Slashdot Mirror


Matrix 3D memory is World's Smallest

nokiator writes "Most of the headlines about cool new high density memory technology are from DRAM or Flash manufacturers these days. Matrix Semiconductor, a small Silicon Valley start-up, broke the trend today and announced that the world's smallest 1-Gbit memory chip. Matrix's chip is an antifuse-based one-time programmable ROM. The total die area of the 1Gb chip is 31 square millimeters (smaller than the blue/red pills in the Matrix movie). Matrix claims that they can achieve this density through a proprietary 3D circuit technology that combines 150nm and 130nm process geometries. When Matrix moves to 90nm process technology, it should be possible to manufacture a 8Gb memory chip on a reasonable sized (i.e. cheap) die. There are many potential applications of this kind of low cost, very high density ROM technology, mostly in content distribution area. One 8Gb ROM chip would have sufficient storage capacity to store the contents of an entire movie using H.264 encoding."

42 of 183 comments (clear)

  1. Sweet! by AKAImBatman · · Score: 4, Interesting

    I can think of one use right off the top of my head. Anyone remember the console design I suggested? Well, if these chips are cheap enough, it may actually make sense to go back to cartriges! Which means that copious quantities of graphics (including videos and prerecorded music) could be used in games for an inexpensive console system!

    Anyone else have any good ideas for this chip?

    P.S. Definition of an antifuse. Usually the type of thing you only learn about when you're playing with FPGAs, ASICs, and CPLDs. (The "history of programmable hardware" book that comes with Xilinx's Starter kit gives a good overview of the different technologies including antifuse chips.)

    P.P.S. If I'm doing my math right, 1-GBit of memory is ~119 megabytes. 128 megabytes if you're calculating 1-GBit == 2^30.

    1. Re:Sweet! by Short+Circuit · · Score: 4, Informative

      A CD/DVD's data area is around 10,000mm^2. That's enough area for 343 of these chips at their current size. 343*128MB=42.875GB

      A better arrangement would be to make a 5" (127mm) square cartridge to fit in the same stackable region as a 5" circle. That gives you 520 of these chips. 520*128MB=65GB, which is better than Blu-Ray, and nowhere near as fragile.

      And that's on their current process, which is apparently a blend of 130nm and 150nm. Wait until they shrink that down a bit.

      Data density in the world has just gone up.

    2. Re:Sweet! by AKAImBatman · · Score: 2, Interesting

      I don't know about that. 128 megabytes is very small compared to the size of games today.

      If you read the post I linked to, the idea was to bring back classic gaming at a low price point, not compete with today's games. I was originally thinking games along the lines of Duke Nukem II and Halloween Harry. But with this chip, we could jump all the way to Super Wing Commander! (With better voice acting, of course.)

    3. Re:Sweet! by kesuki · · Score: 4, Interesting

      Well, if these chips are cheap enough, it may actually make sense to go back to cartriges!

      For classic gaming maybe, for portable gaming sure. but you'll never get the price of solid state memory below the cost of optical storage. you can deal with the problems optical storage has currently by moving the laser beam with microscopic mirrors, rather than trying to spin the media. The problem with optical media is and was that they used design principals that work great for Magnetic media, and tried to pair that technology with optical storage. Since light can move exponetially faster (light can be moved to read 299,792,458 meters of data per second) than any physical device, it makes massively more sense to move the light, rather than the media or the laser. At current data densities.. that means the entire content of a DVD-rom would be read in 1/19933rds of a second. In other words, you'd have a 14,351,760x DVD-rom if instead of moving the DVD you move the laser light, and managed to move the laser light at the speed of light. There are of course scienitific limitations that prevent us from manipulating a beam of light in order so that it is redirected at the speed of light, but the theoretical limits of rotational speeds for DVD media are being reached. You can probabbly spin them faster than 16X, I seem to recall that at 1x a DVD-rom is moving the disc at the same rotational speed as 4x cdrom would be rotating and cd-roms got as high as 52x before cheaper media began fragmenting in peoples drives..

      So what would you rather be capped with? 18x dvd-rom drives? or not have to worry about the engineering limitations until you can figure out a way to reach 14,351,760x?

      Note: to those wondering, I based my calculations on the assumption that a dvd-rom has 4.7 billion bytes or 37.6 billion pits .4 micrometers apart, for a total length of 15,400 meters. I then used the knowledge that at 1x it takes 2 hours to read that distance, and calculated the speed rating based on that. I didn't check my math twice, so I might have made a miscalculation, but if I did someone will probably coreect me.

    4. Re:Sweet! by jerde · · Score: 3, Informative

      You're not trying to say that the speed of light has ANYTHING to do with the speed at which a beam of light can be swept across a medium, are you?

      A point of light can be moved as fast or as slow as you want it to be. Aim a laser at the moon, now sweep it across the moon as fast as you want. Poof! The "spot" of light just moved across the moon at 18 times the speed of light... no problem.

      No, the real limitation to the speed at which light can be moved along a medium has more to do with how long the spot of light must be focused on each point on the medium for enough photons to reflect back to be read. The faster you sweep your laser across a surface, the more dimly that surface is illuminated.

      (At the limit, you're moving the spot of light faster than the rate photons are being emitted, although at 1 Watt that's something like 10^20 photons per second. If you need at least 10 photons per nanometer, say, you can do the math to find your maximum speed.)

      --
      INsigNIFICANT
    5. Re:Sweet! by mr3038 · · Score: 2, Informative
      Two things:
      1. The point where ray of light hits a surface can move faster than light. Information (light) goes from light source to surface or the other way around but it doesn't go from one surface location to another so you're not limited by the speed of light
      2. You have to remember the little thing called wavelenght. You cannot read details smaller than the wavelength. The smaller the angle the ray of light hits the surface, the fussier the surface seems to be. We're going towards blueray laser systems because normal laser has too long wavelength even for next generation spinning disk technology.

      If it wasn't the cost, one could make a pretty high speed optical reader by creating 12cm x 12cm CCD chip capable of reading every single pit in the surface of DVD disk at once. It would be just like a flat bed scanner, just faster. Scanning the whole disk would take 1/100th a second at most. Then it would be just matter of moving bits from the CCD chip to system memory fast enough. I won't even try to guess how much a 12cm x 12cm CCD chip with enough resolution to contact read a DVD disc would cost.

      --
      _________________________
      Spelling and grammar mistakes left as an exercise for the reader.
    6. Re:Sweet! by stonecypher · · Score: 2, Interesting

      For classic gaming maybe, for portable gaming sure. but you'll never get the price of solid state memory below the cost of optical storage.

      You know, it's funny: I remember someone saying exactly the converse of this to me about fifteen years ago, when NeXT adopted the laserdisc as a standard storage mechanism for the Cube, back when ROM was considered cheap.

      The older you get, the less likely you are to use the word never, especially in regards to the future.

      --
      StoneCypher is Full of BS
  2. Now, with an infinitely redundant power supply by Trizor · · Score: 4, Funny

    I can ramdisk the internet. I just need a warehouse!

    1. Re:Now, with an infinitely redundant power supply by AKAImBatman · · Score: 4, Informative

      I can ramdisk the internet.

      Except for the fact that this is ROM. It makes use of antifuse technolgy which works a lot like fuse technology. The idea in fuse technology is that you blow the pathways you don't want, thus creating the circut. With antifuse technology, the fuses don't normally conduct electricity so you have to blow the fuse to create pathways.

      Info

  3. Oh good by Anonymous Coward · · Score: 5, Funny

    The total die area of the 1Gb chip is 31 square millimeters (smaller than the blue/red pills in the Matrix movie).

    Just what I always wanted - another unit of measurement. How many millifootballfields is one blue pill? What can this chip hold in terms of LibrariesOfCongress-per-BluePill?

  4. USB Linux-on-ROM by Short+Circuit · · Score: 3, Interesting

    I could do with seeing one of the fortold DVD-based Linux LiveCDs expanded even further and put on a read-only USB stick.

    Oh, and it's OTP? You mean, like CD-Rs and DVD-Rs?

  5. Comment removed by account_deleted · · Score: 4, Funny

    Comment removed based on user account deletion

  6. Nice....... by compmanio36 · · Score: 3, Interesting

    Maybe this will help the emergence of solid state memory, as I find something like a Compact Flash card much more handy than a CD. I have had more DVD's that just wouldn't play because of the tiniest scratch on them. No, if there was a slightly more expensive, but much more reliable and robust form of memory storage, I would snatch it right up. Of course, I am waiting for my crystal-based isolinear memory chips that can hold gigaquads of data (whatever the hell a gigaquad is).

  7. Not just ROM's by Transcendent · · Score: 3, Informative

    ...but could this be used for CPU on-die caches, or is it too slow/consumes too much power? I couldn't imagine even having 8MB of cache let alone 8GB. (Which will come to haunt me later like the ol' 640K quote).

    1. Re:Not just ROM's by Short+Circuit · · Score: 2, Informative

      The technology dictates write-only. Even with a sliding write window ala multisession CDs, it wouldn't be useful as a cache.

    2. Re:Not just ROM's by Anonymous Coward · · Score: 5, Funny

      Read only. Cache.

    3. Re:Not just ROM's by antifoidulus · · Score: 2, Informative

      A lot of Sun workstations already have 8 mb of L2 cache, for instance SunBlade 1000s. However, they like pretty much every other commercial chip in wide use(P4, Athlon, G4, G5 etc) all have 64k l1(32k data 32k instruction).
      But more to the point, did you RTFA? This is anti-fuse technology, ie it cannot be re-written. I guess you could have certain chunks of data that you need to reference again and again that won't change, but for that limited use why would you ever muck up your architecture?

  8. Re:one movie? by Short+Circuit · · Score: 2, Informative

    Try 10 * (1 byte / 8 bits), or one movie. GB is different from Gb.

  9. Density is fine, but speed ? by karvind · · Score: 5, Informative
    What is the latency of this memory module ?

    Secondly it is antifuse-based one-time programmable ROM. It is NOT a flash which can be re-written 100,000 times. So it is more useful for storing application code but not for data storage etc.

    Antifuse base memories are diode like and can be much smaller than regular FLASH memories. But these are inherently slower and also don't have any gain element (like transistor). This requires careful design to achieve good signal-to-noise ration for memory read operation

    More aggressive 3D technology was demonstrated by IBM last year where they have circuits in 3D.

    A startup R-cube logic is also designing 3D microprocessor where memory is put on top of the logic core to reduce latency.

    Xanoptics is more into hybrid design (mixed analog, RF, optics) on a single footprint.

    1. Re:Density is fine, but speed ? by mcc · · Score: 2, Interesting

      Secondly it is antifuse-based one-time programmable ROM. It is NOT a flash which can be re-written 100,000 times. So it is more useful for storing application code but not for data storage etc.

      Sounds great for something like a handheld video game system off the top of my head though. Handheld games are really hurting right now for need of some kind of compromise between hi-latency powerhungry high-capacity discs and low-latency power-cheap low-capacity ROM cartridges...

  10. Some foresight required by motorsabbath · · Score: 3, Insightful

    One 8Gb ROM chip would have sufficient storage capacity to store the contents of an entire movie using H.264 encoding.

    Great, more disposable consumer things. There are many great uses for such a memory config, but the world does not need more disposable devices...

    --
    The heat from below can burn your eyes out
  11. This could actually be bad by RhettLivingston · · Score: 4, Insightful

    ROMs can be very cheap. If they get to 8Gbit and then put it in a multichip stack to get to 4 or 8 GByte capacities, it could possibly give the movies on DVD industry a run for its money. The bad side of that is that we've been benefiting heavily from the demand that that industry has created is responsible for providing cheap RO and later WO and RW DVD drives for our PCs. The movie industry would love this format because the WO and RW versions would always be way more expensive than the RO version. The cost equation of copying would change dramatically.

  12. Re:one movie? by EightMillion · · Score: 3, Informative

    8 Gigabit(Gb) == 1 Gigabyte(GB)
    Check your math.

  13. H.264 by after · · Score: 3, Interesting

    I didn't know what it was right away, so ...



    H.264, or MPEG-4 Part 10, is a high compression digital video codec standard written by the ITU-T Video Coding Experts Group (VCEG) together with the ISO/IEC Moving Picture Experts Group (MPEG) as the product of a collective partnership effort known as the Joint Video Team (JVT). The ITU-T H.264 standard and the ISO/IEC MPEG-4 Part 10 standard (formally, ISO/IEC 14496-10) are technically identical, and the technology is also known as AVC, for Advanced Video Coding. The final drafting work on the first version of the standard was completed in May of 2003.

  14. Amusing by StarManta.Mini · · Score: 3, Funny

    There's something inherently amusing about seeing this:
    Allow me to be the first to say... (Score:0, Redundant)

  15. Now, all we need are 3D Processors and RAM by Xeroc · · Score: 3, Insightful

    It sounds like to me this 3D Memory construction is vastly improving the density, now all we need are 3D-Constructed processors! They use vertically and horizontally stacked chips to multiply the processing capability.

    Also, if we could only get this in RAM! I'm looking for an upgrade, and my computer case is only so big!

    Yes, for some reason, people do seem to mix up the bits and bytes, for example: Most file sizes are in bytes, to make them seem smaller, and connection speeds are in bits, to make them seem faster!*

    *Actually, this probably isn't the "official" reason, but it makes sense!

    --
    "Real programmers don't comment their code. If it was hard to write it should be hard to understand."
    1. Re:Now, all we need are 3D Processors and RAM by koko775 · · Score: 2, Insightful

      Hmm. The problem is, though, 3D processors, unless redesigned, would have a far greater area:surface area ratio, which is bad, since the chip generates heat, and the surface area provides for its dissapation. I'm not saying 3D processors are impossible, it just adds a whole dimension to creating processors, as cooling has just gotten a lot harder. Also, antifuse won't work as RAM, unless you run Windows, in which case your computer, frozen forever, would work as expected (just kidding -- antifuse is write-once).

  16. Long time in the making...but worth it... by robertca · · Score: 4, Interesting

    Great to see the Matrix Semi news on Slashdot! I was one of the early employees (but have since left), so it's cool to see something that I worked on coming to fruition.

    Earlier posters were correct in stating that it's not a complete replacement for flash (yet?) but there are still many very cool potential applications: Game cartridges (much faster access time than CDs/DVDs), toys (i.e. a supercharged Furby with a massive vocabulary), replacement for CDs/DVDs, archival digital "film", etc.

    I really like the idea of a kiosk that houses blank Matrix 3DM cards and loads of digital content. You could walk up to the kiosk and buy a game/software/movie/album/book, have it programmed right then and there, and walk away with your customized content in a few minutes. These kiosks could be everywhere...gas stations, grocery stores, etc. Extremely convenient for consumers, plus it would seriously cut down the overhead for retailers since they wouldn't need to keep inventory or have huge stores to house thousands of DVDs, etc.

    1. Re:Long time in the making...but worth it... by robertca · · Score: 2, Insightful

      Matrix 3D is a fraction of the cost of flash. Also, while the semiconductor structure itself is proprietary (and heavily patented), the actual chip can be used in any sort of form factor, like SD, CompactFlash, etc. In other words, it can look exactly like your run-of-the-mill Sandisk flash card, but will function as a write-once media. The advantage of putting it into a widely accepted formfactor, like SD, is that it can then be used in any device that accepts SD cards at a fraction of the cost of flash...

  17. Gb somewhat aloof measurement? by gumpish · · Score: 3, Insightful

    I know that the bit is the atomic unit of measure when it comes to data storage and transmission, but sometimes I really wish everyone would stick to bytes.

    When I see 1 Gb I have to think for a second to get to 128 MB.

    1. Re:Gb somewhat aloof measurement? by kahei · · Score: 2, Informative


      Bytes are not always the same size; bits are.

      --
      Whence? Hence. Whither? Thither.
  18. 31 mm movies by Anonymous Coward · · Score: 3, Funny

    GUEST: Do you mind if I have some more m&m's?
    HOST: What m&m's? I don't have any m&m's.
    GUEST: In the bowl... on top of the tv...?
    HOST: Aaaaaaargh! That's my movie collection, nimrod!

  19. Smallest memory by Junior+J.+Junior+III · · Score: 4, Funny

    And here, I thought that I had the -- wait, what whas I talking about?

    --
    You see? You see? Your stupid minds! Stupid! Stupid!
  20. Matrix memory is for DS games by tepples · · Score: 2, Informative

    You're on the right track, given this press release, but you misspelled "Nintendo DS".

  21. Motherboards by charlie763 · · Score: 2, Insightful

    With the small physical size and large memory capacity might we eventually see a motherboard manufacturer shipping a Linux distro integrated into the motherboard? Not necessarily for the sake of using as you default OS, but as a distro with a full set of diagnostic tools. In any event, this sort of crap is way cool!

    --
    Welcome to the land of the free...pay toll ahead...no photography...please open your bag...
  22. Re:Matrix 3D? Where's the originality? by robertca · · Score: 2, Informative

    When the name originated in '99, Matrix consisted mostly of engineers. At the time, there was no budget to pay someone to come up with a name, so the engineers were assigned the task of suggesting names that would somehow reflect the technology. Sadly, none of my suggestions won, and I missed my chance to leave a legacy there. The winning suggestion came from one of the process engineers, who, as far as I can recall, received absolutely no compensation for it. So, there you have it: The name describes the actual structure, was coined by a process engineer, and cost the company precisely $0 to come up with.

  23. Re:Sweet! - you;re forgetting one thing by lcsjk · · Score: 2, Informative
    The problem is not the speed of light's round trip. The problem is that to move a beam of light, the light controller must sense position, tell the controller to move the light and then tell it when to stop and where it is at the time. Even if you are traveling along a straight line, the feedback mechanism still has to be there. The speed of the control electronics will be much slower than the speed of light traveling from a source to the reflections surface and back to the sensor. The speed of the electronics will be much faster than any type of mirror control available, including the microscale mirrors. And as the previous poster mentioned, you also have to position a sensor along with positioning the light source. This requires a lot of analog and digital circuitry and the speed/time envolved


    Perhaps the biggest advantage would be the ability to treat the array as random access instead of rotational access with the inherent rotational delay.

  24. Cool by midnight2038 · · Score: 2, Interesting

    Another great technology to be attacked by the RIAA, first in name "3D Matrix", and then for it's use!

  25. Re:but .. by zenst · · Score: 2, Interesting

    easy, changes will be stored on disc but you will still need the base rom image.

  26. Exponential? by Anonymous Coward · · Score: 2, Informative

    Just wondering, were you thinking when you said that light is exponentially faster?
    It is faster, but where have you pulled this exponential crap out of? You can have an exponential relationship between two variables. The speed of light vs the linear speed of a DVD has SFA to do exponents. It makes you sound like you have no clue.
    Big number =! exponential.

  27. obligatory ... by Thoguth · · Score: 2, Funny

    Guess I'll have to buy the White Album again

    --
    The requested URL /iframe/sig.html was not found on this server.
  28. on board base OS by displague · · Score: 2, Interesting

    Does anyone remember early PC systems that had memory cards with a read-only operating system? A friend of mine had one that had dos 5 (or the likes) and a sort of literal folder appearance gui with it.

    Rant begins. If we had ultra fast, high density ROM chips like this it might be nice to put the core of an OS onto the chip and only use the harddrive (or large RAM) for updated components. A new 'Windows' or 'Linux' system would be inserted into a little cube-tray on your computer . All your 3rd party applications would be left on the hard disk. Hrmm, or, the software could also be purchased on cubes like this. Maybe we end up with a daisy chain of USB2 attached cubes, or a cube-tray, each representing a DVD sized 3rd party application. This sounds more attuned to commercial software. Rant over.

    --
    Marques Johansson