Slashdot Mirror


A Magnetic Memory Alternative to Hard Disk

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.'"

258 comments

  1. Freescale's PR by austinpoet · · Score: 5, Informative
    1. Re:Freescale's PR by Phreakiture · · Score: 5, Insightful

      I believe that this is an example of coming full circle

      --
      www.wavefront-av.com
    2. Re:Freescale's PR by arivanov · · Score: 1

      Indeed.

      I have seen the damn things only switched off.

      I have had to help with a wheelbarrow when chucking one or two into a skip and it was pretty damn hard work. They were from the days when nearly all computing equipment was built to last through WW3.

      I can think of very few people around me who have seen one actually in use.

      Anyway, what goes around, comes around. Full circle.

      --
      Baker's Law: Misery no longer loves company. Nowadays it insists on it
      http://www.sigsegv.cx/
    3. Re:Freescale's PR by Anonymous Coward · · Score: 0

      They forgot to tell you that when Windows gives you a Blue Screen of Death, and you turn off the computer and reboot it,
      you start right off with a Blue Screen of Death....

    4. Re:Freescale's PR by face411 · · Score: 1

      that's just what i was thinking.

      --
      # face411 # # writing the bash script to suck your soul #
    5. Re:Freescale's PR by face411 · · Score: 1

      oh, it's cool... just make your own degaussing coil to fix that. ;]

      --
      # face411 # # writing the bash script to suck your soul #
  2. NOT a hard drive alternative by dsginter · · Score: 5, Insightful

    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.

    --
    More
    1. Re:NOT a hard drive alternative by lawaetf1 · · Score: 1

      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.

      --
      CommentBot 0.7a running with args "-module irritate,disagree -target random"
    2. Re:NOT a hard drive alternative by TransEurope · · Score: 5, Informative

      _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

    3. Re:NOT a hard drive alternative by rwven · · Score: 4, Insightful

      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.

    4. Re:NOT a hard drive alternative by IAmTheDave · · Score: 4, Insightful

      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.

      --
      Excuse my speling.
      Making The Bar Project
    5. Re:NOT a hard drive alternative by edrobinson · · Score: 1

      The article did not imply that this was a hard disk. It only said that the MRAM stores data magnetically LIKE a hard drive does...

    6. Re:NOT a hard drive alternative by TheRaven64 · · Score: 1
      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) required for hard drive replacement. If this technology matures at the same rate, then look for MRAM 'hard disks' around 2020...

      --
      I am TheRaven on Soylent News
    7. Re:NOT a hard drive alternative by GeckoX · · Score: 1

      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!

      --
      No Comment.
    8. Re:NOT a hard drive alternative by GeckoX · · Score: 1

      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.

      --
      No Comment.
    9. Re:NOT a hard drive alternative by andrewman327 · · Score: 1

      I would like to think that any implementation of this technology would increase the battery life of my laptop and make things a little bit faster.

      --
      Information wants a fueled airplane waiting at the hangar and no one gets hurt.
    10. Re:NOT a hard drive alternative by jcr · · Score: 1

      It would be extremely expensive to create an "MRAM hard drive".

      This year, yes. However, there's no particular obstacle to MRAM following the same historical trends as other semiconductor devices. One of these years, we'll have computers that don't need moving parts in their bulk storage systems.

      -jcr

      --
      The only title of honor that a tyrant can grant is "Enemy of the State."
    11. Re:NOT a hard drive alternative by harrkev · · Score: 3, Informative
      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.
      --
      "-1 Troll" is the apparently the same as "-1 I disagree with you."
    12. Re:NOT a hard drive alternative by Anonymous Coward · · Score: 0

      MRAM doesn't need to be a hard drive alternative; that wasn't even suggested in the summary. It only needs to make *boot-up* near instantaneous, holding enough (10 gigs?) to get the luser to login prompt and then desktop.

      Loved the start-up speed of C=64 back then...

      However, today's power-saving tech makes it just as good to freeze your machine (compared to turning it off competely) so I'm not sure who will miss "instantaneouds boot-up" -- you'll need to boot-up more seldom. Supposing the driver model of Vista works...

    13. Re:NOT a hard drive alternative by morgan_greywolf · · Score: 5, Insightful

      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.

    14. Re:NOT a hard drive alternative by drinkypoo · · Score: 2, Informative
      MRAM doesn't need to be a hard drive alternative; that wasn't even suggested in the summary. It only needs to make *boot-up* near instantaneous, holding enough (10 gigs?) to get the luser to login prompt and then desktop.

      The fact that you would claim this gig crap proves that you don't have any idea of the issues involved here. Are you a troll, or just posting as AC so that no one calls you on your shit?

      If you just replace your main memory with MRAM, then you can hibernate without writing out the contents of memory to disk. Think of it as a suspend-to-ram mode on steroids. Because the memory is not cleared, you can just restore processor state, pick up from where you were, reinitialize drivers, and move on with life. Just like coming back from hibernation mode.

      This technology also opens up the possibility to use hard power switches on more systems, or low-power electronically switched relays. You don't need to maintain power to the device and run the power supply just so you can keep one memory chip going to retain settings.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    15. Re:NOT a hard drive alternative by theStorminMormon · · Score: 4, Insightful

      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

      --
      The Southern Baptist Convention has creationism. On Slashdot, we have porn.
    16. Re:NOT a hard drive alternative by Intron · · Score: 4, Interesting

      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.

      --
      Intron: the portion of DNA which expresses nothing useful.
    17. Re:NOT a hard drive alternative by JimDaGeek · · Score: 1
      Sure, 4MB is still to small to run an OS on
      Actually, the article said "four-megabit Mram chips". 4 Mbits is a lot smaller than 4 MB. 4 Mbits is 4,000,000 bits. There are 8 bits in a byte. 4,000,000 / 8 = 500,000 bytes. So these chips are just about 512 KB. Yup, that is _very_ small :-). Not even one picture from my digital camera would fit on this chip!
      --
      General, you are listening to a machine! Do the world a favor and don't act like one.
    18. Re:NOT a hard drive alternative by PFI_Optix · · Score: 1

      Or you could just not use virtual memory.

      Maybe someone could explain to my why virtual memory is necessary; I have seen plenty of systems work without it without any significant performance degradation.

      --
      120 characters for a sig? That's bloody useless.
    19. Re:NOT a hard drive alternative by heson · · Score: 1

      I'd rather have a "DRAM hard drive". A PCIe card with a memory controller, some dimm slots, enough battery to keep it running for some week and a device driver making it look like a harddrive. Maybe they already exists.

    20. Re:NOT a hard drive alternative by Psiren · · Score: 1

      If it were a straight swap of disk for MRAM, then yes. But MRAM offers considerably more speed, so people will be willing to pay far more for the equivalent disk space, if their situation will benefit from it. It will start off slow, but the price could drop enventually to a point where MRAM becomes a high-end alternative to disks. Then it's only a matter of time...

    21. Re:NOT a hard drive alternative by orielbean · · Score: 2, Interesting

      When you mean cheap, do you also indicate fail rates, read-write rates, costs of keeping HDD powered up and ready to go? Those are all cost factors too, not just retail price. I have no idea on the data btw. the two types, but certainly there are a few factors here as they are not exactly the same thing. They serve the same function of storage, but differently.

    22. Re:NOT a hard drive alternative by Anonymous Coward · · Score: 1, Informative

      "somewhere in the neighborhood of 10,000 to 1,000,000 write cycles will give you trouble"

      Industrial Compact Flash is >2,000,000 read/write cycles. And some advertise 3,000,000 cycles. http://www.psism.com/industrialcf.htm#industrialCF

    23. Re:NOT a hard drive alternative by tomstdenis · · Score: 1

      If you look closely you'll see the area of the "industrial" part is larger. Likely they use some form of RAID combined with the cream of the crop process output.

      mmmm cream...

      Tom

      --
      Someday, I'll have a real sig.
    24. Re:NOT a hard drive alternative by foreverdisillusioned · · Score: 2, Interesting

      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 (businesses) WILL buy it, and that in turn will drive down the cost to the point that hobbyists and gamers will buy it (though likely just as an OS and maybe application disk--not for media file storage.)

    25. Re:NOT a hard drive alternative by Valdrax · · Score: 1

      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.

      Personally, I'd only do this for a SFF machine. Otherwise, I'd put a minimum of three drives in a single RAID 5 configuration now that RAID 5 is a relatively common motherboard feature.

      Your Mileage May Vary.

      --
      If it's for-profit but free, you're not the customer -- you're the product (e.g., the Slashdot Beta's "audience").
    26. Re:NOT a hard drive alternative by ATinyMouse · · Score: 1

      I've been in the market for a USB key for a while, but I keep delaying a purchase due to my fear of wearouts. Your comment is the first one I've run across saying it doesn't really exist. Now I have to ask, how do you know that a flash device implements a "good load leveling algorithm?" Do they list something on the the package? Can you verify they actually have something in place even if they do? I know modern HDD's can route around bad sectors, which can then later be discovered through software. Does it work the same way on these keys? As it is right now I have a 32MB key I got from a friend and I never remove anything from it until I fill it up, then I wipe once and start filling it up again. That way at least I know the data is being spread out across the complete space of the device.

    27. Re:NOT a hard drive alternative by Millenniumman · · Score: 1

      I don't understand the need for faster boot-ups. I only shut down my computer once every few months (for updates) and boot-up only takes 30 seconds or so. Who is in that much of a hurry?

      --
      Stupidity is like nuclear power, it can be used for good or evil. And you don't want to get any on you.
    28. Re:NOT a hard drive alternative by Nutria · · Score: 1
      A very small 10RPM drive for the OS, programs, and a much larger (but probably slower) drive for storing all my files.

      That does not sound very smart.

      Maybe my thinking is clouded by experience with databases, but data should be on the fastest drives, since you need it quickly, but program load is infrequent, so if it's on a slow disk, no big deal.

      --
      "I don't know, therefore Aliens" Wafflebox1
    29. Re:NOT a hard drive alternative by Nutria · · Score: 1
      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 (businesses) WILL buy it

      But h/w manufactures already use (lots of) DRAM as cache to speed up disk access.

      (I'm thinking here big NAS/SAN cache, not OS-managed cache.)

      --
      "I don't know, therefore Aliens" Wafflebox1
    30. Re:NOT a hard drive alternative by sketerpot · · Score: 1

      Indeed, IIRC Freescale is developing some microcontrollers with Flash and MRAM onboard. One nice thing about this is that Flash writes can take a while, due to the way Flash memory is laid out on the chip, but MRAM should be quite a bit faster.

    31. Re:NOT a hard drive alternative by owlstead · · Score: 1

      True, but economics also values things like speed, reliability, power consumption, access times, heat dissipation, noise (etc). This translates into : No more HDD related calls to helpdesk, no more waiting on programs, the list goes on. If this gets anywhere near 8 GB / $500 for a unit, I would consider buying it for a PC if only to speed up compile time (together with many others I presume). Currently it is at 10 MB / $300 unfortunately. If does not have to go even near 250GB for under 100$ though.

      For now, it is great technology for embedded devices that need to store things in persistent memory at great speeds. And I can imagine quite a few of them, lets hope that is enough to give this memory a boost, so it can compete with the other storage technologies out there.

    32. Re:NOT a hard drive alternative by Phleg · · Score: 2, Interesting

      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.
      --
      No comment.
    33. Re:NOT a hard drive alternative by theStorminMormon · · Score: 1

      Yes, your thinking is clouded by experience. I'm not talking a multi-user server, I'm talking a single-user machine. The data - in this case videos, mp3s, documents - will be accessed on an as-needed basis. At most you may possibly be streaming mp3s somewhere else on a home network while watching a vid on the machine or something (and really, if you're building a media-center type repository there's a whole host of other considerations to take into account as well). I'm mostly talking about the traditional single-user gaming/entertainment/productivity/coding/whatever rig. In this caes it is the OS that is going to be accessed every time you start your computer, while out of the 500 GB of media/data you have only very small portions will be accessed sporadically.

      It's just a very different usage pattern.

      -stormin

      --
      The Southern Baptist Convention has creationism. On Slashdot, we have porn.
    34. Re:NOT a hard drive alternative by Millenniumman · · Score: 1

      Only a wimp needs more than 128KB. GUIs, multiple shells, color, compilers, intarwebs, blah. All one needs is a good shell (Not like these newfangled 1MB contraptions) and a text editor (With two functions, type and save). Programming should be done in binary or not at all. Photo/video/audio editing should be done in hexadecimal. Networking should be done with tape drives and the USPS.

      --
      Stupidity is like nuclear power, it can be used for good or evil. And you don't want to get any on you.
    35. Re:NOT a hard drive alternative by swelke · · Score: 1

      Wearout is a myth with modern flash filesystem software.

      True. Now do me a favor: name an operating system that actually uses a flash-optimized filesystem. Windows doesn't. Linux (most distros) don't use it by default. I dunno if OSX does, but I'd doubt it. (They'd get compatibility issues if they did.) Most of the time flash drives just use FAT32.

      I'm not contradicting you about the flash wearout, however. I've never seen a flash drive wear out, or even heard of it happening with ordinary use (ie not somebody using a flash stick as the working drive or something silly like that). Just don't claim it's the filesystem.

      --
      Have you ever wondered How to Take Over
    36. Re:NOT a hard drive alternative by theStorminMormon · · Score: 2, Interesting

      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 vast majority of desktop users the repeat data access is going to come from the Warcraft III .exe, not from any one section of their vast data collection.

      -stormin

      --
      The Southern Baptist Convention has creationism. On Slashdot, we have porn.
    37. Re:NOT a hard drive alternative by aardvarkjoe · · Score: 1
      Maybe someone could explain to my why virtual memory is necessary...

      It's not. It's just cheaper to set aside a couple gigs of hard drive space rather than getting that much extra RAM.

      And in any case, there are flash-only systems available today. For instance, I think that the $100 laptops don't have hard drives. The original poster is probably right that flash memory will not replace hard drives generally, but in some circumstances it works fine.

      --

      How can we continue to believe in a just universe and freedom to eat crackers if we have no ale?
    38. Re:NOT a hard drive alternative by julesh · · Score: 1

      On a desktop machine, program load time and swap space access speed are much more important than data access. Almost all desktop applications perform relatively little data I/O compared to that involved in loading & executing them. The only exception is probably video capture/editing, which needs a fast disk if you're trying to do real time high definition capture with lossless compression for example.

    39. Re:NOT a hard drive alternative by Sparr0 · · Score: 1

      poor programming. for some reason a machine with 1GB of RAM and no swap space will die while a machine with 512MB of RAM and 512MB of swap space continues to work (slowly) just fine.

    40. Re:NOT a hard drive alternative by lostguru · · Score: 2, Interesting

      Most modern os's wouldn't fit in memory, and if they did you would run out of ram very quickly and be forced to flog your hd for swap

      sure a chopped down linux distro may run in ram but no way in hell that vista will, or xp & 2k for that matter

      what you will want to do is load your data into ram when you access a file

      for a PC (and i mean personal comp. macs, linux, and typewriters included) this makes the most sense

      --
      Jayne: "These are stone killers, little man. They ain't cuddly like me."
      98% of America's teens drink alcohol, smok
    41. Re:NOT a hard drive alternative by kurtdg · · Score: 1

      Unless you're using Windows, enough DRAM (combined with enough compiler threads) gives you about the same compilation speedup as a hypothetical ultra-fast HDD could give you. That is because the OS can reschedule writes ad libitum. Unlike ACID databases, compilations do not need to issue fsyncs at all.

    42. Re:NOT a hard drive alternative by Skinny+Rav · · Score: 1
      For MRAM to become a viable replacement for HDDs, it has to become as cheap as HDDs.


      To become a viable replacement - yes. To become a viable addition - not quite. In fact with quite cheap 4GB flashroms I am surprised that this has not taken off yet - all software installed on flashrom with user files saved to HDD - no problem (or not much of a problem) with number of writes and all the benefit of fast boot times.

      On the machine I am writing it on, I have fairly complete Debian installation, with almost full KDE, OpenOffice, Tex/LaTeX and all that is necessary for writing PhD thesis (gnuplot, octave etc.) - and still it is barely above 2GB. So, 4GB MRAM would be more than enough for me as a storage for the OS.

      Cheers

      Raf
    43. Re:NOT a hard drive alternative by the_real_bto · · Score: 2, Interesting

      Flash drives do not write FAT32 out to the flash.

      "Until recently, the common approach to using Flash memory technology in embedded devices has been to use a pseudo-filesystem on the flash chips to emulate a standard block device and provide wear levelling, and to use a normal file system on top of that emulated block device."

      Taken from http://linux-mtd.infradead.org/~dwmw2/jffs2.pdf.

    44. Re:NOT a hard drive alternative by Anonymous Coward · · Score: 0

      Just noting here that it would seem a bit silly to use mram as swap space.

    45. Re:NOT a hard drive alternative by vertinox · · Score: 1

      For MRAM to become a viable replacement for HDDs, it has to become as cheap as HDDs.

      If having a MRAM drive means 3d games will get 10 more FPS's over a standard HDD, people will buy the MRAM regardless of price.

      But of course the same could be said about $500 video cards, but not everyone will buy them today, but they will in 12 months when those cards are mid-range in performance and price.

      However, they will have to get it to a point where it actually improves performance and doesn't cost more than the computer it is going in.

      --
      "I am the king of the Romans, and am superior to rules of grammar!"
      -Sigismund, Holy Roman Emperor (1368-1437)
    46. Re:NOT a hard drive alternative by swelke · · Score: 1

      If somebody can verify that, then my original post oughta' be modded to oblivion.

      --
      Have you ever wondered How to Take Over
    47. Re:NOT a hard drive alternative by Fordiman · · Score: 1

      How about a machine with 1024M of ram, 512M of it allocated as a RAM disk that has a single 512M loop device mounted as swap?

      --
      110100 1101000 1101000 1100110 0 1101111 1101000 1100011 1
    48. Re:NOT a hard drive alternative by Fordiman · · Score: 1

      I saw nothing that says they don't write fat32 out to the flash there. From what it says, it does distributed writes, changing the location of a written block each time it's written. Meanwhile, the system determines what is used as the FS (on mine, it's JFFS).

      My question: in what form on the device (ie: flash, sram, cmos) is the block translation table stored, and won't that wear out first?

      --
      110100 1101000 1101000 1100110 0 1101111 1101000 1100011 1
    49. Re:NOT a hard drive alternative by lokiomega · · Score: 1

      I'm interested to know if this would really work.

    50. Re:NOT a hard drive alternative by Mattintosh · · Score: 1
      Also, MRAM cells are very large, even compared with flash memory.

      I'm inclined to believe Wikipedia on this one. From Wikipedia:
      MRAM is physically similar to DRAM in makeup, consisting of metal plates and insulators. MRAM and DRAM both have a physically smallest size at which they can be built. As the cell size of a DRAM decreases, the charge able to be stored on the capacitor shrinks, requiring more refreshes. At some point this leads to diminishing returns in terms of performance, and using the best available insulators the current smallest cell size is around 55 nm. In comparison, MRAM is limited by the smallest size of cell that can contain a recognizable magnetic field. Bulk magnetic materials can be self-organized into domains known as quantum dots about 5 nm in size. Thus, in theory at least, MRAM can scale to sizes far smaller than DRAM, which suggests much lower prices.

      I wouldn't call 5nm "large" when DRAM ("regular" memory) is 55nm and flash memory is even larger.

      While they're currently making a 1MB chip, I'd expect that to increase rapidly very soon. This stuff is going to be a godsend to the embedded device industry.
    51. Re:NOT a hard drive alternative by lokiomega · · Score: 1

      I'm inclined to agree with Nutria...the present may now only include a mp3 here and a video there, but in the very near future what is keeping you from streaming a video to your television, podcasting, playing a music file locally, distributing data P2P, etc... all off the same machine. Trends indicate massive increases in multi-tasking technology, with the all the dual-core and multi-processor hoo-hah going on, even on desktop, one-user machines.

    52. Re:NOT a hard drive alternative by the_real_bto · · Score: 1

      In the case that a "normal" filesystem is used, such as FAT, it isn't written out to the chips. NAND flash has special requirements about how it is written that prevent a normal FS from being used on it. There is a software layer between the filesystem the operating system sees and the flash chips. The operating system does not directly write to the flash chips unless it is using a flash filesystem. FAT32, ext2, and other non-embedded filesystems are not written directly to the flash.

      Here is a company that sells flash chips that can be used with normal filesystems:

      http://www.m-systems.com/site/en-US/Technologies/T echnology/TrueFFS_Technology.htm

      On that diagram the DiskOnChip is the physical device. You can see that there is quite a bit going on between what the operating system "sees" and what actually gets written to the chips.

    53. Re:NOT a hard drive alternative by ryusen · · Score: 1

      I forget where, but i remember seeing a PCI card with DIMM slots that would create a dedicated RAM drive for use as virtual memory. It would draw enough power, even when the machine is shutdown, to keep it's memory.

      --

      I believe sex is highly over rated... unless it involves me
    54. Re:NOT a hard drive alternative by theStorminMormon · · Score: 1

      OK, so the basic idea is that you think that desktop usage will, in the near future, start to look like server usage. But this doesn't make sense to me - you have two different types of computers (desktop vs. server) for a reason. Suppose the future does come as quickly as you think, and it's typical for home users to have a single repository for all audio/video data that is then streamed to the house. In such a case you've basically got a media server - and so sure you'd want high-capacity, fast drives. In fact, you'd have trouble doing that based on a commodity drive today - you'd want enterprise-class hardware to really pull that off reliably.

      So on the one hand I'm saying MRAM could be great for desktops, and on the other hand you're saying "we want a server in the house". Well, if a server is what you want, then maybe MRAM won't help you out because you'll want the fast drives to be the high-capacity drives. But unless you plan on having your server ALSO be your gaming rig / coding rig, etc. then you're still going to want MRAM on the computer you use as a desktop.

      And if you want your server to also be your desktop at the same time, then you're still SOL since there's really nothing cheap on the market at all that will give you the performance for both programs (gaming/coding) and data without busting the bank.

      -stormin

      --
      The Southern Baptist Convention has creationism. On Slashdot, we have porn.
    55. Re:NOT a hard drive alternative by morgan_greywolf · · Score: 1

      Well, as far as failure rates go, there are different types -- For example, in terms of failures that cause downtime -- with a decent and appropriately setup RAID system hard drives are damn near 0. Reliability is pretty good even on a single drive system (I average about 1 failure / 3 years on each of my desktops for the last 15 years or so), but these will become increasingly rare as more and more motherboards are coming with built-in RAID controllers and hard drive prices have plummeted so low, that most folks who need that type of reliabiility you can afford to throw two, three or, better yet, 5 into a system. Performance almost doesn't matter. How often do you REALLY sit waiting for the disk on your day to day productivity? With sufficient RAM for the OS to build a significant enough cache and an OS with very little downtime, you'll spend almost no time actually waiting on disk for most day-to-day type apps (Web browsing, e-mail, office apps, etc.)

    56. Re:NOT a hard drive alternative by Intron · · Score: 1

      The lowest number of writes I see in current specs is 100,000, so even without wear leveling you're never going to mess up a USB key that you are copying files to manually. Your fingers will wear out before the device will.

      If the device is mounted in sync mode, then every cluster write causes a FAT update, which drastically increases the number of writes. This was a problem several years ago when FAT was first implemented in Linux. Since FAT is also used for floppies, the default for mounting FAT filesystems is async mode - only write when needed.

      If you want proof that its not a problem, just look at the warrranty. Sandisk isn't going to give you a 3-year warranty if they thought that normal use would kill the part.

      --
      Intron: the portion of DNA which expresses nothing useful.
    57. Re:NOT a hard drive alternative by julesh · · Score: 1

      True. :)

    58. Re:NOT a hard drive alternative by Nutria · · Score: 1
      So on the one hand I'm saying MRAM could be great for desktops, and on the other hand you're saying "we want a server in the house".

      Lokiomega is right, things like video (especially HD) are extremely bandwidth intensive, especially if you are viewing one movie, while writing another.

      Modern desktops are more than capable of handling desktop and video-server tasks.

      --
      "I don't know, therefore Aliens" Wafflebox1
    59. Re:NOT a hard drive alternative by Nutria · · Score: 1
      On a desktop machine, program load time and swap space access speed are much more important than data access. Almost all desktop applications perform relatively little data I/O compared to that involved in loading & executing them.

      Really? How often do you start up your web browser, email client, word processor, spreadsheet app, bit torrent, etc? Once a day or less, depending on the app. You load them, and they sit there, waiting for you to use them.

      Or does Windows suck so bad that you've got to close apps as soon as possible, to free up RAM for other apps?

      --
      "I don't know, therefore Aliens" Wafflebox1
    60. Re:NOT a hard drive alternative by Glonoinha · · Score: 1

      Company name : Gigabyte.
      Product name : iRam

      There's enough there to entertain you on the idea for a while (that 'while' being until you price it with enough RAM to make it worthwhile, at which point you politely consider alternatives.)

      --
      Glonoinha the MebiByte Slayer
    61. Re:NOT a hard drive alternative by Glonoinha · · Score: 1

      See my earlier post.

      --
      Glonoinha the MebiByte Slayer
    62. Re:NOT a hard drive alternative by bufalo_1973 · · Score: 1

      Something like a "scattered load" where only the part that fits in memory is loaded and if there is a jump to a position outside the "slice" loaded, another "slice" is loaded?

    63. Re:NOT a hard drive alternative by Anonymous Coward · · Score: 0

      The grandparent is right. Flash systems intended to be used for a filesystem incorporates a layer, usually called the "Flash Translation Layer", which maps writes to blocks from the OS filesystem layer to actual pages of flash memory.

      For that matter, filesystem flash is usually "NAND" flash, which higher bit density (and thus lower price for a given size) than "NOR" flash. One problem with NAND is that it tends to have more manufacturing defects and bit errors. So, NAND devices are usually constructed with extra sectors, just like a disk drive, and the FTL software is responsible for detecting bad sectors and mapping around them.

      Here's an app note from a more or less typical flash vendor that talks about it.
      http://www.st.com/stonline/products/literature/an/ 10122.pdf

    64. Re:NOT a hard drive alternative by ryusen · · Score: 1

      that's right... thanks for remidning me why i didn't buy it .p

      --

      I believe sex is highly over rated... unless it involves me
    65. Re:NOT a hard drive alternative by Anonymous Coward · · Score: 0

      > but I keep delaying a purchase due to my fear of wearouts

      IMHO, it's not worth bothering about. You can pick up a decent sized flash drive for like $20. Just get one, use it (you won't have to worry about it wearing out for many years unless you're doing something really wacky with it), and if 5 years hence the thing croaks, well, it cost you 4 bucks a year. Big whoop. Way more likely you'll lose it or run it through the wash or something before it dies, anyway.

    66. Re:NOT a hard drive alternative by 5of0 · · Score: 1
      Way more likely you'll lose it or run it through the wash or something before it dies, anyway.
      I ran mine twice through the wash, and lost it several times, and it still worked (when I found it).
      Then again, it did start getting flaky (deciding to chop off all but the first 8k, brobably a FAT problem).
      But by that time, I'd gotten a 1GB cruzer micro w/ retractable USB for $25 on sale at CC, so I'm happy. ;)
      --
      You all have Oo.o and Firefox, so get World Wind.
    67. Re:NOT a hard drive alternative by julesh · · Score: 1

      Really? How often do you start up your web browser, email client, word processor, spreadsheet app, bit torrent, etc? Once a day or less, depending on the app. You load them, and they sit there, waiting for you to use them.

      As you say, it depends on the app. But, yes, to take the example of a word processor, you load it once. This takes about 3-4MB of I/O (it's hard to tell exactly how much, because not everything will be loaded into memory). You'd then typically load a document, and maybe save it 10 or 20 times throughout the day while working on it. Typical document size = about 20K. That's 400K of I/O. The application load I/O time dwarfs the document I/O time.

      Or does Windows suck so bad that you've got to close apps as soon as possible, to free up RAM for other apps?

      No, actually Windows is pretty good at removing apps from memory in order to make additional RAM for others. It does this by removing the app's text pages without putting them into the paging file... they can be reloaded from the disk the app was run from, so it'd be a waste of I/O time and page fle space to copy it into there. So, when you switch back to the app after it has been paged out, you'll start loading it from the disk it was originally run from again, just as soon as it hits a page fault.

      Linux does exactly the same, so the same arguments apply there too.

  3. Price? by bookemdano63 · · Score: 4, Informative

    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

    1. Re:Price? by cyfer2000 · · Score: 4, Interesting

      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.

      --
      There is a spark in every single flame bait point.
    2. Re:Price? by barawn · · Score: 3, Informative

      That is a reasonable price. Right now, MRAM replaces battery-backed SRAM: like the ZEROPOWER 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.

    3. Re:Price? by jcr · · Score: 1

      even faster than DRAM.

      Ok, I'm sold. I'd love to have non-volatile main memory in my computers.

      -jcr

      --
      The only title of honor that a tyrant can grant is "Enemy of the State."
    4. Re:Price? by Cougar1 · · Score: 1

      While you are correct that manufacturing the metal multilayer structures is a significant challenge, the use of such structures is also an advantage. Since the MRAM structures are all in the metal layers and use lower-temperature processes, they are actually easier to integrate with existing semiconductor fabrication technologies for embedded applications.

      Thus, it is actually easier to integrate MRAM into a microcontroller or power device than it would be to integrate FLASH or even SRAM.

  4. When? by joshier · · Score: 1

    When will this be available?

    1. Re:When? by cyfer2000 · · Score: 2, Informative

      From what I am remembering, Freescale began small batch sampling of this kind of 4Mbit MRAM two years or 1 and half years ago, and now a available in large batch.

      --
      There is a spark in every single flame bait point.
  5. Everything old is new again by Billosaur · · Score: 4, Funny
    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!

    --
    GetOuttaMySpace - The Anti-Social Network
    1. Re:Everything old is new again by bigtrike · · Score: 1

      Or you could use one of many available methods to achieve this effect, such as using sram, giving the memory power, or storing the contents of memory on disk.

    2. Re:Everything old is new again by MsWillow · · Score: 1

      Seriously, back in the day, I worked for a distributor which carried a notebook that used bubble memory as a "disk drive." It pre-dates the widespread acceptance of the PC, had a few lines of lcd text display, and ran CPM. I think it was called the Teleram.

      Back then, I'd have given my left nut for one of them. ;^) Ahh, the joys of Wordstar 3.3, BDS C and Mbasic ::sigh::

      --

      Lemon curry?
    3. Re:Everything old is new again by MsWillow · · Score: 1

      FWIW, here's the link about the Teleram notebook. Sweet.

      --

      Lemon curry?
    4. Re:Everything old is new again by Jesus_666 · · Score: 1

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

      That would obviously be the Commodore 67108864.

      --
      USE HOT GRITS WITH STATUE OF NATALIE PORTMAN (NAKED AND PETRIFIED)
  6. Back to the past.... by Anonymous Coward · · Score: 2, Insightful

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

    1. Re:Back to the past.... by Rick.C · · Score: 1
      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 of this taken through a microscope back in the mid-70s, so this is quite old stuff.

      --
      You were 80% angel, 10% demon. The rest was hard to explain. - Over The Rhine
      "Math in a song is good."-Linford
    2. Re:Back to the past.... by badfish99 · · Score: 1
      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.

    3. Re:Back to the past.... by WebCowboy · · Score: 4, Informative

      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...

    4. Re:Back to the past.... by epiphani · · Score: 1

      The great thing about core memory was its tolerance to water. Running into some wierd glitches in your application? Probably a problem with the memory - got dusty or something.

      Pull it out, wash it off, away ya go!

      --
      .
    5. Re:Back to the past.... by rrohbeck · · Score: 1

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

      Cool. I want LED and toggle switch front panels back too.

      Toggling in the bootloader after I blew it away with a buggy program was so much fun. Who needs Flash, anyway? :)

  7. Computer store? Apple Core? Say no more. by Speare · · Score: 1, Funny

    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.
    --
    [ .sig file not found ]
  8. Can anyone say 'Core'. by arthurpaliden · · Score: 2, Insightful

    This held its data for years after it was powered off.

    1. Re:Can anyone say 'Core'. by ---- · · Score: 1

      I remember this!

      A bit big for today's technology tho.

      The Magnetic Core Memory 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".

  9. Is bootup time really that big of an issue? by Skynet · · Score: 4, Interesting

    XP boots in about a minute, and Linux never needs to be rebooted. :)

    What other applications could this have besides boot time?

    --
    Execute? [Y/N] _
    1. Re:Is bootup time really that big of an issue? by rixkix · · Score: 1

      portable machines

    2. Re:Is bootup time really that big of an issue? by j00r0m4nc3r · · Score: 5, Funny

      Instapr0n(tm)

    3. Re:Is bootup time really that big of an issue? by metarox · · Score: 2, Interesting

      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.

    4. Re:Is bootup time really that big of an issue? by DrXym · · Score: 1

      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.

    5. Re:Is bootup time really that big of an issue? by mwvdlee · · Score: 1

      Hibernating in memory without the risk and power consumption of hibernating in memory.

      --
      Slashdot social media options: AIM, ICQ, Yahoo, Jabber and Mobile Text. Why no MySpace?
    6. Re:Is bootup time really that big of an issue? by Brazilian+Joe · · Score: 1

      Save power, which means 1)a smaller electricity bill, and 2) longer battery life. Be it your desktop core or a server farm, it could make its way into cache memory if it's fast enough. That is, IF this technology (or an evolution thereof) can be applied directly inside the cpu core design/building process. Of course, swapping your ram to this MRAM is still years away, but if the technology succeeds, it can happen (and everyone wants it to happen).

      Also, the PDA/Smartphone crowd would benefit from it too. Instead of having too keep juicing 64+MB of memory, you'll only spend power when you have to change information. Judging for the size (4Mbit), this application is a few years away too, maybe farther than the cache scenario (if there are no serious hurdles to swapping from the current cache technologies into this one), but not as much distant as the desktop/server MRAM-only scenario.

    7. Re:Is bootup time really that big of an issue? by Kythe · · Score: 1

      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, radiation that would screw with DRAM/SRAM/Flash memory, or even EPROM). Magnetic memory tends to be immune to such problems. So you could make use of it in space probes and satellites, for example.

      --

      Kythe
    8. Re:Is bootup time really that big of an issue? by MrNemesis · · Score: 3, Interesting

      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...

      --
      Moderation Total: -1 Troll, +3 Goat
    9. Re:Is bootup time really that big of an issue? by Rxke · · Score: 1

      Digital camera's. Today the cheap ones are dog slow.

    10. Re:Is bootup time really that big of an issue? by jcr · · Score: 1

      Actually, the radiation immunity of core memory is more a function of its size than it being magnetic. The smaller a device is, the easier it its for a single cosmic ray to flip a bit, whether it's storing the bit as a static charge or a magnetic field.

      -jcr

      --
      The only title of honor that a tyrant can grant is "Enemy of the State."
    11. Re:Is bootup time really that big of an issue? by fyngyrz · · Score: 2, Informative
      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 abstracted from the PDF data sheet easily found at on this page.

      --
      I've fallen off your lawn, and I can't get up.
    12. Re:Is bootup time really that big of an issue? by UnknowingFool · · Score: 1

      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.

      --
      Well, there's spam egg sausage and spam, that's not got much spam in it.
    13. Re:Is bootup time really that big of an issue? by DrLang21 · · Score: 1

      Think beyond laptop and desktop computers. There are plenty of digital devices out there that rely on SRAM.

      --
      I see the glass as full with a FoS of 2.
    14. Re:Is bootup time really that big of an issue? by Neoprofin · · Score: 1

      Obviously you aren't a file sharer, server, or just someone who uses instant messaging for a majority of your communication.

    15. Re:Is bootup time really that big of an issue? by MrNemesis · · Score: 1

      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.

      --
      Moderation Total: -1 Troll, +3 Goat
    16. Re:Is bootup time really that big of an issue? by asuffield · · Score: 2, Insightful
      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 consumer applications you just live with the risk, but at the top of the market there's definitely a use for fast and safe caching.

      It probably also has any number of useful applications in embedded systems, as a faster alternative to flash.

      But we knew about all this ten years ago. Magnetic memory is one of those things that has been around forever but nobody ever manages to get to market in a practical and affordable fashion. It remains to be seen whether these people can pull it off (so far, their results are underwhelming).
    17. Re:Is bootup time really that big of an issue? by denoir · · Score: 1
      How about a complete revolution of computer architecture as we know it? No more slow disk reading; no more start up time for applications. The traditional architecture of the dual use of RAM/HDD will be gone, replaced by a single medium.

      This will happen, because it must. Whether it will be MRAM or something else remains to be seen, but it will certainly be something having the same features.

      It must because we're reaching the practical limits of how much you can pack on hard disk platters. You can only squeeze in so many bits per cm^2.

      Also, read speed and access time is severely limited by the simple fact that it's a mechanical construction with a read/write head having to move over the platters. As software and media is progressively becoming larger in terms of storage space, the current drives are being increasingly responsible for slowing it down due to excessive loading times.

      The current HDD technology is the last remnant of the electro-mechanical approach to computing. Its death warrant was signed by the transistor, but the dinosaur managed to live on as there was no alternative.

      The HDD is the most antiquated, out-of date technology found in a modern computer and MRAM is a good candidate for a future replacement. It won't happen in two or three years, but in the 5-10 years range, HDDs will be replaced with some form of fast, non-volatile semiconductor memory.

    18. Re:Is bootup time really that big of an issue? by Skynet · · Score: 1

      Very interesting insights, thanks. :)

      --
      Execute? [Y/N] _
    19. Re:Is bootup time really that big of an issue? by Kythe · · Score: 1

      Hmmm...I guess I'll have to check into this a little more. My understanding was that the problem with cosmic rays is that they leave a trail of damage in the form of charged particles through semiconductor devices, and when that happens to gate material (e.g. flash memory), it provides a path for charge to escape.

      Obviously, no such problem would be encountered in a magnetic material. What is the mechanism by which a cosmic ray would flip the domain magnetization in e.g. a pseudo spin valve?

      --

      Kythe
    20. Re:Is bootup time really that big of an issue? by jcr · · Score: 1

      Basically, the impact of a energetic particle, whether it's a cosmic ray, a gamma particle, etc, is able to cause a local current, which if the device is small enough, can induce a field that weakens or flips the existing field. For a given feature size, the magnet probably is more robust, but the radiation resistance of an MRAM won't be anything close to that of core memory.

      -jcr

      --
      The only title of honor that a tyrant can grant is "Enemy of the State."
    21. Re:Is bootup time really that big of an issue? by wwahammy · · Score: 1

      Does the cache use much power as it is? Every little bit helps of course but would replacing cache with MRAM justify the increased cost in the near future (5 years or so)?

    22. Re:Is bootup time really that big of an issue? by DrXym · · Score: 1

      An obviously file sharers and people who like to receive IMs when they are not there are a small percentage of users. I'm sure they could igure out how to change the power saving options if they want to leave their machine on all night. Servers obviously wouldn't sleep when not in use, but there is no reason that desktop machines shouldn't by default.

    23. Re:Is bootup time really that big of an issue? by mr_zorg · · Score: 1
      XP boots in about a minute, and Linux never needs to be rebooted. :)
      What other applications could this have besides boot time?

      I think when most people talk "boot time" they're really taking about "completely off-to-completely functional" time. Sure, boot time isn't that big of a deal because we have sleep modes, hibernate, etc. But wouldn't it be nice if when I snapped closed the lid on my laptop that it physically powered off (drawing zero power) instead of merely going to sleep?

    24. Re:Is bootup time really that big of an issue? by Cougar1 · · Score: 1

      While I don't know how MRAM's radiation hardness would compare to core memory, Honeywell has in fact licensed Freescales MRAM technology for use in radiation-sensitive applications.

    25. Re:Is bootup time really that big of an issue? by TexasDex · · Score: 1

      Mod parent +1 insightful, because I just upgraded about 25 graphics cards in low-profile Dell Optiplex workstations, and boy am I cranky.

      --
      The Cheese Stands Alone.
    26. Re:Is bootup time really that big of an issue? by Kythe · · Score: 1

      For a given feature size, the magnet probably is more robust, but the radiation resistance of an MRAM won't be anything close to that of core memory.

      I'm actually rather skeptical of this. If I recall the research I read on GMR for my graduate study (it's been several years), the magnetic field required to make spin valves switch actually increases as size decreases.

      --

      Kythe
    27. Re:Is bootup time really that big of an issue? by smithmc · · Score: 1

        What other applications could this have besides boot time?

      How 'bout really rugged environments, embedded systems, etc. Flash is useful here but is sometimes hampered by the limited number of write cycles.

      --
      Downmodding is the refuge of the weak. Don't downmod, make a better argument!
    28. Re:Is bootup time really that big of an issue? by PB_TPU_40 · · Score: 1

      Actually leaving your computer 24/7 is considerably less stressful on the hardware. The shock of turning the system on and off tends to wear out electrolytic caps at a much higher rate. None of my friends turn off our computers for that reason unless we're not going to be infront of them for a week or more or there is a severe storm and brown outs and fluctuations would screw the system up, but thats a not that often.

      In corporate enviroments you have hundreds if not thousands of machines, with that your statistical probability of a failure begins going up, coupled with the extra stress of constantly turning them off at night and back on in the morning, you'd probably eventually loose on average 3 -4 machines a week due to dead caps, and thats a very low estimate. Couple that with the fact that most administrative tasks such as updates and installing new software are done remotely at night while the user is away from work. The energy costs are minor compared to wasting employees time, as well as burning up hardware.

      Where I see this technology really being used though is in embedded systems. Often all you have is EEPROM or Flash for storing information, reading is slow, writing is even slower, and a lot of work. EEPROM you have to rewrite the whole chip, Flash whole blocks. However you could use this new ram to store critical information so if a power failure occurs the system would recover much quicker, as well as the fact that system status and configuration informat would be preserved through the power failure.

      Suprisingly everyone seems focused on boot time, the access times are considerably lower, so making an OS call would be quicker without having to cache as much of the OS in RAM.

      --
      -PB_TPU_40 The trick to flying is to throw yourself at the ground and miss.
  10. Given the size requirements... by grasshoppa · · Score: 1

    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.

    --
    Mod me down with all of your hatred and your journey towards the dark side will be complete!
    1. Re:Given the size requirements... by TheRaven64 · · Score: 1

      They are currently producing 512KB ICs. They need to scale the technology quote a lot before they're even close to 6GB.

      --
      I am TheRaven on Soylent News
  11. Re:more vaporware by TransEurope · · Score: 4, Informative

    First: freescale aims on the usage of MRAM in embeddet devices and microcontrollers. There will be no MRAM-Harddisk next month in the shops. 2nd: There is not only Freescale. Micromem will produce MRAM-Chips for the Aerospace industry. And IBM/Infineon already have an 16-MBit-MRAM-Chip since last year. There are also Renesas/Toshiba in the race. It's a completely new tech, you heard about years ago, when the first theories about mram came from the labs. But such a thing needs everytime many years to go to the serial production lines.

  12. I can barely read this! by Anonymous Coward · · Score: 0

    Aren't editors supposed to edit for things like grammar?

    What do /. editors do? Stick a pin in an article and throw it on the front page without even reading it?

  13. Old news by dpaton.net · · Score: 4, Informative

    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 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 to write more.

    --
    This is not a sig. this is a duck. quack.
    1. Re:Old news by Anonymous Coward · · Score: 1, Informative

      I assume you meant Ramtron, not the misspelled "rantron" in the URL.

    2. Re:Old news by Kythe · · Score: 1

      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.

      --

      Kythe
    3. Re:Old news by cyfer2000 · · Score: 1
      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 area like iPod in foreseeable future.
      3. If I have non-volatile RAM faster than DRAM, should I think something different. A computer without DRAM and HD at all?
      4. As FRAM, don't think it can compare the speed of MRAM. Due to the speed of ferroelectric phase transition, I think ghz is the ultimate limit of FRAM. But MRAM working Ghz has been shown. Anyway, I don't understand why you are talking about FRAM.
      5. Making a 500GB FRAM component is... You know what I'am going to say.
      --
      There is a spark in every single flame bait point.
    4. Re:Old news by barawn · · Score: 1

      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 based upon the size (4 MBit) and the price ($25), they're targeting battery-backed SRAM currently. I'm sure they'll target all external SRAM chips next, and then flash as the production scales.

    5. Re:Old news by dpaton.net · · Score: 2, Informative

      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 the power switching infrastructure on that many sqft of PCB (damn TSSOP packages) would be impossibly problematic. The design of the chips isn't supportive of anything large scale...these are indeed for cellphone scratch pad use, or for NV storage in other small devices.

      And remember, my numbers were only for a 500GB x 1 byte array. That's horribly inefficient. If they can bump the width and depth of the array up, then we can talk. Let's hope they scale it fast and well.

      --
      This is not a sig. this is a duck. quack.
    6. Re:Old news by dpaton.net · · Score: 1

      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 reported for a number of years now. Motorola poured an obscene amount of money into it back before they sold their memory businesses off and spun out Freescale. Even after all these years and hundreds of millions (if not billions) of dollars, we're only getting a 4Mbit chip. Plan on patience.
      3. The day I can get a computer that uses no spinning storage and no volatile memory is the day I have the jack installed in my head. It'll happen eventually, I'm sure, but not soon and definitely not cheap. I'm betting military applications will drive it more than foreign innovation.
      4. I talked about FRAM partly as a contrast (despite my fat-fingering the link to Ramtron), but mainly because it's what's on my desk right now. A few K of parallel FRAM storage for scratch space, and a couple of big I2C units for storage.
      5. Of course. FRAM is for small things.

      I'm not trying to be bitter or mean, but the chip isn't at all what the OP thought. It's for embedded systems, and I want people to recognize that.

      --
      This is not a sig. this is a duck. quack.
    7. Re:Old news by barawn · · Score: 1

      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 instant-on chip.

      And remember, my numbers were only for a 500GB x 1 byte array.

      Two byte. It's a 256Kx16 chip.

    8. Re:Old news by barawn · · Score: 1

      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 power switcher. The current spike and noise can be handled with decently large capacitors on the power supply.

      You don't need to know length, width, etc. of memory. Blocks free? What blocks? It's just SRAM style memory: bunch-o-address lines, and a chip select and write enable. If you want to write to (16-bit) word 0x80001234, the mega-gigantic demux just switches out 0x800012 into the proper chip select and relay, and the addresses just pass on to the newly-activated chip.

      Finding a 20-to-1,048,576 demux might take some work, though, but you'd need it anyway.

    9. Re:Old news by cyfer2000 · · Score: 1
      I am a materials guy. So I know the story inside the plastic package.
      1. The news is after all those years and money, MRAM is commercially available. Actually I thought IBM should have made it happen firstly.
      2. It's not a easy job. Do you know how many years people waited for the commercial SOI wafer? Fabrication is not what you want, and what you designed to work, it is what you can get.
      3. MRAM use the "spin" of electrons to read. So no need to worry about your head.
      --
      There is a spark in every single flame bait point.
    10. Re:Old news by dpaton.net · · Score: 1

      Well, the array size is governed by the memory cell size, but the actual storage geometry is governed by the controller. 500x8 was easier in my head than 250x16 when I was multiplying initially.

      Power on time for the chips is significant WRT access time. 2-3mS as I recall. I don't have the datasheet handy at the moment though.

      As for designing a big array, 32-128 of them is managable with conventional means, but getting to the levels of storage that HDs have makes it laughable. If I was actually going to design a system as large as I initially mentioned, well, there'd be racks with controller backplanes and inifniband or something for interconnects, not to mention 12 layer boards and (old school) Cray levels of hand optimization. Even then it'd be silly. I was just making it as obvious as I could ;-)

      --
      This is not a sig. this is a duck. quack.
    11. Re:Old news by barawn · · Score: 1

      Well, the array size is governed by the memory cell size, but the actual storage geometry is governed by the controller.

      What? How would you write 8 bits to a device that has no way to write only 8-bits of a 16-bit word? This particular device has byte-select for flexibility, but still, in order to have byte-addressable read/write access, you'd need to add an additional pair of 8-bit buffers for each chip and a bit more logic to support 8-bit read/writes.

      But plenty of devices aren't capable of writing to individual bytes. You could rearrange the geometry with a controller (write = read word and rewrite new bits) if you wanted to be insane, but I think you'd have to be a little crazy to do that.

      Power on time for the chips is significant WRT access time. 2-3mS as I recall. I don't have the datasheet handy at the moment though.

      I didn't see it originally, as it's hidden in a note in the data sheet - but it's 1 microsecond. Which is significant but not insane. You could probably build a power-switched large array of these guys with acceptable performance for certain applications.

      Anyway, it's obvious that they're not targeting this thing for large-scale storage (the "10 year minimum data retention" in the data sheet should tip off what other chip they're targetting), but that's just due to the design of the chip (and the current cost), not the technology.

    12. Re:Old news by dpaton.net · · Score: 1

      Looks like they've gone and dashed our hopes for us ;-)

      [We have] no intention to become a commodity MRAM vendor." - Saied Tehrani
      from an Embedded.com article.

      --
      This is not a sig. this is a duck. quack.
  14. TV not PC by ds_job · · Score: 4, Insightful

    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.

    1. Re:TV not PC by austinpoet · · Score: 1

      We can put it into alarm clocks too! then we won't be able to blame a power outage for oversleeping and skipping work. "No sir, I hadn't thought about putting my alarm clock on an UPS system."

      maybe we shouldn't put them into alarm clocks.

    2. Re:TV not PC by Anonymous Coward · · Score: 0
      We can put it into alarm clocks too!


      I suppose that might be useful for knowing what time is was when the power went out.



      (Yes, I realize you are talking about those momentary 1/10 of a second power flickers that reset the alarm clock to blinkynoon, but couldn't resist)

    3. Re:TV not PC by slavik1337 · · Score: 2, Insightful

      MRAM heating the CRT faster???

      --
      just my 2 bytes
    4. Re:TV not PC by Jedi+Alec · · Score: 1

      I can't do that anyway, I work for the power company...

      --

      People replying to my sig annoy me. That's why I change it all the time.
    5. Re:TV not PC by poot_rootbeer · · Score: 1

      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.

    6. Re:TV not PC by Anonymous Coward · · Score: 0

      Don't thay make alarm clocks that take batteries to keep time when the power goies out anymore?

      The last alarm clock I bought had that feature and that was over 10 years ago, I just use my phone as an alarm nowadays, so its very unlikely a power cut would affect it.

    7. Re:TV not PC by ds_job · · Score: 1

      The "Off" button on the front of the TV is probably just a mechanical switch to interrupt the power. If you turn it off and then back on again, it reverts the alarm function back to off, the display is set to "Normal 1" and I have to rejig it. I get the feeling that it is just the way this was made.
      My Cable TV box on the other hand is much more modern and every time takes ages to scan, verify, authenticate etc. onto the cable network and this would benefit from a new chip to store all of this once and not need to discover most of it each time.
      I'm basically looking to get this adopted so that when I upgrade my TV and A/V kit next year I can do it with a view to keeping my power consumption (and energy bills) down. It's all self, self self, ;-)

    8. Re:TV not PC by Anonymous Coward · · Score: 0
      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.
      Unlike some, I still have run-of-the-mill standard cable TV, I get the channels I want and I don't bother with specialized channels for cooking, gardening, or infomercials. I turn my TV on, and I can start flipping channels right away. I don't have to turn my TV on 2 minutes before my favourite TV show just to take into account TV-initialization. I can turn it on during the intro theme song and not miss a minute of fun! :)


      And now for something completely different...

      [rant]When it comes to any technology that The Media can use in some way to get ads through, 9 times out of 10, the older your equipment is, the less you're bothered. Even when ads aren't involved, usually older technology is better. An example? Tapes may hold less sound and be of lower quality than CDs, but at least the inventors had the sense to protect the sensitive ribbon with a casing! One scratch on your CD and the odds are good that you've screwed up the contence in some way. The inventor(s) of the Compact Disc should be shot for this! The only possible reason they made CDs look the way they do is for the "shiny reflective 'Ooh, Cool!' factor". Why would they do this? Marketing and sales! Knowing that, subconciously, people will think that since the item looks nothing like the day's technology (built sturdy and sometimes ugly vs shiny and with only the essentials, leaving the data relatively unprotected from day-to-day (mis-)handling), so it must be better (read: "future-y").

      It's like exposing a nuclear plant's reactor cores to the open air because it looks cooler, and having the PR team explain that the green glows surrounding everyone and everything in the city is A Good Thing(tm), which will make all cleaning agents obsolete.[/rant]


      P.S. I know that my rant will get me modded as Troll, and I already regret that I'm going to Submit it! I just needed to get it off my chest, if for no other reason than to say that I didn't waste my time thinking of it and typing it up, because it's been posted.

      Nothing for you to read here, move along.

    9. Re:TV not PC by Anonymous Coward · · Score: 0

      I don't want this in my PC to boot my O/S quicker.

      So you don't want a non-volatile solid state "disk" which is faster than DRAM? You don't want "disk" storage which can sustain hundreds of megabytes to gigabytes per second and has random access times which when rounded to the closest millisecond, are 0mS?

      Okay. You go without. I'll take it though. I'm not interested in quicker OS boot times, that is just a bonus to all the other benefits.

      A technology like this, once it is dense enough, will be such a huge leap forward, that it will have OS developers re-thinking VM subsystems. Suddenly main memory becomes the slowest part of a computers main processing!

  15. Re:more vaporware by Yusaku+Godai · · Score: 2, Informative

    Did you RTFA? This is the first commercial MRAM product which is being produced in volume. They have customers for it, and they've already built up a stock of the stuff. Can't call it vaporware if it supposedly actually exists somewhere and is ready to be shipped.

  16. Re:more vaporware by barawn · · Score: 2, Informative

    We've been hearing vaporware mram chip stories for almost a decade now... When is it going to be on the market for people to purchase and use?

    Now, apparently. That's what this story is about. Here's a link to the actual chip's spec sheet. Here's a link to the chip's page on Freescale, where you can order it for $25/chip in 1000 unit quantities.

    It's not in any consumer products yet, no, but it is available to purchase, which means it isn't vaporware.

  17. Re:more vaporware by Yusaku+Godai · · Score: 1

    Note also that Freescale has close ties to Motorola. I would not be surprised if this starts showing up in consumer electronics before long now.

  18. It doesn't quite seem to be (Re:) more vaporware by beh · · Score: 1
    According to the article:

    Freescale has been producing the four-megabit Mram chips at an Arizona factory for two months to build up levels of stock.


    It's not like they're saying "we WILL have something tangible", but rather "we HAVE something tangible".

    On the other hand - sorry, I don't quite see how these will be in competition with hard-drives, if you see that they are working on 4(!) MEGAbit chips... To Freescale: Call me again when it's 4 GIGAbit chips... ;-) I'm just not convinved I'd want a 1GB harddisk replacement made from 2048 of those chips...

    I see those as small stepping stones, but not more, right now.

  19. Alternative to Hard Disk by TheVelvetFlamebait · · Score: 2, Funny

    Don't you mean Hard Disk Killer?

    --
    You know, there is a difference between trolling and pointing out the flaws in your reasoning. Just saying.
  20. 512kB chip: $25 by Demon-Xanth · · Score: 2, Informative

    http://www.freescale.com/webapp/sps/site/prod_summ ary.jsp?code=MR2A16A&srch=1

    "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.

    --
    If you think education is expensive, you should try ignorance -- Derek Bok, president of Harvard
  21. Article misses the point almost completely... by Gadzinka · · Score: 4, Informative
    I am not really suprised, that no one bothered to google for MRAM, not even tried to look it up in WP. 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
    --
    Bastard Operator From 193.219.28.162
    1. Re:Article misses the point almost completely... by jandrese · · Score: 1

      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.

      --

      I read the internet for the articles.
    2. Re:Article misses the point almost completely... by Anonymous Coward · · Score: 0

      not even tried to look it up in WP

      I don't have WordPerfect anymore, you insensitive clod.

    3. Re:Article misses the point almost completely... by FridayBob · · Score: 1

      Indeed. Over the years I've read stories about MRAM that said it would some some day be possible to have PCs that would not necessarily have to be rebooted as a consequence for every time that they are turned off. In most cases the operating would simply remain in memory (MRAM) and continue its operations as soon as the PC is turned back on again. It would work like suspend-to-disk or suspend-to-RAM, except that, respectively, you wouldn't have to write/read anything to/from disk first or keep refreshing your RAM (using up power) to get the same results.

      This would probably be good news in most cases, but there would still need to be some kind of reset button to wipe the MRAM banks in case the operating seizes up -- particularly important when running unstable operating systems, such as Windows. Now we just have to wait for the stuff to decrease in size and price. I think it's possible that a similar technology will eventually replace those old spinning, magnetic platters, but if this stuff only ends up replacing my RAM and cache without being too expensive, that will still be a big step forward.

    4. Re:Article misses the point almost completely... by Gadzinka · · Score: 1
      The problem is that MRAM always seems to be 20 years behind SRAM in the cost/mb department.

      What are you talking about? ;) The physical phenomenon governing MRAM is known since 1989, and first theorethical/prototyping work didn't start before mid-nineties (I was mistaken about it being developed since the eighties). If I remember correctly, DRAM/SRAM twenty years ago was barely breaking 64KB per computer and reached these outrageous capabilities after twenty years of development. So, only 10 years from nothing to 4Mb available for sampling (and 16Mb in prototypes) is unbelievable speed ;)

      The problem is that these guys are shooting at a moving target, and they're barely keeping up.

      Well, as everything in IT, DRAM and SRAM will soon hit the wall of diminishing returns in advances by process shrink alone. MRAM has a lot to catch up, but I think it will get there, eventually. But I wouldn't hold back with buying new RAM or Flash card just yet. Or for another ten years ;)

      Robert
      --
      Bastard Operator From 193.219.28.162
  22. Still pretty small by wonkavader · · Score: 2, Informative
    Currently, it's 256K x 16-Bit

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

    1. Re:Still pretty small by ooze · · Score: 1

      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.

      --
      Just because I can imagine doing a hippopotamus, doesn't mean I'd like to do it.
  23. Re:Vaporware by Kythe · · Score: 2, Informative

    As was noted above, this is actually being produced, so by definition it isn't vaporware.

    The problems MRAM could address are very real, and people have been working on using MRAM/GMR-based memory for a long time for that very reason.

    --

    Kythe
  24. Not likely to replace RAM by tygerstripes · · Score: 3, Insightful

    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.

    --
    Meta will eat itself
    1. Re:Not likely to replace RAM by Heir+Of+The+Mess · · Score: 1

      Imagine though the possibility for when it does replace RAM. People here are talking about hard drive replacements and RAM replacements, but what if it replaces both? We have 64 bit operating systems and CPUs, why not just have all applications loaded and the data loaded in them, and the OS just marks which applications are currently active. Of course there would have to be a major change in the way applications and operating systems currently work. Data formats would become memory based layouts for editing. That texture you are editing in Photoshop would be shared with your 3D modelling software in memory so it should change on the screen as you edit it.

      --
      Australian running a company that does C# / C++ / Java / SQL / Python / Mathematica
    2. Re:Not likely to replace RAM by barawn · · Score: 1

      Seriously though, this is hardly going to make waves for some time.

      Depends what you're interested in. Take a look at integrated battery-backed SRAM: some form of this is used for realtime clocks in PCs, for instance. Large quantity battery-backed SRAM is expensive: 4 MBit (which this is) is huge (a 32-pin DIP package) and is $50 in quantity.

      This is half the price. The large-size integrated battery-backed SRAM market just became completely pointless. I wouldn't be surprised if manufacturers of those parts (like Maxim, ST Microelectronics) announces that those parts are discontinued within a year.

  25. Re:Vaporware by 1stpreacher · · Score: 3, Informative
    I don't get the vaporware argument here... They're being SOLD... But aside from that, I see MANY uses for this - first in cell phones, according to this "In February of 2006, Toshiba and NEC announced a 16 megabit MRAM chip with a new "power-forking" design. It achieves a transfer rate of 200 MB/s, with a 34 ns cycle time - the best performance of any MRAM chip. It also boasts the smallest physical size in its class -- 78.5 square millimeters..."


    so we're looking at 'about' 3 inches for 16meg (in this case) ... I'd LOVE my phone to be able to use it's memory more quickly, and to be able to sync more quickly with my pc. And that's just the first thing I could think of...

  26. Core Memory Redux? by sboyko · · Score: 1

    It's core memory 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.

    --
    SCO, Microsoft, P2P, what's your hot button?
    1. Re:Core Memory Redux? by ekeko · · Score: 1

      IIRC, the threading of the core memory was done in India by craftsmen how had the skill and patience to weave Persian rugs.

    2. Re:Core Memory Redux? by Anonymous Coward · · Score: 0

      One difference, though, I thought core memory could not lose power or it blanked out.

  27. Re:It doesn't quite seem to be (Re:) more vaporwar by barawn · · Score: 2, Informative

    On the other hand - sorry, I don't quite see how these will be in competition with hard-drives

    Right now, they aren't. At that price point, they're competing with battery-backed SRAM (very nicely for the integrated stuff, and it depends on the product for the battery + battery monitor chip + SRAM solution).

    Short primer on different memory technologies: SRAM is very fast, very low power, easy to interface, but it needs a battery for data integrity. DRAM is very cheap, but higher power, much harder to interface, and needs not only a battery but a controller for data integrity. EEPROM is everything SRAM is, but nonvolatile but is expensive, and writing requires awkward voltages, can't be done bytewise, and is slow anyway. Flash is similar to EEPROM, but beats it because it's cheaper, doesn't require weird voltages, but writing is still awkward.

    The only downside to MRAM currently is its cost - fast and easy reads, fast and easy writes, nothing required to maintain it, and low power to boot. If this becomes available at distributors within a factor of 2 of that $25 price point, there's literally no point to integrated battery-backed SRAM chips anymore. If the price drops by a factor of 2 or so, there's no point to battery-backed SRAM at all.

    As the price drops, though, MRAM has the potention to challenge all of those technologies above, as well as hard drives, much like flash is starting to do now.

  28. Re:I bet it's hard to make it very small by Kythe · · Score: 1

    Actually, that's not true, or rather, it depends upon the technology. GMR-based systems can be made quite dense, since it actually takes quite a strong magnetic field to flip them from one state to another. If I recall correctly (I'd need to review), ironically, the smaller the dimensions, the stronger the field required. Since magnetic fields from the electric current in write lines decrease as the square of the distance from the lines, you don't have to worry all that much about crosstalk at write time, either. And they're read directly by current passing through the devices.

    The biggest problem with density is fabrication issues and design of the cells.

    --

    Kythe
  29. I was alive in the 1980s by ajs318 · · Score: 1

    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 on secure deletion. It ought to be possible to store several bits {possibly an infinite number?} in each location, on the basis that storing new data does not completely obliterate the old data. I have never seen anything like that in practice, except an old open-reel tape recorder with a "trick recording" button which disconnected the erase head, allowing you to e.g. play an instrument and then record your voice over the top.

    --
    Je fume. Tu fumes. Nous fûmes!
    1. Re:I was alive in the 1980s by goombah99 · · Score: 2, Informative

      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 powered devices. It's the latter that allows flashram to get a commerical foothold around which it has matured.

      Mram is supposedly going to be faster then ram and consume less power. So it too may have a niche that eluded bubbles. it's main competitor is not flash or disk but ram I think.

      --
      Some drink at the fountain of knowledge. Others just gargle.
  30. Re:more vaporware by Anonymous Coward · · Score: 0
    Note also that Freescale has close ties to Motorola.

    In fact, they are the former semiconductor division of Motorola. They were spun off a few years ago.
  31. Slow Bubbles by Doc+Ruby · · Score: 5, Interesting

    I've been hearing about these kinds of devices since "bubble memory.

    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.

    --

    --
    make install -not war

    1. Re:Slow Bubbles by sgt+scrub · · Score: 1

      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.

      --
      Having to work for a living is the root of all evil.
    2. Re:Slow Bubbles by fdrebin · · Score: 3, Interesting
      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.

      Actually a simple alternative is quite feasible today - after a clean boot, write a "hibernate" image. At boot time, have the selection of the hibernate image as a boot option. 5 second boots!

      Not as good as your suggestion, but $cheaper.

      /F

      --
      Stupidity... has a habit of getting its way.
    3. Re:Slow Bubbles by claussenvenable · · Score: 2, Insightful

      The "Why" here is all about the read/write speeds of Flash memory... It's just not particularly fast.

      Flash memory doesn't "Blit" 512Mbytes over to RAM in a matter of milliseconds. More like a matter of minutes.

      And since the HDD already exists, you can just write your RAM to it a la "hibernate" and accomplish the same thing. Plus, your HDD doesn't have wear-levelling issues, and is already part of the PC, and costs orders of magnitude less. Try booting an embedded Linux system that has to pull its rootfs from NAND Flash. Takes for freaking EVER. All the embedded Linux routers out there use NOR for this reason. But NOR parts are slow to write, and aren't even manufactured in densities above about 32 Mbyte last I designed with them.

      With HDD read/write speeds at Gb/s, there's just not much advantage. MRAM, if it ever makes it to these scales, would be a real boon -- you could execute straight out of it. NAND Flash is too slow for that.

      If you're concerned about the time it takes to write the RAM image to HDD, you could try writing it continually, on-the-fly as you compute, but that seems like a recipe for disaster... eek.

    4. Re:Slow Bubbles by zippthorne · · Score: 1

      That sounds pretty neat. Do you know of any howtos geared to relative novices?

      --
      Can you be Even More Awesome?!
    5. Re:Slow Bubbles by fdrebin · · Score: 1
      That sounds pretty neat. Do you know of any howtos geared to relative novices?

      No, sorry, I don't. I mention it as a concept, not necessarily an existing implementation. Doesn't seem like it'd be overly difficult to do... might even be lying around out there somewhere. And as I use mainly Linux (work) and Mac OS X (personal), and keep my systems on UPSs, I rarely reboot.

      /F

      --
      Stupidity... has a habit of getting its way.
    6. Re:Slow Bubbles by Doc+Ruby · · Score: 1

      Fast NAND Flash will read at over 100Mbps (write doesn't need to be fast). Toshiba has had that part in 1Gb for over 2 years, so it's cheap now, especially in lower densities. Cheap enough to embed in a RAM stick with an ASIC that blits from separate Flash chips to separate RAM chips in parallel at startup. Which should restore the startup image to RAM in a couple of seconds or less. Upgrading the image in Flash is infrequent and low-performance, so Flash's write limitations aren't a problem. GBps HDs are largely wasted in PCs, hogging all the buses and CPU.

      You are correct that hibernate/HD is a cheap way right now. But that Toshiba part (and its peers) target mobile devices. Which is where most of our tech innovation is going. From where it will deploy to the smaller niches of workstations and servers. HDs are power hungry, noisy, heavy, failure-prone, fat, and better replaced by chips. Except in large network storage facilities, which will become even more popular as computing becomes even more mobile than the computers.

      MRAM has been appealing since the 1960s as a single tech for all storage, including executable and even archival. If they pull this off, finally achieving 3D volumes of cheap, fast density, we'll drop a lot of the bottlenecks that specific electronic tech has brought with it. Even more interesting, especially in the long run, will be the widespread deployment of electromagnetoptical devices for engineering the interplay of those fundamental forces. Jumping through electronic hoops like hibernate/HD will be as obscure as magnetic core memories.

      --

      --
      make install -not war

    7. Re:Slow Bubbles by TeknoHog · · Score: 1

      I use Suspend2 on my laptop for conventional hibernation. It's possible to keep old images and choose an image on bootup to achieve what you describe, but there's at least one catch with mounted filesystems. If you have filesystems mounted at hibernation (which is usually the case), you cannot change them until you resume the OS. So if you boot with an old image that assumes some old disk contents, you will corrupt disks.

      So, I think what you want is to save the image before anything is mounted writable, sometime early in the init process. I believe you could use suspend2 for this with only userspace modifications.

      --
      Escher was the first MC and Giger invented the HR department.
  32. A major limitation... by michaelvkim · · Score: 2, Interesting

    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.

    1. Re:A major limitation... by vertinox · · Score: 1

      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

      Um... Data is stored as magnetic bits on regular hard drives. Having it on a chip instead of a platter still haves the same problem, but most people don't seem to have that much of a problem with not sticking magnets inside their computer case.

      Back in the mid-90's, in my highschool and we had one of those floppy disk eraser/bad sector fixers for our 5 1/4" because they used to cost so much to fix and the teacher would have the computer club members help out and earase disk with this device.

      However, this device could be used on say... Hard disks and monitors with various "halarity-ensuses" type of events.

      Did you know a powerful enough magnet can leave a permanent discoloring and distortion on a Gateway 2000 monitor... Fun times.

      --
      "I am the king of the Romans, and am superior to rules of grammar!"
      -Sigismund, Holy Roman Emperor (1368-1437)
  33. Re:I bet it's hard to make it very small by Kythe · · Score: 2, Informative

    Since magnetic fields from the electric current in write lines decrease as the square of the distance from the lines, you don't have to worry all that much about crosstalk at write time, either.

    Oops -- slaughtered that one, didn't I? It's been too long since I looked at the equations. Straightfoward Ampere's Law: the decrease is linear, not with the square of the distance.

    Still, the decrease is significant enough, and the resistance to switching state high enough, that you don't generally have to worry about write lines inadvertently flipping more than one bit.

    --

    Kythe
  34. too much memory!!!!!! by Anonymous Coward · · Score: 0

    I wonder if it will run vista?

    640k is enough for anyone

  35. From the CNN writeup on this... by Experiment+626 · · Score: 2, Insightful

    "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

    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.

  36. Re:It doesn't quite seem to be (Re:) more vaporwar by OnlineAlias · · Score: 1

    Why all of the sudden did everyone start talking in Mbits for size of memory? It just forces one to convert it to a known quantity...please, for grandma, its a 500 meg chip.

  37. So?? by epp_b · · Score: 1
    ...allowing computers to start up faster when switched on
    So?? I thought Vista was supposed to boot up, like, instantly!!
  38. Great hard drive companion by egarland · · Score: 3, Insightful

    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.

    --
    set softtabstop=4 shiftwidth=4 expandtab nocp worlddomination
    1. Re:Great hard drive companion by Anonymous Coward · · Score: 0

      Making MRAM visible to file systems is a great idea, as is using MRAM for directory structures. You can even compress the heck out of the directory structures to save space. It doesn't take much time, and you can get a factor of 2-3 over "standard" Unix inodes. Check out http://www.ssrc.ucsc.edu/mram.shtml for more information.

  39. Core corrupted by davidwr · · Score: 2

    Everything old is new 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.

    --
    Knowledge is how to play a game, intelligence is how to win, wisdom is knowing what game to play.
    1. Re:Core corrupted by kintin · · Score: 1

      You know, I was about to go on some huge environmental rant about how "people like you are the ones killing because you don't want to wait 90 seconds for your computer to come on." But then I did a little research and found out that turning your computer off at night isn't much different then letting it sleep. Of course, the computer has to be configured to do this, but it's not all that complicated. Now, I'm sure that if the quad-zillion computers around the world were all turned off at night (Energy Star says that minimal usage is 2.3 watts) as opposed to just sleeping, that's 2.3 quad-zillion watts saved. But such mass conformity is unreasonable.

      I do, however, take issue that it's "bad" for reboots to be perceived as a pain in the ass. I would encourage users everywhere to complain loudly whenever they have to reboot, specifically to the authors of whatever software forced it upon them. I think the more people that find things unacceptable (IE's implementation of CSS, for example) and refuse to abide them, the more things either get fixed or replaced. This goes quad-zillion-double for reinstalling the OS.

  40. For Some Reason... by Valthan · · Score: 1

    I just don't think they will ever be able to make the capacity big enough to hold an install of Vista and all of the security updates associated with it, and that is just the OS, no programs, those would be on a separate solid-state platter... :P

    --
    --Valthan
  41. Experience with core memory by Anonymous Coward · · Score: 0

    Cores were quite far apart compared with the size of the core. Making the domains hard to switch protects you from external fields. That's desirable for keeping your credit card from being erased by random magnets. It doesn't provide much benefit for making cores dense. (It does provide a stronger pulse on the read line though.) Hard to switch domains mean that you need a bigger field to switch them. Thus, it doesn't mean that you can place the cores closer together.

    The magnetic domains on a hard disk platter are quite close together but the disk doesn't have to contain circuitry with its resultant currents and fields. The hard disk successfully keeps all fields adjacent to the gap in the head.

    The other limitation is actually thermal. The heat generated by the current necessary to switch domains causes thermal vibration that can cause the domains to switch. If the domains are harder to switch, the current goes up and so does the heat.

    1. Re:Experience with core memory by Kythe · · Score: 1

      It all depends upon the strength of the applied magnetic field, either from an external magnet (e.g. another spin valve or "bit") or from a write line.

      If it takes a higher demagnetizing field to flip a domain, then logically, you can place the domain closer to the source of a field of equal strength (e.g. another domain).

      As for the heat, well, that's going to remain a problem, but given the switching time (on the order of 1 ns has been reported), you're not talking about applying a whole lot of energy overall, and when considering the Tc values for the materials generally used, I'd be surprised if it were that much of a problem.

      But I'd be interested in any research or numbers on the subject.

      --

      Kythe
  42. I'd rather see MRAMs used ... by constantnormal · · Score: 2, Interesting

    ... 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.

  43. Found the datasheet... by jcr · · Score: 4, Informative
    --
    The only title of honor that a tyrant can grant is "Enemy of the State."
    1. Re:Found the datasheet... by stefanb · · Score: 2, Informative

      Two clicks away from freescale.com homepage, instead of your nice ad-loaded page, and with quite a bit more info.

    2. Re:Found the datasheet... by jcr · · Score: 1

      instead of your nice ad-loaded page,

      Not my page, dude.. It was the first one I found when I googled for the part number.

      -jcr

      --
      The only title of honor that a tyrant can grant is "Enemy of the State."
  44. Unfortunately by Flying+pig · · Score: 3, Informative

    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.

    --
    Pining for the fjords
    1. Re:Unfortunately by arthurpaliden · · Score: 1

      No, but I remember entering in a boot loader by flipping switches.

  45. Re:Vaporware by treeves · · Score: 1
    from another FA (French Spin-off Plans MRAM Production - 6/27/2006 - http://www.reed-electronics.com/electronicnews/art icle/CA6347413.html)

    "Crocus [Technology] is moving toward first production devices. The aim is to create a first memory, test vehicle in the next 12 months and its first commercial product should follow "shortly thereafter." "We now have everything we need to be the first to bring to the marketplace a competitive MRAM memory that will fulfill the customers' expectations, in particular with regards to reliability, speed and capacity," said Braun. MRAM has been pursued for over a decade as a promising non-volatile memory technology by major companies including IBM and Infineon Technologies without making it into the mainstream memory market. However, the technology has never been made to match the density of flash or DRAM because a single MRAM memory cell has had to consist of multiple transistors and multiple magnetic tunnel junctions. When Cypress Semiconductor sold its MRAM business last year after successfully sampling a 256Kbit device, CEO Rodgers commented: "We no longer believe 1T-1MTJ MRAM technology can successfully attack the SRAM market, leaving MRAM as a niche technology with higher bit pricing than SRAM." Earlier this year researchers in Maryland's John Hopkins University made a breakthrough in MRAM design by shrinking the storage element of ring-type MRAM to less than 100x100nm per bit. MRAM requires a magnetic structure with two stable magnetic states manipulated predictably. One structure, for which read and write techniques are already established, is the ring in which magnetism can run around in either a clockwise or anticlockwise direction. Experiments so far, using bulk read and write to billions of rings on a substrate, indicate a ring-type MRAM would be fast. According to the research, MRAM read time can be 1ns and write time is 0.8ns."
    --
    ...the future crusty old bastards are already drinking the Kool-Aid.
  46. I think I will just go back... by s31523 · · Score: 1

    to my good ol' vaccum tubes!

  47. IIRC thre's a minimum size.... by Ancient_Hacker · · Score: 1

    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.

    1. Re:IIRC thre's a minimum size.... by cyfer2000 · · Score: 1

      A ferromagnetic domain can be as small as 20nm in diameter or even smaller and stable at room temperature. A reference can be found at http://www.biophysics.uwa.edu.au/STAWA/magbac_5.ht ml. This size is way smaller than current fabrication limit.

      Also, only two magnets are required to form a magnetic tunneling junction in the MRAM. While pretty complicated circuit is need to store one bit in DRAM.

      --
      There is a spark in every single flame bait point.
    2. Re:IIRC thre's a minimum size.... by Ancient_Hacker · · Score: 1
      Whew, that is small. But there isnt a clue in that article, or others like it, whether these small domains are stable, easily settable, reliable, or how much ancillary circuitry is needed to control them, or how much space you need around each domain to prevent neighboring cells to bleed into each other.

      By contrast, the dram cells are known to work well, require only miniscule cell walls, require only ONE small and simple transistor to read/write/refresh. And the basic patents have run out so royalty costs are low.

      I'd love to see them work, but still IMHO there's LOTS of hurdles for these magneto-thingies to be practical.

    3. Re:IIRC thre's a minimum size.... by cyfer2000 · · Score: 1

      A basic structure of MRAM can be found at http://www.research.ibm.com/resources/news/2000120 7_mramimages.shtml, no transistor is needed to read or write, no refresh need, :-) The space need to seperate two domains should be in the scale of Angstrom.

      Right, there are too many troubles around fabrication of MRAM, mostly in the deposition and etching of multiple magnetic metal layers. But at least it is selling commercially, so it is practical now.

      --
      There is a spark in every single flame bait point.
  48. Re:Vaporware by Macthorpe · · Score: 1

    I'll bite, if only to inform you that the first 3 links out of 4 of your 'proof' were not vaporware at all, not even at the time.

    Nice try.

    --
    "It does not do to leave a live dragon out of your calculations, if you live near him." - Tolkien
  49. Re:It doesn't quite seem to be (Re:) more vaporwar by barawn · · Score: 1

    Why all of the sudden did everyone start talking in Mbits for size of memory?

    Everyone always has. Go look at chip descriptions in Digikey, or anywhere else for that matter. They only get converted to megabyte, etc. at the end-user level. Mbits are useful if you don't care about the arrangement of the memory, because usually they specify 256Kx16, for instance, which is what this is.

    please, for grandma, its a 500 meg chip.

    It's a 512K chip. Half a meg.

  50. Nonsense by gweihir · · Score: 2, Interesting

    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.

    --
    Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
    1. Re:Nonsense by jafuser · · Score: 1

      I guess this product does not have any real application.

      I love how you picked the two most overhyped potential applications, combined them into one example, and then declared the technology useless because that one example doesn't seem practical.

      I suppose you've never heard of embedded systems or disk write caching?

      --
      Please consider making an automatic monthly recurring donation to the EFF
  51. Here's one niche application by Beryllium+Sphere(tm) · · Score: 1

    Hard disk write cache.

    How would you like to have a write-behind cache that's safe when the power goes out?

  52. Or Bubble Memory by jaxent · · Score: 1

    It was going to replace hard drives too. http://www.decodesystems.com/tib0203.html

    --
    "I was gratified to be able to answer promptly. I said I don't know." Mark Twain
  53. Obligatory by breckinshire · · Score: 1

    Yeah, but does it run Linux?

  54. Flash FS. Hm. How 'bout something actually used. by Valdrax · · Score: 1

    Wearout is a myth with modern flash filesystem software.

    How much of a myth is it when you use least common denominator, portable file systems like FAT?

    Until proper flash file systems go cross-platform (or just to the Windows platform), it's not necessarily a myth.

    --
    If it's for-profit but free, you're not the customer -- you're the product (e.g., the Slashdot Beta's "audience").
  55. Tesla by sinack69 · · Score: 0

    It's amazing that the most awesome ideas stem from the most basic ideas. I'm still amazed at how electricity works, and we continue to advance way beyond that.

    --
    http://www.thirdrake.com - Best Webcomic of all time.
  56. Yeah, but... by rsilvergun · · Score: 1

    OS's keep getting larger too. Vista's going to be 8 gig with a pretty barebones software library pre installed, and my last linux install hit about 6 or 7 gigs. For this to work, you'd have to get OS vendors to cut down their software, or at least segment it across drives. Both are pains to support and you'll have a hard time getting them to do it. Maybe for laptops (non-mechanical storage would be nice).

    --
    Hi! I make Firefox Plug-ins. Check 'em out @ https://addons.mozilla.org/en-US/firefox/addon/youtube-mp3-podcaster/
    1. Re:Yeah, but... by Millenniumman · · Score: 1, Funny

      my last linux install hit about 6 or 7 gigs

      And 70% of that was emacs.

      --
      Stupidity is like nuclear power, it can be used for good or evil. And you don't want to get any on you.
    2. Re:Yeah, but... by sketerpot · · Score: 1

      Wrong, asshat. Emacs is remarkably lightweight by modern standards. Stop repeating stuff that hasn't been true for over a decade.

    3. Re:Yeah, but... by Millenniumman · · Score: 1

      I was joking. The lesson here is: Never underestimate the fervor of a Linux user regarding his chosen text editor.

      --
      Stupidity is like nuclear power, it can be used for good or evil. And you don't want to get any on you.
    4. Re:Yeah, but... by russotto · · Score: 1

      Even we Emacs partisans make fun of its size.

      I remember when Eight Megs And Counting Still was an indictment of its gluttony rather than a celebration of its parsimony...

    5. Re:Yeah, but... by Fordiman · · Score: 1

      Meh. My last linux install was 500M. It still won't fit in 512k.

      --
      110100 1101000 1101000 1100110 0 1101111 1101000 1100011 1
    6. Re:Yeah, but... by sketerpot · · Score: 0, Offtopic

      The lesson here is: when repeating variants of jokes that were tired and old years ago, make sure that they aren't based on ridiculous premises. Would you like to hear my Prohibition jokes? They're so timely and relevant!

    7. Re:Yeah, but... by maxwell+demon · · Score: 1

      I knew that as Eight Megabytes And Continuously Swapping.

      --
      The Tao of math: The numbers you can count are not the real numbers.
  57. Similar concern by darthservo · · Score: 1
    I was wondering something similar. Magnetic storage worries me enough with hard drives (more paranoia than realistic fear, probably).

    While MRAM's speed and power consumption outperform DRAM and Flash, I still don't know if I'd be fully comfortable with MRAM replacing devices specifically built for portability and ease of use. If these are to replace current uses for other types of memory such as Flash, would we have to worry about close proximity with anything magnetic? Would I not be able to carry my MRAM based phone, MP3 player, or USB drive in a single pocket, or nearby pockets?

    --

    Prove it.

  58. Well, think after a while by Moraelin · · Score: 1
    So?? I thought Vista was supposed to boot up, like, instantly!


    Yeah, well, wait until the user installs some 100 pieces of spyware on it, because he still doesn't read dialog boxes before clicking "Yes". Add a few viruses, trojans and spam zombies as he still believes that all those people sending him .exe attachments actually are some long lost relative/friend/business-partner/whatever. Add a gazillion crap that insists on pre-loading itself. (Yay for making a crap program seem like it loads faster, by loading itself in memory from the start. Surely the user has _nothing_ better to do with their RAM than keeping some crap programs pre-loaded.) Etc.

    Now watch that machine take 15 minutes to boot and load all that crap.

    Now imagine having MRAM. Imagine just hitting the power button and _instantly_ having all that spyware up. I mean, wow, the monitor is just finishing warming up and you already have your first pop-up windows waiting to sell you "H3rb@l \/i@gr@" or penis enlargement pills or "Hundreds Of Barely Legal Teens Waiting For You!!!" In fact, one has already taken the liberty of opening your browser and redirecting it to that site already. All before even the monitor warmed up. Now _that_ is progress :P
    --
    A polar bear is a cartesian bear after a coordinate transform.
  59. thank you by deevnil · · Score: 1

    What don't ppl get about having their os on a ramdrive that can survive a reboot. Mine is on a 15k disk, thanks to this attitude that hard drives need to be at least a terabyte I was able to pick up a 15k disk brand new for 75$. suckahs.

  60. 6 years ago I bought a 16 megabyte flash card by rebelcool · · Score: 1

    Then I splurged, and bought a 32! It cost $50. Today, $50 will get you a gigabyte.

    My camera today cannot even store 1 picture on a 16 megabyte card.

    If this technology accelerates anywhere near the pace of flash (and considering the usefulness of it in all kinds of fields, it may), we'll all be using mram or similar in a few years and look back at DRAM as those quaint old days, much like using floppies...

    --

    -

  61. Embedded systems by swg101 · · Score: 1

    For embedded systems, the really big draw here is the speed. EEPROM is great, but you have to have long delays after writing (~10ms usually) where the data sheet from freescale shows the entire write cycle at less than 35ns! That, plus true random access writes (unlike the Flash page read/modify/write method) is great news for embedded systems developers.

    --
    Like pi? Try 10,000 digits.
  62. Re:Flash FS. Hm. How 'bout something actually used by julesh · · Score: 3, Informative

    How much of a myth is it when you use least common denominator, portable file systems like FAT?

    A decent flash disk will have write-spreading as a layer on top of the filesystem, so it will remap sectors on the fly to avoid wearout.

  63. Re:NOT a hard dri~#**snarf by deviceb · · Score: 1

    I like my memory the way it is. Just make me a cheap solid-state hard drive & stop beating around the bush. The whole RPM thing on hard drives has to go.
    No moving parts.
    I heard this same story back in the 90s when a friend I know invested in a similar company with what sounds like exactly the same product. Wonder-ram that never looses its memory! It also never came out due to whatever issues, perhaps marketing. And all the investors lost there loot. -and that's my story

    --
    Kill your TV
  64. MRAMs are power hungry and low density by erice · · Score: 1

    * 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

    Not at present. MRAM's have a problem with cells influencing and flipping the values of their neighbors. To combat this effect, designers have resorted to using some rather complex shapes that are difficult to scale down.

    * much less energy-hungry than SRAM, DRAM and Flash while working; when not working it can keep information at least as well as Flash

    No way. Current MRAM devices read by sensing current. They are much more power hungry than DRAM, SRAM, or flash.

    To summerise, MRAM's

    - High Power
    - Poor density
    + Non volitile
    + Radiation resistant

    The last one is what is driving current consumption. They are used in space appliations. The first two are deal breakers for most non-space applications. Major breakthroughs are required before you see MRAM in your desktop or notebook.

    1. Re:MRAMs are power hungry and low density by Gadzinka · · Score: 1

      I was talking more about theoretical limits of underlying physics, rather than practical problems of current technology. Which it has many. Just check how promising (not!) DRAM was after 10 years of development. I bet there were lots of people back then who discouraged everybody from investing in this nonsense, niche novelty instead of using tried and true core memory ;)

      Robert

      --
      Bastard Operator From 193.219.28.162
  65. haha by andreyw · · Score: 1

    Gee I hope Motorola execs start biting their knuckles sometime soon. Those knuckleheads managed to spin off what's probably the last innovative and profitable division they had. Now they just make crappy phones.

  66. Supercomputer applications by zymano · · Score: 1

    This would work nicely with supercomputers.

    Maybe this could increase speeds by x2 ?

  67. Good, bad and ugly core memory by WebCowboy · · Score: 1

    The great thing about core memory was its tolerance to water.

    Core memory is also immune to electromagnetic radiation--and EMP would wipe out conventional memory but ferrite cre memories would retain their data. IIRC spacecraft make use of core memory in certain applications to this day for that reason.

    Core memory is nasty in some ways too--besides being bulky and a bit slow and reads being destructive operations they were temperature sensitive--the current required to flip bits varies with temperature. If you used core memory in an environment where temperature varied too greatly you'd have to include a feedback loop with a thermistor to control the current level used to drive the address lines. I'm kinda like Woz...all that messy analogue stuff makes my brain ache and I like to avoid it. I'm glad that new magnetic memories don't require this sort of messy stuff.

  68. MmmmmRam! by Treacle+Treatment · · Score: 1

    I understand this is what Windows Vista says the first time it fires up... "mmmmmm, ram". Feed me Seymore!

    --
    TT
  69. Re:Flash FS. Hm. How 'bout something actually used by Derek+Pomery · · Score: 1

    And it seems to me that actually FAT32 is superior for this purpose because it does not try reordering the filesystem to "defrag" it like an inode one would. And since the fragmentation that occurs with FAT32 can be ignored in a random access space like a flash drive, it really does seem ideal?

    --
    -- perl -e'print pack"H*","6e656d6f406d38792e6f7267"' /. ate my old sig. Bastards.
  70. Like ROM? by John+Bokma · · Score: 1

    "Mram chips could one day be used in PCs to store an operating system, allowing computers to start up faster when switched on."." Like ROM did many many years ago? I mean, Acorn Archimedes: power switch on: .... beep, and presto, the desktop. Modules could be upgraded by loading them of harddisk, or buying a new ROM set (or burning your own).

  71. Re:in the market for a USB key by WhatDoIKnow · · Score: 1

    I don't think you could even find a USB flash drive as small as 32MB any more. You can get a 256MB or 512MB from ebay for $15-$30 or so. What are you waiting for?

  72. Core memory! What's next? by FeatherBoa · · Score: 1

    Now that we have someone trying to make core memory new again, what's next?
    Miniature mercury delay lines in the next iPod?
    I'm going to hold out for the new storage-scope notebook.

    Whatever happened to bubble-memory anyway? It looked cool under a microscope.

  73. Security issues with keeping OS data in MRAM by Anonymous Coward · · Score: 0

    Anyone thought about this yet? I'm no expert but it sounds like having the OS constantly loaded into MRAM would be a trojan writers dream.

  74. what the fuck? admins, ban this twat by Admins+ban+this+twat · · Score: 0, Offtopic

    what the fuck? admins, ban this twat

    --
    what the fuck? admins, ban this twat
    1. Re:what the fuck? admins, ban this twat by joshier · · Score: 0, Offtopic

      what the fuck? admins, ban this twat!

  75. not just faster... by Anonymous Coward · · Score: 0

    allowing computers to start up faster when switched on.'" ...and malware to stick better too.

  76. totaly off topic here by Mycroft_VIII · · Score: 1

    RE: your sig.
    I pretty much think web sites that lock crap down how they liked it (I assume drunk and on 1322x906 or other odd res monitor) are bad myself, ESPECIALLY the ones that do the whole microtype thing.
    However if you're not stuck using IE or some other braindead browser you can get around this. I set firefox up to enforce MY prefered minimum font sizes ( also CTRL+ and CTRL-).
        Just a thought I hope helps.

    Mycroft

    --
    https://signup.leagueoflegends.com/?ref=4c3ed6600b6ea
  77. Re:Vaporware by Anonymous Coward · · Score: 0

    16 mbit ain't 16 meg.

    It is only 2megs.

  78. OT: Your sig by A+Name+Appears! · · Score: 1

    It sounds brilliant, could you provide a reference?

    Thanks in advance.

    1. Re:OT: Your sig by Flying+pig · · Score: 1
      It's from Edna St Vincent Millay. Sonnet begins "Euclid alone has looked on Beauty bare...". The final lines are

      Euclid alone
      Has looked on Beauty bare. Fortunate they
      Who though once only and but from far away
      Have heard her massive sandal set on stone.

      I had an Eureka moment last week...it is far from her best sonnet, though.
      Google the first line, it is all over the Internet (so much for copyright)

      --
      Pining for the fjords