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

 


Forgot your password?
Close
typodupeerror
×
Hardware

Magnetic RAM from IBM 153

Posted by CmdrTaco from the interesting-ideas-with-lots-of-buzzwords dept.
n8willis writes "ZDNet has an article about IBM's latest breakthrough, Magnetic RAM (MRAM) that actually works. The story is a bit fluffy, rolling out every possible buzzword (eg, wireless video will now be feasible due to faster RAM technology???), but the tech - in development since 1974 - is indeed going into production as we speak. Gotta hand it to IBM these days: copper interconnects, 200ppi LCD monitors and now this." I'll believe it when I can read/write from it.
This discussion has been archived. No new comments can be posted.

Magnetic RAM from IBM More

Magnetic RAM from IBM

Comments Filter:
  • Geez, from the questions here, such as "How will this affect my floppies/other media/hardware?" and "how will this be affected by my monitor/speakers?"

    I must only presume that none of you has ever heard of shielding.

    *GOOD* quality speakers and monitors (not the $20 speakers from compusa) have shielding that minimize the magnetic energy escaping the equipment. place your cheapo speakers against your monitor. if it affects the monitor image, then you know you bought crap.

    If things are properly shielded, you won't have interference or suffer any negative effects.

    Geez, you don't overclock without proper cooling, why would you think of using a magnetic storage media without shielding?

    (course, now all the tin foil hat freaks will come out and claim they were right all along....)



    A host is a host from coast to coast, but no one uses a host that's close

  • what this actually means (Score:5)

    by Rog12 ( 261558 ) on Thursday December 07, 2000 @05:20AM (#575664)
    Magnetic RAM, MRAM, is a non volatile memory with unlimited read and write cycles. It also has the potential
    to be very fast, and very dense.

    Virtually all products that involve digital electronics (which includes just about everything these days: computers,
    cellular phones, but also household appliances like washers, dryers, microwave ovens, refrigerators, and entertainment
    devices like televisions, CD players, VCR's...) need memory. The choice of memory has historically involved a tradeoff.

    Non volatile memories (memories that hold the information whether or not power is supplied) like EEPROM's can be
    expensive and may have long term reliability problems - you can read and write to them only so many times or cycles
    before you degrade the ability of the memory to "remember".

    Volatile memories (memories that hold the information only if power is supplied) can be static RAM's or dynamic RAM's.
    SRAM's (static RAM's) consume a lot less power than DRAM'S (dynamic RAM's), but take up a lot more chip area for a
    given memory size, so are a lot more expensive. Because cost is generally the driving force in electronics, DRAM's
    tend to have the highest volume of sales...they are the lowest cost, but consume a lot more power. In fact, to get the
    density in a DRAM, we use a simple capacitor as the memory device. A charge on the capacitor can represent a "1"
    and no charge can represent a "0". However, over time, the charge leaks off....losing all the information. To avoid this,
    the DRAM must be REFRESHED. Essentially, a REFRESH cycle involves reading all the information out, and then putting it
    all back in. Looking at a data sheet for a DRAM, the example has the 64 Meg DRAM needing to be refreshed every 64
    msec ...being refreshed over 15,000 times per second!

    That refresh cycle on the DRAM explains the much greater power consumption of the less expensive DRAM compared
    to the more expensive SRAM. While it may not be typical, a quick browsing through data sheets found a 64 M DRAM
    that consumed 1 Watt of power, and a 64 M SRAM that consumed less than 400 mW.

    An MRAM can have the density of a DRAM...and since cost goes with density, it is possible that an MRAM can have a
    cost that is competitive with a DRAM...but it will have much lower power consumption...effectively zero power
    consumption in the standby mode, which is the mode the memory spends most of its time in.

    The MRAM doesn't require the refresh of a DRAM, and has the nonvolatility of a EEPROM, but has reliability superior to
    the EEPROM. So, an MRAM may be able to replace DRAM's, SRAM's. amd EEPROM's, without involving any major
    compromise or tradeoff.

    It is hard to judge the improvement in the battery life of a cellular phone. With digital cellular phones used just
    sporadically for voice phone calls, the battery life now is very good, but might perhaps be doubled with an MRAM - this
    is just my guess, and may be way off. If the digital cellular phone is heavily used for phone calls, the power
    consumption involved in sending the signal out would tend to dominate over the impact of improved power
    consumption in the memory, and the impact on battery life might be minimal.

    However, future applications of wireless products like the cellular phone include adding more functionality beyond
    voice calls. For communication products, MRAM may make it possible to have access to the internet with the ability to
    get video in addition to data and voice.
  • The concept of a storage hierarchy for computers goes well beyond just main memory and hard drives. For example, on the smaller/faster end of things there are SRAM caches on chips and motherboard; on the bigger/slower end of things there are tape and CD backups. I think that though it is tempting for a programmer to throw out the storage hierarchy ("Everything is fast and big! Yay!"), they are with us to stay and serve a verry useful purpose.

    Ben
  • I'll believe it when I can read/write from it.
    CmdrTaco must be feeling cynical today. When have IBM ever announced a technology which doesn't work? Some more details from their site are here [ibm.com] and here [ibm.com].

  • Redux: Magnetic interference (Score:3)

    by Wise Dragon ( 71071 ) on Thursday December 07, 2000 @06:44AM (#575667) Homepage
    Will this memory be susceptible to magnetic interference from ordinary magnetic sources?

    (*Imagine*)

    The SmartFridge(tm)... A billion dollar effort by GE brings you a Fridge that remembers what you put in and take out, generates shopping lists for your agent software, and doesn't open after midnight.

    *enter a small child*

    "Oooh, this magnet stick to the fridge!"
    (future engineer here)

    SmartFridge orders 10lbs of Guacamole because its megnetic memory is scrambled like the eggs you can't have for breakfast because of the former.
  • Did you read that article? It points out that Honeywell's devices where 10 times slower and 256 times less dense than DRAM in 1997. Not even close to competitive. The article actually mentions the technology IBM are talking about (Magnetic Tunnel Junctions [ibm.com]):
    In March a team of IBM engineers led by William J. Gallagher and Stuart S. P. Parkin announced that it had constructed arrays of 14 bits from such tunnel junctions, as they are known. They have demonstrated bits that are as small as 200 nanometers wide and that switch in five nanoseconds or less, Gallagher reports.
    Of the other technologies mentioned, I haven't heard anything from Motorola and Ramtron's [ramtron.com] FRAM is also too slow by an order of magnitude for use in todays machines (70+ns access time) in place of SDRAM or RDRAM.
  • Yes it is. No it's not the first magnetic memory, that predates Honeywell's 1997 efforts too. But it is the first to use the particular technology involved (Magnetic Tunnel Junctions).

  • The differences: (Score:3)

    by Anonymous Coward on Thursday December 07, 2000 @06:47AM (#575670)
    1) It's integrated. Cores were a whole lot of tiny magnetic donuts, threaded into a two or D array by wires passing through the center holes. In most cases, three wires were used per core, X and Y selects and Read Out. Core memory arrays were enormous and they cost dollars per bit -- a small college I was attending in 1972 had ONE computer with just 16K-bytes of core memory. It sounds like IBM has worked out a way to grow the magnetic material and the read and write circuits on a chip--smaller and cheaper. (Whether it will ever be small and cheap enough to compete with other forms of non-volatile memory -- battery-backed static CMOS, EEPROM, and Flash -- is questionable. Let alone competing with DRAM, which would be necessary for many of those predictions in the article to come true.)

    2) In the 1970's there wasn't a good way to read a constant magnetic field electronically. So what they did for readout was to send out the erase (write 0) signals on the X,Y wires. If a core was 1, this caused a pulse on the Read wire. After reading, it had to write the data back. Now, there are silicon sensors that can directly read out a magnetic field, so I assume that IBM is building these into the chips and you don't have to erase to read.

    3. Power and interface requirements: It took a lot of power to write to those cores. Because of the erase-to-read, it took just as much to read them. They were low power only when you didn't use them. So the wire drivers had to use higher voltages than solid-state logic devices can handle, requiring level-changing interface circuits. The article doesn't say, but I would assume that the MRAM has much smaller magnetic thingies, requiring little power to switch, and can run at normal voltages.

  • The idea of a uniform storage device is interesting in the theory of computing. Buffers and all are great, but could we even think about the way we work with computers the same if they had a uniform storage system. The idea of allocating memory would change from being a buffer to that of temporary calculations, but moreover we would see a dramatic change in the way that the computer would operate - it would be simpler, certainly, but how would you divvy up the storage - all storage would be presumably permanent, so if the power went out, the state would be completely preserved, but if the machine crashed you'd have to reinvent the idea of a reboot to some sort of "intelligent" wiping mechanism, but a lock up would be permanent. (not really, but you understand what I'm getting at)

    I agree that it is a scenario unlikely to ever happen, but it has many problems like the one I've mentioned, should the appropriate "perfect" storage technology ever arise. These problems offer us insight into how other things work, and their solutions would perhaps help us predict and design things better in the long term.

  • That should be a pretty easy problem to solve. Just initialize a chip that can reset the RAM to 0. This isn't a very complicated process, it just needs to index every address and set it to 0. Since the power button is used to turn it on and off, one could have it set up so that if a user holds the power button down for 4 seconds, the motherboard will resets it's memory. Or, you could simply design a memory reset switch. Not a big deal.
  • Uhm 256 sounds pretty crappy considering they don't expect mainstream production for 10 years. By that time 256 meg will be meaningless. The average amount fo ram today is like 64 to 128 meg. it will only be about a year or two until the average is 256. In ten years i wiouldn't be surprised fi the average RAM per computer is like 2 gig.
  • IBM announced a colabrative effort with the US DOE to develop a "reactionless space drive" based on thier new MRAM technology. The idea came about when casing vibrations were observed during photoshop benchmarking of computers equiped with MRAM. Brokehaven researchers are modeling the effect in order to determine the optimum layout of memory slots for propelling laptops, spacecraft etc.
  • I hope this puts an end to Rambus, their patents, and their royalties very, very soon. I sure hope someone's had the foresight to keep MRAM patents out of the grubby little hands of Rambus.
  • This is like MS claiming to have invented a new technology when they came out with their "optical mouse".

    Well, they did. All previous optical mice required grids. Microsoft's mouse uses a camera and software capable of comparing images very quickly to determine speed and direction. A far cry from grid-based optical mice.


  • According to this article [eetimes.com] in EETimes [eetimes.com] and this press release [fujitsu.co.jp] by Fujitsu [fujitsu.co.jp], they have been producing their version ("FRAM") in volume since late 1999, and should be churning out 128KB parts even as we speak.

    The cool part is that it works by wiggling atoms around in the crystal structure:

    external electric field shifts Zr/Ti atoms in crystal to move away from electric neutrality

  • I'm not too worried about the various *nix servers we have here. It just seems our NT servers need to reboot every day or two.

    Well, rebooting them would return those servers to their frozen state right after the POST tests. That is, if the reason they reboot is because the NT boxes crashed and not because the NT administrators were told that it's good for the machine to reboot it every day or two ;).

  • I'll believe it when I can read/write from it.

    And he does not mean with a pen. :)

  • In other news... (Score:4)

    by Linux_ho ( 205887 ) on Thursday December 07, 2000 @05:23AM (#575680) Homepage
    IBM recently announced their astonishing, new, unprecedented breakthrough in MAGNETIC memory that ACTUALLY WORKS, (some old industry wags are referring to it as core, for some unknown reason). Shortly afterward, they announced a startling new breakthrough method of storing data by punching holes in cards, a development no doubt inspired by the efficient vote tabulations in Florida.

  • Speech recognition requires fast access to the memory and to the processer. Any speed bump in that chain decreases performance of the recognition at hand.

    Remove the weakest link in the chain, and all memory speed-reliant applications will improve, until the applications are re-written to heavily tax the new capabilities of the memory.

    That's what you weren't seeing. That, and IBM is infatuated with speech recognition (via voice for linux? it's available from alphaworks if you run a JDK.)

    A host is a host from coast to coast, but no one uses a host that's close
  • However, I don't see how this helps much with speech recognition or easier downloading as the article suggests

    I think they are trying to indicate how faster memory will make things like these work faster. They are probably trying to put things in perspective for the "common man". If they were trying to drum up interest, they should have said something like: "Hey, this will let you download more porn much faster!"
    The thing is, if this takes ten years before it gets to the point that this memory is cheap enough for widespread use (like it says in the article), then there will probably be something else with similar functionality already in place, and the whole thing will go the way of 8-track tapes.

  • Wired (Score:1)

    by krb ( 15012 )
    Wired had an article about this a few months back too... cool tech. Search the online archive.

    -k
  • Since it's been announced, you know that they have already submitted a patent application for the use of Random Access Memory storage via magnetism. Making them the sole distributor of said technology.

    Then again, if it takes them 10 years to get this out, their patent will be almost up. :)

  • D%$#it! spintronics.com is already registered.

  • a jointpress [ibm.com] release [infineon.com] which says "[IBM and MRAM partner Infineon Technologies AG [infineon.com]] believe MRAM products could be available commercially as soon as 2004."
  • Moderators, come on! This is not insightfull.

    MRAM won't be available soon, so the dilemna between RDRAM and DDRAM will be long forgotten.

    An Amulet processor while having very low power consumption (no clock) is not very powerfull so in a few years it would look very underpowered for a laptop, maybe a PDA would be a better place.

    Who cares about the need of a new motherboard, you wont see this until many years!
  • It also minimizes the chance for getting the crap kicked out of you if you know that your potential victim is armed.

    you are a bad-grammar poo poo head.

    It also minimizes the chance for getting the crap kicked out of you if your attacker knows that his potential victim is armed.

  • This is like MS claiming to have invented a new technology when they came out with their "optical mouse".

    Well, they did. All previous optical mice required grids. Microsoft's mouse uses a camera and software capable of comparing images very quickly to determine speed and direction. A far cry from grid-based optical mice.

    Yes it was a breakthrough, but it was invented not by Microsoft, but by Gary Gordon at HP Labs [hp.com]. I hope Microsoft had to pay a lot for the right to not mention HP in all the publicity.

  • And worrying about if a new motherboard will be needed in two years is insightfull??

    And if you believe the release-date of new product like this, then I have a bridge to sell to you.

    I don't care at all about this moderation system if you want to know.
  • One of the biggest bottlenecks on the internet occurs with routers and switches. Routers require very high speed memory. I imagine that having higher speed memory could increase the bandwidth of routers significantly, which, as a result will help to speed up the internet.
  • No power consumption on laptops... Imagine a laptop using this and an Amulet processor

    Not no power consumption. No power consumption when not reading or writing data. And that isn't even 100% sure, it may need sense and positiong circuits powered up for any sort of acceptable memory access time. For all we know the actual power needed to read and write may be far more then DRAM (or far less).

    We don't know what kind of memory this thing will actually replace until there is more info on operating power/speed/tempature, and storage tempature/duration, and density, and sheilding required (which is effectavly density).

    This could be the next DRAM, or the next FLASH, or just the next Bubble Memory.

  • One question: how would this apply to the majority of users? The only times i restart Windows (you know, the OS that the majority of computer users use) are when it crashes or when i install new software. Now my Linux boxes with this stuff be cool, but the problem still exists in the stability of the OS for most people.

    Well, if you're running a basic workstation (that is, nobody needs 24/7 remote access to it), You can save a fair chunk of energy by powering down your system without losing system state--a fair step up from current suspend methods, which basically need to write the contents of RAM to disk and then read and reinstate said contents to RAM (which can be a tricky/time consuming proposition.) Extend this tech to other components (processor, periphrials, etc) and you could eventually have a truly persistent-state computer, where the concept of "powering off" falls by the wayside, as power is simply siphoned when needed; since your computer wouldn't need a constant flow of electricity to maintain state, it could effectively draw zero power in an when idle, thus being (theoretically) as effecient as if it were off.

    So basically, in the short term, snapping the power on and off when you finish using the computer becomes a quick, simple thing to do. If you get a little visionary with this, you may not even need a power switch on your computer eventually. Funky thought, huh?

    $ man reality

  • My guess is that all computers equipped with this type of memory are going to have a hardware reset switch in case of crashes/freezes.

    Looks like Apple was ahead of their time again B-)

    DB
  • ...will it need shielding?

  • Hasn't this been done before? (Score:3)

    by RJ11 ( 17321 ) <serge@guanotronic.com> on Thursday December 07, 2000 @05:05AM (#575696) Homepage
    This is nothing new, they were called CORES, and they've been around since the '70s!!!

    This is like MS claiming to have invented a new technology when they came out with their "optical mouse".
  • Bubble RAM missed its window--other storage got bigger (in capacity) and faster not long after it came out. (Sort of like the "floptical"--I have one of those, wanna buy it? It's a big 20 Mbytes; I got along with a 20 M hard drive on my CoCo for a long time. :-)
  • Now, here's technology that we've needed for ages... all those poor shepards losing their sheep... now they can keep them all in place with a big magnetic ram... I didn't even realize that IBM was into genetic engineering...

  • I don't buy it -- seems to me that the major reason machines crash is some lousy program(mer) has hosed the contents of memory -- so you boot back up to have the same hosed memory contents -- this does not seem like a win.

    Of course, it would help for normal shutdown or for sleepy laptops, but it is not the end-all/be-all of quick reboots.

  • ... (Score:1)

    by SETY ( 46845 )
    It actually seems like these things will be usable. 256mb for initial runs don't sound too shabby.
    I'm a little curious on the size of them. The mention all the wireless buzz words, but no size estimates for the actual devices.

  • Spintronics and the Future (Score:5)

    by wass ( 72082 ) on Thursday December 07, 2000 @05:25AM (#575701)
    Welcome to the new world of spintronics. It's amazing, I was just talking to one of the faculty here in the physics department about this stuff yesterday, to learn about all the good research the condensed matter group is doing here. So here's what I learened, in a nutshell.

    Most electronics up until now work within the charge domain. That is, devices all deal with moving, changing, transferring, etc, electric charge and the lack of electric charge. Amplifiers, for instance, can amplify current, which is the flow of charge, or voltage, which is the energy/charge ratio. Semiconductors exploit all kinds of funky physics to do these things.

    However, there's a whole other degree of freedom of the electron that's virtually unused. Spin. In any elementary quantum mechanics course you'll learn rather soon on that electrons are Fermions with total spin 1/2, which means there are two spin states an electron can be in, usually called spin-up and spin-down.

    So the new world of spintronics aims at manipulating the spin of the electrons, instead of the charge. Spin is a different beast than charge, in that it can be manipulated by magnetic fields and light, in vastly-different ways than does charge flow. Spin is a fundamental nature of angular momentum, so whereby the total charge is conserved within a small sample, so too is the angular momentum.

    Some of these MRAM's were specifically mentioned yesterday, in that the parity of the spin can be used to store bits. One nice fact about this could be that information isn't lost if power is turned off, unlike DRAM's and many SRAM's.

    It's a VERY new field, spintronics. I did a search on Google last night for only 'spintronics' and only 665 sites were listed. It's been around for a few years so far, but there have been problems with finding the right magnetic materials. You need the right combination of ferromagnetic and antiferromagnetic layers, and certain ways to test materials, before you can really start doing some good stuff. However, materials are starting to be found, so it's an exciting time for this potentially huge field.

    Hopefully soon there'll be spin-like transistors, leading to spin amplifiers, and all sorts of other goodies. Sorry I don't have any specifics about this, but I just found out about it yesterday.

  • MRAM = GOOOOD (Score:3)

    by billyo ( 258487 ) on Thursday December 07, 2000 @05:26AM (#575702)
    Instant on? Of course. Think about. Saving all of the startup files and bootloader in the ram, that will store information all the time. How could it losse power? It wont. It doesn't need an electric charge to store the bits in the ram, so will hold, in theroy, for ever. This is a huge breakthrough. And the amount of mem it could hold in one chip could easily be much higher then the 256MB that the early chips will run. Think about having 1GB of RAM on your home machine with just one chip, that will boot up your machine instantly and will never losse the information stored in the memory if your power get's cut off from not paying the electric company :) awwww, that will be sweat.

    And yes, faster surfing and faster downloads as well. The high-end servers will be able to store (or cache) the file's its serving up in the lighting fast memory. It will access the memory faster than a scsi raid getting thousands of hits per minute, or even per second.

    And I'm SURE that the chips will be shielded, so you dont need to worry if it will wipe out your hard drive or floppy when its turned on. I would think that IBM wouldn't be THAT stupid :)

    --we are the music makers, and we are the dreamers of the dreams.
  • You can find an article on Stuart Parkin (also developer of the GMR head in your hard-drive) who is the lead scientist on this project at http://www.wired.com/wired/archive/8.04/mram.html [wired.com]
  • Ok, those devices are out there since years. Ok, it's not something actually new.

    ..So what?

    If it works and is cheap enough to be put everywhere, wouldn't that be nice? Technology may sometimes be useful, what's wrong in that?

    I'm just hoping it won't be vaporware, again.

    anybody has any idea if the cost of producing such a chip would be to high compared to 'regular' ram?
  • Magnetic tape and drums aren't quite analogous to modern memory modules. The article says that most of the development time has been spent making MRAM chips (no, not tape, drums, etc) small enough to be cost effective. It doesn't say that IBM invented the magnet, nor magnetic storage, but Magnetic Random Access Memory chips.
  • http://www.technews.com/news/00/159086.html [technews.com]

    "The speed increase is thanks to subtle a twist on the solid-state memory technology that has driven computers for almost for decades. The technology is known as interlocked pipelined CMOS (complimentary metal oxide semiconductor) and will allow memory chips to reach speeds - in theory, at least - of between 3.3 gigahertz (GHz) and 4.5 GHz, using conventional silicon transistors. "

    "The key to the new technology is a distributed "clock" function. In computer chips, the clock paces the speed of the circuits. Standard designs use a centralized clock to synchronize the operations of an entire chip, ensuring that all operations run at the same interval, or cycle. The clock waits for all the operations on a chip to finish before starting the next cycle, so the speed of the entire chip is limited to the pace of the slowest operation. To increase the speed, the IBM researchers decentralized the clock, using locally generated clocks to run smaller sections of circuits. Infineon says that it is working closely with IBM's New York Fishkill research operation on developing MRAM technology still further, with the intention of allowing the memory chips to function like bubble memory, which retails the computer data, even when power is removed from the chipset. "



    We emerge from our mother's womb an unformatted diskette; our culture formats us.
  • The point was speech recognition on cell phones, presumably because these MRAM chips are so tiny and energy efficient that you can cram 256 megs into a phone. I'm baffled by the "easier downloads" thing though... maybe MRAM will we very very fast, speeding up computers in general....
    Or its just marketing crap. One Best Buy ad for an HP with a Pnetium IV claimed that MP3 downloads would go faster on the new chip....
  • "Gotta hand it to IBM these days: copper interconnects, 200ppi LCD monitors and now this."

    Add to that the death of the Aptiva series and the 75GB 7200RPM Deskstar, and you have a nice company. Now if only they could ditch Avery Brooks... "When, after six years, you finally realize that DS9 was just a pathetic Star Trek offshoot and that no one was watching it; that is an epiphany."

  • My statement to IBM is this: Before you release this "MRAM" technology, develop a shielding strategy for it.

    Boy, it's a good thing you brought that issue up. I'm sure IBM's top engineers didn't even think of it!

    ;)

    - MFN

  • I hope Microsoft had to pay a lot for the right to not mention HP in all the publicity.

    Yes, the Microsoft *the corporation* did not create the new mouse technology. The article you linked to says Gary "co-created" the technology, but it doesn't say who else helped.

    Rarely are the engineers themselves given credit for the new technology that comes out. Apple claims to have created FireWire, but actually an engineer or group of engineers (probably at Apple) created the technology.

    The original person I was responding to was trying to imply that the technology in the new Microsoft mice wasn't a breakthrough... i.e. that similar mice already existed.
  • One of the newer tricks (er, relatively speaking - early 90's) in magnetic memory is using Giant Magnetoresistive materials in the memory cell. The polarities of a sandwich of various layers of GMR stuff actually causes a change in resistance which you can check on by comparing to a reference cell (if 2 layers are polarized so that the moments are parallel, the unit has a lower resistance than if the polarities are antiparallel). I'm not sure if IBM is gonna use a pseudo spin valve or a magnetic tunneling junction as the base of their cell design, though. That article was pretty vague. In any case, some designs do have non-destructive read out, so you don't have to rewrite after reading. Lots of tasty research papers have been written on the subject, so go visit your local college library for details.
  • [...]
    EEPROM's can be expensive and may have long term reliability problems - you can read and write to them only so many times or cycles before you degrade the ability of the memory to "remember".

    I know EEPROMs (and FLASH!) have a limited number of write cycles. I was utterly unaware of a limit on the number of reads. Do you have any pointers to data sheets?

    I've used (recently) some mid-80's CoinOp games (video and pinball) that used EEPROMs. They looked like the originals, but I have no idea. I suppose they also could copy the EEPROM contents to RAM, but I didn't see enough RAM on the boards for that (and I know when I worked for MP Games we executed code stright from the EEPROM, and I saw on of our games running um, maybe six months ago, so eight plus years from the build date). So I'm guessing either the number of reads is astronomicly high, or I'm misunderstanding you...

    FYI FLASH can have a ton of write cycles (some AMD FLASH's in the mid 90's claimed 1,000,000 write cycles). So they make fine storage systems for code and (mostly) static data. Not so sure I would want to use one as a log disk or swap space though...

  • I thought the difficulty of measuring spin on electrons without losing the spin in the process was what made quantum channels so great for secure transmissions...

    Yes, this is one of the major difficulties, measuring the spin state of one of these samples (or a one bit of data, if you prefer). As far as I know, you need more than one electon to store the information using spin.

    What was explained to me yesterday was that most ferromagnetic metals half about a 50% polarization, meaning if it's a magnetized sample and you withdraw an electron at random from it, there's an approx 50% probability that electron is polarized properly with the rest of that sample, when you measure the spin. This has to do with band gap stuff and hysteresis and other effects akin to ferromagnetics that I don't understand yet. (My QM is rusty too, that's why I dropped from the grad QM course to undergrad, a move I STRONGLY recommend to any grad student with shaky background hoping to really learn QM).

    Recently, some new materials, called half-metals, have been found to match older theoretical predictions that there is 100% probability a withdrawn electron is aligned with the spin. So that's why this field of spintronics is really exciting now, real materials are being discovered to actually make the theory possible.

    From what I understand, though, we're not at the point of storing a bit in the spin of a single electron. I don't know the specifics of how these MRAM chips work, though, so maybe I shouldn't comment on it.

    And about your point of losing the spin once you measure it. If, by manipulation in a magnetic field, you set the spin to point in say the Z direction. So this is the axis of spin (or angular momentum if you prefer). If you now measure the spin in EXACTLY this direction, you haven't changed the state of the system. Well, you have collapsed the wave function, but you can measure the bit infinitely many times, and you'll always get the same value for the spin. If you change spin axes, and try measuring the X or Y component, then you've lost all information of the Z-component (non-parallel spin operators don't commute, remember). So as long as you're in the same direction, you can measure with impunity.

    In the real world, there may be a small angular difference between the spin state of the atom, and that direction in which it's read, but spin uncertainty can be minimized by keeping this angular uncertainty small.

  • Magnetic charge? If turning on your monitor creates magnetic charge, I know a lot of people who would be very happy to meet you. They've been searching for magnetic monopoles for a long time, and haven't found any yet.
  • They are already at the same level as Bell Labs and i think they are nearly as old. Personally i'de say they are the two most imrpessive private research firms. They are the only computer companies that can claim nobel prizes. Here is a list of the years in which each was one. The only one which is actually related to computers is Bell's 1956 award for the discovery fo the transistor. Bell: 1988,1978,1977,1956 IBM: 1987,1986,1973
  • the rampant use of buzzwords.

    Yes, it is a catchy buzzword, but at least it's an applicable one.

  • Re:what this actually means (Score:2)

    by Anonymous Coward
    I don't think that MRAM will replace SRAM for the cases where speed is the most important parameter (the L1/L2 caches integrated with the processor). The IBM paper give MRAM access time of the order of 10 ns. This makes them a serious competitor for DRAM if the price can be brought down to levels comparable to DRAM. Even if the cost is higher but within reasonable limits, the advantages for battery powered applications (removing the stupid refresh requirements of DRAM which in the end consume significant power) would justify the switch. The other big advantage of MRAM is that initial access time is also much lower than for DRAM (which engineers try to hide behind a curtain of tricks).

    Internal caches and cache tag arrays often have multiple read/write ports which are to my knowledge much easier to implement with conventional, flip-flop based, SRAM. That's another reason why I think that SRAM will stay as on-chip memory for processors (adding the magnetic material would add steps to the fabrication process but I have no clear idea of the impact on yields etc...). Individual memory chips are another story, since speed of discrete SRAM chips are limited by the time to get the signals on/off chips and MRAM speed does not seem to be that far behind the state of the art.

    As a side note, I have trouble understanding why the IBM paper calls these MRAM "DRAM" while MRAM are static in nature. Is it because the cell is simpler than standard SRAM and closer to the DRAM cell ?

    Note that if you have gobs of RAM which do not need any refresh and keeps data for weeks with power off, you want to have some form of error detection and correction. Whatever the technology, I would never trust any large array to keep my data for very long without any kind of safeguard.

    Apart from the fact that I don't believe that MRAM will ever replace SRAM in some cases as explained above, I basically agree with your post. Except for the gross error that DRAM has to be refreshed about 15 times per second, not 15 thousand for a 64 millisecond refresh cycle. Mind you, in the early eighties, the refresh cycle was 2 milliseconds.

    I also believe that your power consumption figure for an 64Mb SRAM array can easily be reduced (with chips that can be put in data retention mode, these are not the fastest ones however). What is certain is that most of the power consumed in a computer when it is off is used by the crystal oscillator, not by the CMOS RAM, even when it is quite large.

  • Me too, me too!!! My mama told me I could be a GangBanger too when I grow up! I just love shooting people for the fun of of it. I works much better than common Sence

    You silly Poo Poo head
  • it is good engineering practice not to assume the conditions of the situation to be anything more than extremely less than ideal that is...a consumer owning shitty speakers, a conumer who eats magnets for breakfast..etc, etc. It's idiotic to assume things when it is very probable to be otherwise.
  • Rubbish.
    The RAM may contain the same data, but the registers, IP and all, certainly won't.
    FP.
  • Does this mean that main memory and mass storage can now merge on the same medium? So essentially your filesystem IS your memory. The heap/stack/whatever is just located in some separate protected area. This would mean entirely redesigning the vast majority of operating systems which were designed to optimize the exact problem of memory/disk space usage, protection, etc. All of a sudden "disk cache", DMA, binary loaders, etc. are all history. Memory fragmentation and disk fragmentation are now the same thing. Anyway, sounds really cool. However, 256 MB mass storage is pretty damn small, and will be even orders of magnitude smaller 10 years from now. They better be able to ramp that number up.
  • Nice explanation! Just a nitpick: doing something every 64 msec means you do it about 15 times per second, not 15000. :)
  • Seriously, EMP terrorist attacks on a server farm could become all the more deadly. There would be disgruntled techies running around in the server closet with refrigerator magnets (or, even worse, the magnets from hard drive voice coils!).

    My statement to IBM is this: Before you release this "MRAM" technology, develop a shielding strategy for it.

  • Will MRAM be regarded as a breakthrough in 4 years? If they could ship it NOW, it would. Especially the non-volatile feature rocks, but I am pretty cautious to jump this train: wasn't there some company that promised a kind of optical RAM made of polymeres with access times around 5ns?
  • According to the press release issued by IBM, "IBM Research pioneered development of a miniature component called the 'magnetic tunnel junction' as early as 1974, eventually adapting it as a means to store information and to build a working MRAM chip in 1998." So, while magnetic field lines have been around since quite some time before 1974, IBM developed the technology to make small, efficient RAM chips possible using magnetism.
  • But.......

    As soon as your hard drive spins up, all information is erased!

    Back to the old drawing board.

  • The picture you paint is perhaps overly optimistic. "The MRAM doesn't require the refresh of a DRAM, and has the nonvolatility of a EEPROM, but has reliability superior to the EEPROM. So, an MRAM may be able to replace DRAM's, SRAM's. amd EEPROM's, without involving any major compromise or tradeoff. " You're not an engineer, are you? An engineer knows that there are ALWAYS compromises and tradeoffs. The word "yield" has not been spoken. Need I? Chances are that if you see no reason not to do something, you're missing a detail. Your "may" didn't have enough emphasis and your picture was too rosy for my taste. SRAMS are high speed devices. Their density is not beyond reproach, but their speeds are. MRAM is not currently being touted to replace SRAM for speed applications. The highest cycle time I saw was 10ns. A 3d video card needs closer to half that! The last MRAM I heard about, which may rely on a different technology than this one (but it sounds the same) had a hurdle to overcome-- how do you sense a non-changing magnetic field? The way they overcame it was by running current past it, writing it to a known state and then running current past it again. If they are the same, then the stored bit is the same as the known state. If the currents are different, then they are different states. What does all that crap mean? Well, it's non-volatile-- you don't need to give it power to keep its state. It does, however, require refresh in the sense that every read must be re-written back. If, on the other hand, it truly has the strengths of all of those types of memory and none of the weaknesses, it will indeed be a great day. I'm not saying it's impossible-- I'm just encouraging realism. Dense, non volatile, high speed and high yield?! So end the rants of an SRAM designer.
  • something like... television?
  • Yeah..but how MUCH sheilding? I could just imagine a couple of crazy kids driving through silicon valley with a huge electromagnate mounted on their car. What if I have my computer in a machine shop? What then? Do I have to specify how much sheilding I want in the online store? Do my costs get jacked accordingly? Just my 2 cents.

    Mask
  • Ramtron has been making Ferroelectric RAM's for years. It is a non-volatile RAM. It has unlimited life. I am curious how this is any different.
  • Do you seriously think that 10 years from now we are still going to have portable mp3 players?

    Yes. Take a look at Walkmans. Those are still around after a long while. People still use them every day. Casette decks are still in almost every car sold. And how's this, something even earlier, the RADIO. Yeah, people still use those. Imagine that.

    Linux is only free if your time is of no value

  • I'll believe it when I C it.
  • Every "new" technology is claimed to improve "the web experience" these days. The addition of the speech recognition is just because it was IBM they were talking about (they love speech recognition). Personally, I think anyone with a clue know that what's holding back the "web experience" is that we don't have fat enough pipes yet. I don't care if you buy the latest and greatest PIII (or I guess it's PIV now), if you stick a 56k modem in there (that can actually only connect at 23.5k) you are not going to massively increase the speed of downloads over that old Pentium 133 with the same modem.

    Sorry, that's a little pet peeve of mine. Taking advantage of the computer clueless should be outlawed. But that would mean arresting every marketing idiot, er I mean genius, in the industry.

  • If I bought an Imac I wouldn't need that floppy... Now if they only fit with my current dimm's
  • 1980's - 1 k SRAM chips VS 32K and 64K bubble memory. 256 K and 512 K was projected.

    Now...how did this all turn out for Intel?

    Memtech [memtech.com] bought out all of Intel's patents/technology. They are no longer being made by memtech, however they will repair them for you :-)

    Will IBM fare better? If the goal is to target servers with 256 mb chips, I wouldn't go out and buy IBM stock based on this revelation. I'm sure this technology has a place in the market, I just don't share the optimisim of the ZD author of this RAM being a server RAM replacement.

  • But you probably wouldn't need shielding. Since you'd assume that at any time about 1/2 of your bits are up or down, then there wouldn't be too much cumulative effect.
    Furthermore, these things have to be small enough not to effect each other, let alone your monitor.

  • The thought of not having to wait for some of the servers here to reboot is even more appealing.

    Why should you not have to wait for your servers to reboot? If your servers reboot because of power failures (in which case I'd advice a UPS ;) then there is still the issue of fsck and mount that renders the RAM useless, if your server reboot because new hardware is added.. then you still need to reboot because you need to install a new kernel, if your machine crashes then a reboot won't help much, etc.

  • The idea of a uniform storage device has been around for a long time. It means quite a number of things, particularly getting rid of buffers as they would no longer be necessary, which also means simpler software and hardware. This assumes one "best" storage device.

    Interestingly, the idea of uniform storage isn't used in humans. We have a short term and long term memory - which duals, at least in pedantic respects, that of RAM and magnetic media right now. It will be interesting to see how computers would evolve if all memory was addressable in the exact same direct (in terms of no buffer) mechanism.

  • This talks about instant on, presumably by storing files like loader, kernel, etc in what is essentially a different form of NVRAM.

    What I don't understand is why this can't be achieved using EEPROMs or just regular old battery-powered NVRAM. I remember the old Macs used to have a great deal of the system on ROMSs ... why not take it to its logical conclusion and put all the libraries, kernel, system files, and for that matter OS applications on a ROM or EEPROM?

    If the answer is that ROMs are slower than RAMs, can anyone explain why? I would think ROMs would be faster, not having to worry about writes...

  • This just in:

    Rambus claims to hold Magnetic Memory patent, will press IBM for licensing and royalties.

    Microsoft invents Command Line Interpreter interface, says will replace Windows 2000

    Shed 30 Lbs in time for the Holidays, with Linux powered dietary supplements!

    Burroughs spins back out of Unisys, claims old taint associated with name forgotten.

    HeathKit to introduce DNA Lab, l33t k1dd13s will be able to grow own dinos, munch San Diego, make bad movies.

    OSX found to cause baldness in lab mice.

    Black hole found forming in southern California desert, site said to contain Atari ET cartridges. Disney plans to use site for remake.

    Warriors defeat Lakers, credit Buckminster Fuller for inspiration. "We kept thinking of them as Bucky balls and all the potential they encompass!"

    Earth's moon actually stolen from Mars, water too!

    --

  • Re:Honeywell (Score:4)

    by ottffssent ( 18387 ) on Thursday December 07, 2000 @06:07AM (#575759)
    >>Here's an article from Scientific American on the topic.

    Which points out that the data density wasn't there, and that they were slow and expensive. Commercially available isn't what we're looking for: commercially viable is, and Honeywell's product clearly wasn't. Admittedly, it doesn't sound like IBM is going to be able to make them cheaply for quite some time either, but at least they have the access times down (or so it sounds--the article was a bit vague, as is ZDnet's want).
  • 4) We measured MTJ reading and writing times as fast as 10 nanoseconds -- some six times faster than today's fastest DRAM memory. Such an extremely fast speed results from both the high TMR and low device resistance.

    Sadly, with IBM's overly conservative estimates of "We won't have this in large scale production until after the next epoch" it's more torturous than vaporware.

    --

  • Interesting, but... (Score:3)

    by Bob McCown ( 8411 ) on Thursday December 07, 2000 @05:08AM (#575764)
    ...wouldnt the magnetic charge from say, turning on my monitor, cause problems with the MRAM, without some big shielding? Considering if I even think about magnets any floppy I have sitting around goes foom, whats going to happen when I'm relying on my 'instant on' MRAM to be ready?

  • Honeywell (Score:5)

    by Siqnal 11 ( 210012 ) on Thursday December 07, 2000 @05:08AM (#575765) Homepage
    They had commercially availible magnetic RAM chips as early as 1997.

    Here's an article [sciam.com] from Scientific American on the topic.

    --

  • Why is MRAM going to be the solution? (Score:3)

    by Trinition ( 114758 ) on Thursday December 07, 2000 @05:09AM (#575767) Homepage
    What about the old-fashioned Bubble RAM? What about organic-crystalline hologrpahic memory? What about how my Visor Deluxe can store 8MB of contents for 2 months on a pair of AAAs?

    Seriously. What makes MRAM so special that it can beat out those other concepts?

  • It needs the memory cleared every so often or it dies!

    On a slightly more serious note, some of the early palmtops had problems when they didn't have a way to clear memory and so had no equivalent of "reboot" if the system gets hosed. I think we'll see a BIOS ability to clear the "memory" on reboot and reload everything. Or maybe OS's will improve, but when something dies really badly I find it nice (windows or linux! I find this happening under both, though more for linux) to be able to start over with a freshly cleared memory.

  • The problem isn't the ram effecting the monitor but the monitor wiping the ram. Magnetism works both ways.
    ----

  • Re:what this actually means (Score:3)

    by Raphael ( 18701 ) on Thursday December 07, 2000 @05:57AM (#575783) Homepage Journal

    Another interesting thing is that the layout of the MRAM cells is relatively simple (like a grid) and the chip does not need any refresh circuitry. Therefore, MRAM could scale up very well and exceed the capacity of the biggest DRAM chips.

    There are many technological hurdles ahead (read: many years until the price goes down), but the magnetic RAM may even compete with the magnetic disks that we use today. This would blur the line between the mass storage (hard disk) and the main memory (RAM). Think about a computer that has only one type of storage: it's just "the memory" and you do not have to care about the difference between files on a disk and data loaded in RAM.

    In a several years, the only interesting difference could be between the "local storage" (MRAM, used for everything) and the "remote storage" (stuff accessed over the Internet). And even this line is already a bit blurry.

  • Here are some links to the data at the IBM sites
    1. http://www.almaden.ibm.com/st/projects/magneto/mra m/ [ibm.com]
    2. Ibm Scientist Interview, Dr. Stuart Parkin [ibm.com]
    3. http://www.research.ibm.com/ [ibm.com] magazine/1998/issue_3/cmos398.html - information towards end of write up
    4. The nitty gritty super geeky research document [ibm.com]

      1. Lots of interesting reading

  • IBM apparently layed off all of their marketing people. I can't imagine, other than some extensive testing of product and production, what would be holding this up. It seems IBM takes a casual "Oh, my sock drawer is full of diamonds. I suppose I should do something about that some day" approach to good fortune. Seemingly anyone else would be hyping the hell out of this. I just hope theire playing it cool, but we will see this MRAM soon. Now the 64 question, do you need a degaussing coil to erase/reformat your memory?

    --

  • This is very good news to such a lazy chargers as me. I've lost my data and settings so many times from my Cassiopeia because I've forgotten the thing laying somewhere without no AC connection.

    With conventional memory this thing eat battery even if it's turned off and when the batteries run out - whooosh! All data stored in the RAM is gone.

  • In production by 2004
    There will be some test versions out in 2003, but IBM, which will make the chips at its own plants, doesn't expect volume production until sometime in 2004, Davari said.

    If this is correct, you will not want any of the initial run. Who things we'll still want a 256Mb ram chip in 2004? More likely we'll be at 512 as a minimum, and as such, these will be worthless. Not to mention that they will be expensive, in all likelyhood.

    I'll wait until it's less expensive, personally, and more usefull - like say a 1Gb chip. THAT would be cool. I'd think it has OTHER applications as well - imagine a storage CUBE of these, say 100Gb? I'd find that VERY useful. Since it's magnetic, it could be treated like a big drive. Imagine the access time!

    Fawking Trolls! [slashdot.org]

  • Full circle (Score:3)

    by American AC in Paris ( 230456 ) on Thursday December 07, 2000 @05:14AM (#575792) Homepage
    How about not waiting a minute or more for your personal computer or laptop to boot up? With MRAM, "instant-on" computing becomes possible

    Even though I'm well aware of the fact that MRAM is decidedly far more advanced than the magnetic RAM of old, I can't help but chuckle at the article's starry-eyed vision of tomorrow's "instant-on" computers. I can close my eyes and imagine...

    ...coding on the old PDP8/E my college had. That had magnetic memory, and it was indeed "instant on" (unless you count the 25-odd seconds it took the two cooling fans to rev up to full speed, that is.) Best of all, if the group before you forgot to erase their program, you could avoid the hassle of manually entering it yourself...

    $ man reality

  • But it says 10 years (Score:3)

    by CMiYC ( 6473 ) on Thursday December 07, 2000 @05:15AM (#575793) Homepage
    Well its great and all that the inital chips will be available in 256mb varities...and a smaller physical chip is great for MP3s player and such... but the article says IBM doesn't think it'll be in volume production for another 10 years. So um...what difference does it make on the products we have today? Do you seriously think that 10 years from now we are still going to have portable mp3 players?

    I don't like how the article makes it seem like MRAM is the answer to today's memory design challenges, when most of the products its going to benefit probably won't be around in 10 years. Or of they are around, they'll be completely different.

    ---

  • Here's some more information... (Score:3)

    by taliver ( 174409 ) on Thursday December 07, 2000 @05:15AM (#575795)
    That I got from the IBM site here [ibm.com]

  • So there's two spin states and when you store a spin state to a bunch of electrons, half of them remember it? Isn't that kind useless? How would you know what spin you stored there originally?

    That's the point. Up until now, due to this problem, there have been limitations in the development of spintronics. Now new materials have just been discovered in the last few months that are the so-called half-metals, and thus ALL electrons within them posess the same spin. This ain't your normal class of ferromagnetic materials.

    But then again, this is all new to me too, so I may be mussing up the details.

  • What I am waiting for is a 10Gig (or more) bank of non-volitile memory.. It wouldn't even have to be fast.. Hell, if it were 100 times slower than SDRAM it would still be worth while.. The reason is that you could treat main-memory as a cache into a very very special and protected read-write region of the nvram. With this you could do away with all swapping and most of the complexities of disk-writes.
    In fact, you could finally treat files as character devices instead of block devices (though you could maintain the latter for compatibility). When you do this, memory mapping of disk-space is nothing more than literally allocating a chunk of nvram into your address space.
    You'd still have to perform disk-syncing, though it would be more like cache flushing than anything else. The disk sector would shrink from 512Bytes to 128Bytes (a typical cache line)
    Through the use of memory mapping and independant read/write/execute permissions on memory pages, you could achieve a whole new software design structure which completely eliminates the need for OS-calls for disk access for anything other than setup and shut down. Databases could achieve phenominal performance gains.
    I know that nvram disks have been around for a while, but they've been incredibly expensive, and only support very small disk sizes (couple gig max).
    Assuming the power requirements on MRAM are low, and that the cell size can be comparable to that of DRAM, then we should be able to achieve 40Gig MRAM disk drives at some point, which are a good size for serious servers. So long as you can daisy-chain them as with SCSI, then you're good to go.
    On 64bit machines, all you need are the appropriate drivers and you're golden.. Sadly, 32bit machines would require some sort of banked paging. Thankfully, this would enhance the general desire for 64bit machines and then things like AMDs x86-64 and Intels Italium would receive a brand new source of demand. SUN and Alpha would be the immediate benificiaries, of course.
  • I don't wait for my laptop to boot - I suspend and resume it like most laptop users. The people who write articles for ZDnet are clearly so inexperienced with computers they've never even used a laptop (or maybe they have but they were too scared to select 'suspend' from a menu). No wonder they can't figure out what faster RAM is all about.
    --

  • Re:Why is MRAM going to be the solution? (Score:3)

    by stripes ( 3681 ) on Thursday December 07, 2000 @06:38AM (#575806) Homepage Journal
    BTW, your Visor uses FlashRAM, and MRAM is more efficient.

    The Visor doesn't have FLASH, and has taken a lot of crap for it. The Palm (and as far as I know, the TRG Palm clone, and Sony Palm clone) all use Flash to store the OS, and with 3rd party software (er, TRG's software, which they bundle with the Pro) they can store some apps, and some read-only data in the FLASH as well.

    However they all use RAM (DRAM, or SDRAM, or some kind of ram with a P in it) to store most user installed programs and data. They get multi-week run times on 2 AAA batts because they put the RAM into a low power refresh mode (the exact kind depends on the RAM, and the clone, and if you installed a patch, and...). There is no reason you can't do that with a desktop system, or laptop, but it does take some power. More power for the 64M and 128M desktops and laptops we are seeing now then for the little 8M palm tops.

    MRAM would use no power to keep it's memory. If it can have a decent read speed and size and power use (oh, and price) it will kill the flash market. If it can't get good speed and power use, but can get gread prices then it will kill the disk drive market. If it gets great speed and fair power and great price it can kill the DRAM market. Other combinations may not impact any existing market, but may make new ones. Or just turn it into an also-ran.

    P.S. FLASH uses no power while you are not reading or writing it (i.e. no power when merely storing data). So MRAM is no better in that respect. We don't know that it will be better in any other way when it finally gets to market, but we can hope!

    P.P.S. it isn't 100% true that the Visor has no FLASH. It has no FLASH as shipped. Many 3rd party modules have (or pretty much are) FLASH, like the backup module, or the 8M FLASH module.

  • I've always wanted to be able to stick computer memory to my fridge door!

    --
  • We used to call it Core, hence Segementation fault (core dumped)

    I'm truly impressed, though, since I saw that tiny little 340Meg hard drive that could hide behind a Kennedy half-dollar. They've figured out how to make all those tiny little wires and ferrite beads on a micron scale, eh? At last we can upgrade the 360/40! Kewl! ;-)

    --

  • Pros, cons, issues. (Score:3)

    by mirko ( 198274 ) on Thursday December 07, 2000 @05:19AM (#575815) Journal
    1. Pros:
      • No more dilemma between RDRAM and DDRAM
      • No power consumption on laptops... Imagine a laptop using this and an Amulet [man.ac.uk] processor
    2. Cons:
      • Will new motherboards be required ?
    3. Questions:
      • Access time ?
      • Transfer rate ?

    --

Slashdot Top Deals

The goal of Computer Science is to build something that will last at least until we've finished building it.

Close