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

 



Forgot your password?
typodupeerror
×
Technology

New RAM Based On CD-RW Film On Horizon 103

SiliconShaman writes: "Ovonyx Corporation is reporting initial success at producing a very cheap non-volatile RAM. Supposed to be cheaper, faster, etc. than conventional Flash memory. Applications include satellite and aerospace, cell phones, the list goes on. Details can be found here: Short Technical Presentation in HTML." "OUM memory technology," says Ovonics' Web site, "is similar to DRAM and many orders of magnitude faster than Flash write." The proliferation of devices which will need copious nonvolatile memory should mean a healthy market if this technology reaches the production line. I know my camera could use some more storage ...
This discussion has been archived. No new comments can be posted.

New RAM Based On CD-RW Film On Horizon

Comments Filter:
  • just make the swap act AS the RAM ;)

    Hmmm... go to the store and you buy a 50GB HD. Go home, partition disk as swap, pull out your old (outdated) RAM chips, now you've got 10GB of memory running at RAM speed (see above) :)
  • wow, I'm sorry man. That must really suck... losing karma points, and worst of all, you didn't even make first post...
  • They've (As in Energy Conversion Devices) had prototypes of this technology for years (in fact, since the early to mid 70's!). The problem (as it is also with holographic storage) has been getting it to be economically manufactured. Perhaps they've finally gotten it down from atmospheric pricing.
  • I can't believe that those idiot moderators gave you points. well Trolled that man !
  • by XChemie ( 122421 ) on Wednesday May 24, 2000 @05:22PM (#1049804)
    For a little background (I'm a chemistry grad student working in this area), the maturing of this technology is good to see, after many years of battle vs. magnetic storage for both CD-RW and non-volatile memory. I think the potential here is very great because of the relative prodcution simplicity and cost benefit compared to competing technologies. This stuff is not vaporware! The technology of phase change media (based upon optically/electrically induced reversible amorphous to crystalline transitions) has been researched extensively over the last two decades by big names like Philips, Micron, 3M, IBM, etc. But magnetic storage had more research money for quite awhile for alot of reasons; however, it's phase change media that eventually got used for your CD-RW (not CD-R though...) discs. Making non-volatile RAM was the next obvious target, but latency was a problem until recently (and the inertia problem of changing manufacturing methods). For some more info, goto the website of the parent company Energy Conversion Devices [ovonic.com]. It's based out of Troy, Michigan and was founded by Stan Ovshinsky, who's somewhat of a rogue in the physics community. But it's a cool company that also uses a similar technology to make surge protectors against the EMP from a nuclear blast! :)
  • by jbuhler ( 489 ) on Wednesday May 24, 2000 @06:58PM (#1049805) Homepage
    The presentation states that OUM is only good for about 10 trillion writes. If I bang on the same bit for a week or two at a rate of (say) 10^7 writes per second, won't it wear out?

    Of course, most bits won't see this kind of punishment, but I can imagine data acquisition apps that might trash a few bytes of storage within a year or two or ten. Hopefully the machine's L2 cache would effectively rate-limit writebacks to main memory, but it should still be possible to set up an aliasing situation that would cause a line to be flushed on every write.
  • So many people have written something to this effect that I'm just going to say here, this is not about storing little re-writable CDs in your computer. It uses the same material (that's chemical composition, no more) as the re-writable CDs. Other things, like the filesystems they use or the cute little motor to spin them up, will not come with the package. For people who already know this, I apologize, but I'm convinced I do have an audience out there.

    Thank you.
  • BADBLOCKS(8) BADBLOCKS(8)

    NAME
    badblocks - search a device for bad blocks

    SYNOPSIS
    badblocks [ -b block-size ] [ -o output_file ] [ -s ] [ -v
    ] [ -w ] device blocks-count[start-block]

    DESCRIPTION
    badblocks is used to search for bad blocks on a device
    (usually a disk partition). device is the special file
    corresponding to the device (e.g /dev/hdc1). blocks-count
    is the number of blocks on the device.

    +++ATH0
  • I suspect the big issue will be whether the company can get these non-standard layers integrated into normal semiconductor fab processes. They sound very optimistic, but I wouldn't be--the obstacles may be less technological and more social in nature.

    Furthermore, in order to catch on, the product has to be compatible with existing systems and be either a lot faster, significantly cheaper, and/or come in much higher capacities; otherwise, they are not going to catch up with the economies of scale of flash memory. If they can do that, I think there is a market: non-volatile, fast storage is useful in more and more applications.

    (As an aside, they are not talking about optical storage, they are talking about taking advantage of electrical properties of materials that are ordinarily used for optical storage.)

  • Must have been a transient electromagnetic field in your drive actuator. Did you try the usual fix?
  • Maybe, but I didn't tell you how I was measuring latency, did I? =)
  • transient electromagnetic field in your drive actuator

    I can't seem to remember that one. Was that the Dynamic Transient Magnetic Re-allocation Policy of my hard disk [ntk.net] or the transient hysterisis loops in the head media [ntk.net]? If it's the Re-allocation Policy of my hard disk, then I'm fscked, cuz I didn't do those backup things that everybody said I should do (but my AOL should back up important things, right? It said that it would make sure that I had an excellent browsing experiance!). If it's the transient hysterisis loops in the head media, then I already tried the reasonant magentic distortion rectifier. But I didn't really have one after you told me to use the 'highly-acidic battery charge' on the supply cabinet while they were plugging in the new networking room, so I just used the hammer and screwdriver, like last time. But now my hard drive is sort of bent and part of the metal box broke, and now that floppy circly thing is hanging out. And the AOL tech support people keep hitting the 'mute' button on their microphones for long periods of time after I call them and tell them what I did. It's almost as if they're laughing at me. But AOL wouldn't do that, right? Right?
  • Within the first few sentences of this story there are several glaring spelling errors. Does nobody double-check these stories before they go up? Failing that, can't they even run some kind of rudimentary spellcheck before hitting the "send to millions" button?? It's pathetic and embarassing that this site is still so amateurish...
  • I was thinking the same thing (re: Transmeta). Low power processors, low power ram, plus the possibilities of replacing the hard drive (which requires power to stay spinning) could make for a very energy-efficient box.

    Hell, as long as we are dreaming, why not some of these long-promised, low-energy color flat-panel displays! =) Mmmmm... a laptop that runs for a week on one recharge...

  • Prtty good, but not up to your usual. Still, it's the best troll this article is going to see!!

    Perhaps osm and Miss. Portman as Captain Kirk and Yeoman Randall in 'Star (as in hot young actress) Trek'? Or Scully and Mulderin 'OS/X Files'? ESR could star as Cancer Man!
  • that, as they say, is the point.
  • is the sound of me farting. The sound of the Creater is the second most supreme sound.
  • this wouldn't be necessary for anything except Windows machines....
    Hey now, Macs have their own share of problems.. ;)
  • yeah, but how much you want to bet that the process responsible for doing the writing would be the first to go. or you'd get a process which hangs, not badly enough for the whole machine to go down, but enough to cause a reboot--too bad multitasking let that backup process do the backing up with a frozen one. oops!

    for this to be really effective you'd need multiple layers of backups so you could choose the state most trouble free. on the other hand, you'd be restoring the ram to the state it was in JUST before a major crash--not a very comforting state of affairs.

    A more promising situation would be using the stuff to store ram so that a power failure would not result in catastrohic downtime for rebooting. again, this would be more applicable to windows. but i'm getting tired of waiting for my linux and bsd boxen to boot up after i power them down (which I do a couple times a week so i don't have to hear the fans, or so I don't have to pay the giant boston edison bill).

    But there is nothing special about OUM as NV storage--that's what hard drives do best as long as you don't have size/power/price/portability constraints.

    Don't laugh, my other .sig is a porsche!

  • IIRC, in most cases the cache only mirrors what's in the main memory, so it wouldn't be a problem. However there would be 2 other issues.

    Firstly, booting would write over part of the memory - you'd have to tell the OS to recover, unless that's what it did all the time. You could have a reserved area for booting, then the system looks at the main memory and recovers.

    The other problems is saving the entire state - you know the memory, but not what was going on in the processor, network, etc. when the thing goes down. So some things will be unrecoverable. And of course if the thing really crashes it won't help without some pretty serious recovery tools.

  • In the event of system lockup, the hardware can clear the memory and write the OUM backup back into RAM. Voila! You're back where you started (more or less).

    Voila! You're back, 0.5 seconds before you crashed, with an identical stream of code and data coming... so you crash again!

    Your blue screen of death just flickers REAL FAST. See loop, infinite.

    Now, if there were some smarts that could trap and diagnose the cause of the crash, reload the memory, fix the problem, and THEN restart things... you'd have something.

    Hmmm... sounds like something the High Availability folks could look at....

  • The article says they are exploiting electrical behavior of the phase-change material, not it's optical properties so I don't think it's terribly applicable to holography.

  • yeah, but how much you want to bet that the process responsible for doing the writing would be the first to go. or you'd get a process which hangs, not badly enough for the whole machine to go down, but enough to cause a reboot--too bad multitasking let that backup process do the backing up with a frozen one. oops!
    Not necessarily.

    Perform the copy CPU register state and RAM image to secondary RAM in hardware as an atomic operation which occers once per clock tick -- if possible, by some subdivision otherwise. From then on copy only deltas between any two states in the rest of secondary RAM like most versioned filesytems. The number of potential versions stored is limited to the size of secondary RAM and the amount of change over time, like any other cache.

    It's a pretty cool idea... anyone know if some exotic hardware with these kinds of capabilities has ever been tried?
  • by Jage ( 164751 ) on Wednesday May 24, 2000 @05:34PM (#1049823)

    AmigaOS, or should I say Kickstart, partially implemented recovering memory state after reboot (yeah, and this was done way back in 1985.) After rebooting, it wouldn't erase memory, but the OS would look for some system vector tables and do some basic sanity checks to see if the tables are corrupted. Some nice uses were for example a RAM-disk that could survive rebooting.

    Sometimes the system hanged in repeating crashes and reboots, though. Then your only option was to really erase memory, for example by toggling The Most Significant Bit (ie. power switch).

    Other bad point was that also viruses liked to hook themselves to those vectors, enabling them to survive reboots.

    For the rest of the state, maybe you could log some state changes to for example display adapter, network card and etc. Or maybe your devices would have to expose their internal state in some compact structure you could just copy to log areas periodically (when the system would be in special recoverable state.)

    I don't know. :)

  • I'm sorry, but Microsoft now owns all of this new memory technology. As you know, Microsoft holds a patent on Vapourware technology and a copyright on the phrase Vaporware, Vapourware, and DMCA. In fact, this post itself is a violation of the DMCA for even refering to the DMCA, because the DMCA prohibits use of copyrighted property which would include the phrase DMCA. And Vapourware.
  • Well, it does say "written" more that ten trillion times - I'm assuming you can read it as much as you like after that.

    What consumer devices are you going to have that are going to be generating data at the rate of one million items per second?
  • Imagine your swap partition running at the same speed as your RAM. That'd be pretty spiffy.

    It would also be kind of silly. If you had a device that was as fast as RAM, it should be addressed like RAM, not swap. The point of swap is to be a storage area for programs that don't currently fit into memory because others are loaded. So instead, the OUM should be used by the system the same way as normal RAM, instead of as swap.

  • Check this [sciam.com] out. HP gets closer to the final goal.
  • It was a pretty bit o' prose, but it had an ending as predictable and sudden as an Arnold "I'm a Kennedy now!" Schwarzenegger movie..

    And who says I'm an armchair troll ;)
    Perhaps I'm a closet troll and not just a 'karma-whore'...

    Besides, osm and Miss Portman are yours to do with as you like (literally), and it wouldn't be my place to do an osm troll..
  • The distinction is probably very similar to FORMAT /Q (QuickFormat -- just rewrite the FAT), and FORMAT /U (unconditional format). The former rewrites just the FAT table, with the presumption that the media has not grown any defects. The latter reformats the entire media, thereby "Refreshing" the sector boundaries (if a floppy) and possibly identifying any grown defects.

    In the case of a CD-RW, I'd imagine performing a full-blank gives you a marginal increase in recording quality (ie. you're more likely to get a good, clean "burn" subsequently), and it may possibly identify defects (such as scratches) during the erase. Not sure.

    --Joe
    --
  • 2. What effect will magnetic forces (and/or electro-magnetic forces) has on this type of memory?
    As far as I know, and I'm pretty confident on my E&M physics, it shouldn't matter much as long as the memory is properly packaged (i.e. shielded).

    Here's how it works: you surround the memory with a conductive metal; it's really that simple. external electric fields can only get inside if there are holes in the enclosure. this is why you wouldn't be able to pick up radio signals if you were inside a metal box, or why radio signals would sound really really weak if you were inside a giant birdcage. (incidentally, this is also why a car is a safe place to be in a lightning storm)

    so, you just make sure to wrap some foil around it, and then the memory's only vulnerabilities are through the connection it has to the rest of the components.

    as for magnetic fields, I'm less sure but I think external magnetic fields can be shielded from by an iron (because iron is ferromagnetic) enclosure.

    someone with better physics knowledge correct me if I'm wrong?

  • That's why those pesky virii survived all the time on my friend's Amiga 500. We had some hefty discussions about how they managed to survive, too bad none of us had any clue on the Amiga-hardware.

    - Steeltoe

    In time, everything will be revealed.
  • by orpheus ( 14534 ) on Wednesday May 24, 2000 @10:18PM (#1049832)
    Thanks for the update. I'd seen those implications in the ECD website, but...

    I am not sure that NiMH batteries were invented by ECD. The ECD website only claims a) all "significant" manufacturers of NiMH have a license with them (implying that some don't - why?) and b) the first commercial NiMH manufacturer 'used' Ovionics technolgy. This company (Gold Peak) was also 'one of ECD's early licensees' -- this seems like an odd way of saying "we invented NiMH". It is almost as if they are trying to imply that without actually saying it

    I tried checking the USPTO database, but if he had the groundbreaking patents, they are too old to show up on the database. I concluded this by checking the bibliographic entries for current Ovshinsky NiMH patents (which contain the patent numbers of preceding/related art) I presume he would cite his own groundbreaking patents. It is possible that I'd learn more by reading the complete applications, but IANAL (and no one's paying me for *that* depth of research)

    I was aware of their early flexible amorphous solar cells in the 70's, but I didn't know these were a major part of today's market. Are they?

    Besides I'm not sure that one major product (or maybe two) in 40 years is a "decent track record in products" (ECD was founded in 1960) ECD seems to have some viable products, but I'm surprised that they seem to be incremental improvements over the state of the art, while their past (and present) technology always seems billed as 'revolutionary'

    Of course, that can happen. I think Harry Bede is a good example. He designed and produced the BD-5 airplanes and an interesting 'inline' automobile -- both products I'd have bought instantly (well, once I could afford them) but his companies can't seem to stay in production very long.
    _____________
  • "(but my AOL should back up important things, right? It said that it would make sure that I had an excellent browsing experiance!)."

    If AOL didn't back it up, it wasn't important d:-)

    - Steeltoe
  • by dbirchall ( 191839 ) on Wednesday May 24, 2000 @04:24PM (#1049834) Journal
    I especially liked the read/write cycle lifespan, since for anything to replace existing memory technologies (like flash ram and CD-RW), it needs to improve on that performance parameter.

    I'm a little curious, though, whether this is best suited for compact applications like flash RAM, or as a means of replacing both RAM and fixed-disk technologies. If the size reduction is substantial enough, and it's as fast as RAM, it's possible that a system might ship with a single fixed rotating rewritable drive (like a hard drive) using OUM technology to provide a significant chunk of storage space (say, multiple gigs) with high access and transfer speeds. Imagine your swap partition running at the same speed as your RAM. That'd be pretty spiffy.
    --

  • Is there any information about the power requirements of this technology? It seems to me that something based on CD-RW film would be rather high; although I admit I haven't done much reading on it.

    Also, I know that most flash devices have a limited number of writes they can perform before failure (a large number, I'll admit). Is this a worry with this technology or not?

    Most of the small devices that would be using this technology would require both of these things.

  • The technical intro does not mention how fast the devices will be.

    I bet they'll be a few orders of magnitude slower than conventional electron-based storage since the bits are stored by using atomic phase changes, which are much slower than the speed that electrons can zip around.

    Jeff

  • Pricing info? I know there is an EEPROM shortage keeping pricing high.. For it to make waves in the cell phone and consumer devices it will have to be dirt cheap first post?
  • I am not aware of any hardware that does this, but I saw a very interesting-sounding software package at an event last year (Fall Internet World?) that does something like this. I really, really considered buying it! (-8

    Is the device to read/write this stuff going to be independent of the medium? So it could come in PC-Cards, 3 1/2" diskettes, RAM, EPROM form factors, etc.? If it's durable and has good resistance to heat, movement, etc., it might be perfect for the wearable PC I keep trying to design (but I can't keep up with all these innovations it would be great to incorporate!).

  • by mr3038 ( 121693 ) on Wednesday May 24, 2000 @11:51PM (#1049839)
    Just wanted to add that if you have (cheap enough) memory with low latency you already have memory with low latency and high bandwidth. Just interleave those memory chips and you are done.

    For example if I have SDRAM (64 bit bus) PC133 10 ns memory with bandwidth of 1.06GB/s and RDRAM (16 bit bus) PC800 20 ns memory with 1.6GB/s which ones I can interleave to get memory with latency of 12 ns and bandwidth of 4GB/s (256 bit)? (I have really no idea of real latencies of those memory types and it hugely depends how you measure it - time it takes for chip to read bits or processor to receive required bits. But what I know is that SDRAM has much lower latency)

    I'm not aware of motherboards supporting SDRAM interleaving but Intel already does this with RDRAM in its new mobos so it should be possible. I think that this is because SDRAM already provides enough bandwidth in most cases.

    Note that when using DDR SDRAM you can double the bandwidth (for SDRAM) and one can only wonder why is/was Intel trying to push something like RDRAM into market?

    For those still wondering the answer to second paragraph I will give a hint: you cannot reduce latency with interleaving.
    _________________________

  • Nice article coming only hours after I ordered 32 mb of SmartMedia for my digital camera. I can imagine laughing at myself in 5 years for spending $75 on such small and slow media..
  • Solar cells came later... ECD began in the 1960s with amorphous discrete transistors, whose raison d'etre was to be cheaper to make than crystalline silicon ones. But they were not quite as reliable and, uh, silicon got better and cheaper faster. Eventually he hit upon solar cells and NIMH. But I found it fascinating that he went something like 30 years without a profitable quarter! And that was probably a fluke. Investors have poured money into Ovshinsky's dreams for years. I'm not surprised that ECD was the main holding of the Steadman Fund, long famous as the country's worst-performing mutual fund. (It's not even allowed in some states.) So again I take his inventions with a grain of salt. They're probably based on real physics and chemistry, are demonstrable in the lab, and exciting to investors. But only rarely do they make it to market. I'm trying to visualize his life as a movie. Sort of a Tom Edison Story starring Woody Allen. Tucker as a comedy.
  • Little calculation: assume the cache is 256kb, randomly written by one in 5 instructions, at a pace of 200MHZ (how fast is cache these days?).
    Cache width 4 bytes at a time.
    I guess these are conservative estimates:

    10*10e12 / 200*10e6 * 5 * 256*1024 /4 =
    16384000000 seconds it would last,

    ah, that's 532 years. OK, no problem :)

    OTOH if it's only as fast as DRAM, it isn't good enough for cache. invalidating the cache (thus refilling it) after a power-on doesn't really seem a problem to me.
  • As far as life span, the web site presentation said something about 10 trillion write cycles.
    --
  • Sounds very similar to so-called "holographic" memory that was oft discussed in various glossy computer and popSci mags a decade ago, tho this is presumably a depth of 1 bit vs multi-axis. Maybe the first step to reality ? -eb
  • Reading this article, I have to say that this technology sounds similar in almost every respect to FRAM, which has been around for years. In fact, SAMSUNG is probably already out with their 32Mbit FRAM part:
    http://www.edtn.com/story/chipw ire/OEG19991207S0006 [edtn.com]
  • Well, at least we'll have a choice... CD-RW based RAM or little chips based on that FMD-ROM technology we saw here [slashdot.org] on Slashdot a few months ago...

    Oh well, at least we won't have to rely on Scotch tape [slashdot.org] to hold our data.... ;)

  • Hmm... I wonder if the write layer could be separated from the data layer alowing the read/write transisters to stay in the device while you insert and remove just plain film layer. That could get really cheap!
    Also if a media could be developed that could be made semiconducting you could make erasable processors. That could have some interesting aplications.
  • by zpengo ( 99887 ) on Wednesday May 24, 2000 @04:28PM (#1049848) Homepage
    I can't wait for the day when I can get something like this installed in my skull, so that when I think to myself, "Mental note: remember to...", I'll actually do it!
  • One million memory accesses per second is not unrealistic. At that rate, your OUM will wear out in about four months.

    What that number means is that they only TESTED it for a few months. B-) If you look at the curves, they were showing no sign of curving. So there's no indication that it would stop working after 10 trillion, or even 100 quintillion.

    Read another foil, and you see that read is CONstructive when it's in the high-conductance state, and "the current is negligable" for the low-conductance state.

    If there's any destructive effect, it would be the read current in the low-conductance state gradually coaxing the device to grow a crystal across the boundary and switch to the high-conductance. But even if you hammer on the bit that won't happen for at least four months.

    So even if that turns out to be a problem, you could treat it like a dynamic RAM that has to be refreshed ONCE every FOUR MONTHS. B-) Much better than silicon DRAM that needs a refresh a thousand times a second or so. Kick off a cron job three times a year to refresh your RAM.

    Do that and it looks like it could last until the rest of the computer fails from diffusion of impurities through the silicon.

  • What is it about electronics and lack of useful memory? I bought a TV a while back, and it let you program the station call letters in for each channel. I thought, "Cool." As I start going along, come to find out that you can put four characters per channel, and a limit of about 25 channels. It may have been two or three years ago, but even back then memory was cheap. Can Panasonic only afford to dedicate 100 bytes to this function? If we can't get manufacturers to put much memory in simple things, what good is any other advances?
  • by Anonymous Coward
    Well, after quickly pasring through the document, I must say that this is a really great thing. :) I have always thought that the major problems with the current types of memory are obvious: standard SD-RAM is speedy in MODERN terms, and (thank god) is cheap again, but it will become a major bottleneck in the years to come. That is where DDR, QDR, and RDR memory come in, but they are all costly and, as often ascoiated with speed, hot running. RDR Memory especially. Those things get so darn hot! I see this as a major advantage in small electronics, too. flash memory is the current leader, but it is slightly larger than Smart Memory, which has problems of its own. Even though compact flash is somewhat fast, it is still slow, and the only real advantage smart memory has is its size and weight, but it is the slowest, and it is NOT durable. If this type of memory is applied, and can be compressed into a small space, it would be perfect. Also hope it is durable, too, as that would give it all the advantages. What about PCs? WOuld it be workable in those? I hope it can, but It sounds like this would require a whole different way of processing data from, and operating, the ram itself. This means that the majority of people would be unable to use this type of ram, as their hardware would not support itin anyway. OK, that is enough for now --Sanfam was here I am Spoo, Hear me sigh.
  • Strange link between this name and the name of the outfit that was promoting amorphous semiconductors with great performance promises about 30-35 years ago. It was headed by an inventor named Ovshinsky...

    If you'll read all the foils you'll see they licensed the amorphous switching element from one of his companies (which is using it to make CD media.)

    Another successful product from him is the flexible amorphous solar panel. Three layers of amorphous solar cell (intercepting three different bands of sunlight), electrically in series and grown on a stainless steel base.

    Because it's amorphous it can be bent quite a bit without breaking (though it isn't quite as efficient as crystaline cells because there are more sites where carrier-pairs can anhialate rather than giving you current).

    You see 'em on boats all the time. I've got one tied to the cabin-top on mine, keeping the battery up when the boat sits for a while. (On a previous boat it was the only thing charging the 85 AHr deep-cycle battery, which powered the radio and lights. It could bring the battery from 25% to full charge in a couple weeks. We never needed to hook up the charge circuit from the aux engine.)

  • If this becomes available, EROS [eros-os.org] and other persistent OS'es would be easier to develop and/or better fitting to available hardware?

    If these things were in 10-100GB class, maybe we could unify random access memory and traditional more-or-less persistent storage (read: hard disks). Especially considering 32bit addressing is being left behind, so you could simply have it mapped to memory.

    On the other hand, that annoying javascript scroller on their front page seriously damaged their credibility in my eyes. Also, keeping in mind, most of these 'revolutionary storage technologies' never see day of light.

  • The technical details of this article are close to zero, if you look closely.

    Read the foils from the presentation of the research report here [ovonic.com].

    It gives far more detail than I've ever seen for an announcement of any other memory technology. B-)
  • the OUM memory state can be written more than 10 trillion times, making this memory useful for program storage (Flash) as well as general purpose interactive (DRAM) data storage memory.

    Um, I don't think that will work for general purpose storage. One million memory accesses per second is not unrealistic. At that rate, your OUM will wear out in about four months. Wouldn't mind a few GB of it in my handheld MP3 player, but I'll take volitile memory for my system, TYVM.

    --

  • 1. What effect will this type of memory device has under radiation bombardments?

    The conductive state is a (poly?)crystaline material that shorts two electrodes.

    The resistive state has a region of amorphous (glassy) material in the space between the electrodes, surrounded by the remaining material which is still in the (poly?)crystaline state.

    Writing it consists of MELTING the region between the electrodes, leaving it either cool enough that it solidifies quickly into the amorphous state, or hot enough that it solidifies slowly and the crystals grow into the melted region as it freezes. Think frost on a window in the winter.

    (Of course at these scales, even "slowly" is measured in nanoseconds of elapsed time.)

    Charge carriers from particles won't make significant increases in current in the glassy state, or remelt it and let it crystalize. Particles might disrupt SOME of the crystaline conductive state - but there is a LOT of it in parallel. By the time enough raidation hits it to increase its resistance measurably the rest of the components in the computer will be approaching the "sand" state.

    Think about trying to use radiation to disrupt a wire until it won't conduct, or a glass bottle until it will.

    2. What effect will magnetic forces (and/or electro-magnetic forces) has on this type of memory?

    It isn't made of magnetic material. (Again, think of using a magnet to disrupt a copper wire until it stops conducting, or a glass bottle until it starts.)

    If you put a big enough EMP into such a chip you might generate enough voltage and current to write the bit. But you'll probably fry both the static protection and the components in the pad driver/receivers on the chip's terminals with much smaller EMPs, because the interconnect wiring is a much bigger antenna.
  • Is there anything else such as applications, server services (ftp, http, nfs, etc) or non-games that I can see the performance increase in?

    When I said "frame rate," I didn't necessarily mean first-person shooters. I could have meant radiosity raytracing frame rate in a m****n p*****e studio's rendering farm (T*y S***y 2 took nearly forever to render). And there's always SETI@home, distributed.net, and that new one [processtree.com] that pays you for your MIPS.

  • dbirchall wrote, in re. to this newfangled memory stuff:

    "If it works, and can be used as a replacement for DRAM and Flash, I can't think of anything to stop them from making SmartMedia and CompactFlash cards with OUM technology inside them. And if it stores more data in the same space, that'd be a pretty nice feature for digital cameras, too. Keep the interface pinout and form factor and all that the same, just replace the storage innards."

    You said it!

    I like smart media's shape and size; besides that, my Leica Digilux uses it, so for better for worse I am stuck with it at present for happy reasons. (the digilux, same as Fuji model, what, D-700?, is really nice).

    I don't like the sony memory sticks, CF is still much bulkier even though the capacity goes much higher, I don't want to trust a floppy drive like on the mavicas and certain others ... darn it, SM is really nice:)

    if this stuff can raise its capacity, I am all for it.

    timothy
  • RAM
    Hmm.. what an informative title. Can we get something a little longer, next time?

    I'll give you a few hints and leave you to it: magnets and optics. Enjoy!
    This didn't work for me. I got the case off of the computer, yanked the newfangled RAM thingy out (that little clipper thingy snapped right off, landed on that noisy dusty box right in the middle) and stuck a magnet in. Nothin happened, cept my screen got all weird and frizzled and colory (I forgot to turn it off, but it didn't seem to make much difference). My AOL login screen got all screwed up. So I yanked the magenty bit out and stuck it back onto my box of floppie disks (gotta hold em down somehow).
    The optics thing didn't werk either. I went to the network room of the office and yanked out some of that orange optical fibur cable from the big gray box in the middle of the room, and then cut it open. I yanked out the little thingy thing inside and jammed in into the RAM socket. That seemed to work, so I put the lid thing back on the computer boxie and started clicking on AOL, but it was slow and stupid, not faster. You stupid Slashdot person screwed up my computah.
  • The technical details of this article are close to zero, if you look closely. It gives no
    performance numbers nor does it have any specifics. It sounds plausible, but I would be very cautious in believing this, unless I
    had seen some real results published, such as from the ISSCC or something. I mean, you look at what the
    RAM manufacturers show at these conferences, die photos, highly specific performance numbers, process details, etc. And contrast it with the
    fluff in this article.

    It certainly looks like a great promise, and
    what they say is true - trench capacitor DRAM
    technology is an unholy mess for processing,
    but you have to be a little skeptical in this
    industry, if there is nothing but
    a press release to believe.

  • But my mind is already clogged with plenty of
    other useless skills..... *shrug*
    Until then.. it's just pops and buzzez...
    (static in my ear) *shrug*
  • Actually, I know it's not *true* flash memory, but the CompactFlash IBM Microdrive is up to a whoppin' 340 megs!

    Which is part of the reason I'm only buying Compactflash Type II peripherals... So when I can afford a Microdrive, it'll work with what I got. =P

  • by orpheus ( 14534 ) on Wednesday May 24, 2000 @07:36PM (#1049863)
    As soon as I heard the name "Ovonyx" I was reminded of Stanford Ovshinsky, a physicist who claimed to revolutionize amorphous silicon technology, reportedly 'inventing' a field of Materials Science called "ovonics". He was a minor hero to me as a teenager (the 70's). I'm not such a fan now.

    Though I can hardly blame /. for not checking further, I think readers might want to.

    Sure enough, on the "About the Corporation [ovonyx.com]" page, it confirms: "The Corporation Ovonyx, Inc. (Ovonyx) was formed in 1999 as a joint venture between Energy Conversion Devices, Inc. (ECD) and Messrs. Tyler Lowrey and Ward Parkinson. ECD is Ovshinsky's company (founded in 1960). Surprisingly, no link or further information is provided on ECD, which according to the Ovonyx Corporate page "has been actively pursuing phase-change material and device structure development,optimization and characterization for many applications - but principally for optical and electrical memories."

    From what I recall from the 70's/80's, ECD wasn't 'focused' in these areas, but on solar panels (hence the name "Energy Conversion Devices"). This may explain why "ECD's contribution to the Ovonyx joint venture was all of its intellectual property (IP) in this area" [optical and electrical memory]. Perhaps ECD didn't feel it could make use of this IP, and turned it over to two former top Micron Technology (chip) execs. Read on for details

    THE BACKGROUND
    Ovshinsky was a darling of the Japanese in the 70's/80's when Americans were in shock because the Japanese were using American findings like the management theories of Edwards Deming (who was revered like a god in Japan), 'process control', and "just in time" to turn out cars that the US auto giants couldn't match. American business was also awash in culture shock from dealing with the Japanese business systems (kureitsu, etc.) as equals and as a potential market.

    Ovshinsky raised money by chiding US corps that they would miss the Next Big Thing if they didn't invest in his work, but his primary business relationships were with the Japanese.

    The PBS show NOVA even did a one hour documentary on him ("Japan's American Genius" 10/27/87) that seemed to promise that cheap high efficiency amorphous solar cells would be around any day now. I've kept my eyes peeled ever since (I instantly made the Ovonyx connection in 5/2000!), and never heard anything about ECD. The advances in amorphous technology always seemed to come from elsewhere.

    I haven't been impressed by ECD's ability to bring *any* product to market in 40 years, and I don't know of any breakthroughs they have made or licensed -- and all their 'background' and 'product' links seem to point to nonexistent documents in a 'drafts' folder. However, I may be wrong, or perhaps the documents are being updated, so I refer you to ECD's home page, which is (perhaps unsurprisingly, considering Ovshinsky supposedly pioneered 'ovonics') http://www.ovonic.com [ovonic.com] not to be confused with the OVONYX [ovonyx.com] site in the /. article

    Perhaps I am a little jaded, because I was once a big fan of Ovshinsky (as he was presented), but what I've read in the OVONIX and ECD (OVONIC)web sites seems to have an unusual, almost Microsoftian degree of 'spin'. Caveat emptor.

    However, if anyone out there knows of some concrete product or technical advance that proceeded directly from ECD or Ovshinsky, I would be *most* happy to hear about it. You have to reclaim those childhood heroes when you can! It's good for the soul.

    _____________
  • by Taco Cowboy ( 5327 ) on Wednesday May 24, 2000 @06:32PM (#1049864) Journal


    Questions -

    1. What effect will this type of memory
    device has under radiation bombardments?

    If this memory is to be used on spacecrafts, it has to be able to withstand radiation bombardments.

    2. What effect will magnetic forces (and/or
    electro-magnetic forces) has on this
    type of memory?

    If this memory is to be applied in miniature appliances, the chances that these appliances be in contact with (or being put next to) magnets or under magnetic fields is very large. So, will the amorphous (disordered atomic structure) and crystalline (regular, highly repetitive, and ordered atomic structure) stage be reversed/change/effected due to the magnetic effects?

    We do have to be concerned with the effects, because we just do not know what this type of memory device will ultimately be used on - it could be used on embedded devices to control anti-lock brakes on cars, for example - and if the memory device is "affectabled" by either magnetic or radiations, then, this type of memory device should not be used to power computers which controls critical functions that may affect the safety of human lives.

    This is just my humble 2 cents.

  • Voila! You're back, 0.5 seconds before you crashed, with an identical stream of code and data coming... so you crash again!

    Would be damned handy for debugging though...
  • Programs have to allocate memory. The programs we use currently need memory. This memory is usually finite in a computer. If I am to increase the complexity and size of programs that my computer uses how exactly does it help to increase the speed of the memory? Try running say quake in a machine with 4Mb of ram? Kinda hard isn't it. I say the cheaper the ram you can make and the more of it you can get the better. I can't tell you have much I hate the sound of my machine's hd grinding for lack of ram.
  • by Mr Z ( 6791 ) on Wednesday May 24, 2000 @07:49PM (#1049867) Homepage Journal
    IRC, in most cases the cache only mirrors what's in the main memory, so it wouldn't be a problem.

    That's only half true. The cache holds a copy of what should be in RAM. There are two possible common scenarios:

    • If you have a write through cache, then whenever the CPU writes something, it updates both the cache and memory immediately. Older 486s sported that sort of cache. Some are switchable.
    • If you have a write back cache (just about every modern machine falls into this category), writes will stay in the cache until some other cache/bus traffic causes the results to be written to memory.

    The latter form of cache performs alot better, for a couple reasons. First, writes to memory are slow and a write-through cache doesn't hide them. Second, alot of writes are redundant or can be combined with other nearby writes and a write-back cache serves as a filtering and combining mechanism. The drawback is that the cache has a different picture of memory than the external memory has.

    Anyway, the way you do "recovery" is to checkpoint the OSes state every so often (like, say, every timer tick when you do a task switch). You can save all the registers, flush the cache, and checkpoint off to the OUM. The device issue you mentioned is solved in a similar manner to APM, I'd imagine (not that I know the solution, but I'm saying it's a familiar problem that's already being attacked).

    --Joe
    --
  • by raka ( 17481 )
    Your TV probably has some little microcontroller inside, and this chipee will will have a small amount of EEPROM. 256, 512 bytes, someting like that. This is all the NVRAM they can get without adding extra chips, and no one wants to add extra chips to a design. If it worries you, then maybe OUM can be integrated onto MCU's, and replace eeprom. We could then have whole kilobytes!
  • by Anonymous Coward
    I see that ECD says it has 'a licensing agreement' with all the 'major' manufacturers of NiMH bateries, and almost posted to tell you that they must have a breakthrough there.

    Then I reliazed that if they didn't have licence agreemants with all the NiMH manufacturers, maybe the patent wasn't so critical. I read some posts this year saying how the big Japanese companies all have tons of cross-licenses. (was that you?)

    Your right, there's alot of spin on those websites -- pretty sneaky!
  • That way you can change and upgrade your hardware.
  • Nice, but with CD-RW and DVD-RW drives, the problem you encounter is that you must blank ALL the media (or a large block of it) to reuse it.

    I would think that no matter how fast of a phase change they can manage, they're still going to have a lot of delay doing the blanking.

    But they don't use the same technology (laser) as in CD-RW/DVD-RAM optical disks but a transistor for every single data bit. That would mean that they do not need to blank the entire ram (or entire blocks of it) to reuse it.

    Or did i miss something in the technical description [ovonyx.com] of the OUM, where they also mention that every single bit can be uniquely addressed for read and write?


  • Some clarification:

    - They dont use RW "Film". Their IC will just contain small amounts of a similar ternary alloy. (Ge2Sb2Te5)

    - Writing to the memory cell works by heating it with an electrical current !! Temperatures in excess of 600 degress celcius are required for a phase change. It seems that this is the main problem with this kind of memory.

    - Reading is done by measuring the resistance. No refreshing or anything similar required.

    - They dont have a working sample of a full memory chip yet. As of now it seems to be VAPORWARE

    In case you want to know more than written in the short HTML marketing piece check this out:
    http://www.ovonic.com/technology.pdf

    However there are other companies with very interesting (and available) products in the nvRam
    sector, which are trying to come by the disadvanteage of flashram:

    RAMTRON: Using perovskite crystals to store data. (FRAM) Advantage over flashram: Faster , less power consumption, higher data retention.

    Quite interesting: www.ramtron.com

    SIMTEK: They have srams that automatically store the containing data to an on-chip Flashram when the power drops. And vice versa.
    Seems a litte brute-force to me, but seems to serve its purpose well.

    www.simtek.com

    ZMD: Has almost the same product as SIMTEK. They just do less bragging about it:

    www.zmda.com
  • I notice the article doesn't say anything specific about the amount of time and energy required to write to this stuff.

    AIUI the reading is done by simply measuring the resistance of a tiny cell of this amorphous material, and that would be pretty fast and easy. But writing to it requires a phase change induced by heating. That sounds slow and expensive by comparison.

    Add this to the problem of the memory "wearing out" after a few weeks of being toggled at 10MHz and it looks more like a replacement for Flash memory than for DRAM.

    Nevertheless, it sounds pretty cool.

    Paul.

  • by Signal 11 ( 7608 ) on Wednesday May 24, 2000 @04:29PM (#1049874)
    It's a common misconception that we need more RAM. That is false. We need faster RAM. Repeat after me: Latency is bad. Latency is evil. I must keep latency to a minimum.

    My tech friends are usually stunned when I pick up a stick of PC100 that has 4.5ns instead of PC133 at 5.5ns - they say "PC133 is better!".. and nevermind why. Alittle arm-wringing and explanations of latency and what cache hits v. misses do to their processor performance usually helps. For the stubborn, I ask them to bring their "PC133" ram over and we run a Quake demo. Guess who wins?

    I don't want to hear about how much more RAM the industry is capable of making - I'm interested in hearing how fast they can make it. Bandwidth * Latency = Performance.. you cannot have high bandwidth and HIGH latency and get good performance - we've used up all our tricks in that area.

    That being said, there are alternatives underway. I'll give you a few hints and leave you to it: magnets and optics. Enjoy!

  • If they can get the sizes and speed up enough, perhaps it could one day be used for damage control on Windows systems.

    All you'd need to do is have the RAM written to the OUM every few minutes (or even seconds). In the event of system lockup, the hardware can clear the memory and write the OUM backup back into RAM. Voila! You're back where you started (more or less).

    Of course, this wouldn't be necessary for anything except Windows machines....

  • Why should I care about and/or buy faster RAM?

    Two words: Frame rate.

  • However, unfortunately, due to the fact that devices of this nature could conceivably store illegal copyrighted materials, the DMCA precludes this technology being made available in the US.

  • This is still far better than today's flash memory, which can only remain usable through hundreds of thousands to millions of writes.

    If this stuff has more writes than flash and is faster than flash, then it has great potential as a successor to flash.

  • Also, I know that most flash devices have a limited number of writes they can perform before failure (a large number, I'll admit). Is this a worry with this technology or not?

    Did you read the article? Right next to the pretty graph it says:

    "Further, Flash memory 'wears out' (fails) after 100,000 write cycles, while the OUM memory state can be written more than 10 trillion times..."
  • The page was last updated in Feb 2000. While these processes do take time do develop, if progress hasn't been made in the last 4 months since the big announcement, progress in internet time will wash them under.
  • by Soko ( 17987 ) on Wednesday May 24, 2000 @04:33PM (#1049881) Homepage
    Thier news page [ovonyx.com] shows they have deals and investment from Intel.

    Very cool stuff, especially for laptops. You could selectively power RAM to save a few watts here or there. The only problem I see with a system with nothing but non-volitile RAM is filling the cache inside the processor. Easy to fix I'm sure, but if the cache was non-volitile too, you'd have the entire machine state saved.

    Intel got in early - I'm sure Transmeta would be terribly interested in RAM that you can take power away from, and have it maintain state...

  • Why have swap run the same speed as RAM... just make the swap act AS the RAM ;)

  • by multipartmixed ( 163409 ) on Wednesday May 24, 2000 @04:34PM (#1049883) Homepage
    > Bandwidth * Latency = Performance..
    > you cannot have high bandwidth and HIGH latency
    > and get good performance - we've used up all
    > our tricks in that area.

    According to your formula, if you keep bandwidth constant and increase latency, then your performance increases.

    Clearly, this is wrong.

    How about:

    Performance = Bandwith / Latency

    Have a nice day.

    --
  • Yeah, I was just thinking about buying more memory for my camera too. Plus I'm extra pissed bcs I got a 2.4 mpixel clicker and now (a scant 6-7 mos later) 3 mpixel + are coming in at the same price point as mine. Being a gear junkie sucks sometimes. Still, can't wait to get my hands on some of this when (if?) it becomes available.
  • Anyone find anything about this stuff actually being produced and used? I could very well be wrong here but it sounds like classic vapourware. I think the old saying could stand; when something sounds to good to be true it normally is. However, if this stuff is being produced and does work as advertised it could be a great leap for gadgets. I would like to have this stuff in my mp3 walkman and pc if it works as advertised. Hardly revolutionary though

    "Patience is a virtue, afforded those with nothing better to do." - I don't remember

  • You know what really upsets me? They talk about this thing in a bit of detail, but they didn't say anything about prototypes, or the new plant they've got for making this stuff, or anything like that. So, is this stuff in production? I doubt it. Quite honestly, I hate hearing about this stuff two-three years before it comes to market. It's starting to piss me off. Tell me about something when I can buy it, or tell me about it with enough time to plan for it. Not before.

    Dave
  • No, more RAM is useful, quite useful. Sure, RAM and drives may have not been getting faster lately, but they have been getting larger, just as have everything else.

    Hard drives are getting larger. Hard to aruge with that. RAM is getting larger. RAM is used to cache the hard drive. Caches are getting larger. RAM gets cached in the L1 and L2. And I don't follow that part too much, but I'm sure there are more registers now than there used to be, though I suspect that's a bit slower to change. And registers "cache" the cache. Well, sort of. You know what I mean.

    So if you only care about latency, think of it this way: bigger RAM means faster hard drives. (well, this is non-volatile RAM anyway; it would replace hard drives). Wait a second, what are you complaining about anyway? Large non-volatile RAM is VERY useful. It's not supposed to replace the RAM in your computer).
  • could selectively power RAM to save a few watts here or there
    Wasnt't that what 'Standby' is? Swapping the RAM to HD and then cutting power, essentially?

    terribly interested in RAM that you can take power away from, and have it maintain state...
    Um... sounds great... until the machine crashes.. and you have to use a magnet (or bulk eraser) to reboot... well... not without an operating system, since a magnet would wipe the hard drive...
  • by Anonymous Coward
    Even more exciting is really dense stuff like HP's ATOMIC RESOLUTION STORAGE [sciam.com]
  • It looks to me like they're relying on the resistance change, rather than optical properties, to read the phase state of the storage material - a quick examination of their logo confirms this :) So no light needs to be emitted to read the state; that ought to be a considerable power savings right there.

    My guess on writing is that of course it would take more power, but since they are working with a greatly reduced area, the amount of energy required to effect a state change should also be less than for CDRs. Also the shorter distance from the "write head" to the storage material should help them at least a little.
  • The idea for FRAM has been around for years. But just recently FRAM with sufficiant density has been announced. Btw. it seems that Samsungs FRAM is not in production, yet. FRAM uses a different technology. FRAM stores data by moving atoms in a crystal grid. OUM memory stores data by altering the resistance of an alloy through phase changing. Quite a difference after all...
  • I did some mental calculations when I read the article:

    10 trillion writes = 10^13
    Maximum write rate on a PC approx 100MHz = 10^8/s
    Therefore, minimum time before write cycle exhausted = 10^5s which is about a day.

    Put like this, it isn't very impressive. Of course, nobody is going to write bits quite that fast with current technology. If a computer has 100Mb memory and writes byte to a random location (a major assumption) 10^9 times a second (1 GHz) then each byte changes about 10 times a second, and the memory lasts 10^12 seconds, which is 'ample' (over 1000 years.)

    There may have to be some twiddling to ensure some parts of the memory don't get hit much more often than others.

    Even if the lifetime is only 5 years, I can live with replacing my memory that often.

  • by Animats ( 122034 ) on Wednesday May 24, 2000 @08:00PM (#1049893) Homepage
    However, if anyone out there knows of some concrete product or technical advance that proceeded directly from ECD or Ovshinsky, I would be *most* happy to hear about it. You have to reclaim those childhood heroes when you can! It's good for the soul.

    Ovshinsky has a decent track record in products:

    • His companies manufacture amorphous solar cells in volume, but they cost about the same as silicon solar cells. However, they're flexible, and so they're widely used on boats. Some sailboats even have them on the sails.
    • Nickel-metal-hydride (NiMH) battery technology was developed by Ovshinsky's company, and all 16 makers of NiMH batteries license his patents. Camcorders, laptops, electric scooters, and the GM EV-1 use this technology.

    Ovshinsky's big problem has always been with his manufacturing processes. Since he's just about the only player in amorphous semiconductors, he has to develop his own fab techniques. That's a big job; many billions of dollars have gone into making silicon semiconductor technology work as well as it does. ECD has to match that, working alone. They never really have, which is why amorphous transistors and amorphous ICs never took off, although both did work. (Burroughs even shipped some machines with his early non-volatile memory in the 1970s.) His battery technology also has fabrication problems. But slowly the stuff is starting to work.

  • Well, not!

    I would like to have 4 gigs of RAM in my machine.
    Then at boot do a burst transfer of the first two in memory (that's the OS) and then, every 5 minutes all my data to one of the two gigs left.

    Imagine: all my data and the OS in memory. And a UPS capable to last until everything lands on disk.

    I WANT MORE RAM!
  • by MinaInerz ( 25726 ) on Thursday May 25, 2000 @03:39AM (#1049895) Homepage
    I think you fail to understand that the PC### rating is based on latency.

    If a memory has a latency of, say, 5.5ns, and is able to sustain it, then you get the speed from the following equation. 1000/5.5ns = 181MHz (5.5ns is very fast, very expensive RAM - you'll see it on those new hotshot video cards). More commonly, on PC133, you will see 7ns. 1000/7ns = 143MHz (ergo, PC133).

    Nobody, to my knowledge, can even manufacture memory that fast. Even the new NVidia cards don't have memory that fast. (1000/4.5ns = 220MHz!)

    More than likely, your better Quake performance is due to a more optimized system, better video card, etc, etc, and certainly not due to your main memory (PC133 is faster than PC100). Additionally, the BX chipset on PC100 is a little bit faster than the VIA Apollo Pro133A chipset on PC133 (in some cases). An overclocked BX chipset at 133MHz(!) is incredibly fast.
  • It's a pretty cool idea... anyone know if some exotic hardware with these kinds of capabilities has ever been tried?

    No, but an emulator (like Nesticle) could be easily modified to do it.

  • They should ban books, too! According to the DCMA, they are also illegal.

    --
  • The fact you have to erase the medium before use is because the UDF file system requires that. It has nothing to do with the medium itself.
  • Indeed. I'm looking at shelling out some money for another CompactFlash card for my camera soon too. (Couldn't imagine using SmartMedia, with its 64-meg limit, when CF is now up to 192-meg...)

    When I stop to think about it, though, this OUM stuff doesn't replace a certain form factor, or a certain interface or API - it replaces a memory technology. If it works, and can be used as a replacement for DRAM and Flash, I can't think of anything to stop them from making SmartMedia and CompactFlash cards with OUM technology inside them. And if it stores more data in the same space, that'd be a pretty nice feature for digital cameras, too. Keep the interface pinout and form factor and all that the same, just replace the storage innards.
    --

The reward of a thing well done is to have done it. -- Emerson

Working...