.'"
This discussion has been archived. No new comments can be posted.

A Magnetic Memory Alternative to Hard Disk More

A Magnetic Memory Alternative to Hard Disk

Comments Filter:

  • NOT a hard drive alternative (Score:5, Insightful)

    by dsginter ( 104154 ) on Monday July 10, 2006 @08:59AM (#15690745)
    MRAM is *not* a hard drive alternative because it needs to be fabricated with traditional chip lithography. Also, MRAM cells are very large, even compared with flash memory.

    It would be extremely expensive to create an "MRAM hard drive". This is just more pump and dump for Freescale daytraders.
    • Yeah, exactly. Wasn't there a recently release about a 40GB flash module? Obviously flash memory has issues with wearing out after thousands of RW operations but it seems like a more likely candidate for hard drive replacement (especially in laptops) in the near future than this magnetic memory.
      • Do we HAVE to have this discussion, _again_?!

        It simply can't. Period. It _could_, in a limited fashion, work along with a hard drive, but if you have virtual memory requirements of ANY sort, flash memory will be thrashed to unuseable in no time. So you'd need a hard drive still anyways for virtual mem, and then you'd still have everything else stored on memory that WILL degrade over time.

      • Re:NOT a hard drive alternative (Score:5, Interesting)

        by Intron ( 870560 ) on Monday July 10, 2006 @11:04AM (#15691688)
        What wearout? Imagine that you start doing writes continuously spread over a 40GB flash drive for 5-years (typical high-end HD warranty period). How many times will you write to any given sector assume that you have a good load leveling algorithm?

        Assume 15 MB/s write. 40 GB will take about 45 mins. So in 5 years, you will only write each block 175,200 times which is within the 1,000,000 writes spec for flash. And this assumes that you do no reads at all.

        Wearout is a myth with modern flash filesystem software.

    • Re:NOT a hard drive alternative (Score:5, Informative)

      by TransEurope ( 889206 ) <eniac@uni- k o b l e nz.de> on Monday July 10, 2006 @09:07AM (#15690819)
      _Today_ they are larger. But tomorrow Freescale

      plans to shrink their new chips (29nm) under the

      scales of the future standard 6T-SRAMs (still 45nm).

      http://www.heise.de/newsticker/meldung/75243 [heise.de]

    • Re:NOT a hard drive alternative (Score:5, Insightful)

      by rwven ( 663186 ) on Monday July 10, 2006 @09:09AM (#15690831)
      Seeing as everything in this industry gets cheaper, faster, smaller and all around better with time, I wouldn't be surprised in the least if this ends up being a widely used alternative to flash memory. It may take years, but what doesn't... There has been news of this MRAM floating around for about 5 years now (maybe more?)...it's just finally been produced in force.
    • Don't be so cynical - all progress starts with a product like this. Time will see memory capacity become denser, physical space requirements smaller, etc.

      Two years ago 40G flash (hell, my 4G USB drive) would have been laughed at. Progress will continue unabated, so let's let MRAM get its foot in the door, and see where it is in a year or two. RAM sans power requirements is a nice place to be.
      • The technology is indeed in its infancy. I've been hearing about MRAM for about a decade, but I believe this is the first time it has been commercially produced.

        Having said that, FreeScale are currently producing 4Mbit (512KB) modules. Unless your hard drive is incredibly small, I think that it is going to take a long while before this is a viable replacement. For reference, I was using 512KB flash devices over 12 years ago, and Flash is still not quite available in the quantities (per unit cost) requ

        • I'd view the MRAM hard disks as the long term goal.

          Short term, and what I don't see mentioned...non-volatile ram. True instant-on.

          And of course, once the price comes down and the memory size goes up, replacement for flash drives since it doesn't have the limited write capacity.

          Hard disk replacement would be the end goal, but there are a TON of applications between here and there!
        • You seem to be trapped in the current (already outdated?) paradigm of hard drive usage. If I were to put together a high-end machine right now I would certainly throw in at least 2 hard drives. A very small 10RPM drive for the OS, programs, and a much larger (but probably slower) drive for storing all my files.

          If you RTFA you'll notice that that's exactly what they mention: using the MRAM to run the OS. So, yeah, it may not work to replace your entire hard drive, but it makes a lot of sense to split hard drive usage between the files you are going to be booting from, accessing constantly, and files you only access when you have a specific need to.

          Sure, 4MB is still to small to run an OS on (yeah yeah, except linux, and that's great) - but if you're goal is to get large enough to have a bootable OS and NOT to replace an entire hard drive (especially since hard drive capacity is getting cheaper and cheaper) then I think you start to see the potential of this technology.

          -stormin

          • If I were to put together a high-end machine right now I would certainly throw in at least 2 hard drives. A very small 10RPM drive for the OS, programs, and a much larger (but probably slower) drive for storing all my files.
            And you would be making an extraordinarily silly mistake. The OS is loaded from the disk at most once and stored in memory. Data is accessed over and over, giving a *much* better increase in performance if stored on the faster drive.
            • Clarification: I mean the OS and other executables.

              And I just think you're flat out wrong in your assertion. Maybe on a server data is accessed over and over, but for normal desktop use data-access is sporadic. I don't listen to the same mp3s over and over, and I certainly don't watch the same 5 minutes of a DVD on a loop pattern. I suppose if I was doing intensive video editing, I would want that video stored on high-performance drives. Same with any other very intensive read-write activity.

              But for the

      • Re:NOT a hard drive alternative (Score:5, Insightful)

        by morgan_greywolf ( 835522 ) on Monday July 10, 2006 @10:36AM (#15691485) Homepage Journal
        The key isn't even speed, capacity or size ... it's economics. To be a hard drive replacement, it needs to be as cheap as hard drives. Your 4GB USB drive may be 'cheap' in your mind, but if it were as cheap as any current PATA or SATA hard drive, it would have cost $4, not $40-80 ... IOW, your USB drive is at least 10x and as much as 20x more expensive than a hard drive. For MRAM to become a viable replacement for HDDs, it has to become as cheap as HDDs.

        Only time will tell if the economies of scale kick in and make this economically viable.
        • As someone else pointed out, there's a vast difference between HD meant for media file storage and HDs meant for OS and application storage. The latter do not need to be nearly as big as the former, but for them speed is much more critical. If MRAM is as fast as today's DDR2, then it will be several orders of magnitude faster than hard drives. That performance difference (as well as the reliability and power improvements) makes your dollar/gigabyte comparisons completely irrelevant. People who need it (
    • Comment removed based on user account deletion

    • Re:NOT a hard drive alternative (Score:4, Informative)

      by harrkev ( 623093 ) <(moc.liamg) (ta) (noslerrah.nivek)> on Monday July 10, 2006 @10:14AM (#15691318) Homepage
      It would be extremely expensive to create an "MRAM hard drive". This is just more pump and dump for Freescale daytraders.

      Bzzzzt. Wrong. Thank you for playing.

      OK. You are half-right. It would be expensive to crate an "MRAM hard drive." So, getting 20 gigs of MRAM would cost a small fortune. But this is NOT a "pump-n-dump." This is really cool stuff. I can easily imagine some embedded systems that could really use this stuff. This is non-volatile system memory. The problem with FLASH and EEPROM memory is that the cells wear out after a lot of writing (somewhere in the neighborhood of 10,000 to 1,000,000 write cycles will give you trouble). For some applications, this is not enough, so you have to resort to battery-backed SRAM. Now there is at least another option.

      • Do you need to store data without having a constant battery backup?
      • Do you need to store a relatively small amount?
      • Will the data be changing rapidly enough to kill a FLASH in short order?
      • Would a hard drive be too big or too power hungry?
      If you answered "yes" to all those questions, MRAM might be for you:

      Although, really, this seems to solve the exact same problem as Phase-Change RAM [wikipedia.org].

  • Price? (Score:4, Informative)

    by bookemdano63 ( 261600 ) <bookemdano@noSpAm.gmail.com> on Monday July 10, 2006 @09:00AM (#15690755)
    It will be a while before they get their $25 / 4 megabit wholesale price to anywhere close to reasonable.
    http://online.wsj.com/public/article/SB11524917130 4801944-v71_ITCad7JIwzqJZ_nfN_pacDg_20060809.html? mod=tff_main_tff_top [wsj.com]

    • Re:Price? (Score:5, Interesting)

      by cyfer2000 ( 548592 ) on Monday July 10, 2006 @09:22AM (#15690924) Journal
      The major advantage of MRAM is speed. They are extreme high speed nonvolatile RAM, even faster than DRAM. So if you need such a thing, you need to pay for it. Also, the current structure of MRAM is pretty complicated. It is made of multilayers of different metals. Depositing different metals onto silicon wafer is still something nasty though people have been depositing Aluminium and Copper for some time. There are some groups working on magnetic semiconductors, so they use common fabrication method to produce MRAM. So the price of MRAM can drop dramatically if these groups succeed. However, so far, the magnetic semiconductors are even expensive than the multilayer metals structure.

    • Re:Price? (Score:4, Informative)

      by barawn ( 25691 ) on Monday July 10, 2006 @09:40AM (#15691051) Homepage
      That is a reasonable price. Right now, MRAM replaces battery-backed SRAM: like the ZEROPOWER [st.com] series from ST Microelectronics, and a 4-Mbit version (M48Z512A) costs $45 in quantity, and the MRAM chip won't take up huge real estate with a gigantic DIP package.

      At $25 in quantity for a 4-Mbit chip, it's about a factor of 5 higher than conventional SRAM. I'd guess that a factor of 5 in cost reduction isn't crazy to expect.

      Too bad this chip didn't come out say, five to ten years ago - otherwise you likely would've been seeing it in video game cartridges for a while now.

  • Everything old is new again (Score:5, Funny)

    by Billosaur ( 927319 ) * <wgrother@optonline. n e t> on Monday July 10, 2006 @09:03AM (#15690779) Journal
    Mram chips could one day be used in PCs to store an operating system, allowing computers to start up faster when switched on.

    I predict the Commodore 64 will rise again, although this time, it will be 64 Gig!

  • Back to the past.... (Score:2, Insightful)

    by Anonymous Coward
    Sounds a lot like the old core memory that used to be used in big iron...

    • Judging from the photomicrograph on their web site, it's not core. I was suspecting magnetic serial "bubble" memory, which was used in products in the late '80s, but they don't really say what the technology is.

      The old "bubble" memory was sandwiched between two strong permanent magnets to force tiny magnetic fields on the die into tiny "bubbles" that could be manipulated electronically. They were moved along an oval "track" on the die and written/read serially at the "start/finish line". I saw a lab film

      • Bubble memory had huge access times, because you had to wait for the bubbles to come past the read/write device before you could read them. In that respect, it was like a conventional hard drive.

        This seems to be more like a flash memory chip, which gives you random access to all the memory cells on the chip, at least when it is in read mode.

        It's certainly not core memory. That used to get delivered (in one-megabyte quantities) by fork-lift truck.

    • Re:Back to the past.... (Score:5, Informative)

      by WebCowboy ( 196209 ) on Monday July 10, 2006 @10:38AM (#15691490)
      MRAM is in some ways a modern take on 1960's era "Core Memory" technology. There are similarities between both, however core memory was not semiconductor-based--it was a plane of copper wires woven together with little ferrite rings strung on where wires intersected. As such is is pretty low density: 16 Kbit of core memory took up 250 cm^2 of area. With MRAM the method of operation is the same and it also involves reversing polarity of magnetic fields. However there are no ferrite cores; MRAM consists of a sandwich of conductor grids around memory cells. Like with core memory an entire row of a grid can be written to in one operation--you charge one "row" line on the write grid and all the columns you want to flip and they all change at once.

      Reading MRAM is simpler than core memory becasue core memory had no read operation--it had "flip to zero" and "flip to one" and a "sense" line--the sense line would emit a pulse if a core element changed state. To read core memory, you had to do a "flip to zero" and watch the sense line--if it pulsed then a one was in the cell and you had to do a "flip to one" to restore it. If there was no pulse then it was already zero. With MRAM reading simply involves measuring the resistance of the insulating layer of a memory cell (the insulating material has the property where resistance increases as the magnetic field passing through it increases). IIRC there is nothing preventing parallel reads either. MRAMs are also much denser--megabits can fit in 0.25 cm^2

      The "MRAM hard drive" thing may be hyperbole right now, but it looks like development of MRAM rechnology is significantly outpacing Moores Law. MRAM is also potentially as fast as SRAM and as dense as SDRAM--without the need for refresh circuitry so designs can be greatly simplified. Further downsizing could make it a good flash replacement. The biggest hurdle could be reduction...

  • Okay, so next time I'm down at the computer store, I need to buy a better machine.

    Yes, an Apple Quartet Quad Core with four extra Core Seed slots for more Cores later. What color? I hear that Mauve has more RAM.
  • This held its data for years after it was powered off.
    • I remember this!

      A bit big for today's technology tho.

      The Magnetic Core Memory [wikipedia.org] article on Wikipedia states that the technology dates from 1949. I guess that makes this the oldest piece of computer technology that's been "rediscovered".

    • Unfortunately (Score:4, Informative)

      by Flying pig ( 925874 ) on Monday July 10, 2006 @11:02AM (#15691675)
      It lost its data the moment you read it if the read/modify/write circuitry failed. Anyone remember the PDP-8, whose accumulator cleared when you read it, presumably so if it was implemented in core, there would not be a wasted rewrite cycle if you didn't need the accumulator data again? Ah, the fun of early machines...and you could even use them in IBMs, which is more than you can do with a P4.

  • Is bootup time really that big of an issue? (Score:5, Interesting)

    by Skynet ( 37427 ) on Monday July 10, 2006 @09:10AM (#15690843) Homepage
    XP boots in about a minute, and Linux never needs to be rebooted. :)

    What other applications could this have besides boot time?

    • Re:Is bootup time really that big of an issue? (Score:5, Funny)

      by j00r0m4nc3r ( 959816 ) on Monday July 10, 2006 @09:17AM (#15690886)
      Instapr0n(tm)
    • you could probably get your computer to sleep lowering power consumption to very low values and on a single key-press having everything restored almost instantly.
    • It would be interesting to quantify how much wasted time and energy were caused by slow bootups. To me, it makes absolutely no sense that people leave their machines on overnight and perhaps the reason for this is because it then takes 5 mins in the morning for it to start again. I reckon that flash ram in hard drives + versions of Windows / Linux that enable sleep mode (not standby, sleep) by default would save hundreds of millions if not billions of dollars in wasted energy each year.
    • Hibernating in memory without the risk and power consumption of hibernating in memory.
    • What other applications could this have besides boot time?

      This could potentially (once the storage density grows significantly) compete with flash memory as a longer-lasting, more durable alternative. So I think the potential is obvious in that respect: anything flash could do, this could do better--again, presuming the storage densities can be made comparable.

      There's one other potential upside to MRAM: it likely has the same advantages as core memory in high-radiation environments (in other words, radiati

    • Re:Is bootup time really that big of an issue? (Score:4, Interesting)

      by MrNemesis ( 587188 ) on Monday July 10, 2006 @09:55AM (#15691174) Homepage Journal
      Personally, I don't give a rats arse about bootup time.

      What I do want, however, is good rewritable storage with NO MOVING PARTS! It'll make things like under-the-TV HTPC's much, much more feasible - you have a small ~10GB boot drive for the core OS components, and a big ol' hard drive that spends much of it's time spun down. On top of that, you could have almost instant resume from hibernate

      Corporate users would also gain colossal benefits; I know that by far the most common failure I see at work is a dead or dying hard drive, which are a pain to replace in OEM machines which tend to be built so that only people with advanvced degrees it WTF Ergonomics and How To Wire Like A Spider On Drugs can open them. Replace that with a solid state unit with no moving parts and the problem is more or less instantly solved. Heck, depending on its overall reliabilty we might even be able to dump things like RAID in the mid to long term.

      Does anyone have any non-fluff stuff about wha power consumption, max transfer and the like is? Since it's MRAM I expect that it'll only need to use power when reading or writing to disc, right? Hence I'd expect power usage to be practically zero - another huge boon for corporate users. Colossal possible bandwidth and low latency are the icing on the cake.

      Disclaimer: I know little about MRAM other than what I've read in fluff pieces before. Time to visit Wikipedia...

      • Does anyone have any non-fluff stuff about wha power consumption, max transfer and the like is?

        35 ns cycle time for read or write (about 28.57 MHz), read modes 50 ma to 80 ma max, write modes 105 ma to 155 ma max, 9 ma to 12 ma max for stanndby (no pins changing state) and 18 ma to 28 ma with pins flying but no selection enabled for the chip. This is with a 4 mbit chip organized as either 8- or 16-bit. Couldn't find a spec for "the like", you'll have to be more specific. :-)

        Those specs were abstrac

        • Bingo, thanks for rooting that out for me. I do wish the eds would link to stuff like this instead of press releases the whole time...

          10 years data retention with no power = incredible. Three out of four hard drives I've seen refuse to spin up if they're left spun down for more than five years, and consumer grade optical media is just as bad if not worse.

          Anyhoo, glad to see MRAM out of the larval vapourware stage. The wikipedia page makes it sounds damned impressive.
    • Digital camera's. Today the cheap ones are dog slow.
    • Hmmm. How about cutting that boot time to seconds instead of minutes? Plus, it can take longer than a minute depending on how much crap you have installed that needs to be loaded at boot. The trend these days is that consumer electronics is becoming more PC like and more PCs are being more like consumer electronics. So in the future, booting your laptop/tablet/PDA device will take no time.

    • What other applications could this have besides boot time?

      Replacement for battery-backed cache memory in hardware RAID controllers. Nothing worse than having the server go down and then discovering that the battery is dead, so you've got to spend the next eight hours running fsck.

      In general, this stuff would make a great *write* cache for larger-but-slower hard disks in high-end applications. Read caching can be accomplished with regular volatile memory, but volatile write caching is always risky. In consum

  • This won't be replacing harddrives in personal computers for years to come. However, if they can get these things ~6gigs with a far higher reliability rating than harddrives, these would be ideal for corporate use.

    I would kill for these where I work.

  • Old news (Score:5, Informative)

    by dpaton.net ( 199423 ) on Monday July 10, 2006 @09:21AM (#15690911) Homepage Journal
    Freescale's MRAM technology isn't all that new...it's an old Motorola technology that they kept running with when they were spun off. It's taken them a few years to get going again, but it's already been done [spacedaily.com] for a while.

    That said, MRAM ain't a HD replacement yet. No one outside the aerospace industry is using it for storage right now that I'm aware of, and even if someone was, making a large enough FRAM based drive with 4Mb chips is HARD. 2 chips for every MB. 2048 chips for every GB. a 500GB FRAM disk would require 1,024,000 of these chips, requiring nearly 2,500 sqft of PCB space, and more power than a pile of overclocked P4s (~9mA * 3.3V * 1,024,000 chips = 30.4128kW at IDLE). Even if someone could build that, it'd be farking huge, run inconcievably hot, be incredibly power hungry, and sell for an obscenely expensive price, even for the most extr33m gadget hunters.

    Wait for 32 and 64Mb chips. Then we'll talk.

    Right now I'm too busy working with a serial FRAM from Ramtron [rantron.com] to write more.
    • That's good information. Of course, Freescale is now mass-producing the devices, so this really is an advance, commercially speaking.

      Still, you're right that the densities really need to increase dramatically to make this useful in anything but a few niche applications.
      1. Don't know detail of the chips here. But I believe now it is available at large scale. Also, Freescale has made some progress in their MRAM technology, like use magnesium oxide replace aluminium oxide after they left Motorola. So it is very possible that the chips are different.
      2. I believe the MRAM can reach the density of DRAM or even better very soon. Some Japanese companies are working on some interesting technology in this area. So, replacing HD with MRAM is possible at least in the portable electronics
      • I never tried to compare FRAM to MRAM. I'm an embedded guy, so FRAM is just fine for me. A 150nS cycle time might seem slow to the GHz crowd, but for the vast majority of computers on earth (the little ones no one pays attention to in their cars and STBs and phones) it's just fine.

        As for the points:
        1. They changed the process slightly, but that doesn't mean it's brand new news. I like the Freescale guys a lot, but touting it as a worlds first is misleading.
        2. MRAM has had some very impressive scaling report
    • a 500GB FRAM disk would require 1,024,000 of these chips, requiring nearly 2,500 sqft of PCB space, and more power than a pile of overclocked P4s (~9mA * 3.3V * 1,024,000 chips = 30.4128kW at IDLE)

      The size issue you're right on (based on the current chip, even though the cell size is smaller than SRAM, which means that it is higher density) - but the power usage? C'mon. You just build an address decoder and switch power to the chip that you're selecting. MRAM's power usage is basically the same as SRAM.

      But

      • Re:Old news (Score:3, Informative)

        by dpaton.net ( 199423 )
        That would be right on, but I quoted the CMOS sustained idle current. Write current jumps to 155mA, and read current is 80ish as I recall. Keeping the chips alive but idle is the easiest way to design the system. Switching the power to the chips required to store a chunk of data would require knowing the length and width of the memory required, and then knowing what blocks are free, and then powering on the required chips (with a huge current spike and associated noise), and then making the write. Designing
        • Keeping the chips alive but idle is the easiest way to design the system.

          Yes, but if you're proposing a massively gigantic chip array, I think you've already abandoned the "easiest way to design the system" approach, and you'll probably optimize away the need for a kilowatt of idle power. The fact that it maintains power when off means that you can abandon the idle power if you're willing to trade a little bit of speed.

          Note that they don't note the power-on time, though. That'd be nice to know for an instan
        • Switching the power to the chips required to store a chunk of data would require knowing the length and width of the memory required, and then knowing what blocks are free, and then powering on the required chips (with a huge current spike and associated noise), and then making the write.

          My bad, I missed this comment. I think you're misunderstanding how easy this would be: you already need a chip select demux for multiple chips. Add a relay and probably a one-shot to delay the system a bit, and you've got a

  • TV not PC (Score:4, Insightful)

    by ds_job ( 896062 ) on Monday July 10, 2006 @09:23AM (#15690937)
    I don't want this in my PC to boot my O/S quicker. I want this in my TV / Video / STB / whatever so that I can turn them off at night and not have to wait for ages for them to be reinitialised / scan for frequencies / whatever they actually do when they are turned on. It would also make me not have to reprogram my favourites and display settings, which currently do not survive a power cycle. Get these into modern A/V technology and we can finally do away with the necessity of standby just to speed up watching the TV in the morning.

    • Re:TV not PC (Score:2, Insightful)

      by slavik1337 ( 705019 )
      MRAM heating the CRT faster???
    • I find it very strange that your TV does not remember your favorites or display settings after a power cycle.

      1. Is it broken?
      2. Are you using the unit's power button, or cutting power upstream at a power strip or wall switch? It's possible that the TV is designed in such a way to require a trickle of "standby" power to retain those settings.
  • Don't you mean Hard Disk Killer?

  • 512kB chip: $25 (Score:3, Informative)

    by Demon-Xanth ( 100910 ) on Monday July 10, 2006 @09:35AM (#15691026)
    http://www.freescale.com/webapp/sps/site/prod_summ ary.jsp?code=MR2A16A&srch=1 [freescale.com]

    "The MR2A16A is a 4,194,304-bit magnetoresistive random access memory (MRAM) device organized as 262,144 words of 16 bits"

    Not ready for PC time yet.

  • Article misses the point almost completely... (Score:5, Informative)

    by Gadzinka ( 256729 ) <rrw@hell.pl> on Monday July 10, 2006 @09:46AM (#15691100) Journal
    I am not really suprised, that no one bothered to google for MRAM, not even tried to look it up in WP [wikipedia.org]. What's missing in the article and most of the comments is that MRAM is one of those holy grails that most of the industry is chasing, because it promises great returns on investment. Basically MRAM (theoretically) can be:
    • as fast as SRAM (i.e. cache in your processor)
    • as small (i.e. as hight density) as DRAM; single MRAM memory cell is two magnets instead of two conductors of capacitor in DRAM, but the (theoretical) size is of the same order of magnitude
    • non-volatile like Flash, but with random access and orders of magnitude faster, w/o "write penalty" and w/o erase/write cycles limit
    • much less energy-hungry than SRAM, DRAM and Flash while working; when not working it can keep information at least as well as Flash
    It's in development since the eighties and it will take time before we "get there" but it is possible, that one day MRAM could replace cache, main memory and memory cards in our computers.

    When? I have no idea, but AFAIR transistors didn't get from prototype to 65nm in a decade. Hopefully engineergs and managers in some semiconductor companies have longer attention span than an avarage slashdot reader.

    Robert
    • The problem is that MRAM always seems to be 20 years behind SRAM in the cost/mb department. The problem is that these guys are shooting at a moving target, and they're barely keeping up. As a SRAM killer I don't expect to hear much from these guys for awhile, however in specalized roles (especially for stuff that's currrently handled with SRAM and a backup battery) I can see some value in this technology.

  • Still pretty small (Score:3, Informative)

    by wonkavader ( 605434 ) on Monday July 10, 2006 @09:48AM (#15691114)
    Currently, it's 256K x 16-Bit

    Here's the datasheet link: http://www.freescale.com/files/microcontrollers/do c/data_sheet/MR2A16A.pdf [freescale.com]

    • Well, but it could be used as a cache for other permanent storage like flash or a hd. This could have strong improvements in database performance especially in transaction management.

  • Not likely to replace RAM (Score:4, Insightful)

    by tygerstripes ( 832644 ) on Monday July 10, 2006 @09:55AM (#15691175)
    This would be wonderful as a RAM replacement IF it scaled up enough. Trouble is, RAM has been a necessary computer component for years, so it was inevitable that it would get cheaper & smaller as the necessary manufacturing processes were refined.

    This has an awfully long way to come, so it's not going to be adopted wide-scale as a RAM replacement in PCs - at least not straight away. How long would it take the production of this stuff to get up to a competitive scale?

    It might work its way in eventually:

    1. Small MRAM chips used in phones, PDAs, A/V devices to store state, speeding up boot-time.
    2. Pervades handheld-electronics market - becomes ubiquitous enough to scale up and improve manufacturing processes
    3. Eventually finds some server-use to improve operation (maybe mirroring RAM periodically to recover quickly from crash, whatever)
    4. Finally works its way onto desktop motherboards
    (5. Profit?)

    Seriously though, this is hardly going to make waves for some time.
  • It's core memory [wikipedia.org] all over again! But in a smaller package.

    Did you know core memory was hand-made?

    Seriously, I can see some application for this between flash memory and hard drives, but it will take some time to get the costs down.
  • I was alive and mucking about with computers in the 1980s and the "next big thing" was always going to be magnetic bubble memory. That never materialised. The closest thing I remember, apart from endless articles oversimplifying how the "bubbles" "moved along" like an old-fashioned drum memory, was a preview of a portable computer which was going to be built using bubble memory.

    What I'd really like to see is a magnetic memory device using the same remanence phenomena of which Gutmann spoke in his paper
    • I worked on magnetic bubble development before IBM canceled their program. it was a matter of finding a commercial niche.

      Magnetic bubbles did exist and were sold and used in computers. But at the time their was no niche for them like their is flashram. bubbles were faster than disks but more expensive and slower than ram but cheaper. Thus they got caught in a squeeze play. Although they consumed no current when off they were not particularly low power devices so they were not suited for battery powere

  • Slow Bubbles (Score:5, Interesting)

    by Doc Ruby ( 173196 ) on Monday July 10, 2006 @10:04AM (#15691244) Homepage Journal
    I've been hearing about these kinds of devices since "bubble memory [wikipedia.org].

    Why can't I get a motherboard with 500MB Flash for storing an image of system memory exactly after the OS is loaded and initialized, that is blitted over to RAM and then tweaked (system clock, network counters, etc) in a few milliseconds? All the "loading" from storage to RAM includes minutes of computation like a second "compilation" that's practically identical every time I start the machine. How much computing power is wasted on that redundant exercise every day, around the world? I'd like to reinit only when the startup becomes corrupt, which a "known good" ROM instance could avoid better than the current chaotic process.
    • Exactly what I was thinking. I read the posts regarding fast boot times, and the lack for instant on. What some people fail to realize is "Boot to Last State". If we had the ability to dump the state of ram to Flash then back to system ram, like you just pointed out, instant on would take on a whole new meaning. Also, falling back to a standard boot for recovery would be no yeld less data loss if the flashed memory was used like a journal is to a file system.

    • Re:Slow Bubbles (Score:3, Interesting)

      by fdrebin ( 846000 )
      Why can't I get a motherboard with 500MB Flash for storing an image of system memory exactly after the OS is loaded and initialized, that is blitted over to RAM and then tweaked (system clock, network counters, etc) in a few milliseconds? All the "loading" from storage to RAM includes minutes of computation like a second "compilation" that's practically identical every time I start the machine. How much computing power is wasted on that redundant exercise every day, around the world? I'd like to reinit only
  • If data is stored as magnetic bits, wouldn't a very small magnet corrupt all this data? Computer users are warned to keep magnets away from your hard drive due to data loss, but it seems this would magnify (get it?) that problem tenfold.

  • From the CNN writeup on this... (Score:3, Insightful)

    by Experiment 626 ( 698257 ) on Monday July 10, 2006 @10:18AM (#15691348)

    "The first markets for MRAM chips are likely to be in automotive and industrial settings, where durability is critical. Tehrani said they would also be suited for data-logging devices, such as airline black boxes that store data on aircraft performance and must be recoverable after a crash."

    CNN.com article [cnn.com]

    Because we all know that the best way to test out new and unproven technologies is in critical applications where lives are on the line.

  • Great hard drive companion (Score:4, Insightful)

    by egarland ( 120202 ) on Monday July 10, 2006 @10:25AM (#15691409)
    Hard drive controlers could use this type of memory for write caching without risking losing data. This is huge for RAID controlers since they could now lose their bulky batery packs and time limits on cached data integrity. This also has nice implications for write buffering in hard drive controlers since it could be done without the OS even knowing or caring. It would allow for out-of-order writes on drives where the controler decides what gets written first and even if it gets written at all without risking data integrity.

    This is also huge for tiny devices that need very little local storage but do need it. Tiny linux boxes with 64MB MRam hard drives could be quite useful.

    If we make mram visible to filesystems, they could decide to store their core data structures, directories, and inodes in mram space so that access to the start of each file could require only 1 drive seek.
  • Everything old [wikipedia.org] is new [wikipedia.org] again. Thanks to suspend-to-ram/disk [Hibernate for you Windows users] the problem of "corrupted core" is more real than in the days of daily shutdowns. This will only make it worse.

    Without volitile RAM, rebooting a computer will become rare [good] but perceived as a pain in the ass [bad]. Not as bad as reinstalling your OS [very bad] but bad nonetheless.

  • I'd rather see MRAMs used ... (Score:3, Interesting)

    by constantnormal ( 512494 ) on Monday July 10, 2006 @10:42AM (#15691519)
    ... in place of flash memory to provide that speedy boot-up. At least MRAM would not have an upper limit on cycles of use as flash memory does. There's also the possibility that MRAMs could be used in a memory hierarchy in place of power-hungry SRAMs, providing a faster layer of memory than DRAMs for a lot less power consumption. And finally, there is the possibility of re-designing an OS to take advantage of this new form of non-volatile memory, putting most-frequently referenced objects or objects that are essential to running the system in MRAM to take advantage of either the speed or non-volatile aspects of it.

    I think Freescale has produced this because they don't know how to market it, and are willing to listen and see how what marketplace does with a device having these unique characteristics.

    It will, of course, get smaller, cheaper, faster over time. Whether it gets cheaper fast enough to open new markets remains an open question.

  • Comment removed (Score:5, Informative)

    by account_deleted ( 4530225 ) on Monday July 10, 2006 @10:49AM (#15691575)
    Comment removed based on user account deletion
  • to my good ol' vaccum tubes [vacuumtubesinc.com]!
  • IIRC there's a certain minimum size for magnetic domains, a whole lot larger than a typical DRAM well. Seeing as the current magnetic memories are *much* larger than dram cells, and have been under development since way back in the middle of the last century, , one might hazard a guess they're not going to get a lot smaller anytime soon, if ever.

  • Nonsense (Score:3, Interesting)

    by gweihir ( 88907 ) on Monday July 10, 2006 @11:34AM (#15691907)
    Why allways the nonsense applications?

    "Alternative to harddisks"

    "Make the OS load faster"

    This is complete and utter nonsense. It is not a HDD alternative, because it if ar too small. OS loading is dominated by hardware detection and initialisation. A Linux-Kernel, e.g., is less than 2MB in size and is typically loaded in less than a second. This could be brought down further by the BIOS setting UDMA mode.

    I guess this product does not have any real application.

Slashdot Top Deals

Don't compare floating point numbers solely for equality.

Close